diff options
516 files changed, 11490 insertions, 3569 deletions
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.txt b/Documentation/devicetree/bindings/input/gpio-keys.txt index 996ce84352cb..7cccc49b6bea 100644 --- a/Documentation/devicetree/bindings/input/gpio-keys.txt +++ b/Documentation/devicetree/bindings/input/gpio-keys.txt @@ -1,4 +1,4 @@ -Device-Tree bindings for input/gpio_keys.c keyboard driver +Device-Tree bindings for input/keyboard/gpio_keys.c keyboard driver Required properties: - compatible = "gpio-keys"; diff --git a/Documentation/devicetree/bindings/mips/mscc.txt b/Documentation/devicetree/bindings/mips/mscc.txt index ae15ec333542..bc817e984628 100644 --- a/Documentation/devicetree/bindings/mips/mscc.txt +++ b/Documentation/devicetree/bindings/mips/mscc.txt @@ -41,3 +41,19 @@ Example: compatible = "mscc,ocelot-cpu-syscon", "syscon"; reg = <0x70000000 0x2c>; }; + +o HSIO regs: + +The SoC has a few registers (HSIO) handling miscellaneous functionalities: +configuration and status of PLL5, RCOMP, SyncE, SerDes configurations and +status, SerDes muxing and a thermal sensor. + +Required properties: +- compatible: Should be "mscc,ocelot-hsio", "syscon", "simple-mfd" +- reg : Should contain registers location and length + +Example: + syscon@10d0000 { + compatible = "mscc,ocelot-hsio", "syscon", "simple-mfd"; + reg = <0x10d0000 0x10000>; + }; diff --git a/Documentation/devicetree/bindings/net/mscc-ocelot.txt b/Documentation/devicetree/bindings/net/mscc-ocelot.txt index 0a84711abece..9e5c17d426ce 100644 --- a/Documentation/devicetree/bindings/net/mscc-ocelot.txt +++ b/Documentation/devicetree/bindings/net/mscc-ocelot.txt @@ -12,7 +12,6 @@ Required properties: - "sys" - "rew" - "qs" - - "hsio" - "qsys" - "ana" - "portX" with X from 0 to the number of last port index available on that @@ -45,7 +44,6 @@ Example: reg = <0x1010000 0x10000>, <0x1030000 0x10000>, <0x1080000 0x100>, - <0x10d0000 0x10000>, <0x11e0000 0x100>, <0x11f0000 0x100>, <0x1200000 0x100>, @@ -59,10 +57,9 @@ Example: <0x1280000 0x100>, <0x1800000 0x80000>, <0x1880000 0x10000>; - reg-names = "sys", "rew", "qs", "hsio", "port0", - "port1", "port2", "port3", "port4", "port5", - "port6", "port7", "port8", "port9", "port10", - "qsys", "ana"; + reg-names = "sys", "rew", "qs", "port0", "port1", "port2", + "port3", "port4", "port5", "port6", "port7", + "port8", "port9", "port10", "qsys", "ana"; interrupts = <21 22>; interrupt-names = "xtr", "inj"; diff --git a/Documentation/devicetree/bindings/phy/phy-ocelot-serdes.txt b/Documentation/devicetree/bindings/phy/phy-ocelot-serdes.txt new file mode 100644 index 000000000000..332219860187 --- /dev/null +++ b/Documentation/devicetree/bindings/phy/phy-ocelot-serdes.txt @@ -0,0 +1,43 @@ +Microsemi Ocelot SerDes muxing driver +------------------------------------- + +On Microsemi Ocelot, there is a handful of registers in HSIO address +space for setting up the SerDes to switch port muxing. + +A SerDes X can be "muxed" to work with switch port Y or Z for example. +One specific SerDes can also be used as a PCIe interface. + +Hence, a SerDes represents an interface, be it an Ethernet or a PCIe one. + +There are two kinds of SerDes: SERDES1G supports 10/100Mbps in +half/full-duplex and 1000Mbps in full-duplex mode while SERDES6G supports +10/100Mbps in half/full-duplex and 1000/2500Mbps in full-duplex mode. + +Also, SERDES6G number (aka "macro") 0 is the only interface supporting +QSGMII. + +This is a child of the HSIO syscon ("mscc,ocelot-hsio", see +Documentation/devicetree/bindings/mips/mscc.txt) on the Microsemi Ocelot. + +Required properties: + +- compatible: should be "mscc,vsc7514-serdes" +- #phy-cells : from the generic phy bindings, must be 2. + The first number defines the input port to use for a given + SerDes macro. The second defines the macro to use. They are + defined in dt-bindings/phy/phy-ocelot-serdes.h + +Example: + + serdes: serdes { + compatible = "mscc,vsc7514-serdes"; + #phy-cells = <2>; + }; + + ethernet { + port1 { + phy-handle = <&phy_foo>; + /* Link SERDES1G_5 to port1 */ + phys = <&serdes 1 SERDES1G_5>; + }; + }; diff --git a/Documentation/fb/uvesafb.txt b/Documentation/fb/uvesafb.txt index f6362d88763b..aa924196c366 100644 --- a/Documentation/fb/uvesafb.txt +++ b/Documentation/fb/uvesafb.txt @@ -15,7 +15,8 @@ than x86. Check the v86d documentation for a list of currently supported arches. v86d source code can be downloaded from the following website: - http://dev.gentoo.org/~spock/projects/uvesafb + + https://github.com/mjanusz/v86d Please refer to the v86d documentation for detailed configuration and installation instructions. @@ -177,7 +178,7 @@ from the Video BIOS if you set pixclock to 0 in fb_var_screeninfo. -- Michal Januszewski <spock@gentoo.org> - Last updated: 2009-03-30 + Last updated: 2017-10-10 Documentation of the uvesafb options is loosely based on vesafb.txt. diff --git a/Documentation/networking/devlink-params-bnxt.txt b/Documentation/networking/devlink-params-bnxt.txt new file mode 100644 index 000000000000..481aa303d5b4 --- /dev/null +++ b/Documentation/networking/devlink-params-bnxt.txt @@ -0,0 +1,18 @@ +enable_sriov [DEVICE, GENERIC] + Configuration mode: Permanent + +ignore_ari [DEVICE, GENERIC] + Configuration mode: Permanent + +msix_vec_per_pf_max [DEVICE, GENERIC] + Configuration mode: Permanent + +msix_vec_per_pf_min [DEVICE, GENERIC] + Configuration mode: Permanent + +gre_ver_check [DEVICE, DRIVER-SPECIFIC] + Generic Routing Encapsulation (GRE) version check will + be enabled in the device. If disabled, device skips + version checking for incoming packets. + Type: Boolean + Configuration mode: Permanent diff --git a/Documentation/networking/devlink-params.txt b/Documentation/networking/devlink-params.txt new file mode 100644 index 000000000000..ae444ffe73ac --- /dev/null +++ b/Documentation/networking/devlink-params.txt @@ -0,0 +1,42 @@ +Devlink configuration parameters +================================ +Following is the list of configuration parameters via devlink interface. +Each parameter can be generic or driver specific and are device level +parameters. + +Note that the driver-specific files should contain the generic params +they support to, with supported config modes. + +Each parameter can be set in different configuration modes: + runtime - set while driver is running, no reset required. + driverinit - applied while driver initializes, requires restart + driver by devlink reload command. + permanent - written to device's non-volatile memory, hard reset + required. + +Following is the list of parameters: +==================================== +enable_sriov [DEVICE, GENERIC] + Enable Single Root I/O Virtualisation (SRIOV) in + the device. + Type: Boolean + +ignore_ari [DEVICE, GENERIC] + Ignore Alternative Routing-ID Interpretation (ARI) + capability. If enabled, adapter will ignore ARI + capability even when platforms has the support + enabled and creates same number of partitions when + platform does not support ARI. + Type: Boolean + +msix_vec_per_pf_max [DEVICE, GENERIC] + Provides the maximum number of MSIX interrupts that + a device can create. Value is same across all + physical functions (PFs) in the device. + Type: u32 + +msix_vec_per_pf_min [DEVICE, GENERIC] + Provides the minimum number of MSIX interrupts required + for the device initialization. Value is same across all + physical functions (PFs) in the device. + Type: u32 diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 8313a636dd53..960de8fe3f40 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -425,7 +425,7 @@ tcp_mtu_probing - INTEGER 1 - Disabled by default, enabled when an ICMP black hole detected 2 - Always enabled, use initial MSS of tcp_base_mss. -tcp_probe_interval - INTEGER +tcp_probe_interval - UNSIGNED INTEGER Controls how often to start TCP Packetization-Layer Path MTU Discovery reprobe. The default is reprobing every 10 minutes as per RFC4821. diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index b5407163d53b..605e00cdd6be 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -1069,6 +1069,31 @@ The kernel interface functions are as follows: This function may transmit a PING ACK. + (*) Get reply timestamp. + + bool rxrpc_kernel_get_reply_time(struct socket *sock, + struct rxrpc_call *call, + ktime_t *_ts) + + This allows the timestamp on the first DATA packet of the reply of a + client call to be queried, provided that it is still in the Rx ring. If + successful, the timestamp will be stored into *_ts and true will be + returned; false will be returned otherwise. + + (*) Get remote client epoch. + + u32 rxrpc_kernel_get_epoch(struct socket *sock, + struct rxrpc_call *call) + + This allows the epoch that's contained in packets of an incoming client + call to be queried. This value is returned. The function always + successful if the call is still in progress. It shouldn't be called once + the call has expired. Note that calling this on a local client call only + returns the local epoch. + + This value can be used to determine if the remote client has been + restarted as it shouldn't change otherwise. + ======================= CONFIGURABLE PARAMETERS diff --git a/MAINTAINERS b/MAINTAINERS index 8501eb004429..86e83ea6ad08 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -324,7 +324,6 @@ F: Documentation/ABI/testing/sysfs-bus-acpi F: Documentation/ABI/testing/configfs-acpi F: drivers/pci/*acpi* F: drivers/pci/*/*acpi* -F: drivers/pci/*/*/*acpi* F: tools/power/acpi/ ACPI APEI @@ -1251,7 +1250,7 @@ N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg <tsahee@annapurnalabs.com> -M: Antoine Tenart <antoine.tenart@free-electrons.com> +M: Antoine Tenart <antoine.tenart@bootlin.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-alpine/ @@ -2956,7 +2955,6 @@ F: include/linux/bcm963xx_tag.h BROADCOM BNX2 GIGABIT ETHERNET DRIVER M: Rasesh Mody <rasesh.mody@cavium.com> -M: Harish Patil <harish.patil@cavium.com> M: Dept-GELinuxNICDev@cavium.com L: netdev@vger.kernel.org S: Supported @@ -2977,6 +2975,7 @@ F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER M: Ariel Elior <ariel.elior@cavium.com> +M: Sudarsana Kalluru <sudarsana.kalluru@cavium.com> M: everest-linux-l2@cavium.com L: netdev@vger.kernel.org S: Supported @@ -5470,7 +5469,8 @@ S: Odd Fixes F: drivers/net/ethernet/agere/ ETHERNET BRIDGE -M: Stephen Hemminger <stephen@networkplumber.org> +M: Roopa Prabhu <roopa@cumulusnetworks.com> +M: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> L: bridge@lists.linux-foundation.org (moderated for non-subscribers) L: netdev@vger.kernel.org W: http://www.linuxfoundation.org/en/Net:Bridge @@ -8607,7 +8607,6 @@ F: include/linux/spinlock*.h F: arch/*/include/asm/spinlock*.h F: include/linux/rwlock*.h F: include/linux/mutex*.h -F: arch/*/include/asm/mutex*.h F: include/linux/rwsem*.h F: arch/*/include/asm/rwsem.h F: include/linux/seqlock.h @@ -9725,13 +9724,6 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ S: Maintained F: drivers/media/dvb-frontends/mn88473* -PCI DRIVER FOR MOBIVEIL PCIE IP -M: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> -L: linux-pci@vger.kernel.org -S: Supported -F: Documentation/devicetree/bindings/pci/mobiveil-pcie.txt -F: drivers/pci/controller/pcie-mobiveil.c - MODULE SUPPORT M: Jessica Yu <jeyu@kernel.org> T: git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next @@ -10958,7 +10950,7 @@ M: Willy Tarreau <willy@haproxy.com> M: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> S: Odd Fixes F: Documentation/auxdisplay/lcd-panel-cgram.txt -F: drivers/misc/panel.c +F: drivers/auxdisplay/panel.c PARALLEL PORT SUBSYSTEM M: Sudip Mukherjee <sudipm.mukherjee@gmail.com> @@ -11146,6 +11138,13 @@ F: include/uapi/linux/switchtec_ioctl.h F: include/linux/switchtec.h F: drivers/ntb/hw/mscc/ +PCI DRIVER FOR MOBIVEIL PCIE IP +M: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> +L: linux-pci@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/pci/mobiveil-pcie.txt +F: drivers/pci/controller/pcie-mobiveil.c + PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support) M: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> M: Jason Cooper <jason@lakedaemon.net> @@ -11212,8 +11211,14 @@ F: tools/pci/ PCI ENHANCED ERROR HANDLING (EEH) FOR POWERPC M: Russell Currey <ruscur@russell.cc> +M: Sam Bobroff <sbobroff@linux.ibm.com> +M: Oliver O'Halloran <oohall@gmail.com> L: linuxppc-dev@lists.ozlabs.org S: Supported +F: Documentation/PCI/pci-error-recovery.txt +F: drivers/pci/pcie/aer.c +F: drivers/pci/pcie/dpc.c +F: drivers/pci/pcie/err.c F: Documentation/powerpc/eeh-pci-error-recovery.txt F: arch/powerpc/kernel/eeh*.c F: arch/powerpc/platforms/*/eeh*.c @@ -11982,7 +11987,7 @@ F: Documentation/scsi/LICENSE.qla4xxx F: drivers/scsi/qla4xxx/ QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER -M: Harish Patil <harish.patil@cavium.com> +M: Shahed Shaikh <Shahed.Shaikh@cavium.com> M: Manish Chopra <manish.chopra@cavium.com> M: Dept-GELinuxNICDev@cavium.com L: netdev@vger.kernel.org @@ -11990,7 +11995,6 @@ S: Supported F: drivers/net/ethernet/qlogic/qlcnic/ QLOGIC QLGE 10Gb ETHERNET DRIVER -M: Harish Patil <harish.patil@cavium.com> M: Manish Chopra <manish.chopra@cavium.com> M: Dept-GELinuxNICDev@cavium.com L: netdev@vger.kernel.org @@ -15398,7 +15402,7 @@ S: Maintained UVESAFB DRIVER M: Michal Januszewski <spock@gentoo.org> L: linux-fbdev@vger.kernel.org -W: http://dev.gentoo.org/~spock/projects/uvesafb/ +W: https://github.com/mjanusz/v86d S: Maintained F: Documentation/fb/uvesafb.txt F: drivers/video/fbdev/uvesafb.* @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts index b10dccd0958f..3b1baa8605a7 100644 --- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts @@ -11,6 +11,7 @@ #include "sama5d2-pinfunc.h" #include <dt-bindings/mfd/atmel-flexcom.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/pinctrl/at91.h> / { model = "Atmel SAMA5D2 PTC EK"; @@ -299,6 +300,7 @@ <PIN_PA30__NWE_NANDWE>, <PIN_PB2__NRD_NANDOE>; bias-pull-up; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; ale_cle_rdy_cs { diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi index 43ee992ccdcf..6df61518776f 100644 --- a/arch/arm/boot/dts/bcm63138.dtsi +++ b/arch/arm/boot/dts/bcm63138.dtsi @@ -106,21 +106,23 @@ global_timer: timer@1e200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x1e200 0x20>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&axi_clk>; }; local_timer: local-timer@1e600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0x1e600 0x20>; - interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_EDGE_RISING)>; clocks = <&axi_clk>; }; twd_watchdog: watchdog@1e620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0x1e620 0x20>; - interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_LEVEL_HIGH)>; }; armpll: armpll { @@ -158,7 +160,7 @@ serial0: serial@600 { compatible = "brcm,bcm6345-uart"; reg = <0x600 0x1b>; - interrupts = <GIC_SPI 32 0>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -167,7 +169,7 @@ serial1: serial@620 { compatible = "brcm,bcm6345-uart"; reg = <0x620 0x1b>; - interrupts = <GIC_SPI 33 0>; + interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -180,7 +182,7 @@ reg = <0x2000 0x600>, <0xf0 0x10>; reg-names = "nand", "nand-int-base"; status = "disabled"; - interrupts = <GIC_SPI 38 0>; + interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "nand"; }; diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index 661be948ab74..185541a5b69f 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -1078,8 +1078,8 @@ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rcc SPI6_K>; resets = <&rcc SPI6_R>; - dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>, - <&mdma1 35 0x0 0x40002 0x0 0x0 0>; + dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>, + <&mdma1 35 0x0 0x40002 0x0 0x0>; dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi index ffd9f00f74a4..5f547c161baf 100644 --- a/arch/arm/boot/dts/sun8i-r40.dtsi +++ b/arch/arm/boot/dts/sun8i-r40.dtsi @@ -800,8 +800,7 @@ }; hdmi_phy: hdmi-phy@1ef0000 { - compatible = "allwinner,sun8i-r40-hdmi-phy", - "allwinner,sun50i-a64-hdmi-phy"; + compatible = "allwinner,sun8i-r40-hdmi-phy"; reg = <0x01ef0000 0x10000>; clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>, <&ccu 7>, <&ccu 16>; diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index fc91205ff46c..5bf9443cfbaa 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type) int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { - BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); + BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT); return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K, diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index fbc74b5fa3ed..8edf93b4490f 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -413,3 +413,4 @@ 396 common pkey_free sys_pkey_free 397 common statx sys_statx 398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07256b08226c..a6c9fbaeaefc 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); } +static int validate_core_offset(const struct kvm_one_reg *reg) +{ + u64 off = core_reg_offset_from_id(reg->id); + int size; + + switch (off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + case KVM_REG_ARM_CORE_REG(regs.sp): + case KVM_REG_ARM_CORE_REG(regs.pc): + case KVM_REG_ARM_CORE_REG(regs.pstate): + case KVM_REG_ARM_CORE_REG(sp_el1): + case KVM_REG_ARM_CORE_REG(elr_el1): + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + size = sizeof(__u64); + break; + + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + size = sizeof(__uint128_t); + break; + + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + size = sizeof(__u32); + break; + + default: + return -EINVAL; + } + + if (KVM_REG_SIZE(reg->id) == size && + IS_ALIGNED(off, size / sizeof(__u32))) + return 0; + + return -EINVAL; +} + static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { /* @@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; + if (validate_core_offset(reg)) + return -EINVAL; + if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; + if (validate_core_offset(reg)) + return -EINVAL; + if (KVM_REG_SIZE(reg->id) > sizeof(tmp)) return -EINVAL; @@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { - u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK; + u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK; switch (mode) { case PSR_AA32_MODE_USR: + if (!system_supports_32bit_el0()) + return -EINVAL; + break; case PSR_AA32_MODE_FIQ: case PSR_AA32_MODE_IRQ: case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: + if (!vcpu_el1_is_32bit(vcpu)) + return -EINVAL; + break; case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: + if (vcpu_el1_is_32bit(vcpu)) + return -EINVAL; break; default: err = -EINVAL; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 192b3ba07075..f58ea503ad01 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm, /* * If HW_AFDBM is enabled, then the HW could turn on - * the dirty bit for any page in the set, so check - * them all. All hugetlb entries are already young. + * the dirty or accessed bit for any page in the set, + * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); } if (valid) { @@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, return get_clear_flush(mm, addr, ptep, pgsize, ncontig); } +/* + * huge_ptep_set_access_flags will update access flags (dirty, accesssed) + * and write permission. + * + * For a contiguous huge pte range we need to check whether or not write + * permission has to change only on the first pte in the set. Then for + * all the contiguous ptes we need to check whether or not there is a + * discrepancy between dirty or young. + */ +static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) +{ + int i; + + if (pte_write(pte) != pte_write(huge_ptep_get(ptep))) + return 1; + + for (i = 0; i < ncontig; i++) { + pte_t orig_pte = huge_ptep_get(ptep + i); + + if (pte_dirty(pte) != pte_dirty(orig_pte)) + return 1; + + if (pte_young(pte) != pte_young(orig_pte)) + return 1; + } + + return 0; +} + int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { - int ncontig, i, changed = 0; + int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; pgprot_t hugeprot; @@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; + if (!__cont_access_flags_changed(ptep, pte, ncontig)) + return 0; + orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); - if (!pte_same(orig_pte, pte)) - changed = 1; - /* Make sure we don't lose the dirty state */ + /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); + if (pte_young(orig_pte)) + pte = pte_mkyoung(pte); + hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot)); - return changed; + return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi index f7eb612b46ba..8ce317c5b9ed 100644 --- a/arch/mips/boot/dts/mscc/ocelot.dtsi +++ b/arch/mips/boot/dts/mscc/ocelot.dtsi @@ -107,7 +107,6 @@ reg = <0x1010000 0x10000>, <0x1030000 0x10000>, <0x1080000 0x100>, - <0x10d0000 0x10000>, <0x11e0000 0x100>, <0x11f0000 0x100>, <0x1200000 0x100>, @@ -121,10 +120,10 @@ <0x1280000 0x100>, <0x1800000 0x80000>, <0x1880000 0x10000>; - reg-names = "sys", "rew", "qs", "hsio", "port0", - "port1", "port2", "port3", "port4", "port5", - "port6", "port7", "port8", "port9", "port10", - "qsys", "ana"; + reg-names = "sys", "rew", "qs", "port0", "port1", + "port2", "port3", "port4", "port5", "port6", + "port7", "port8", "port9", "port10", "qsys", + "ana"; interrupts = <21 22>; interrupt-names = "xtr", "inj"; @@ -231,5 +230,15 @@ pinctrl-0 = <&miim1>; status = "disabled"; }; + + hsio: syscon@10d0000 { + compatible = "mscc,ocelot-hsio", "syscon", "simple-mfd"; + reg = <0x10d0000 0x10000>; + + serdes: serdes { + compatible = "mscc,vsc7514-serdes"; + #phy-cells = <2>; + }; + }; }; }; diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 1a951b00465d..1fffbba8d6a5 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern unsigned long long memory_limit; +extern bool init_mem_is_free; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index ea04dfb8c092..2d8fc8c9da7a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION mfspr r10,SPRN_HSRR1 - mfspr r11,SPRN_HSRR0 /* save HSRR0 */ andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ - addi r11,r11,-4 /* HSRR0 is next instruction */ bne+ denorm_assist #endif @@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) */ XVCPSGNDP32(32) denorm_done: + mfspr r11,SPRN_HSRR0 + subi r11,r11,4 mtspr SPRN_HSRR0,r11 mtcrf 0x80,r9 ld r9,PACA_EXGEN+EX_R9(r13) diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 6bffbc5affe7..7716374786bd 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim) std r1, PACATMSCRATCH(r13) ld r1, PACAR1(r13) - /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + /* + * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is + * clobbered by an exception once we turn on MSR_RI below. + */ + ld r11, PACATMSCRATCH(r13) + std r11, GPR1(r1) + + /* + * Store r13 away so we can free up the scratch SPR for the SLB fault + * handler (needed once we start accessing the thread_struct). + */ + GET_SCRATCH0(r11) + std r11, GPR13(r1) + /* Reset MSR RI so we can take SLB faults again */ li r11, MSR_RI mtmsrd r11, 1 + /* Store the PPR in r11 and reset to decent value */ mfspr r11, SPRN_PPR HMT_MEDIUM @@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim) SAVE_GPR(8, r7) /* user r8 */ SAVE_GPR(9, r7) /* user r9 */ SAVE_GPR(10, r7) /* user r10 */ - ld r3, PACATMSCRATCH(r13) /* user r1 */ + ld r3, GPR1(r1) /* user r1 */ ld r4, GPR7(r1) /* user r7 */ ld r5, GPR11(r1) /* user r11 */ ld r6, GPR12(r1) /* user r12 */ - GET_SCRATCH0(8) /* user r13 */ + ld r8, GPR13(r1) /* user r13 */ std r3, GPR1(r7) std r4, GPR7(r7) std r5, GPR11(r7) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 933c574e1cf7..998f8d089ac7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -646,6 +646,16 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ local_irq_disable(); ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + /* + * If the PTE disappeared temporarily due to a THP + * collapse, just return and let the guest try again. + */ + if (!ptep) { + local_irq_enable(); + if (page) + put_page(page); + return RESUME_GUEST; + } pte = *ptep; local_irq_enable(); diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 886ed94b9c13..d05c8af4ac51 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic) addc r0, r8, r9 ld r10, 0(r4) ld r11, 8(r4) +#ifdef CONFIG_CPU_LITTLE_ENDIAN + rotldi r5, r5, 8 +#endif adde r0, r0, r10 add r5, r5, r7 adde r0, r0, r11 diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 850f3b8f4da5..6ae2777c220d 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -28,6 +28,12 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr, { int err; + /* Make sure we aren't patching a freed init section */ + if (init_mem_is_free && init_section_contains(exec_addr, 4)) { + pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr); + return 0; + } + __put_user_size(instr, patch_addr, 4, err); if (err) return err; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5c8530d0c611..04ccb274a620 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -63,6 +63,7 @@ #endif unsigned long long memory_limit; +bool init_mem_is_free; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; @@ -396,6 +397,7 @@ void free_initmem(void) { ppc_md.progress = ppc_printk_progress; mark_initmem_nx(); + init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 35ac5422903a..59d07bd5374a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu) int new_nid; /* Use associativity from first thread for all siblings */ - vphn_get_associativity(cpu, associativity); + if (vphn_get_associativity(cpu, associativity)) + return cpu_to_node(cpu); + new_nid = associativity_to_nid(associativity); if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; @@ -1452,7 +1454,8 @@ static struct timer_list topology_timer; static void reset_topology_timer(void) { - mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); + if (vphn_enabled) + mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index 333b1f80c435..b271b283c785 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -45,7 +45,7 @@ static void scan_pkey_feature(void) * Since any pkey can be used for data or execute, we will just treat * all keys as equal and track them as one entity. */ - pkeys_total = be32_to_cpu(vals[0]); + pkeys_total = vals[0]; pkeys_devtree_defined = true; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index 6c5db1acbe8d..fe9691040f54 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, level_shift = entries_shift + 3; level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT); - if ((level_shift - 3) * levels + page_shift >= 60) + if ((level_shift - 3) * levels + page_shift >= 55) return -EINVAL; /* Allocate TCE table */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..c9fecd120d18 --- /dev/null +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PROTOTYPES_H + +#include <linux/ftrace.h> +#include <asm-generic/asm-prototypes.h> + +#endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index aee603123030..b2d26d9d8489 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -186,7 +186,7 @@ static void __init setup_bootmem(void) BUG_ON(mem_size == 0); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = pfn_base + PFN_DOWN(mem_size); + max_low_pfn = memblock_end_of_DRAM(); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index eaa843a52907..a480356e0ed8 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit) push %ebx push %ecx push %edx - push %edi - - /* - * RIP-relative addressing is needed to access the encryption bit - * variable. Since we are running in 32-bit mode we need this call/pop - * sequence to get the proper relative addressing. - */ - call 1f -1: popl %edi - subl $1b, %edi - - movl enc_bit(%edi), %eax - cmpl $0, %eax - jge .Lsev_exit /* Check if running under a hypervisor */ movl $1, %eax @@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit) movl %ebx, %eax andl $0x3f, %eax /* Return the encryption bit location */ - movl %eax, enc_bit(%edi) jmp .Lsev_exit .Lno_sev: xor %eax, %eax - movl %eax, enc_bit(%edi) .Lsev_exit: - pop %edi pop %edx pop %ecx pop %ebx @@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask) ENDPROC(set_sev_encryption_mask) .data -enc_bit: - .int 0xffffffff #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index fa3f439f0a92..141d415a8c80 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS) + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + CFL += $(RETPOLINE_VDSO_CFLAGS) +endif +endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) @@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) +endif +endif + $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(obj)/vdso32.so.dbg: FORCE \ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index f19856d95c60..e48ca3afa091 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -43,8 +43,9 @@ extern u8 hvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; } @@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; } @@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 981ba5e8241b..8671de126eac 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -36,6 +36,7 @@ static int num_counters_llc; static int num_counters_nb; +static bool l3_mask; static HLIST_HEAD(uncore_unused_list); @@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; + /* + * SliceMask and ThreadMask need to be set for certain L3 events in + * Family 17h. For other events, the two fields do not affect the count. + */ + if (l3_mask) + hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK); + if (event->cpu < 0) return -EINVAL; @@ -525,6 +533,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l3"; format_attr_event_df.show = &event_show_df; format_attr_event_l3.show = &event_show_l3; + l3_mask = true; } else { num_counters_nb = NUM_COUNTERS_NB; num_counters_llc = NUM_COUNTERS_L2; @@ -532,6 +541,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l2"; format_attr_event_df = format_attr_event; format_attr_event_l3 = format_attr_event; + l3_mask = false; } amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 51d7c117e3c7..c07bee31abe8 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id); if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; @@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3), }, { /* M3UPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0), }, { /* M3UPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1), }, { /* M3UPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2), }, { /* end: all zeroes */ } }; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 12f54082f4c8..78241b736f2a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -46,6 +46,14 @@ #define INTEL_ARCH_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) +#define AMD64_L3_SLICE_SHIFT 48 +#define AMD64_L3_SLICE_MASK \ + ((0xFULL) << AMD64_L3_SLICE_SHIFT) + +#define AMD64_L3_THREAD_SHIFT 56 +#define AMD64_L3_THREAD_MASK \ + ((0xFFULL) << AMD64_L3_THREAD_SHIFT) + #define X86_RAW_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_EVENT | \ ARCH_PERFMON_EVENTSEL_UMASK | \ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index a80c0673798f..e60c45fd3679 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -10,8 +10,13 @@ struct cpumask; struct mm_struct; #ifdef CONFIG_X86_UV +#include <linux/efi.h> extern enum uv_system_type get_uv_system_type(void); +static inline bool is_early_uv_system(void) +{ + return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab); +} extern int is_uv_system(void); extern int is_uv_hubless(void); extern void uv_cpu_init(void); @@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, #else /* X86_UV */ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } +static inline bool is_early_uv_system(void) { return 0; } static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 22ab408177b2..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6490f618e096..b52bd2b6cdb4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -26,6 +26,7 @@ #include <asm/apic.h> #include <asm/intel-family.h> #include <asm/i8259.h> +#include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1433,6 +1434,9 @@ void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; + /* Don't change UV TSC multi-chassis synchronization */ + if (is_early_uv_system()) + return; if (!determine_cpu_tsc_frequencies(true)) return; loops_per_jiffy = get_loops_per_jiffy(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d7e9bce6ff61..51b953ad9d4e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; */ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; +/* + * In some cases, we need to preserve the GFN of a non-present or reserved + * SPTE when we usurp the upper five bits of the physical address space to + * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll + * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask + * left into the reserved bits, i.e. the GFN in the SPTE will be split into + * high and low parts. This mask covers the lower bits of the GFN. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; + + static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); @@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | - shadow_nonpresent_or_rsvd_mask; - u64 gpa = spte & ~mask; + u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) & shadow_nonpresent_or_rsvd_mask; @@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static void kvm_mmu_reset_all_pte_masks(void) { + u8 low_phys_bits; + shadow_user_mask = 0; shadow_accessed_mask = 0; shadow_dirty_mask = 0; @@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void) * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. */ + low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) + 52 - shadow_nonpresent_or_rsvd_mask_len) { shadow_nonpresent_or_rsvd_mask = rsvd_bits(boot_cpu_data.x86_phys_bits - shadow_nonpresent_or_rsvd_mask_len, boot_cpu_data.x86_phys_bits - 1); + low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + } + shadow_nonpresent_or_rsvd_lower_gfn_mask = + GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); } static int is_cpuid_PSE36(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06412ba46aa3..612fd17be635 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO); #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 -#define MSR_BITMAP_MODE_LM 4 #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL @@ -857,6 +856,7 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u64 vmcs01_guest_bndcfgs; u16 vpid02; u16 last_vpid; @@ -2899,8 +2899,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } - if (is_long_mode(&vmx->vcpu)) - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); @@ -2951,8 +2950,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) vmx->loaded_cpu_state = NULL; #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); @@ -2980,24 +2978,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - rdmsrl(MSR_KERNEL_GS_BASE, - vmx->msr_guest_kernel_gs_base); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + preempt_enable(); return vmx->msr_guest_kernel_gs_base; } static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - wrmsrl(MSR_KERNEL_GS_BASE, data); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + wrmsrl(MSR_KERNEL_GS_BASE, data); + preempt_enable(); vmx->msr_guest_kernel_gs_base = data; } #endif @@ -3533,9 +3526,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; - if (kvm_mpx_supported()) - msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; @@ -3552,8 +3542,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_ENTRY_LOAD_IA32_PAT; msrs->entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); - if (kvm_mpx_supported()) - msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; @@ -3601,12 +3589,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high); msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING; + /* * We can emulate "VMCS shadowing," even if the hardware * doesn't support it. @@ -3663,6 +3651,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (flexpriority_enabled) + msrs->secondary_ctls_high |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, msrs->misc_low, @@ -5073,19 +5065,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!msr) return; - /* - * MSR_KERNEL_GS_BASE is not intercepted when the guest is in - * 64-bit mode as a 64-bit kernel may frequently access the - * MSR. This means we need to manually save/restore the MSR - * when switching between guest and host state, but only if - * the guest is in 64-bit mode. Sync our cached value if the - * guest is transitioning to 32-bit mode and the CPU contains - * guest state, i.e. the cache is stale. - */ -#ifdef CONFIG_X86_64 - if (!(efer & EFER_LMA)) - (void)vmx_read_guest_kernel_gs_base(vmx); -#endif vcpu->arch.efer = efer; if (efer & EFER_LMA) { vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); @@ -6078,9 +6057,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) mode |= MSR_BITMAP_MODE_X2APIC_APICV; } - if (is_long_mode(vcpu)) - mode |= MSR_BITMAP_MODE_LM; - return mode; } @@ -6121,9 +6097,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) if (!changed) return; - vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, - !(mode & MSR_BITMAP_MODE_LM)); - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); @@ -6189,6 +6162,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static u8 vmx_get_rvi(void) +{ + return vmcs_read16(GUEST_INTR_STATUS) & 0xff; +} + static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6201,7 +6179,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) return false; - rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff; + rvi = vmx_get_rvi(); vapic_page = kmap(vmx->nested.virtual_apic_page); vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); @@ -10245,15 +10223,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; + if (!flexpriority_enabled && + !cpu_has_vmx_virtualize_x2apic_mode()) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_need_tpr_shadow(vcpu)) - return; - sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); @@ -10375,6 +10354,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } +static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) +{ + u8 rvi = vmx_get_rvi(); + u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -11264,6 +11251,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) #undef cr4_fixed1_update } +static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (kvm_mpx_supported()) { + bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); + + if (mpx_enabled) { + vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; + } else { + vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; + } + } +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -11280,8 +11284,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (nested_vmx_allowed(vcpu)) + if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); + nested_vmx_entry_exit_ctls_update(vcpu); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -12049,8 +12055,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - if (vmx_mpx_supported()) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + if (kvm_mpx_supported()) { + if (vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + else + vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); + } if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) @@ -12595,15 +12606,21 @@ 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; + bool evaluate_pending_interrupts; int r = 0; - vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) + evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + if (kvm_mpx_supported() && + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); @@ -12643,16 +12660,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) * 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)) { + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request, or checking RVI during evaluation of + * pending virtual interrupts. 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 (unlikely(evaluate_pending_interrupts)) kvm_make_request(KVM_REQ_EVENT, vcpu); - } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index edbf00ec56b3..ca717737347e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4698,7 +4698,7 @@ static void kvm_init_msr_list(void) */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: - if (!kvm_x86_ops->mpx_supported()) + if (!kvm_mpx_supported()) continue; break; case MSR_TSC_AUX: diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 94e1ed667b6e..41317c50a446 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -322,16 +322,11 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, /* * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and - * queue_hw_ctx after freeze the queue. So we could use q_usage_counter - * to avoid race with it. __blk_mq_update_nr_hw_queues will users - * synchronize_rcu to ensure all of the users go out of the critical - * section below and see zeroed q_usage_counter. + * queue_hw_ctx after freeze the queue, so we use q_usage_counter + * to avoid race with it. */ - rcu_read_lock(); - if (percpu_ref_is_zero(&q->q_usage_counter)) { - rcu_read_unlock(); + if (!percpu_ref_tryget(&q->q_usage_counter)) return; - } queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_tags *tags = hctx->tags; @@ -347,7 +342,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, bt_for_each(hctx, &tags->breserved_tags, fn, priv, true); bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false); } - rcu_read_unlock(); + blk_queue_exit(q); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, diff --git a/block/blk-mq.c b/block/blk-mq.c index 85a1c1a59c72..e3c39ea8e17b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1628,7 +1628,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) BUG_ON(!rq->q); if (rq->mq_ctx != this_ctx) { if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); @@ -1648,7 +1648,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) * on 'ctx_list'. Do those. */ if (this_ctx) { - trace_block_unplug(this_q, depth, from_schedule); + trace_block_unplug(this_q, depth, !from_schedule); blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list, from_schedule); } diff --git a/block/elevator.c b/block/elevator.c index 6a06b5d040e5..fae58b2f906f 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -609,7 +609,7 @@ void elv_drain_elevator(struct request_queue *q) while (e->type->ops.sq.elevator_dispatch_fn(q, 1)) ; - if (q->nr_sorted && printed++ < 10) { + if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) { printk(KERN_ERR "%s: forced dispatching is broken " "(nr_sorted=%u), please report this\n", q->elevator->type->elevator_name, q->nr_sorted); diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index cbec9adc01c7..ae4aa02e4dc6 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -2689,11 +2689,10 @@ static void ns_poll(struct timer_list *unused) PRINTK("nicstar: Entering ns_poll().\n"); for (i = 0; i < num_cards; i++) { card = cards[i]; - if (spin_is_locked(&card->int_lock)) { + if (!spin_trylock_irqsave(&card->int_lock, flags)) { /* Probably it isn't worth spinning */ continue; } - spin_lock_irqsave(&card->int_lock, flags); stat_w = 0; stat_r = readl(card->membase + STAT); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 3f68e2919dc5..a690fd400260 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1713,8 +1713,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_subordinate(dev, async); - if (async_error) + if (async_error) { + dev->power.direct_complete = false; goto Complete; + } /* * If a device configured to wake up the system from sleep states @@ -1726,6 +1728,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_wakeup_event(dev, 0); if (pm_wakeup_pending()) { + dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a71d817e900d..429d20131c7e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2670,8 +2670,8 @@ static void purge_persistent_grants(struct blkfront_info *info) 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); + gnt_list_entry->gref = GRANT_INVALID_REF; + list_add_tail(&gnt_list_entry->node, &rinfo->grants); } spin_unlock_irqrestore(&rinfo->ring_lock, flags); diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index ec8a4376f74f..2fab18fae4fc 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -180,26 +180,29 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) data->base = of_iomap(node, 0); if (!data->base) { pr_err("Could not map PIT address\n"); - return -ENXIO; + ret = -ENXIO; + goto exit; } data->mck = of_clk_get(node, 0); if (IS_ERR(data->mck)) { pr_err("Unable to get mck clk\n"); - return PTR_ERR(data->mck); + ret = PTR_ERR(data->mck); + goto exit; } ret = clk_prepare_enable(data->mck); if (ret) { pr_err("Unable to enable mck\n"); - return ret; + goto exit; } /* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { pr_err("Unable to get IRQ from DT\n"); - return -EINVAL; + ret = -EINVAL; + goto exit; } /* @@ -227,7 +230,7 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) ret = clocksource_register_hz(&data->clksrc, pit_rate); if (ret) { pr_err("Failed to register clocksource\n"); - return ret; + goto exit; } /* Set up irq handler */ @@ -236,7 +239,8 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) "at91_tick", data); if (ret) { pr_err("Unable to setup IRQ\n"); - return ret; + clocksource_unregister(&data->clksrc); + goto exit; } /* Set up and register clockevents */ @@ -254,6 +258,10 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) clockevents_register_device(&data->clkevt); return 0; + +exit: + kfree(data); + return ret; } TIMER_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit", at91sam926x_pit_dt_init); diff --git a/drivers/clocksource/timer-fttmr010.c b/drivers/clocksource/timer-fttmr010.c index c020038ebfab..cf93f6419b51 100644 --- a/drivers/clocksource/timer-fttmr010.c +++ b/drivers/clocksource/timer-fttmr010.c @@ -130,13 +130,17 @@ static int fttmr010_timer_set_next_event(unsigned long cycles, cr &= ~fttmr010->t1_enable_val; writel(cr, fttmr010->base + TIMER_CR); - /* Setup the match register forward/backward in time */ - cr = readl(fttmr010->base + TIMER1_COUNT); - if (fttmr010->count_down) - cr -= cycles; - else - cr += cycles; - writel(cr, fttmr010->base + TIMER1_MATCH1); + if (fttmr010->count_down) { + /* + * ASPEED Timer Controller will load TIMER1_LOAD register + * into TIMER1_COUNT register when the timer is re-enabled. + */ + writel(cycles, fttmr010->base + TIMER1_LOAD); + } else { + /* Setup the match register forward in time */ + cr = readl(fttmr010->base + TIMER1_COUNT); + writel(cr + cycles, fttmr010->base + TIMER1_MATCH1); + } /* Start */ cr = readl(fttmr010->base + TIMER_CR); diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c index 29e2e1a78a43..6949a9113dbb 100644 --- a/drivers/clocksource/timer-ti-32k.c +++ b/drivers/clocksource/timer-ti-32k.c @@ -97,6 +97,9 @@ static int __init ti_32k_timer_init(struct device_node *np) return -ENXIO; } + if (!of_machine_is_compatible("ti,am43")) + ti_32k_timer.cs.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; + ti_32k_timer.counter = ti_32k_timer.base; /* diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index a1830fa25fc5..2a3675c24032 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -44,7 +44,7 @@ enum _msm8996_version { struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev; -static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void) +static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void) { size_t len; u32 *msm_id; @@ -222,7 +222,7 @@ static int __init qcom_cpufreq_kryo_init(void) } module_init(qcom_cpufreq_kryo_init); -static void __init qcom_cpufreq_kryo_exit(void) +static void __exit qcom_cpufreq_kryo_exit(void) { platform_device_unregister(kryo_cpufreq_pdev); platform_driver_unregister(&qcom_cpufreq_kryo_driver); diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index d67667970f7e..ec40f991e6c6 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -1553,8 +1553,8 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request edesc->src_nents = src_nents; edesc->dst_nents = dst_nents; edesc->sec4_sg_bytes = sec4_sg_bytes; - edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) + - desc_bytes; + edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc + + desc_bytes); edesc->iv_dir = DMA_TO_DEVICE; /* Make sure IV is located in a DMAable area */ @@ -1757,8 +1757,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc( edesc->src_nents = src_nents; edesc->dst_nents = dst_nents; edesc->sec4_sg_bytes = sec4_sg_bytes; - edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) + - desc_bytes; + edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc + + desc_bytes); edesc->iv_dir = DMA_FROM_DEVICE; /* Make sure IV is located in a DMAable area */ diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 5c539af8ed60..010bbf607797 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -367,7 +367,8 @@ static inline void dsgl_walk_init(struct dsgl_walk *walk, walk->to = (struct phys_sge_pairs *)(dsgl + 1); } -static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid) +static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid, + int pci_chan_id) { struct cpl_rx_phys_dsgl *phys_cpl; @@ -385,6 +386,7 @@ static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid) phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR; phys_cpl->rss_hdr_int.qid = htons(qid); phys_cpl->rss_hdr_int.hash_val = 0; + phys_cpl->rss_hdr_int.channel = pci_chan_id; } static inline void dsgl_walk_add_page(struct dsgl_walk *walk, @@ -718,7 +720,7 @@ static inline void create_wreq(struct chcr_context *ctx, FILL_WR_RX_Q_ID(ctx->dev->rx_channel_id, qid, !!lcb, ctx->tx_qidx); - chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id, + chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id, qid); chcr_req->ulptx.len = htonl((DIV_ROUND_UP(len16, 16) - ((sizeof(chcr_req->wreq)) >> 4))); @@ -1339,16 +1341,23 @@ static int chcr_device_init(struct chcr_context *ctx) adap->vres.ncrypto_fc); rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan; txq_perchan = ntxq / u_ctx->lldi.nchan; - rxq_idx = ctx->dev->tx_channel_id * rxq_perchan; - rxq_idx += id % rxq_perchan; - txq_idx = ctx->dev->tx_channel_id * txq_perchan; - txq_idx += id % txq_perchan; spin_lock(&ctx->dev->lock_chcr_dev); - ctx->rx_qidx = rxq_idx; - ctx->tx_qidx = txq_idx; + ctx->tx_chan_id = ctx->dev->tx_channel_id; ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id; ctx->dev->rx_channel_id = 0; spin_unlock(&ctx->dev->lock_chcr_dev); + rxq_idx = ctx->tx_chan_id * rxq_perchan; + rxq_idx += id % rxq_perchan; + txq_idx = ctx->tx_chan_id * txq_perchan; + txq_idx += id % txq_perchan; + ctx->rx_qidx = rxq_idx; + ctx->tx_qidx = txq_idx; + /* Channel Id used by SGE to forward packet to Host. + * Same value should be used in cpl_fw6_pld RSS_CH field + * by FW. Driver programs PCI channel ID to be used in fw + * at the time of queue allocation with value "pi->tx_chan" + */ + ctx->pci_chan_id = txq_idx / txq_perchan; } out: return err; @@ -2503,6 +2512,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req, struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct dsgl_walk dsgl_walk; unsigned int authsize = crypto_aead_authsize(tfm); + struct chcr_context *ctx = a_ctx(tfm); u32 temp; dsgl_walk_init(&dsgl_walk, phys_cpl); @@ -2512,7 +2522,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req, dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma); temp = req->cryptlen + (reqctx->op ? -authsize : authsize); dsgl_walk_add_sg(&dsgl_walk, req->dst, temp, req->assoclen); - dsgl_walk_end(&dsgl_walk, qid); + dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id); } void chcr_add_cipher_src_ent(struct ablkcipher_request *req, @@ -2544,6 +2554,8 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req, unsigned short qid) { struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req); + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req); + struct chcr_context *ctx = c_ctx(tfm); struct dsgl_walk dsgl_walk; dsgl_walk_init(&dsgl_walk, phys_cpl); @@ -2552,7 +2564,7 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req, reqctx->dstsg = dsgl_walk.last_sg; reqctx->dst_ofst = dsgl_walk.last_sg_len; - dsgl_walk_end(&dsgl_walk, qid); + dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id); } void chcr_add_hash_src_ent(struct ahash_request *req, diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index 54835cb109e5..0d2c70c344f3 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -255,6 +255,8 @@ struct chcr_context { struct chcr_dev *dev; unsigned char tx_qidx; unsigned char rx_qidx; + unsigned char tx_chan_id; + unsigned char pci_chan_id; struct __crypto_ctx crypto_ctx[0]; }; diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c index a10c418d4e5c..56bd28174f52 100644 --- a/drivers/crypto/mxs-dcp.c +++ b/drivers/crypto/mxs-dcp.c @@ -63,7 +63,7 @@ struct dcp { struct dcp_coherent_block *coh; struct completion completion[DCP_MAX_CHANS]; - struct mutex mutex[DCP_MAX_CHANS]; + spinlock_t lock[DCP_MAX_CHANS]; struct task_struct *thread[DCP_MAX_CHANS]; struct crypto_queue queue[DCP_MAX_CHANS]; }; @@ -349,13 +349,20 @@ static int dcp_chan_thread_aes(void *data) int ret; - do { - __set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); - mutex_lock(&sdcp->mutex[chan]); + spin_lock(&sdcp->lock[chan]); backlog = crypto_get_backlog(&sdcp->queue[chan]); arq = crypto_dequeue_request(&sdcp->queue[chan]); - mutex_unlock(&sdcp->mutex[chan]); + spin_unlock(&sdcp->lock[chan]); + + if (!backlog && !arq) { + schedule(); + continue; + } + + set_current_state(TASK_RUNNING); if (backlog) backlog->complete(backlog, -EINPROGRESS); @@ -363,11 +370,8 @@ static int dcp_chan_thread_aes(void *data) if (arq) { ret = mxs_dcp_aes_block_crypt(arq); arq->complete(arq, ret); - continue; } - - schedule(); - } while (!kthread_should_stop()); + } return 0; } @@ -409,9 +413,9 @@ static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb) rctx->ecb = ecb; actx->chan = DCP_CHAN_CRYPTO; - mutex_lock(&sdcp->mutex[actx->chan]); + spin_lock(&sdcp->lock[actx->chan]); ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base); - mutex_unlock(&sdcp->mutex[actx->chan]); + spin_unlock(&sdcp->lock[actx->chan]); wake_up_process(sdcp->thread[actx->chan]); @@ -640,13 +644,20 @@ static int dcp_chan_thread_sha(void *data) struct ahash_request *req; int ret, fini; - do { - __set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); - mutex_lock(&sdcp->mutex[chan]); + spin_lock(&sdcp->lock[chan]); backlog = crypto_get_backlog(&sdcp->queue[chan]); arq = crypto_dequeue_request(&sdcp->queue[chan]); - mutex_unlock(&sdcp->mutex[chan]); + spin_unlock(&sdcp->lock[chan]); + + if (!backlog && !arq) { + schedule(); + continue; + } + + set_current_state(TASK_RUNNING); if (backlog) backlog->complete(backlog, -EINPROGRESS); @@ -658,12 +669,8 @@ static int dcp_chan_thread_sha(void *data) ret = dcp_sha_req_to_buf(arq); fini = rctx->fini; arq->complete(arq, ret); - if (!fini) - continue; } - - schedule(); - } while (!kthread_should_stop()); + } return 0; } @@ -721,9 +728,9 @@ static int dcp_sha_update_fx(struct ahash_request *req, int fini) rctx->init = 1; } - mutex_lock(&sdcp->mutex[actx->chan]); + spin_lock(&sdcp->lock[actx->chan]); ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base); - mutex_unlock(&sdcp->mutex[actx->chan]); + spin_unlock(&sdcp->lock[actx->chan]); wake_up_process(sdcp->thread[actx->chan]); mutex_unlock(&actx->mutex); @@ -997,7 +1004,7 @@ static int mxs_dcp_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sdcp); for (i = 0; i < DCP_MAX_CHANS; i++) { - mutex_init(&sdcp->mutex[i]); + spin_lock_init(&sdcp->lock[i]); init_completion(&sdcp->completion[i]); crypto_init_queue(&sdcp->queue[i], 50); } diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/qat/qat_c3xxx/adf_drv.c index ba197f34c252..763c2166ee0e 100644 --- a/drivers/crypto/qat/qat_c3xxx/adf_drv.c +++ b/drivers/crypto/qat/qat_c3xxx/adf_drv.c @@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_C3XXX_PCI_DEVICE_ID: @@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c index 24ec908eb26c..613c7d5644ce 100644 --- a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c +++ b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c @@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_C3XXXIOV_PCI_DEVICE_ID: @@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c index 59a5a0df50b6..9cb832963357 100644 --- a/drivers/crypto/qat/qat_c62x/adf_drv.c +++ b/drivers/crypto/qat/qat_c62x/adf_drv.c @@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_C62X_PCI_DEVICE_ID: @@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/crypto/qat/qat_c62xvf/adf_drv.c b/drivers/crypto/qat/qat_c62xvf/adf_drv.c index b9f3e0e4fde9..278452b8ef81 100644 --- a/drivers/crypto/qat/qat_c62xvf/adf_drv.c +++ b/drivers/crypto/qat/qat_c62xvf/adf_drv.c @@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_C62XIOV_PCI_DEVICE_ID: @@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c index be5c5a988ca5..3a9708ef4ce2 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c +++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c @@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_DH895XCC_PCI_DEVICE_ID: @@ -237,8 +238,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c index 26ab17bfc6da..3da0f951cb59 100644 --- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c +++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c @@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct adf_hw_device_data *hw_data; char name[ADF_DEVICE_NAME_LENGTH]; unsigned int i, bar_nr; - int ret, bar_mask; + unsigned long bar_mask; + int ret; switch (ent->device) { case ADF_DH895XCCIOV_PCI_DEVICE_ID: @@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Find and map all the device's BARS */ i = 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); - for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, - ADF_PCI_MAX_BARS * 2) { + for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) { struct adf_bar *bar = &accel_pci_dev->pci_bars[i++]; bar->base_addr = pci_resource_start(pdev, bar_nr); diff --git a/drivers/dax/device.c b/drivers/dax/device.c index bbe4d72ca105..948806e57cee 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -535,6 +535,11 @@ static unsigned long dax_get_unmapped_area(struct file *filp, return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); } +static const struct address_space_operations dev_dax_aops = { + .set_page_dirty = noop_set_page_dirty, + .invalidatepage = noop_invalidatepage, +}; + static int dax_open(struct inode *inode, struct file *filp) { struct dax_device *dax_dev = inode_dax(inode); @@ -544,6 +549,7 @@ static int dax_open(struct inode *inode, struct file *filp) dev_dbg(&dev_dax->dev, "trace\n"); inode->i_mapping = __dax_inode->i_mapping; inode->i_mapping->host = __dax_inode; + inode->i_mapping->a_ops = &dev_dax_aops; filp->f_mapping = inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); filp->private_data = dev_dax; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e8f8a1999393..a57300c1d649 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -571,7 +571,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_descs; lh->descs[i] = desc; - count = i; + count = i + 1; if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 0cc5190f4f36..5f3f54073818 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -258,6 +258,8 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) { int i; + cancel_delayed_work_sync(&adev->vce.idle_work); + if (adev->vce.vcpu_bo == NULL) return 0; @@ -268,7 +270,6 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0; - cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index fd654a4406db..400fc74bbae2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -153,11 +153,11 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) unsigned size; void *ptr; + cancel_delayed_work_sync(&adev->vcn.idle_work); + if (adev->vcn.vcpu_bo == NULL) return 0; - cancel_delayed_work_sync(&adev->vcn.idle_work); - size = amdgpu_bo_size(adev->vcn.vcpu_bo); ptr = adev->vcn.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ec0d62a16e53..4f22e745df51 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -358,8 +358,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd) { - int retval; struct mqd_manager *mqd_mgr; + int retval; mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE); if (!mqd_mgr) @@ -387,8 +387,12 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, if (!q->properties.is_active) return 0; - retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, - &q->properties, q->process->mm); + if (WARN(q->process->mm != current->mm, + "should only run in user thread")) + retval = -EFAULT; + else + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, + &q->properties, current->mm); if (retval) goto out_uninit_mqd; @@ -545,9 +549,15 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) retval = map_queues_cpsch(dqm); else if (q->properties.is_active && (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || - q->properties.type == KFD_QUEUE_TYPE_SDMA)) - retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, - &q->properties, q->process->mm); + q->properties.type == KFD_QUEUE_TYPE_SDMA)) { + if (WARN(q->process->mm != current->mm, + "should only run in user thread")) + retval = -EFAULT; + else + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, + q->pipe, q->queue, + &q->properties, current->mm); + } out_unlock: dqm_unlock(dqm); @@ -653,6 +663,7 @@ out: static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { + struct mm_struct *mm = NULL; struct queue *q; struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; @@ -686,6 +697,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, kfd_flush_tlb(pdd); } + /* Take a safe reference to the mm_struct, which may otherwise + * disappear even while the kfd_process is still referenced. + */ + mm = get_task_mm(pdd->process->lead_thread); + if (!mm) { + retval = -EFAULT; + goto out; + } + /* activate all active queues on the qpd */ list_for_each_entry(q, &qpd->queues_list, list) { if (!q->properties.is_evicted) @@ -700,14 +720,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, q->properties.is_evicted = false; q->properties.is_active = true; retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, - q->queue, &q->properties, - q->process->mm); + q->queue, &q->properties, mm); if (retval) goto out; dqm->queue_count++; } qpd->evicted = 0; out: + if (mm) + mmput(mm); dqm_unlock(dqm); return retval; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 800f481a6995..6903fe6c894b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -641,6 +641,87 @@ amdgpu_dm_find_first_crtc_matching_connector(struct drm_atomic_state *state, return NULL; } +static void emulated_link_detect(struct dc_link *link) +{ + struct dc_sink_init_data sink_init_data = { 0 }; + struct display_sink_capability sink_caps = { 0 }; + enum dc_edid_status edid_status; + struct dc_context *dc_ctx = link->ctx; + struct dc_sink *sink = NULL; + struct dc_sink *prev_sink = NULL; + + link->type = dc_connection_none; + prev_sink = link->local_sink; + + if (prev_sink != NULL) + dc_sink_retain(prev_sink); + + switch (link->connector_signal) { + case SIGNAL_TYPE_HDMI_TYPE_A: { + sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C; + sink_caps.signal = SIGNAL_TYPE_HDMI_TYPE_A; + break; + } + + case SIGNAL_TYPE_DVI_SINGLE_LINK: { + sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C; + sink_caps.signal = SIGNAL_TYPE_DVI_SINGLE_LINK; + break; + } + + case SIGNAL_TYPE_DVI_DUAL_LINK: { + sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C; + sink_caps.signal = SIGNAL_TYPE_DVI_DUAL_LINK; + break; + } + + case SIGNAL_TYPE_LVDS: { + sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C; + sink_caps.signal = SIGNAL_TYPE_LVDS; + break; + } + + case SIGNAL_TYPE_EDP: { + sink_caps.transaction_type = + DDC_TRANSACTION_TYPE_I2C_OVER_AUX; + sink_caps.signal = SIGNAL_TYPE_EDP; + break; + } + + case SIGNAL_TYPE_DISPLAY_PORT: { + sink_caps.transaction_type = + DDC_TRANSACTION_TYPE_I2C_OVER_AUX; + sink_caps.signal = SIGNAL_TYPE_VIRTUAL; + break; + } + + default: + DC_ERROR("Invalid connector type! signal:%d\n", + link->connector_signal); + return; + } + + sink_init_data.link = link; + sink_init_data.sink_signal = sink_caps.signal; + + sink = dc_sink_create(&sink_init_data); + if (!sink) { + DC_ERROR("Failed to create sink!\n"); + return; + } + + link->local_sink = sink; + + edid_status = dm_helpers_read_local_edid( + link->ctx, + link, + sink); + + if (edid_status != EDID_OK) + DC_ERROR("Failed to read EDID"); + +} + static int dm_resume(void *handle) { struct amdgpu_device *adev = handle; @@ -654,6 +735,7 @@ static int dm_resume(void *handle) struct drm_plane *plane; struct drm_plane_state *new_plane_state; struct dm_plane_state *dm_new_plane_state; + enum dc_connection_type new_connection_type = dc_connection_none; int ret; int i; @@ -684,7 +766,13 @@ static int dm_resume(void *handle) continue; mutex_lock(&aconnector->hpd_lock); - dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + if (!dc_link_detect_sink(aconnector->dc_link, &new_connection_type)) + DRM_ERROR("KMS: Failed to detect connector\n"); + + if (aconnector->base.force && new_connection_type == dc_connection_none) + emulated_link_detect(aconnector->dc_link); + else + dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); if (aconnector->fake_enable && aconnector->dc_link->local_sink) aconnector->fake_enable = false; @@ -922,6 +1010,7 @@ static void handle_hpd_irq(void *param) struct amdgpu_dm_connector *aconnector = (struct amdgpu_dm_connector *)param; struct drm_connector *connector = &aconnector->base; struct drm_device *dev = connector->dev; + enum dc_connection_type new_connection_type = dc_connection_none; /* In case of failure or MST no need to update connector status or notify the OS * since (for MST case) MST does this in it's own context. @@ -931,7 +1020,21 @@ static void handle_hpd_irq(void *param) if (aconnector->fake_enable) aconnector->fake_enable = false; - if (dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD)) { + if (!dc_link_detect_sink(aconnector->dc_link, &new_connection_type)) + DRM_ERROR("KMS: Failed to detect connector\n"); + + if (aconnector->base.force && new_connection_type == dc_connection_none) { + emulated_link_detect(aconnector->dc_link); + + + drm_modeset_lock_all(dev); + dm_restore_drm_connector_state(dev, connector); + drm_modeset_unlock_all(dev); + + if (aconnector->base.force == DRM_FORCE_UNSPECIFIED) + drm_kms_helper_hotplug_event(dev); + + } else if (dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD)) { amdgpu_dm_update_connector_after_detect(aconnector); @@ -1031,6 +1134,7 @@ static void handle_hpd_rx_irq(void *param) struct drm_device *dev = connector->dev; struct dc_link *dc_link = aconnector->dc_link; bool is_mst_root_connector = aconnector->mst_mgr.mst_state; + enum dc_connection_type new_connection_type = dc_connection_none; /* TODO:Temporary add mutex to protect hpd interrupt not have a gpio * conflict, after implement i2c helper, this mutex should be @@ -1042,7 +1146,24 @@ static void handle_hpd_rx_irq(void *param) if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) && !is_mst_root_connector) { /* Downstream Port status changed. */ - if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) { + if (!dc_link_detect_sink(dc_link, &new_connection_type)) + DRM_ERROR("KMS: Failed to detect connector\n"); + + if (aconnector->base.force && new_connection_type == dc_connection_none) { + emulated_link_detect(dc_link); + + if (aconnector->fake_enable) + aconnector->fake_enable = false; + + amdgpu_dm_update_connector_after_detect(aconnector); + + + drm_modeset_lock_all(dev); + dm_restore_drm_connector_state(dev, connector); + drm_modeset_unlock_all(dev); + + drm_kms_helper_hotplug_event(dev); + } else if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) { if (aconnector->fake_enable) aconnector->fake_enable = false; @@ -1433,6 +1554,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) struct amdgpu_mode_info *mode_info = &adev->mode_info; uint32_t link_cnt; int32_t total_overlay_planes, total_primary_planes; + enum dc_connection_type new_connection_type = dc_connection_none; link_cnt = dm->dc->caps.max_links; if (amdgpu_dm_mode_config_init(dm->adev)) { @@ -1499,7 +1621,14 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) link = dc_get_link_at_index(dm->dc, i); - if (dc_link_detect(link, DETECT_REASON_BOOT)) { + if (!dc_link_detect_sink(link, &new_connection_type)) + DRM_ERROR("KMS: Failed to detect connector\n"); + + if (aconnector->base.force && new_connection_type == dc_connection_none) { + emulated_link_detect(link); + amdgpu_dm_update_connector_after_detect(aconnector); + + } else if (dc_link_detect(link, DETECT_REASON_BOOT)) { amdgpu_dm_update_connector_after_detect(aconnector); register_backlight_device(dm, link); } @@ -2494,7 +2623,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (dm_state && dm_state->freesync_capable) stream->ignore_msa_timing_param = true; finish: - if (sink && sink->sink_signal == SIGNAL_TYPE_VIRTUAL) + if (sink && sink->sink_signal == SIGNAL_TYPE_VIRTUAL && aconnector->base.force != DRM_FORCE_ON) dc_sink_release(sink); return stream; @@ -4504,12 +4633,18 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) } spin_unlock_irqrestore(&adev->ddev->event_lock, flags); - /* Signal HW programming completion */ - drm_atomic_helper_commit_hw_done(state); if (wait_for_vblank) drm_atomic_helper_wait_for_flip_done(dev, state); + /* + * FIXME: + * Delay hw_done() until flip_done() is signaled. This is to block + * another commit from freeing the CRTC state while we're still + * waiting on flip_done. + */ + drm_atomic_helper_commit_hw_done(state); + drm_atomic_helper_cleanup_planes(dev, state); /* Finally, drop a runtime PM reference for each newly disabled CRTC, 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 37eaf72ace54..fced3c1c2ef5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -195,7 +195,7 @@ static bool program_hpd_filter( return result; } -static bool detect_sink(struct dc_link *link, enum dc_connection_type *type) +bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type) { uint32_t is_hpd_high = 0; struct gpio *hpd_pin; @@ -604,7 +604,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) if (link->connector_signal == SIGNAL_TYPE_VIRTUAL) return false; - if (false == detect_sink(link, &new_connection_type)) { + if (false == dc_link_detect_sink(link, &new_connection_type)) { BREAK_TO_DEBUGGER(); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index d43cefbc43d3..1b48ab9aea89 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -215,6 +215,7 @@ void dc_link_enable_hpd_filter(struct dc_link *link, bool enable); bool dc_link_is_dp_sink_present(struct dc_link *link); +bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type); /* * DPCD access interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 14384d9675a8..b2f308766a9e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2560,7 +2560,7 @@ static void pplib_apply_display_requirements( dc->prev_display_config = *pp_display_cfg; } -void dce110_set_bandwidth( +static void dce110_set_bandwidth( struct dc *dc, struct dc_state *context, bool decrease_allowed) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h index e4c5db75c4c6..d6db3dbd9015 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h @@ -68,11 +68,6 @@ void dce110_fill_display_configs( const struct dc_state *context, struct dm_pp_display_configuration *pp_display_cfg); -void dce110_set_bandwidth( - struct dc *dc, - struct dc_state *context, - bool decrease_allowed); - uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context); void dp_receiver_power_ctrl(struct dc_link *link, bool on); diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c index 5853522a6182..eb0f5f9a973b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c @@ -244,17 +244,6 @@ static void dce120_update_dchub( dh_data->dchub_info_valid = false; } -static void dce120_set_bandwidth( - struct dc *dc, - struct dc_state *context, - bool decrease_allowed) -{ - if (context->stream_count <= 0) - return; - - dce110_set_bandwidth(dc, context, decrease_allowed); -} - void dce120_hw_sequencer_construct(struct dc *dc) { /* All registers used by dce11.2 match those in dce11 in offset and @@ -263,6 +252,5 @@ void dce120_hw_sequencer_construct(struct dc *dc) dce110_hw_sequencer_construct(dc); dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating; dc->hwss.update_dchub = dce120_update_dchub; - dc->hwss.set_bandwidth = dce120_set_bandwidth; } diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index 08b5bb219816..94d6dabec2dc 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -754,6 +754,7 @@ static int malidp_bind(struct device *dev) drm->irq_enabled = true; ret = drm_vblank_init(drm, drm->mode_config.num_crtc); + drm_crtc_vblank_reset(&malidp->crtc); if (ret < 0) { DRM_ERROR("failed to initialise vblank\n"); goto vblank_fail; diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c index c94a4422e0e9..2781e462c1ed 100644 --- a/drivers/gpu/drm/arm/malidp_hw.c +++ b/drivers/gpu/drm/arm/malidp_hw.c @@ -384,7 +384,8 @@ static long malidp500_se_calc_mclk(struct malidp_hw_device *hwdev, static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev, dma_addr_t *addrs, s32 *pitches, - int num_planes, u16 w, u16 h, u32 fmt_id) + int num_planes, u16 w, u16 h, u32 fmt_id, + const s16 *rgb2yuv_coeffs) { u32 base = MALIDP500_SE_MEMWRITE_BASE; u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK); @@ -416,6 +417,16 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h), MALIDP500_SE_MEMWRITE_OUT_SIZE); + + if (rgb2yuv_coeffs) { + int i; + + for (i = 0; i < MALIDP_COLORADJ_NUM_COEFFS; i++) { + malidp_hw_write(hwdev, rgb2yuv_coeffs[i], + MALIDP500_SE_RGB_YUV_COEFFS + i * 4); + } + } + malidp_hw_setbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL); return 0; @@ -658,7 +669,8 @@ static long malidp550_se_calc_mclk(struct malidp_hw_device *hwdev, static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev, dma_addr_t *addrs, s32 *pitches, - int num_planes, u16 w, u16 h, u32 fmt_id) + int num_planes, u16 w, u16 h, u32 fmt_id, + const s16 *rgb2yuv_coeffs) { u32 base = MALIDP550_SE_MEMWRITE_BASE; u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK); @@ -689,6 +701,15 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev, malidp_hw_setbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN, MALIDP550_SE_CONTROL); + if (rgb2yuv_coeffs) { + int i; + + for (i = 0; i < MALIDP_COLORADJ_NUM_COEFFS; i++) { + malidp_hw_write(hwdev, rgb2yuv_coeffs[i], + MALIDP550_SE_RGB_YUV_COEFFS + i * 4); + } + } + return 0; } diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h index ad2e96915d44..9fc94c08190f 100644 --- a/drivers/gpu/drm/arm/malidp_hw.h +++ b/drivers/gpu/drm/arm/malidp_hw.h @@ -191,7 +191,8 @@ struct malidp_hw { * @param fmt_id - internal format ID of output buffer */ int (*enable_memwrite)(struct malidp_hw_device *hwdev, dma_addr_t *addrs, - s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id); + s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id, + const s16 *rgb2yuv_coeffs); /* * Disable the writing to memory of the next frame's content. diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index ba6ae66387c9..91472e5e0c8b 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -26,6 +26,8 @@ struct malidp_mw_connector_state { s32 pitches[2]; u8 format; u8 n_planes; + bool rgb2yuv_initialized; + const s16 *rgb2yuv_coeffs; }; static int malidp_mw_connector_get_modes(struct drm_connector *connector) @@ -84,7 +86,7 @@ static void malidp_mw_connector_destroy(struct drm_connector *connector) static struct drm_connector_state * malidp_mw_connector_duplicate_state(struct drm_connector *connector) { - struct malidp_mw_connector_state *mw_state; + struct malidp_mw_connector_state *mw_state, *mw_current_state; if (WARN_ON(!connector->state)) return NULL; @@ -93,7 +95,10 @@ malidp_mw_connector_duplicate_state(struct drm_connector *connector) if (!mw_state) return NULL; - /* No need to preserve any of our driver-local data */ + mw_current_state = to_mw_state(connector->state); + mw_state->rgb2yuv_coeffs = mw_current_state->rgb2yuv_coeffs; + mw_state->rgb2yuv_initialized = mw_current_state->rgb2yuv_initialized; + __drm_atomic_helper_connector_duplicate_state(connector, &mw_state->base); return &mw_state->base; @@ -108,6 +113,13 @@ static const struct drm_connector_funcs malidp_mw_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; +static const s16 rgb2yuv_coeffs_bt709_limited[MALIDP_COLORADJ_NUM_COEFFS] = { + 47, 157, 16, + -26, -87, 112, + 112, -102, -10, + 16, 128, 128 +}; + static int malidp_mw_encoder_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, @@ -157,6 +169,9 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder, } mw_state->n_planes = n_planes; + if (fb->format->is_yuv) + mw_state->rgb2yuv_coeffs = rgb2yuv_coeffs_bt709_limited; + return 0; } @@ -239,10 +254,12 @@ void malidp_mw_atomic_commit(struct drm_device *drm, drm_writeback_queue_job(mw_conn, conn_state->writeback_job); conn_state->writeback_job = NULL; - hwdev->hw->enable_memwrite(hwdev, mw_state->addrs, mw_state->pitches, mw_state->n_planes, - fb->width, fb->height, mw_state->format); + fb->width, fb->height, mw_state->format, + !mw_state->rgb2yuv_initialized ? + mw_state->rgb2yuv_coeffs : NULL); + mw_state->rgb2yuv_initialized = !!mw_state->rgb2yuv_coeffs; } else { DRM_DEV_DEBUG_DRIVER(drm->dev, "Disable memwrite\n"); hwdev->hw->disable_memwrite(hwdev); diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h index 3579d36b2a71..6ffe849774f2 100644 --- a/drivers/gpu/drm/arm/malidp_regs.h +++ b/drivers/gpu/drm/arm/malidp_regs.h @@ -205,6 +205,7 @@ #define MALIDP500_SE_BASE 0x00c00 #define MALIDP500_SE_CONTROL 0x00c0c #define MALIDP500_SE_MEMWRITE_OUT_SIZE 0x00c2c +#define MALIDP500_SE_RGB_YUV_COEFFS 0x00C74 #define MALIDP500_SE_MEMWRITE_BASE 0x00e00 #define MALIDP500_DC_IRQ_BASE 0x00f00 #define MALIDP500_CONFIG_VALID 0x00f00 @@ -238,6 +239,7 @@ #define MALIDP550_SE_CONTROL 0x08010 #define MALIDP550_SE_MEMWRITE_ONESHOT (1 << 7) #define MALIDP550_SE_MEMWRITE_OUT_SIZE 0x08030 +#define MALIDP550_SE_RGB_YUV_COEFFS 0x08078 #define MALIDP550_SE_MEMWRITE_BASE 0x08100 #define MALIDP550_DC_BASE 0x0c000 #define MALIDP550_DC_CONTROL 0x0c010 diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index baff50a4c234..df31c3815092 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -63,20 +63,21 @@ static void drm_client_close(struct drm_client_dev *client) EXPORT_SYMBOL(drm_client_close); /** - * drm_client_new - Create a DRM client + * drm_client_init - Initialise a DRM client * @dev: DRM device * @client: DRM client * @name: Client name * @funcs: DRM client functions (optional) * + * This initialises the client and opens a &drm_file. Use drm_client_add() to complete the process. * The caller needs to hold a reference on @dev before calling this function. * The client is freed when the &drm_device is unregistered. See drm_client_release(). * * Returns: * Zero on success or negative error code on failure. */ -int drm_client_new(struct drm_device *dev, struct drm_client_dev *client, - const char *name, const struct drm_client_funcs *funcs) +int drm_client_init(struct drm_device *dev, struct drm_client_dev *client, + const char *name, const struct drm_client_funcs *funcs) { int ret; @@ -95,10 +96,6 @@ int drm_client_new(struct drm_device *dev, struct drm_client_dev *client, if (ret) goto err_put_module; - mutex_lock(&dev->clientlist_mutex); - list_add(&client->list, &dev->clientlist); - mutex_unlock(&dev->clientlist_mutex); - drm_dev_get(dev); return 0; @@ -109,13 +106,33 @@ err_put_module: return ret; } -EXPORT_SYMBOL(drm_client_new); +EXPORT_SYMBOL(drm_client_init); + +/** + * drm_client_add - Add client to the device list + * @client: DRM client + * + * Add the client to the &drm_device client list to activate its callbacks. + * @client must be initialized by a call to drm_client_init(). After + * drm_client_add() it is no longer permissible to call drm_client_release() + * directly (outside the unregister callback), instead cleanup will happen + * automatically on driver unload. + */ +void drm_client_add(struct drm_client_dev *client) +{ + struct drm_device *dev = client->dev; + + mutex_lock(&dev->clientlist_mutex); + list_add(&client->list, &dev->clientlist); + mutex_unlock(&dev->clientlist_mutex); +} +EXPORT_SYMBOL(drm_client_add); /** * drm_client_release - Release DRM client resources * @client: DRM client * - * Releases resources by closing the &drm_file that was opened by drm_client_new(). + * Releases resources by closing the &drm_file that was opened by drm_client_init(). * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set. * * This function should only be called from the unregister callback. An exception diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index 9da36a6271d3..9ac1f2e0f064 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -160,7 +160,7 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev, fb_helper = &fbdev_cma->fb_helper; - ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL); + ret = drm_client_init(dev, &fb_helper->client, "fbdev", NULL); if (ret) goto err_free; @@ -169,6 +169,8 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev, if (ret) goto err_client_put; + drm_client_add(&fb_helper->client); + return fbdev_cma; err_client_put: diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 16ec93b75dbf..515a7aec57ac 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -3218,12 +3218,14 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) if (!fb_helper) return -ENOMEM; - ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs); + ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs); if (ret) { kfree(fb_helper); return ret; } + drm_client_add(&fb_helper->client); + fb_helper->preferred_bpp = preferred_bpp; drm_fbdev_client_hotplug(&fb_helper->client); diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index b54fb78a283c..b82da96ded5c 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -566,14 +566,14 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, lessee_priv->is_master = 1; lessee_priv->authenticated = 1; - /* Hook up the fd */ - fd_install(fd, lessee_file); - /* Pass fd back to userspace */ DRM_DEBUG_LEASE("Returning fd %d id %d\n", fd, lessee->lessee_id); cl->fd = fd; cl->lessee_id = lessee->lessee_id; + /* Hook up the fd */ + fd_install(fd, lessee_file); + DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n"); return 0; diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index b902361dee6e..1d9a9d2fe0e0 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -24,7 +24,6 @@ #include <linux/err.h> #include <linux/module.h> -#include <drm/drm_device.h> #include <drm/drm_crtc.h> #include <drm/drm_panel.h> @@ -105,13 +104,6 @@ int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector) if (panel->connector) return -EBUSY; - panel->link = device_link_add(connector->dev->dev, panel->dev, 0); - if (!panel->link) { - dev_err(panel->dev, "failed to link panel to %s\n", - dev_name(connector->dev->dev)); - return -EINVAL; - } - panel->connector = connector; panel->drm = connector->dev; @@ -133,8 +125,6 @@ EXPORT_SYMBOL(drm_panel_attach); */ int drm_panel_detach(struct drm_panel *panel) { - device_link_del(panel->link); - panel->connector = NULL; panel->drm = NULL; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index adb3cb27d31e..759278fef35a 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -97,6 +97,8 @@ static int drm_syncobj_fence_get_or_add_callback(struct drm_syncobj *syncobj, { int ret; + WARN_ON(*fence); + *fence = drm_syncobj_fence_get(syncobj); if (*fence) return 1; @@ -743,6 +745,9 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { for (i = 0; i < count; ++i) { + if (entries[i].fence) + continue; + drm_syncobj_fence_get_or_add_callback(syncobjs[i], &entries[i].fence, &entries[i].syncobj_cb, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 9b2720b41571..83c1f46670bf 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -592,8 +592,6 @@ static int etnaviv_pdev_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct component_match *match = NULL; - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (!dev->platform_data) { struct device_node *core_node; @@ -655,13 +653,30 @@ static int __init etnaviv_init(void) for_each_compatible_node(np, NULL, "vivante,gc") { if (!of_device_is_available(np)) continue; - pdev = platform_device_register_simple("etnaviv", -1, - NULL, 0); - if (IS_ERR(pdev)) { - ret = PTR_ERR(pdev); + + pdev = platform_device_alloc("etnaviv", -1); + if (!pdev) { + ret = -ENOMEM; + of_node_put(np); + goto unregister_platform_driver; + } + pdev->dev.coherent_dma_mask = DMA_BIT_MASK(40); + pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + + /* + * Apply the same DMA configuration to the virtual etnaviv + * device as the GPU we found. This assumes that all Vivante + * GPUs in the system share the same DMA constraints. + */ + of_dma_configure(&pdev->dev, np, true); + + ret = platform_device_add(pdev); + if (ret) { + platform_device_put(pdev); of_node_put(np); goto unregister_platform_driver; } + etnaviv_drm = pdev; of_node_put(np); break; diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.h b/drivers/gpu/drm/exynos/exynos_drm_iommu.h index 87f6b5672e11..797d9ee5f15a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_iommu.h +++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.h @@ -55,37 +55,12 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv, static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv, unsigned long start, unsigned long size) { - struct iommu_domain *domain; - int ret; - - domain = iommu_domain_alloc(priv->dma_dev->bus); - if (!domain) - return -ENOMEM; - - ret = iommu_get_dma_cookie(domain); - if (ret) - goto free_domain; - - ret = iommu_dma_init_domain(domain, start, size, NULL); - if (ret) - goto put_cookie; - - priv->mapping = domain; + priv->mapping = iommu_get_domain_for_dev(priv->dma_dev); return 0; - -put_cookie: - iommu_put_dma_cookie(domain); -free_domain: - iommu_domain_free(domain); - return ret; } static inline void __exynos_iommu_release_mapping(struct exynos_drm_private *priv) { - struct iommu_domain *domain = priv->mapping; - - iommu_put_dma_cookie(domain); - iommu_domain_free(domain); priv->mapping = NULL; } @@ -94,7 +69,9 @@ static inline int __exynos_iommu_attach(struct exynos_drm_private *priv, { struct iommu_domain *domain = priv->mapping; - return iommu_attach_device(domain, dev); + if (dev != priv->dma_dev) + return iommu_attach_device(domain, dev); + return 0; } static inline void __exynos_iommu_detach(struct exynos_drm_private *priv, @@ -102,7 +79,8 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv, { struct iommu_domain *domain = priv->mapping; - iommu_detach_device(domain, dev); + if (dev != priv->dma_dev) + iommu_detach_device(domain, dev); } #else #error Unsupported architecture and IOMMU/DMA-mapping glue code diff --git a/drivers/gpu/drm/i2c/tda9950.c b/drivers/gpu/drm/i2c/tda9950.c index 5d2f0d548469..250b5e02a314 100644 --- a/drivers/gpu/drm/i2c/tda9950.c +++ b/drivers/gpu/drm/i2c/tda9950.c @@ -191,7 +191,8 @@ static irqreturn_t tda9950_irq(int irq, void *data) break; } /* TDA9950 executes all retries for us */ - tx_status |= CEC_TX_STATUS_MAX_RETRIES; + if (tx_status != CEC_TX_STATUS_OK) + tx_status |= CEC_TX_STATUS_MAX_RETRIES; cec_transmit_done(priv->adap, tx_status, arb_lost_cnt, nack_cnt, 0, err_cnt); break; @@ -310,7 +311,7 @@ static void tda9950_release(struct tda9950_priv *priv) /* Wait up to .5s for it to signal non-busy */ do { csr = tda9950_read(client, REG_CSR); - if (!(csr & CSR_BUSY) || --timeout) + if (!(csr & CSR_BUSY) || !--timeout) break; msleep(10); } while (1); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index f7f2aa71d8d9..a262a64f5625 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -232,6 +232,20 @@ static bool compress_init(struct compress *c) return true; } +static void *compress_next_page(struct drm_i915_error_object *dst) +{ + unsigned long page; + + if (dst->page_count >= dst->num_pages) + return ERR_PTR(-ENOSPC); + + page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN); + if (!page) + return ERR_PTR(-ENOMEM); + + return dst->pages[dst->page_count++] = (void *)page; +} + static int compress_page(struct compress *c, void *src, struct drm_i915_error_object *dst) @@ -245,19 +259,14 @@ static int compress_page(struct compress *c, do { if (zstream->avail_out == 0) { - unsigned long page; - - page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN); - if (!page) - return -ENOMEM; + zstream->next_out = compress_next_page(dst); + if (IS_ERR(zstream->next_out)) + return PTR_ERR(zstream->next_out); - dst->pages[dst->page_count++] = (void *)page; - - zstream->next_out = (void *)page; zstream->avail_out = PAGE_SIZE; } - if (zlib_deflate(zstream, Z_SYNC_FLUSH) != Z_OK) + if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK) return -EIO; } while (zstream->avail_in); @@ -268,19 +277,42 @@ static int compress_page(struct compress *c, return 0; } -static void compress_fini(struct compress *c, +static int compress_flush(struct compress *c, struct drm_i915_error_object *dst) { struct z_stream_s *zstream = &c->zstream; - if (dst) { - zlib_deflate(zstream, Z_FINISH); - dst->unused = zstream->avail_out; - } + do { + switch (zlib_deflate(zstream, Z_FINISH)) { + case Z_OK: /* more space requested */ + zstream->next_out = compress_next_page(dst); + if (IS_ERR(zstream->next_out)) + return PTR_ERR(zstream->next_out); + + zstream->avail_out = PAGE_SIZE; + break; + + case Z_STREAM_END: + goto end; + + default: /* any error */ + return -EIO; + } + } while (1); + +end: + memset(zstream->next_out, 0, zstream->avail_out); + dst->unused = zstream->avail_out; + return 0; +} + +static void compress_fini(struct compress *c, + struct drm_i915_error_object *dst) +{ + struct z_stream_s *zstream = &c->zstream; zlib_deflateEnd(zstream); kfree(zstream->workspace); - if (c->tmp) free_page((unsigned long)c->tmp); } @@ -319,6 +351,12 @@ static int compress_page(struct compress *c, return 0; } +static int compress_flush(struct compress *c, + struct drm_i915_error_object *dst) +{ + return 0; +} + static void compress_fini(struct compress *c, struct drm_i915_error_object *dst) { @@ -917,6 +955,7 @@ i915_error_object_create(struct drm_i915_private *i915, unsigned long num_pages; struct sgt_iter iter; dma_addr_t dma; + int ret; if (!vma) return NULL; @@ -930,6 +969,7 @@ i915_error_object_create(struct drm_i915_private *i915, dst->gtt_offset = vma->node.start; dst->gtt_size = vma->node.size; + dst->num_pages = num_pages; dst->page_count = 0; dst->unused = 0; @@ -938,28 +978,26 @@ i915_error_object_create(struct drm_i915_private *i915, return NULL; } + ret = -EINVAL; for_each_sgt_dma(dma, iter, vma->pages) { void __iomem *s; - int ret; ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0); s = io_mapping_map_atomic_wc(&ggtt->iomap, slot); ret = compress_page(&compress, (void __force *)s, dst); io_mapping_unmap_atomic(s); - if (ret) - goto unwind; + break; } - goto out; -unwind: - while (dst->page_count--) - free_page((unsigned long)dst->pages[dst->page_count]); - kfree(dst); - dst = NULL; + if (ret || compress_flush(&compress, dst)) { + while (dst->page_count--) + free_page((unsigned long)dst->pages[dst->page_count]); + kfree(dst); + dst = NULL; + } -out: compress_fini(&compress, dst); ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE); return dst; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index f893a4e8b783..8710fb18ed74 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -135,6 +135,7 @@ struct i915_gpu_state { struct drm_i915_error_object { u64 gtt_offset; u64 gtt_size; + int num_pages; int page_count; int unused; u32 *pages[0]; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 90628a47ae17..29877969310d 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3091,36 +3091,27 @@ gen11_gt_irq_handler(struct drm_i915_private * const i915, spin_unlock(&i915->irq_lock); } -static void -gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl, - u32 *iir) +static u32 +gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl) { void __iomem * const regs = dev_priv->regs; + u32 iir; if (!(master_ctl & GEN11_GU_MISC_IRQ)) - return; + return 0; + + iir = raw_reg_read(regs, GEN11_GU_MISC_IIR); + if (likely(iir)) + raw_reg_write(regs, GEN11_GU_MISC_IIR, iir); - *iir = raw_reg_read(regs, GEN11_GU_MISC_IIR); - if (likely(*iir)) - raw_reg_write(regs, GEN11_GU_MISC_IIR, *iir); + return iir; } static void -gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv, - const u32 master_ctl, const u32 iir) +gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv, const u32 iir) { - if (!(master_ctl & GEN11_GU_MISC_IRQ)) - return; - - if (unlikely(!iir)) { - DRM_ERROR("GU_MISC iir blank!\n"); - return; - } - if (iir & GEN11_GU_MISC_GSE) intel_opregion_asle_intr(dev_priv); - else - DRM_ERROR("Unexpected GU_MISC interrupt 0x%x\n", iir); } static irqreturn_t gen11_irq_handler(int irq, void *arg) @@ -3157,12 +3148,12 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg) enable_rpm_wakeref_asserts(i915); } - gen11_gu_misc_irq_ack(i915, master_ctl, &gu_misc_iir); + gu_misc_iir = gen11_gu_misc_irq_ack(i915, master_ctl); /* Acknowledge and enable interrupts. */ raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ | master_ctl); - gen11_gu_misc_irq_handler(i915, master_ctl, gu_misc_iir); + gen11_gu_misc_irq_handler(i915, gu_misc_iir); return IRQ_HANDLED; } diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 6a4d1388ad2d..1df3ce134cd0 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -592,7 +592,6 @@ static const struct intel_device_info intel_cannonlake_info = { GEN10_FEATURES, \ GEN(11), \ .ddb_size = 2048, \ - .has_csr = 0, \ .has_logical_ring_elsq = 1 static const struct intel_device_info intel_icelake_11_info = { diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 5146ee029db4..bc49909aba8e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -976,7 +976,6 @@ #define USB_DEVICE_ID_SIS817_TOUCH 0x0817 #define USB_DEVICE_ID_SIS_TS 0x1013 #define USB_DEVICE_ID_SIS1030_TOUCH 0x1030 -#define USB_DEVICE_ID_SIS10FB_TOUCH 0x10fb #define USB_VENDOR_ID_SKYCABLE 0x1223 #define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07 diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index f3076659361a..4e3592e7a3f7 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -47,7 +47,7 @@ /* quirks to control the device */ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) -#define I2C_HID_QUIRK_RESEND_REPORT_DESCR BIT(2) +#define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2) /* flags */ #define I2C_HID_STARTED 0 @@ -169,9 +169,8 @@ static const struct i2c_hid_quirks { { USB_VENDOR_ID_WEIDA, USB_DEVICE_ID_WEIDA_8755, I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, - I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, - { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH, - I2C_HID_QUIRK_RESEND_REPORT_DESCR }, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET | + I2C_HID_QUIRK_NO_RUNTIME_PM }, { 0, 0 } }; @@ -1105,7 +1104,9 @@ static int i2c_hid_probe(struct i2c_client *client, goto err_mem_free; } - pm_runtime_put(&client->dev); + if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM)) + pm_runtime_put(&client->dev); + return 0; err_mem_free: @@ -1130,7 +1131,8 @@ static int i2c_hid_remove(struct i2c_client *client) struct i2c_hid *ihid = i2c_get_clientdata(client); struct hid_device *hid; - pm_runtime_get_sync(&client->dev); + if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM)) + pm_runtime_get_sync(&client->dev); pm_runtime_disable(&client->dev); pm_runtime_set_suspended(&client->dev); pm_runtime_put_noidle(&client->dev); @@ -1236,22 +1238,13 @@ static int i2c_hid_resume(struct device *dev) /* Instead of resetting device, simply powers the device on. This * solves "incomplete reports" on Raydium devices 2386:3118 and - * 2386:4B33 + * 2386:4B33 and fixes various SIS touchscreens no longer sending + * data after a suspend/resume. */ ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); if (ret) return ret; - /* 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. - */ - if (ihid->quirks & I2C_HID_QUIRK_RESEND_REPORT_DESCR) { - ret = i2c_hid_command(client, &hid_report_descr_cmd, NULL, 0); - if (ret) - return ret; - } - if (hid->driver && hid->driver->reset_resume) { ret = hid->driver->reset_resume(hid); return ret; diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index da133716bed0..08a8327dfd22 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 ICL_MOBILE_DEVICE_ID 0x34FC #define SPT_H_DEVICE_ID 0xA135 #define REVISION_ID_CHT_A0 0x6 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index a1125a5c7965..256b3016116c 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, ICL_MOBILE_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)}, {0, } }; diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 0bee1f4b914e..3208ad6ad540 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -338,6 +338,39 @@ static int add_roce_gid(struct ib_gid_table_entry *entry) } /** + * del_gid - Delete GID table entry + * + * @ib_dev: IB device whose GID entry to be deleted + * @port: Port number of the IB device + * @table: GID table of the IB device for a port + * @ix: GID entry index to delete + * + */ +static void del_gid(struct ib_device *ib_dev, u8 port, + struct ib_gid_table *table, int ix) +{ + struct ib_gid_table_entry *entry; + + lockdep_assert_held(&table->lock); + + pr_debug("%s device=%s port=%d index=%d gid %pI6\n", __func__, + ib_dev->name, port, ix, + table->data_vec[ix]->attr.gid.raw); + + write_lock_irq(&table->rwlock); + entry = table->data_vec[ix]; + entry->state = GID_TABLE_ENTRY_PENDING_DEL; + /* + * For non RoCE protocol, GID entry slot is ready to use. + */ + if (!rdma_protocol_roce(ib_dev, port)) + table->data_vec[ix] = NULL; + write_unlock_irq(&table->rwlock); + + put_gid_entry_locked(entry); +} + +/** * add_modify_gid - Add or modify GID table entry * * @table: GID table in which GID to be added or modified @@ -358,7 +391,7 @@ static int add_modify_gid(struct ib_gid_table *table, * this index. */ if (is_gid_entry_valid(table->data_vec[attr->index])) - put_gid_entry(table->data_vec[attr->index]); + del_gid(attr->device, attr->port_num, table, attr->index); /* * Some HCA's report multiple GID entries with only one valid GID, and @@ -386,39 +419,6 @@ done: return ret; } -/** - * del_gid - Delete GID table entry - * - * @ib_dev: IB device whose GID entry to be deleted - * @port: Port number of the IB device - * @table: GID table of the IB device for a port - * @ix: GID entry index to delete - * - */ -static void del_gid(struct ib_device *ib_dev, u8 port, - struct ib_gid_table *table, int ix) -{ - struct ib_gid_table_entry *entry; - - lockdep_assert_held(&table->lock); - - pr_debug("%s device=%s port=%d index=%d gid %pI6\n", __func__, - ib_dev->name, port, ix, - table->data_vec[ix]->attr.gid.raw); - - write_lock_irq(&table->rwlock); - entry = table->data_vec[ix]; - entry->state = GID_TABLE_ENTRY_PENDING_DEL; - /* - * For non RoCE protocol, GID entry slot is ready to use. - */ - if (!rdma_protocol_roce(ib_dev, port)) - table->data_vec[ix] = NULL; - write_unlock_irq(&table->rwlock); - - put_gid_entry_locked(entry); -} - /* rwlock should be read locked, or lock should be held */ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid, const struct ib_gid_attr *val, bool default_gid, diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 5f437d1570fb..21863ddde63e 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1759,6 +1759,8 @@ static int ucma_close(struct inode *inode, struct file *filp) mutex_lock(&mut); if (!ctx->closing) { mutex_unlock(&mut); + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); /* rdma_destroy_id ensures that no event handlers are * inflight for that id before releasing it. */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index a21d5214afc3..e012ca80f9d1 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2027,33 +2027,55 @@ static int modify_qp(struct ib_uverbs_file *file, if ((cmd->base.attr_mask & IB_QP_CUR_STATE && cmd->base.cur_qp_state > IB_QPS_ERR) || - cmd->base.qp_state > IB_QPS_ERR) { + (cmd->base.attr_mask & IB_QP_STATE && + cmd->base.qp_state > IB_QPS_ERR)) { ret = -EINVAL; goto release_qp; } - attr->qp_state = cmd->base.qp_state; - attr->cur_qp_state = cmd->base.cur_qp_state; - attr->path_mtu = cmd->base.path_mtu; - attr->path_mig_state = cmd->base.path_mig_state; - attr->qkey = cmd->base.qkey; - attr->rq_psn = cmd->base.rq_psn; - attr->sq_psn = cmd->base.sq_psn; - attr->dest_qp_num = cmd->base.dest_qp_num; - attr->qp_access_flags = cmd->base.qp_access_flags; - attr->pkey_index = cmd->base.pkey_index; - attr->alt_pkey_index = cmd->base.alt_pkey_index; - attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify; - attr->max_rd_atomic = cmd->base.max_rd_atomic; - attr->max_dest_rd_atomic = cmd->base.max_dest_rd_atomic; - attr->min_rnr_timer = cmd->base.min_rnr_timer; - attr->port_num = cmd->base.port_num; - attr->timeout = cmd->base.timeout; - attr->retry_cnt = cmd->base.retry_cnt; - attr->rnr_retry = cmd->base.rnr_retry; - attr->alt_port_num = cmd->base.alt_port_num; - attr->alt_timeout = cmd->base.alt_timeout; - attr->rate_limit = cmd->rate_limit; + if (cmd->base.attr_mask & IB_QP_STATE) + attr->qp_state = cmd->base.qp_state; + if (cmd->base.attr_mask & IB_QP_CUR_STATE) + attr->cur_qp_state = cmd->base.cur_qp_state; + if (cmd->base.attr_mask & IB_QP_PATH_MTU) + attr->path_mtu = cmd->base.path_mtu; + if (cmd->base.attr_mask & IB_QP_PATH_MIG_STATE) + attr->path_mig_state = cmd->base.path_mig_state; + if (cmd->base.attr_mask & IB_QP_QKEY) + attr->qkey = cmd->base.qkey; + if (cmd->base.attr_mask & IB_QP_RQ_PSN) + attr->rq_psn = cmd->base.rq_psn; + if (cmd->base.attr_mask & IB_QP_SQ_PSN) + attr->sq_psn = cmd->base.sq_psn; + if (cmd->base.attr_mask & IB_QP_DEST_QPN) + attr->dest_qp_num = cmd->base.dest_qp_num; + if (cmd->base.attr_mask & IB_QP_ACCESS_FLAGS) + attr->qp_access_flags = cmd->base.qp_access_flags; + if (cmd->base.attr_mask & IB_QP_PKEY_INDEX) + attr->pkey_index = cmd->base.pkey_index; + if (cmd->base.attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) + attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify; + if (cmd->base.attr_mask & IB_QP_MAX_QP_RD_ATOMIC) + attr->max_rd_atomic = cmd->base.max_rd_atomic; + if (cmd->base.attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) + attr->max_dest_rd_atomic = cmd->base.max_dest_rd_atomic; + if (cmd->base.attr_mask & IB_QP_MIN_RNR_TIMER) + attr->min_rnr_timer = cmd->base.min_rnr_timer; + if (cmd->base.attr_mask & IB_QP_PORT) + attr->port_num = cmd->base.port_num; + if (cmd->base.attr_mask & IB_QP_TIMEOUT) + attr->timeout = cmd->base.timeout; + if (cmd->base.attr_mask & IB_QP_RETRY_CNT) + attr->retry_cnt = cmd->base.retry_cnt; + if (cmd->base.attr_mask & IB_QP_RNR_RETRY) + attr->rnr_retry = cmd->base.rnr_retry; + if (cmd->base.attr_mask & IB_QP_ALT_PATH) { + attr->alt_port_num = cmd->base.alt_port_num; + attr->alt_timeout = cmd->base.alt_timeout; + attr->alt_pkey_index = cmd->base.alt_pkey_index; + } + if (cmd->base.attr_mask & IB_QP_RATE_LIMIT) + attr->rate_limit = cmd->rate_limit; if (cmd->base.attr_mask & IB_QP_AV) copy_ah_attr_from_uverbs(qp->device, &attr->ah_attr, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 6d974e2363df..50152c1b1004 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -440,6 +440,7 @@ static int ib_uverbs_comp_event_close(struct inode *inode, struct file *filp) list_del(&entry->obj_list); kfree(entry); } + file->ev_queue.is_closed = 1; spin_unlock_irq(&file->ev_queue.lock); uverbs_close_fd(filp); diff --git a/drivers/infiniband/core/uverbs_uapi.c b/drivers/infiniband/core/uverbs_uapi.c index 73ea6f0db88f..be854628a7c6 100644 --- a/drivers/infiniband/core/uverbs_uapi.c +++ b/drivers/infiniband/core/uverbs_uapi.c @@ -248,6 +248,7 @@ void uverbs_destroy_api(struct uverbs_api *uapi) kfree(rcu_dereference_protected(*slot, true)); radix_tree_iter_delete(&uapi->radix, &iter, slot); } + kfree(uapi); } struct uverbs_api *uverbs_alloc_api( diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 20b9f31052bf..85cd1a3593d6 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -78,7 +78,7 @@ static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); /* Mutex to protect the list of bnxt_re devices added */ static DEFINE_MUTEX(bnxt_re_dev_lock); static struct workqueue_struct *bnxt_re_wq; -static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait); +static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev); /* SR-IOV helper functions */ @@ -182,7 +182,7 @@ static void bnxt_re_shutdown(void *p) if (!rdev) return; - bnxt_re_ib_unreg(rdev, false); + bnxt_re_ib_unreg(rdev); } static void bnxt_re_stop_irq(void *handle) @@ -251,7 +251,7 @@ static struct bnxt_ulp_ops bnxt_re_ulp_ops = { /* Driver registration routines used to let the networking driver (bnxt_en) * to know that the RoCE driver is now installed */ -static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev, bool lock_wait) +static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc; @@ -260,14 +260,9 @@ static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev, bool lock_wait) return -EINVAL; en_dev = rdev->en_dev; - /* Acquire rtnl lock if it is not invokded from netdev event */ - if (lock_wait) - rtnl_lock(); rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev, BNXT_ROCE_ULP); - if (lock_wait) - rtnl_unlock(); return rc; } @@ -281,14 +276,12 @@ static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev) en_dev = rdev->en_dev; - rtnl_lock(); rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP, &bnxt_re_ulp_ops, rdev); - rtnl_unlock(); return rc; } -static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait) +static int bnxt_re_free_msix(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc; @@ -298,13 +291,9 @@ static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait) en_dev = rdev->en_dev; - if (lock_wait) - rtnl_lock(); rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP); - if (lock_wait) - rtnl_unlock(); return rc; } @@ -320,7 +309,6 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus()); - rtnl_lock(); num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP, rdev->msix_entries, num_msix_want); @@ -335,7 +323,6 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) } rdev->num_msix = num_msix_got; done: - rtnl_unlock(); return rc; } @@ -358,24 +345,18 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg, fw_msg->timeout = timeout; } -static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, - bool lock_wait) +static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id) { struct bnxt_en_dev *en_dev = rdev->en_dev; struct hwrm_ring_free_input req = {0}; struct hwrm_ring_free_output resp; struct bnxt_fw_msg fw_msg; - bool do_unlock = false; int rc = -EINVAL; if (!en_dev) return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - if (lock_wait) { - rtnl_lock(); - do_unlock = true; - } bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1); req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL; @@ -386,8 +367,6 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, if (rc) dev_err(rdev_to_dev(rdev), "Failed to free HW ring:%d :%#x", req.ring_id, rc); - if (do_unlock) - rtnl_unlock(); return rc; } @@ -405,7 +384,6 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr, return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - rtnl_lock(); bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1); req.enables = 0; req.page_tbl_addr = cpu_to_le64(dma_arr[0]); @@ -426,27 +404,21 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr, if (!rc) *fw_ring_id = le16_to_cpu(resp.ring_id); - rtnl_unlock(); return rc; } static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, - u32 fw_stats_ctx_id, bool lock_wait) + u32 fw_stats_ctx_id) { struct bnxt_en_dev *en_dev = rdev->en_dev; struct hwrm_stat_ctx_free_input req = {0}; struct bnxt_fw_msg fw_msg; - bool do_unlock = false; int rc = -EINVAL; if (!en_dev) return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - if (lock_wait) { - rtnl_lock(); - do_unlock = true; - } bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1); req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id); @@ -457,8 +429,6 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, dev_err(rdev_to_dev(rdev), "Failed to free HW stats context %#x", rc); - if (do_unlock) - rtnl_unlock(); return rc; } @@ -478,7 +448,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - rtnl_lock(); bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(1000); @@ -490,7 +459,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, if (!rc) *fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id); - rtnl_unlock(); return rc; } @@ -929,19 +897,19 @@ fail: return rc; } -static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev) { int i; for (i = 0; i < rdev->num_msix - 1; i++) { - bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, lock_wait); + bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id); bnxt_qplib_free_nq(&rdev->nq[i]); } } -static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_free_res(struct bnxt_re_dev *rdev) { - bnxt_re_free_nq_res(rdev, lock_wait); + bnxt_re_free_nq_res(rdev); if (rdev->qplib_res.dpi_tbl.max) { bnxt_qplib_dealloc_dpi(&rdev->qplib_res, @@ -1219,7 +1187,7 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) return 0; } -static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev) { int i, rc; @@ -1234,28 +1202,27 @@ static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait) cancel_delayed_work(&rdev->worker); bnxt_re_cleanup_res(rdev); - bnxt_re_free_res(rdev, lock_wait); + bnxt_re_free_res(rdev); if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) { rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to deinitialize RCFW: %#x", rc); - bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, - lock_wait); + bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id); bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx); bnxt_qplib_disable_rcfw_channel(&rdev->rcfw); - bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, lock_wait); + bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id); bnxt_qplib_free_rcfw_channel(&rdev->rcfw); } if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) { - rc = bnxt_re_free_msix(rdev, lock_wait); + rc = bnxt_re_free_msix(rdev); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to free MSI-X vectors: %#x", rc); } if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) { - rc = bnxt_re_unregister_netdev(rdev, lock_wait); + rc = bnxt_re_unregister_netdev(rdev); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to unregister with netdev: %#x", rc); @@ -1276,6 +1243,12 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) { int i, j, rc; + bool locked; + + /* Acquire rtnl lock through out this function */ + rtnl_lock(); + locked = true; + /* Registered a new RoCE device instance to netdev */ rc = bnxt_re_register_netdev(rdev); if (rc) { @@ -1374,12 +1347,16 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000)); } + rtnl_unlock(); + locked = false; + /* Register ib dev */ rc = bnxt_re_register_ib(rdev); if (rc) { pr_err("Failed to register with IB: %#x\n", rc); goto fail; } + set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags); dev_info(rdev_to_dev(rdev), "Device registered successfully"); for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++) { rc = device_create_file(&rdev->ibdev.dev, @@ -1395,7 +1372,6 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) goto fail; } } - set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags); ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, &rdev->active_width); set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags); @@ -1404,17 +1380,21 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) return 0; free_sctx: - bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, true); + bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id); free_ctx: bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx); disable_rcfw: bnxt_qplib_disable_rcfw_channel(&rdev->rcfw); free_ring: - bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, true); + bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id); free_rcfw: bnxt_qplib_free_rcfw_channel(&rdev->rcfw); fail: - bnxt_re_ib_unreg(rdev, true); + if (!locked) + rtnl_lock(); + bnxt_re_ib_unreg(rdev); + rtnl_unlock(); + return rc; } @@ -1567,7 +1547,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, */ if (atomic_read(&rdev->sched_count) > 0) goto exit; - bnxt_re_ib_unreg(rdev, false); + bnxt_re_ib_unreg(rdev); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); break; @@ -1646,7 +1626,10 @@ static void __exit bnxt_re_mod_exit(void) */ flush_workqueue(bnxt_re_wq); bnxt_re_dev_stop(rdev); - bnxt_re_ib_unreg(rdev, true); + /* Acquire the rtnl_lock as the L2 resources are freed here */ + rtnl_lock(); + bnxt_re_ib_unreg(rdev); + rtnl_unlock(); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); } diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 2c19bf772451..e1668bcc2d13 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -6733,6 +6733,7 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags) struct hfi1_devdata *dd = ppd->dd; struct send_context *sc; int i; + int sc_flags; if (flags & FREEZE_SELF) write_csr(dd, CCE_CTRL, CCE_CTRL_SPC_FREEZE_SMASK); @@ -6743,11 +6744,13 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags) /* notify all SDMA engines that they are going into a freeze */ sdma_freeze_notify(dd, !!(flags & FREEZE_LINK_DOWN)); + sc_flags = SCF_FROZEN | SCF_HALTED | (flags & FREEZE_LINK_DOWN ? + SCF_LINK_DOWN : 0); /* do halt pre-handling on all enabled send contexts */ for (i = 0; i < dd->num_send_contexts; i++) { sc = dd->send_contexts[i].sc; if (sc && (sc->flags & SCF_ENABLED)) - sc_stop(sc, SCF_FROZEN | SCF_HALTED); + sc_stop(sc, sc_flags); } /* Send context are frozen. Notify user space */ @@ -10674,6 +10677,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); handle_linkup_change(dd, 1); + pio_kernel_linkup(dd); /* * After link up, a new link width will have been set. diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index c2c1cba5b23b..752057647f09 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -86,6 +86,7 @@ void pio_send_control(struct hfi1_devdata *dd, int op) unsigned long flags; int write = 1; /* write sendctrl back */ int flush = 0; /* re-read sendctrl to make sure it is flushed */ + int i; spin_lock_irqsave(&dd->sendctrl_lock, flags); @@ -95,9 +96,13 @@ void pio_send_control(struct hfi1_devdata *dd, int op) reg |= SEND_CTRL_SEND_ENABLE_SMASK; /* Fall through */ case PSC_DATA_VL_ENABLE: + mask = 0; + for (i = 0; i < ARRAY_SIZE(dd->vld); i++) + if (!dd->vld[i].mtu) + mask |= BIT_ULL(i); /* Disallow sending on VLs not enabled */ - mask = (((~0ull) << num_vls) & SEND_CTRL_UNSUPPORTED_VL_MASK) << - SEND_CTRL_UNSUPPORTED_VL_SHIFT; + mask = (mask & SEND_CTRL_UNSUPPORTED_VL_MASK) << + SEND_CTRL_UNSUPPORTED_VL_SHIFT; reg = (reg & ~SEND_CTRL_UNSUPPORTED_VL_SMASK) | mask; break; case PSC_GLOBAL_DISABLE: @@ -921,20 +926,18 @@ void sc_free(struct send_context *sc) void sc_disable(struct send_context *sc) { u64 reg; - unsigned long flags; struct pio_buf *pbuf; if (!sc) return; /* do all steps, even if already disabled */ - spin_lock_irqsave(&sc->alloc_lock, flags); + spin_lock_irq(&sc->alloc_lock); reg = read_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL)); reg &= ~SC(CTRL_CTXT_ENABLE_SMASK); sc->flags &= ~SCF_ENABLED; sc_wait_for_packet_egress(sc, 1); write_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL), reg); - spin_unlock_irqrestore(&sc->alloc_lock, flags); /* * Flush any waiters. Once the context is disabled, @@ -944,7 +947,7 @@ void sc_disable(struct send_context *sc) * proceed with the flush. */ udelay(1); - spin_lock_irqsave(&sc->release_lock, flags); + spin_lock(&sc->release_lock); if (sc->sr) { /* this context has a shadow ring */ while (sc->sr_tail != sc->sr_head) { pbuf = &sc->sr[sc->sr_tail].pbuf; @@ -955,7 +958,8 @@ void sc_disable(struct send_context *sc) sc->sr_tail = 0; } } - spin_unlock_irqrestore(&sc->release_lock, flags); + spin_unlock(&sc->release_lock); + spin_unlock_irq(&sc->alloc_lock); } /* return SendEgressCtxtStatus.PacketOccupancy */ @@ -1178,11 +1182,39 @@ void pio_kernel_unfreeze(struct hfi1_devdata *dd) sc = dd->send_contexts[i].sc; if (!sc || !(sc->flags & SCF_FROZEN) || sc->type == SC_USER) continue; + if (sc->flags & SCF_LINK_DOWN) + continue; sc_enable(sc); /* will clear the sc frozen flag */ } } +/** + * pio_kernel_linkup() - Re-enable send contexts after linkup event + * @dd: valid devive data + * + * When the link goes down, the freeze path is taken. However, a link down + * event is different from a freeze because if the send context is re-enabled + * whowever is sending data will start sending data again, which will hang + * any QP that is sending data. + * + * The freeze path now looks at the type of event that occurs and takes this + * path for link down event. + */ +void pio_kernel_linkup(struct hfi1_devdata *dd) +{ + struct send_context *sc; + int i; + + for (i = 0; i < dd->num_send_contexts; i++) { + sc = dd->send_contexts[i].sc; + if (!sc || !(sc->flags & SCF_LINK_DOWN) || sc->type == SC_USER) + continue; + + sc_enable(sc); /* will clear the sc link down flag */ + } +} + /* * Wait for the SendPioInitCtxt.PioInitInProgress bit to clear. * Returns: @@ -1382,11 +1414,10 @@ void sc_stop(struct send_context *sc, int flag) { unsigned long flags; - /* mark the context */ - sc->flags |= flag; - /* stop buffer allocations */ spin_lock_irqsave(&sc->alloc_lock, flags); + /* mark the context */ + sc->flags |= flag; sc->flags &= ~SCF_ENABLED; spin_unlock_irqrestore(&sc->alloc_lock, flags); wake_up(&sc->halt_wait); diff --git a/drivers/infiniband/hw/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h index 058b08f459ab..aaf372c3e5d6 100644 --- a/drivers/infiniband/hw/hfi1/pio.h +++ b/drivers/infiniband/hw/hfi1/pio.h @@ -139,6 +139,7 @@ struct send_context { #define SCF_IN_FREE 0x02 #define SCF_HALTED 0x04 #define SCF_FROZEN 0x08 +#define SCF_LINK_DOWN 0x10 struct send_context_info { struct send_context *sc; /* allocated working context */ @@ -306,6 +307,7 @@ void set_pio_integrity(struct send_context *sc); void pio_reset_all(struct hfi1_devdata *dd); void pio_freeze(struct hfi1_devdata *dd); void pio_kernel_unfreeze(struct hfi1_devdata *dd); +void pio_kernel_linkup(struct hfi1_devdata *dd); /* global PIO send control operations */ #define PSC_GLOBAL_ENABLE 0 diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a3a7b33196d6..5c88706121c1 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -828,7 +828,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) if (READ_ONCE(iovec->offset) == iovec->iov.iov_len) { if (++req->iov_idx == req->data_iovs) { ret = -EFAULT; - goto free_txreq; + goto free_tx; } iovec = &req->iovs[req->iov_idx]; WARN_ON(iovec->offset); diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 13374c727b14..a7c586a5589d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1582,6 +1582,7 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) struct hfi1_pportdata *ppd; struct hfi1_devdata *dd; u8 sc5; + u8 sl; if (hfi1_check_mcast(rdma_ah_get_dlid(ah_attr)) && !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH)) @@ -1590,8 +1591,13 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) /* test the mapping for validity */ ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr)); ppd = ppd_from_ibp(ibp); - sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)]; dd = dd_from_ppd(ppd); + + sl = rdma_ah_get_sl(ah_attr); + if (sl >= ARRAY_SIZE(ibp->sl_to_sc)) + return -EINVAL; + + sc5 = ibp->sl_to_sc[sl]; if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf) return -EINVAL; return 0; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index ac116d63e466..f2f11e652dcd 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -723,6 +723,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_HANDLE); struct mlx5_ib_ucontext *c = to_mucontext(uobj->context); struct mlx5_ib_dev *dev = to_mdev(c->ibucontext.device); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; struct devx_obj *obj; int err; @@ -754,10 +755,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len); if (err) - goto obj_free; + goto obj_destroy; return 0; +obj_destroy: + mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out)); obj_free: kfree(obj); return err; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 444d16520506..0b34e909505f 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -2951,7 +2951,7 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) { struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_rdma_ch *ch; - int i; + int i, j; u8 status; shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); @@ -2965,8 +2965,8 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - for (i = 0; i < target->req_ring_size; ++i) { - struct srp_request *req = &ch->req_ring[i]; + for (j = 0; j < target->req_ring_size; ++j) { + struct srp_request *req = &ch->req_ring[j]; srp_finish_req(ch, req, scmnd->device, DID_RESET << 16); } diff --git a/drivers/input/keyboard/atakbd.c b/drivers/input/keyboard/atakbd.c index 6f62da2909ec..6caee807cafa 100644 --- a/drivers/input/keyboard/atakbd.c +++ b/drivers/input/keyboard/atakbd.c @@ -75,8 +75,7 @@ MODULE_LICENSE("GPL"); */ -static unsigned char atakbd_keycode[0x72] = { /* American layout */ - [0] = KEY_GRAVE, +static unsigned char atakbd_keycode[0x73] = { /* American layout */ [1] = KEY_ESC, [2] = KEY_1, [3] = KEY_2, @@ -117,9 +116,9 @@ static unsigned char atakbd_keycode[0x72] = { /* American layout */ [38] = KEY_L, [39] = KEY_SEMICOLON, [40] = KEY_APOSTROPHE, - [41] = KEY_BACKSLASH, /* FIXME, '#' */ + [41] = KEY_GRAVE, [42] = KEY_LEFTSHIFT, - [43] = KEY_GRAVE, /* FIXME: '~' */ + [43] = KEY_BACKSLASH, [44] = KEY_Z, [45] = KEY_X, [46] = KEY_C, @@ -145,45 +144,34 @@ static unsigned char atakbd_keycode[0x72] = { /* American layout */ [66] = KEY_F8, [67] = KEY_F9, [68] = KEY_F10, - [69] = KEY_ESC, - [70] = KEY_DELETE, - [71] = KEY_KP7, - [72] = KEY_KP8, - [73] = KEY_KP9, + [71] = KEY_HOME, + [72] = KEY_UP, [74] = KEY_KPMINUS, - [75] = KEY_KP4, - [76] = KEY_KP5, - [77] = KEY_KP6, + [75] = KEY_LEFT, + [77] = KEY_RIGHT, [78] = KEY_KPPLUS, - [79] = KEY_KP1, - [80] = KEY_KP2, - [81] = KEY_KP3, - [82] = KEY_KP0, - [83] = KEY_KPDOT, - [90] = KEY_KPLEFTPAREN, - [91] = KEY_KPRIGHTPAREN, - [92] = KEY_KPASTERISK, /* FIXME */ - [93] = KEY_KPASTERISK, - [94] = KEY_KPPLUS, - [95] = KEY_HELP, + [80] = KEY_DOWN, + [82] = KEY_INSERT, + [83] = KEY_DELETE, [96] = KEY_102ND, - [97] = KEY_KPASTERISK, /* FIXME */ - [98] = KEY_KPSLASH, + [97] = KEY_UNDO, + [98] = KEY_HELP, [99] = KEY_KPLEFTPAREN, [100] = KEY_KPRIGHTPAREN, [101] = KEY_KPSLASH, [102] = KEY_KPASTERISK, - [103] = KEY_UP, - [104] = KEY_KPASTERISK, /* FIXME */ - [105] = KEY_LEFT, - [106] = KEY_RIGHT, - [107] = KEY_KPASTERISK, /* FIXME */ - [108] = KEY_DOWN, - [109] = KEY_KPASTERISK, /* FIXME */ - [110] = KEY_KPASTERISK, /* FIXME */ - [111] = KEY_KPASTERISK, /* FIXME */ - [112] = KEY_KPASTERISK, /* FIXME */ - [113] = KEY_KPASTERISK /* FIXME */ + [103] = KEY_KP7, + [104] = KEY_KP8, + [105] = KEY_KP9, + [106] = KEY_KP4, + [107] = KEY_KP5, + [108] = KEY_KP6, + [109] = KEY_KP1, + [110] = KEY_KP2, + [111] = KEY_KP3, + [112] = KEY_KP0, + [113] = KEY_KPDOT, + [114] = KEY_KPENTER, }; static struct input_dev *atakbd_dev; @@ -191,21 +179,15 @@ static struct input_dev *atakbd_dev; static void atakbd_interrupt(unsigned char scancode, char down) { - if (scancode < 0x72) { /* scancodes < 0xf2 are keys */ + if (scancode < 0x73) { /* scancodes < 0xf3 are keys */ // report raw events here? scancode = atakbd_keycode[scancode]; - if (scancode == KEY_CAPSLOCK) { /* CapsLock is a toggle switch key on Amiga */ - input_report_key(atakbd_dev, scancode, 1); - input_report_key(atakbd_dev, scancode, 0); - input_sync(atakbd_dev); - } else { - input_report_key(atakbd_dev, scancode, down); - input_sync(atakbd_dev); - } - } else /* scancodes >= 0xf2 are mouse data, most likely */ + input_report_key(atakbd_dev, scancode, down); + input_sync(atakbd_dev); + } else /* scancodes >= 0xf3 are mouse data, most likely */ printk(KERN_INFO "atakbd: unhandled scancode %x\n", scancode); return; diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 96a887f33698..eb14ddf69346 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -410,7 +410,7 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code, min = abs->minimum; max = abs->maximum; - if ((min != 0 || max != 0) && max <= min) { + if ((min != 0 || max != 0) && max < min) { printk(KERN_DEBUG "%s: invalid abs[%02x] min:%d max:%d\n", UINPUT_NAME, code, min, max); diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 44f57cf6675b..2d95e8d93cc7 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1178,6 +1178,8 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = { static const char * const middle_button_pnp_ids[] = { "LEN2131", /* ThinkPad P52 w/ NFC */ "LEN2132", /* ThinkPad P52 */ + "LEN2133", /* ThinkPad P72 w/ NFC */ + "LEN2134", /* ThinkPad P72 */ NULL }; diff --git a/drivers/input/touchscreen/egalax_ts.c b/drivers/input/touchscreen/egalax_ts.c index 80e69bb8283e..83ac8c128192 100644 --- a/drivers/input/touchscreen/egalax_ts.c +++ b/drivers/input/touchscreen/egalax_ts.c @@ -241,6 +241,9 @@ static int __maybe_unused egalax_ts_suspend(struct device *dev) struct i2c_client *client = to_i2c_client(dev); int ret; + if (device_may_wakeup(dev)) + return enable_irq_wake(client->irq); + ret = i2c_master_send(client, suspend_cmd, MAX_I2C_DATA_LEN); return ret > 0 ? 0 : ret; } @@ -249,6 +252,9 @@ static int __maybe_unused egalax_ts_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); + if (device_may_wakeup(dev)) + return disable_irq_wake(client->irq); + return egalax_wake_up_device(client); } diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 4e04fff23977..bee0dfb7b93b 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -246,7 +246,13 @@ static u16 get_alias(struct device *dev) /* The callers make sure that get_device_id() does not fail here */ devid = get_device_id(dev); + + /* For ACPI HID devices, we simply return the devid as such */ + if (!dev_is_pci(dev)) + return devid; + ivrs_alias = amd_iommu_alias_table[devid]; + pci_for_each_dma_alias(pdev, __last_alias, &pci_alias); if (ivrs_alias == pci_alias) @@ -3063,7 +3069,7 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, return 0; offset_mask = pte_pgsize - 1; - __pte = *pte & PM_ADDR_MASK; + __pte = __sme_clr(*pte & PM_ADDR_MASK); return (__pte & ~offset_mask) | (iova & offset_mask); } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 5f3f10cf9d9d..bedc801b06a0 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2540,9 +2540,9 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (dev && dev_is_pci(dev) && info->pasid_supported) { ret = intel_pasid_alloc_table(dev); if (ret) { - __dmar_remove_one_dev_info(info); - spin_unlock_irqrestore(&device_domain_lock, flags); - return NULL; + pr_warn("No pasid table for %s, pasid disabled\n", + dev_name(dev)); + info->pasid_supported = 0; } } spin_unlock_irqrestore(&device_domain_lock, flags); diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h index 1c05ed6fc5a5..1fb5e12b029a 100644 --- a/drivers/iommu/intel-pasid.h +++ b/drivers/iommu/intel-pasid.h @@ -11,7 +11,7 @@ #define __INTEL_PASID_H #define PASID_MIN 0x1 -#define PASID_MAX 0x100000 +#define PASID_MAX 0x20000 struct pasid_entry { u64 val; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 258115b10fa9..ad3e2b97469e 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1241,6 +1241,12 @@ err_unprepare_clocks: static void rk_iommu_shutdown(struct platform_device *pdev) { + struct rk_iommu *iommu = platform_get_drvdata(pdev); + int i = 0, irq; + + while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) + devm_free_irq(iommu->dev, irq, iommu); + pm_runtime_force_suspend(&pdev->dev); } diff --git a/drivers/isdn/gigaset/asyncdata.c b/drivers/isdn/gigaset/asyncdata.c index bc208557f783..c0cbee06bc21 100644 --- a/drivers/isdn/gigaset/asyncdata.c +++ b/drivers/isdn/gigaset/asyncdata.c @@ -65,7 +65,7 @@ static unsigned cmd_loop(unsigned numbytes, struct inbuf_t *inbuf) cs->respdata[0] = 0; break; } - /* --v-- fall through --v-- */ + /* fall through */ case '\r': /* end of message line, pass to response handler */ if (cbytes >= MAX_RESP_SIZE) { @@ -100,7 +100,7 @@ static unsigned cmd_loop(unsigned numbytes, struct inbuf_t *inbuf) goto exit; } /* quoted or not in DLE mode: treat as regular data */ - /* --v-- fall through --v-- */ + /* fall through */ default: /* append to line buffer if possible */ if (cbytes < MAX_RESP_SIZE) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 83504dd8100a..954dad29e6e8 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -965,6 +965,7 @@ void bch_prio_write(struct cache *ca); void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent); extern struct workqueue_struct *bcache_wq; +extern struct workqueue_struct *bch_journal_wq; extern struct mutex bch_register_lock; extern struct list_head bch_cache_sets; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 6116bbf870d8..522c7426f3a0 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -485,7 +485,7 @@ static void do_journal_discard(struct cache *ca) closure_get(&ca->set->cl); INIT_WORK(&ja->discard_work, journal_discard_work); - schedule_work(&ja->discard_work); + queue_work(bch_journal_wq, &ja->discard_work); } } @@ -592,7 +592,7 @@ static void journal_write_done(struct closure *cl) : &j->w[0]; __closure_wake_up(&w->wait); - continue_at_nobarrier(cl, journal_write, system_wq); + continue_at_nobarrier(cl, journal_write, bch_journal_wq); } static void journal_write_unlock(struct closure *cl) @@ -627,7 +627,7 @@ static void journal_write_unlocked(struct closure *cl) spin_unlock(&c->journal.lock); btree_flush_write(c); - continue_at(cl, journal_write, system_wq); + continue_at(cl, journal_write, bch_journal_wq); return; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 94c756c66bd7..30ba9aeb5ee8 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -47,6 +47,7 @@ static int bcache_major; static DEFINE_IDA(bcache_device_idx); static wait_queue_head_t unregister_wait; struct workqueue_struct *bcache_wq; +struct workqueue_struct *bch_journal_wq; #define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE) /* limitation of partitions number on single bcache device */ @@ -2341,6 +2342,9 @@ static void bcache_exit(void) kobject_put(bcache_kobj); if (bcache_wq) destroy_workqueue(bcache_wq); + if (bch_journal_wq) + destroy_workqueue(bch_journal_wq); + if (bcache_major) unregister_blkdev(bcache_major, "bcache"); unregister_reboot_notifier(&reboot); @@ -2370,6 +2374,10 @@ static int __init bcache_init(void) if (!bcache_wq) goto err; + bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0); + if (!bch_journal_wq) + goto err; + bcache_kobj = kobject_create_and_add("bcache", fs_kobj); if (!bcache_kobj) goto err; diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 69dddeab124c..5936de71883f 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1455,8 +1455,8 @@ static int __load_mappings(struct dm_cache_metadata *cmd, if (hints_valid) { r = dm_array_cursor_next(&cmd->hint_cursor); if (r) { - DMERR("dm_array_cursor_next for hint failed"); - goto out; + dm_array_cursor_end(&cmd->hint_cursor); + hints_valid = false; } } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index a53413371725..e13d991e9fb5 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3009,8 +3009,13 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) static bool can_resize(struct cache *cache, dm_cblock_t new_size) { - if (from_cblock(new_size) > from_cblock(cache->cache_size)) - return true; + if (from_cblock(new_size) > from_cblock(cache->cache_size)) { + if (cache->sized) { + DMERR("%s: unable to extend cache due to missing cache table reload", + cache_device_name(cache)); + return false; + } + } /* * We can't drop a dirty block when shrinking the cache. diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d94ba6f72ff5..419362c2d8ac 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -806,19 +806,19 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, } static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, - const char *attached_handler_name, char **error) + const char **attached_handler_name, char **error) { struct request_queue *q = bdev_get_queue(bdev); int r; if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags)) { retain: - if (attached_handler_name) { + if (*attached_handler_name) { /* * Clear any hw_handler_params associated with a * handler that isn't already attached. */ - if (m->hw_handler_name && strcmp(attached_handler_name, m->hw_handler_name)) { + if (m->hw_handler_name && strcmp(*attached_handler_name, m->hw_handler_name)) { kfree(m->hw_handler_params); m->hw_handler_params = NULL; } @@ -830,7 +830,8 @@ retain: * handler instead of the original table passed in. */ kfree(m->hw_handler_name); - m->hw_handler_name = attached_handler_name; + m->hw_handler_name = *attached_handler_name; + *attached_handler_name = NULL; } } @@ -867,7 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps struct pgpath *p; struct multipath *m = ti->private; struct request_queue *q; - const char *attached_handler_name; + const char *attached_handler_name = NULL; /* we need at least a path arg */ if (as->argc < 1) { @@ -890,7 +891,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); if (attached_handler_name || m->hw_handler_name) { INIT_DELAYED_WORK(&p->activate_path, activate_path_work); - r = setup_scsi_dh(p->path.dev->bdev, m, attached_handler_name, &ti->error); + r = setup_scsi_dh(p->path.dev->bdev, m, &attached_handler_name, &ti->error); if (r) { dm_put_device(ti, p->path.dev); goto bad; @@ -905,6 +906,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps return p; bad: + kfree(attached_handler_name); free_pgpath(p); return ERR_PTR(r); } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5ba067fa0c72..c44925e4e481 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3353,7 +3353,7 @@ static const char *sync_str(enum sync_state state) }; /* Return enum sync_state for @mddev derived from @recovery flags */ -static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery) +static enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery) { if (test_bit(MD_RECOVERY_FROZEN, &recovery)) return st_frozen; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 74f6770c70b1..20b0776e39ef 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -832,10 +832,8 @@ static void __set_metadata_reserve(struct dm_pool_metadata *pmd) 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); - } + } else + pmd->metadata_reserve = min(max_blocks, div_u64(total, 10)); } struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, diff --git a/drivers/media/v4l2-core/v4l2-event.c b/drivers/media/v4l2-core/v4l2-event.c index 127fe6eb91d9..a3ef1f50a4b3 100644 --- a/drivers/media/v4l2-core/v4l2-event.c +++ b/drivers/media/v4l2-core/v4l2-event.c @@ -115,14 +115,6 @@ static void __v4l2_event_queue_fh(struct v4l2_fh *fh, const struct v4l2_event *e if (sev == NULL) return; - /* - * If the event has been added to the fh->subscribed list, but its - * add op has not completed yet elems will be 0, treat this as - * not being subscribed. - */ - if (!sev->elems) - return; - /* Increase event sequence number on fh. */ fh->sequence++; @@ -208,6 +200,7 @@ int v4l2_event_subscribe(struct v4l2_fh *fh, struct v4l2_subscribed_event *sev, *found_ev; unsigned long flags; unsigned i; + int ret = 0; if (sub->type == V4L2_EVENT_ALL) return -EINVAL; @@ -225,31 +218,36 @@ int v4l2_event_subscribe(struct v4l2_fh *fh, sev->flags = sub->flags; sev->fh = fh; sev->ops = ops; + sev->elems = elems; + + mutex_lock(&fh->subscribe_lock); spin_lock_irqsave(&fh->vdev->fh_lock, flags); found_ev = v4l2_event_subscribed(fh, sub->type, sub->id); - if (!found_ev) - list_add(&sev->list, &fh->subscribed); spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); if (found_ev) { + /* Already listening */ kvfree(sev); - return 0; /* Already listening */ + goto out_unlock; } if (sev->ops && sev->ops->add) { - int ret = sev->ops->add(sev, elems); + ret = sev->ops->add(sev, elems); if (ret) { - sev->ops = NULL; - v4l2_event_unsubscribe(fh, sub); - return ret; + kvfree(sev); + goto out_unlock; } } - /* Mark as ready for use */ - sev->elems = elems; + spin_lock_irqsave(&fh->vdev->fh_lock, flags); + list_add(&sev->list, &fh->subscribed); + spin_unlock_irqrestore(&fh->vdev->fh_lock, flags); - return 0; +out_unlock: + mutex_unlock(&fh->subscribe_lock); + + return ret; } EXPORT_SYMBOL_GPL(v4l2_event_subscribe); @@ -288,6 +286,8 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh, return 0; } + mutex_lock(&fh->subscribe_lock); + spin_lock_irqsave(&fh->vdev->fh_lock, flags); sev = v4l2_event_subscribed(fh, sub->type, sub->id); @@ -305,6 +305,8 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh, if (sev && sev->ops && sev->ops->del) sev->ops->del(sev); + mutex_unlock(&fh->subscribe_lock); + kvfree(sev); return 0; diff --git a/drivers/media/v4l2-core/v4l2-fh.c b/drivers/media/v4l2-core/v4l2-fh.c index 3895999bf880..c91a7bd3ecfc 100644 --- a/drivers/media/v4l2-core/v4l2-fh.c +++ b/drivers/media/v4l2-core/v4l2-fh.c @@ -45,6 +45,7 @@ void v4l2_fh_init(struct v4l2_fh *fh, struct video_device *vdev) INIT_LIST_HEAD(&fh->available); INIT_LIST_HEAD(&fh->subscribed); fh->sequence = -1; + mutex_init(&fh->subscribe_lock); } EXPORT_SYMBOL_GPL(v4l2_fh_init); @@ -90,6 +91,7 @@ void v4l2_fh_exit(struct v4l2_fh *fh) return; v4l_disable_media_source(fh->vdev); v4l2_event_unsubscribe_all(fh); + mutex_destroy(&fh->subscribe_lock); fh->vdev = NULL; } EXPORT_SYMBOL_GPL(v4l2_fh_exit); diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index abf9e884386c..f57f5de54206 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -235,7 +235,7 @@ int mmc_of_parse(struct mmc_host *host) host->caps |= MMC_CAP_NEEDS_POLL; ret = mmc_gpiod_request_cd(host, "cd", 0, true, - cd_debounce_delay_ms, + cd_debounce_delay_ms * 1000, &cd_gpio_invert); if (!ret) dev_info(host->parent, "Got CD GPIO\n"); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 2a833686784b..86803a3a04dc 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -271,7 +271,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, if (debounce) { ret = gpiod_set_debounce(desc, debounce); if (ret < 0) - ctx->cd_debounce_delay_ms = debounce; + ctx->cd_debounce_delay_ms = debounce / 1000; } if (gpio_invert) diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c index 890f192dedbd..5389c4821882 100644 --- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c @@ -498,7 +498,8 @@ static const struct soc_device_attribute gen3_soc_whitelist[] = { static int renesas_sdhi_sys_dmac_probe(struct platform_device *pdev) { - if (of_device_get_match_data(&pdev->dev) == &of_rcar_gen3_compatible && + if ((of_device_get_match_data(&pdev->dev) == &of_rcar_gen3_compatible || + of_device_get_match_data(&pdev->dev) == &of_rcar_r8a7795_compatible) && !soc_device_match(gen3_soc_whitelist)) return -ENODEV; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0d87e11e7f1d..ee28ec9e0aba 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -210,6 +210,7 @@ static void bond_get_stats(struct net_device *bond_dev, static void bond_slave_arr_handler(struct work_struct *work); static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod); +static void bond_netdev_notify_work(struct work_struct *work); /*---------------------------- General routines -----------------------------*/ @@ -1170,9 +1171,27 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } } - /* don't change skb->dev for link-local packets */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + /* Link-local multicast packets should be passed to the + * stack on the link they arrive as well as pass them to the + * bond-master device. These packets are mostly usable when + * stack receives it with the link on which they arrive + * (e.g. LLDP) they also must be available on master. Some of + * the use cases include (but are not limited to): LLDP agents + * that must be able to operate both on enslaved interfaces as + * well as on bonds themselves; linux bridges that must be able + * to process/pass BPDUs from attached bonds when any kind of + * STP version is enabled on the network. + */ + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (nskb) { + nskb->dev = bond->dev; + nskb->queue_mapping = 0; + netif_rx(nskb); + } return RX_HANDLER_PASS; + } if (bond_should_deliver_exact_match(skb, slave, bond)) return RX_HANDLER_EXACT; @@ -1269,6 +1288,8 @@ static struct slave *bond_alloc_slave(struct bonding *bond) return NULL; } } + INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); + return slave; } @@ -1276,6 +1297,7 @@ static void bond_free_slave(struct slave *slave) { struct bonding *bond = bond_get_bond_by_slave(slave); + cancel_delayed_work_sync(&slave->notify_work); if (BOND_MODE(bond) == BOND_MODE_8023AD) kfree(SLAVE_AD_INFO(slave)); @@ -1297,39 +1319,26 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) info->link_failure_count = slave->link_failure_count; } -static void bond_netdev_notify(struct net_device *dev, - struct netdev_bonding_info *info) -{ - rtnl_lock(); - netdev_bonding_info_change(dev, info); - rtnl_unlock(); -} - static void bond_netdev_notify_work(struct work_struct *_work) { - struct netdev_notify_work *w = - container_of(_work, struct netdev_notify_work, work.work); + struct slave *slave = container_of(_work, struct slave, + notify_work.work); + + if (rtnl_trylock()) { + struct netdev_bonding_info binfo; - bond_netdev_notify(w->dev, &w->bonding_info); - dev_put(w->dev); - kfree(w); + bond_fill_ifslave(slave, &binfo.slave); + bond_fill_ifbond(slave->bond, &binfo.master); + netdev_bonding_info_change(slave->dev, &binfo); + rtnl_unlock(); + } else { + queue_delayed_work(slave->bond->wq, &slave->notify_work, 1); + } } void bond_queue_slave_event(struct slave *slave) { - struct bonding *bond = slave->bond; - struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC); - - if (!nnw) - return; - - dev_hold(slave->dev); - nnw->dev = slave->dev; - bond_fill_ifslave(slave, &nnw->bonding_info.slave); - bond_fill_ifbond(bond, &nnw->bonding_info.master); - INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work); - - queue_delayed_work(slave->bond->wq, &nnw->work, 0); + queue_delayed_work(slave->bond->wq, &slave->notify_work, 0); } void bond_lower_state_changed(struct slave *slave) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 700d86dd5e13..0e4bbdcc614f 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1291,7 +1291,7 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); vl->members |= BIT(port); - if (untagged) + if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); else vl->untag &= ~BIT(port); @@ -1333,7 +1333,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port, pvid = 0; } - if (untagged) + if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag &= ~(BIT(port)); b53_set_vlan_entry(dev, vid, vl); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index b2522e84f482..13eb6a4d98d5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2184,25 +2184,6 @@ error_drop_packet: return NETDEV_TX_OK; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ena_netpoll(struct net_device *netdev) -{ - struct ena_adapter *adapter = netdev_priv(netdev); - int i; - - /* Dont schedule NAPI if the driver is in the middle of reset - * or netdev is down. - */ - - if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags) || - test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags)) - return; - - for (i = 0; i < adapter->num_queues; i++) - napi_schedule(&adapter->ena_napi[i].napi); -} -#endif /* CONFIG_NET_POLL_CONTROLLER */ - static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev, select_queue_fallback_t fallback) @@ -2368,9 +2349,6 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_change_mtu = ena_change_mtu, .ndo_set_mac_address = NULL, .ndo_validate_addr = eth_validate_addr, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ena_netpoll, -#endif /* CONFIG_NET_POLL_CONTROLLER */ }; static int ena_device_validate_params(struct ena_adapter *adapter, diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 29ebbf582010..9f23703dd509 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1031,6 +1031,7 @@ static int dec_lance_probe(struct device *bdev, const int type) int i, ret; unsigned long esar_base; unsigned char *esar; + const char *desc; if (dec_lance_debug && version_printed++ == 0) printk(version); @@ -1216,19 +1217,20 @@ static int dec_lance_probe(struct device *bdev, const int type) */ switch (type) { case ASIC_LANCE: - printk("%s: IOASIC onboard LANCE", name); + desc = "IOASIC onboard LANCE"; break; case PMAD_LANCE: - printk("%s: PMAD-AA", name); + desc = "PMAD-AA"; break; case PMAX_LANCE: - printk("%s: PMAX onboard LANCE", name); + desc = "PMAX onboard LANCE"; break; } for (i = 0; i < 6; i++) dev->dev_addr[i] = esar[i * 4]; - printk(", addr = %pM, irq = %d\n", dev->dev_addr, dev->irq); + printk("%s: %s, addr = %pM, irq = %d\n", + name, desc, dev->dev_addr, dev->irq); dev->netdev_ops = &lance_netdev_ops; dev->watchdog_timeo = 5*HZ; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index faba55fd656a..4122553e224b 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1070,9 +1070,6 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) { u32 reg; - /* Stop monitoring MPD interrupt */ - intrl2_0_mask_set(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG); - /* Disable RXCHK, active filters and Broadcom tag matching */ reg = rxchk_readl(priv, RXCHK_CONTROL); reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK << @@ -1082,6 +1079,17 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv) /* Clear the MagicPacket detection logic */ mpd_enable_set(priv, false); + reg = intrl2_0_readl(priv, INTRL2_CPU_STATUS); + if (reg & INTRL2_0_MPD) + netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n"); + + if (reg & INTRL2_0_BRCM_MATCH_TAG) { + reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) & + RXCHK_BRCM_TAG_MATCH_MASK; + netdev_info(priv->netdev, + "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg); + } + netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n"); } @@ -1106,7 +1114,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id) struct bcm_sysport_priv *priv = netdev_priv(dev); struct bcm_sysport_tx_ring *txr; unsigned int ring, ring_bit; - u32 reg; priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) & ~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS); @@ -1132,16 +1139,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id) if (priv->irq0_stat & INTRL2_0_TX_RING_FULL) bcm_sysport_tx_reclaim_all(priv); - if (priv->irq0_stat & INTRL2_0_MPD) - netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n"); - - if (priv->irq0_stat & INTRL2_0_BRCM_MATCH_TAG) { - reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) & - RXCHK_BRCM_TAG_MATCH_MASK; - netdev_info(priv->netdev, - "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg); - } - if (!priv->is_lite) goto out; @@ -2645,9 +2642,6 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) /* UniMAC receive needs to be turned on */ umac_enable_set(priv, CMD_RX_EN, 1); - /* Enable the interrupt wake-up source */ - intrl2_0_mask_clear(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG); - netif_dbg(priv, wol, ndev, "entered WOL mode\n"); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 61957b0bbd8c..e2d92548226a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1884,8 +1884,11 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) { tx_pkts++; /* return full budget so NAPI will complete. */ - if (unlikely(tx_pkts > bp->tx_wake_thresh)) + if (unlikely(tx_pkts > bp->tx_wake_thresh)) { rx_pkts = budget; + raw_cons = NEXT_RAW_CMP(raw_cons); + break; + } } else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) { if (likely(budget)) rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event); @@ -1913,7 +1916,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) } raw_cons = NEXT_RAW_CMP(raw_cons); - if (rx_pkts == budget) + if (rx_pkts && rx_pkts == budget) break; } @@ -2027,8 +2030,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget) while (1) { work_done += bnxt_poll_work(bp, bnapi, budget - work_done); - if (work_done >= budget) + if (work_done >= budget) { + if (!budget) + BNXT_CP_DB_REARM(cpr->cp_doorbell, + cpr->cp_raw_cons); break; + } if (!bnxt_has_work(bp, cpr)) { if (napi_complete_done(napi, work_done)) @@ -3010,10 +3017,11 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; - dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, - bp->hwrm_cmd_resp_dma_addr); - - bp->hwrm_cmd_resp_addr = NULL; + if (bp->hwrm_cmd_resp_addr) { + dma_free_coherent(&pdev->dev, PAGE_SIZE, bp->hwrm_cmd_resp_addr, + bp->hwrm_cmd_resp_dma_addr); + bp->hwrm_cmd_resp_addr = NULL; + } } static int bnxt_alloc_hwrm_resources(struct bnxt *bp) @@ -4643,7 +4651,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; enables |= ring_grps ? FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; - enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; + enables |= vnics ? FUNC_CFG_REQ_ENABLES_NUM_VNICS : 0; req->num_rx_rings = cpu_to_le16(rx_rings); req->num_hw_ring_grps = cpu_to_le16(ring_grps); @@ -8614,7 +8622,7 @@ 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, bnxt_get_max_func_cp_rings_for_en(bp), - hw_resc->max_irqs); + hw_resc->max_irqs - bnxt_get_ulp_msix_num(bp)); *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)) { @@ -9050,6 +9058,7 @@ init_err_cleanup_tc: bnxt_clear_int_mode(bp); init_err_pci_clean: + bnxt_free_hwrm_resources(bp); bnxt_cleanup_pci(bp); init_err_free: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index ddc98c359488..a85d2be986af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -98,13 +98,13 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1); for (i = 0; i < max_tc; i++) { - u8 qidx; + u8 qidx = bp->tc_to_qidx[i]; req.enables |= cpu_to_le32( - QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << i); + QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << + qidx); memset(&cos2bw, 0, sizeof(cos2bw)); - qidx = bp->tc_to_qidx[i]; cos2bw.queue_id = bp->q_info[qidx].queue_id; if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) { cos2bw.tsa = diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 790c684f08ab..8a10e01f0861 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -21,9 +21,22 @@ static const struct devlink_ops bnxt_dl_ops = { #endif /* CONFIG_BNXT_SRIOV */ }; +enum bnxt_dl_param_id { + BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, +}; + static const struct bnxt_dl_nvm_param nvm_params[] = { {DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV, BNXT_NVM_SHARED_CFG, 1}, + {DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, NVM_OFF_IGNORE_ARI, + BNXT_NVM_SHARED_CFG, 1}, + {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10}, + {DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7}, + {BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK, + BNXT_NVM_SHARED_CFG, 1}, }; static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, @@ -55,8 +68,22 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID; bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE; - if (nvm_param.num_bits == 1) - buf = &val->vbool; + switch (bytesize) { + case 1: + if (nvm_param.num_bits == 1) + buf = &val->vbool; + else + buf = &val->vu8; + break; + case 2: + buf = &val->vu16; + break; + case 4: + buf = &val->vu32; + break; + default: + return -EFAULT; + } data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize, &data_dma_addr, GFP_KERNEL); @@ -78,8 +105,12 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, memcpy(buf, data_addr, bytesize); dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr); - if (rc) + if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { + netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n"); + return -EACCES; + } else if (rc) { return -EIO; + } return 0; } @@ -88,9 +119,15 @@ static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id, { struct hwrm_nvm_get_variable_input req = {0}; struct bnxt *bp = bnxt_get_bp_from_dl(dl); + int rc; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1); - return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); + rc = bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); + if (!rc) + if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK) + ctx->val.vbool = !ctx->val.vbool; + + return rc; } static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id, @@ -100,14 +137,55 @@ static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id, struct bnxt *bp = bnxt_get_bp_from_dl(dl); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1); + + if (id == BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK) + ctx->val.vbool = !ctx->val.vbool; + return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val); } +static int bnxt_dl_msix_validate(struct devlink *dl, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + int max_val; + + if (id == DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX) + max_val = BNXT_MSIX_VEC_MAX; + + if (id == DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN) + max_val = BNXT_MSIX_VEC_MIN_MAX; + + if (val.vu32 < 0 || val.vu32 > max_val) { + NL_SET_ERR_MSG_MOD(extack, "MSIX value is exceeding the range"); + return -EINVAL; + } + + return 0; +} + static const struct devlink_param bnxt_dl_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_SRIOV, BIT(DEVLINK_PARAM_CMODE_PERMANENT), bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, NULL), + DEVLINK_PARAM_GENERIC(IGNORE_ARI, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + NULL), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + bnxt_dl_msix_validate), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + bnxt_dl_msix_validate), + DEVLINK_PARAM_DRIVER(BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, + "gre_ver_check", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set, + NULL), }; int bnxt_dl_register(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 2f68dc048390..5b6b2c7d97cf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -33,8 +33,15 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) } } +#define NVM_OFF_MSIX_VEC_PER_PF_MAX 108 +#define NVM_OFF_MSIX_VEC_PER_PF_MIN 114 +#define NVM_OFF_IGNORE_ARI 164 +#define NVM_OFF_DIS_GRE_VER_CHECK 171 #define NVM_OFF_ENABLE_SRIOV 401 +#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MIN_MAX 128 + enum bnxt_nvm_dir_type { BNXT_NVM_SHARED_CFG = 40, BNXT_NVM_PORT_CFG, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index b574fe8e974e..9a25c05aa571 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -521,7 +521,8 @@ int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode) return 0; } -int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode) +int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct bnxt *bp = bnxt_get_bp_from_dl(devlink); int rc = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h index 38b9a75ad724..d7287651422f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h @@ -30,7 +30,8 @@ static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev) bool bnxt_dev_is_vf_rep(struct net_device *dev); int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode); -int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode); +int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); #else diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index eb96b0613cf6..825a28e5b544 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -1732,7 +1732,7 @@ int liquidio_set_fec(struct lio *lio, int on_off) 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", + "Reload driver to change fec to %s\n", oct->props[lio->ifidx].fec ? "on" : "off"); } @@ -1796,7 +1796,7 @@ int liquidio_get_fec(struct lio *lio) 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", + "Reload driver to change fec to %s\n", oct->props[lio->ifidx].fec ? "on" : "off"); } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 9d70e5c6157f..3d24133e5e49 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3144,7 +3144,8 @@ liquidio_eswitch_mode_get(struct devlink *devlink, u16 *mode) } static int -liquidio_eswitch_mode_set(struct devlink *devlink, u16 mode) +liquidio_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct lio_devlink_priv *priv; struct octeon_device *oct; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 8b0a253a18d8..1e82b9efe447 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2158,6 +2158,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_QSET_PARAMS) + return -EINVAL; if (t.qset_idx >= SGE_QSETS) return -EINVAL; if (!in_range(t.intr_lat, 0, M_NEWTIMER) || @@ -2257,6 +2259,9 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_QSET_PARAMS) + return -EINVAL; + /* Display qsets for all ports when offload enabled */ if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) { q1 = 0; @@ -2302,6 +2307,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; + if (edata.cmd != CHELSIO_SET_QSET_NUM) + return -EINVAL; if (edata.val < 1 || (edata.val > 1 && !(adapter->flags & USING_MSIX))) return -EINVAL; @@ -2342,6 +2349,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_LOAD_FW) + return -EINVAL; /* Check t.len sanity ? */ fw_data = memdup_user(useraddr + sizeof(t), t.len); if (IS_ERR(fw_data)) @@ -2365,6 +2374,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SETMTUTAB) + return -EINVAL; if (m.nmtus != NMTUS) return -EINVAL; if (m.mtus[0] < 81) /* accommodate SACK */ @@ -2406,6 +2417,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SET_PM) + return -EINVAL; if (!is_power_of_2(m.rx_pg_sz) || !is_power_of_2(m.tx_pg_sz)) return -EINVAL; /* not power of 2 */ @@ -2439,6 +2452,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_MEM) + return -EINVAL; if ((t.addr & 7) || (t.len & 7)) return -EINVAL; if (t.mem_id == MEM_CM) @@ -2491,6 +2506,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EAGAIN; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_TRACE_FILTER) + return -EINVAL; tp = (const struct trace_params *)&t.sip; if (t.config_tx) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index 7fc656680299..52edb688942b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -38,7 +38,6 @@ #include "cxgb4.h" #include "sched.h" -/* Spinlock must be held by caller */ static int t4_sched_class_fw_cmd(struct port_info *pi, struct ch_sched_params *p, enum sched_fw_ops op) @@ -67,7 +66,6 @@ static int t4_sched_class_fw_cmd(struct port_info *pi, return err; } -/* Spinlock must be held by caller */ static int t4_sched_bind_unbind_op(struct port_info *pi, void *arg, enum sched_bind_type type, bool bind) { @@ -163,7 +161,6 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) if (e && index >= 0) { int i = 0; - spin_lock(&e->lock); list_for_each_entry(qe, &e->queue_list, list) { if (i == index) break; @@ -171,10 +168,8 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) } err = t4_sched_bind_unbind_op(pi, (void *)qe, SCHED_QUEUE, false); - if (err) { - spin_unlock(&e->lock); - goto out; - } + if (err) + return err; list_del(&qe->list); kvfree(qe); @@ -182,9 +177,7 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) e->state = SCHED_STATE_UNUSED; memset(&e->info, 0, sizeof(e->info)); } - spin_unlock(&e->lock); } -out: return err; } @@ -210,10 +203,8 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) /* Unbind queue from any existing class */ err = t4_sched_queue_unbind(pi, p); - if (err) { - kvfree(qe); - goto out; - } + if (err) + goto out_err; /* Bind queue to specified class */ memset(qe, 0, sizeof(*qe)); @@ -221,18 +212,16 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) memcpy(&qe->param, p, sizeof(qe->param)); e = &s->tab[qe->param.class]; - spin_lock(&e->lock); err = t4_sched_bind_unbind_op(pi, (void *)qe, SCHED_QUEUE, true); - if (err) { - kvfree(qe); - spin_unlock(&e->lock); - goto out; - } + if (err) + goto out_err; list_add_tail(&qe->list, &e->queue_list); atomic_inc(&e->refcnt); - spin_unlock(&e->lock); -out: + return err; + +out_err: + kvfree(qe); return err; } @@ -296,8 +285,6 @@ int cxgb4_sched_class_bind(struct net_device *dev, void *arg, enum sched_bind_type type) { struct port_info *pi = netdev2pinfo(dev); - struct sched_table *s; - int err = 0; u8 class_id; if (!can_sched(dev)) @@ -323,12 +310,8 @@ int cxgb4_sched_class_bind(struct net_device *dev, void *arg, if (class_id == SCHED_CLS_NONE) return -ENOTSUPP; - s = pi->sched_tbl; - write_lock(&s->rw_lock); - err = t4_sched_class_bind_unbind_op(pi, arg, type, true); - write_unlock(&s->rw_lock); + return t4_sched_class_bind_unbind_op(pi, arg, type, true); - return err; } /** @@ -343,8 +326,6 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, enum sched_bind_type type) { struct port_info *pi = netdev2pinfo(dev); - struct sched_table *s; - int err = 0; u8 class_id; if (!can_sched(dev)) @@ -367,12 +348,7 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, if (!valid_class_id(dev, class_id)) return -EINVAL; - s = pi->sched_tbl; - write_lock(&s->rw_lock); - err = t4_sched_class_bind_unbind_op(pi, arg, type, false); - write_unlock(&s->rw_lock); - - return err; + return t4_sched_class_bind_unbind_op(pi, arg, type, false); } /* If @p is NULL, fetch any available unused class */ @@ -425,7 +401,6 @@ static struct sched_class *t4_sched_class_lookup(struct port_info *pi, static struct sched_class *t4_sched_class_alloc(struct port_info *pi, struct ch_sched_params *p) { - struct sched_table *s = pi->sched_tbl; struct sched_class *e; u8 class_id; int err; @@ -441,7 +416,6 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi, if (class_id != SCHED_CLS_NONE) return NULL; - write_lock(&s->rw_lock); /* See if there's an exisiting class with same * requested sched params */ @@ -452,27 +426,19 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi, /* Fetch any available unused class */ e = t4_sched_class_lookup(pi, NULL); if (!e) - goto out; + return NULL; memcpy(&np, p, sizeof(np)); np.u.params.class = e->idx; - - spin_lock(&e->lock); /* New class */ err = t4_sched_class_fw_cmd(pi, &np, SCHED_FW_OP_ADD); - if (err) { - spin_unlock(&e->lock); - e = NULL; - goto out; - } + if (err) + return NULL; memcpy(&e->info, &np, sizeof(e->info)); atomic_set(&e->refcnt, 0); e->state = SCHED_STATE_ACTIVE; - spin_unlock(&e->lock); } -out: - write_unlock(&s->rw_lock); return e; } @@ -517,14 +483,12 @@ struct sched_table *t4_init_sched(unsigned int sched_size) return NULL; s->sched_size = sched_size; - rwlock_init(&s->rw_lock); for (i = 0; i < s->sched_size; i++) { memset(&s->tab[i], 0, sizeof(struct sched_class)); s->tab[i].idx = i; s->tab[i].state = SCHED_STATE_UNUSED; INIT_LIST_HEAD(&s->tab[i].queue_list); - spin_lock_init(&s->tab[i].lock); atomic_set(&s->tab[i].refcnt, 0); } return s; @@ -545,11 +509,9 @@ void t4_cleanup_sched(struct adapter *adap) for (i = 0; i < s->sched_size; i++) { struct sched_class *e; - write_lock(&s->rw_lock); e = &s->tab[i]; if (e->state == SCHED_STATE_ACTIVE) t4_sched_class_free(pi, e); - write_unlock(&s->rw_lock); } kvfree(s); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h index 3a49e00a38a1..168fb4ce3759 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.h +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h @@ -69,13 +69,11 @@ struct sched_class { u8 idx; struct ch_sched_params info; struct list_head queue_list; - spinlock_t lock; /* Per class lock */ atomic_t refcnt; }; struct sched_table { /* per port scheduling table */ u8 sched_size; - rwlock_t rw_lock; /* Table lock */ struct sched_class tab[0]; }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index f85eab57e9e1..cb523949c812 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4204,6 +4204,7 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox, */ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port) { + unsigned int fw_caps = adap->params.fw_caps_support; struct fw_port_cmd c; memset(&c, 0, sizeof(c)); @@ -4211,9 +4212,14 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port) FW_CMD_REQUEST_F | FW_CMD_EXEC_F | FW_PORT_CMD_PORTID_V(port)); c.action_to_len16 = - cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) | + cpu_to_be32(FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_L1_CFG + : FW_PORT_ACTION_L1_CFG32) | FW_LEN16(c)); - c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP32_ANEG); + if (fw_caps == FW_CAPS16) + c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP_ANEG); + else + c.u.l1cfg32.rcap32 = cpu_to_be32(FW_PORT_CAP32_ANEG); return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index b8f75a22fb6c..f152da1ce046 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -753,7 +753,6 @@ struct cpl_abort_req_rss { }; struct cpl_abort_req_rss6 { - WR_HDR; union opcode_tid ot; __be32 srqidx_status; }; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 74d122616e76..534787291b44 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4002,8 +4002,6 @@ static int be_enable_vxlan_offloads(struct be_adapter *adapter) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->features |= NETIF_F_GSO_UDP_TUNNEL; dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", be16_to_cpu(port)); @@ -4025,8 +4023,6 @@ static void be_disable_vxlan_offloads(struct be_adapter *adapter) adapter->vxlan_port = 0; netdev->hw_enc_features = 0; - netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL); - netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL); } static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs, @@ -5320,6 +5316,7 @@ static void be_netdev_init(struct net_device *netdev) struct be_adapter *adapter = netdev_priv(netdev); netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX; if ((be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS)) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index ce74b7a46d07..a17cc973d9a3 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1158,7 +1158,7 @@ static void fec_enet_timeout_work(struct work_struct *work) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -1273,7 +1273,7 @@ skb_done: /* Since we have freed up a buffer, the ring is no longer full */ - if (netif_queue_stopped(ndev)) { + if (netif_tx_queue_stopped(nq)) { entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free >= txq->tx_wake_threshold) netif_tx_wake_queue(nq); @@ -1746,7 +1746,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -2240,7 +2240,7 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index a051e582d541..79d03f8ee7b1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -84,7 +84,7 @@ static void hnae_unmap_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) if (cb->type == DESC_TYPE_SKB) dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); - else + else if (cb->length) dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index f56855e63c96..28e907831b0e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -40,9 +40,9 @@ #define SKB_TMP_LEN(SKB) \ (((SKB)->transport_header - (SKB)->mac_header) + tcp_hdrlen(SKB)) -static void fill_v2_desc(struct hnae_ring *ring, void *priv, - int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu) +static void fill_v2_desc_hw(struct hnae_ring *ring, void *priv, int size, + int send_sz, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) { struct hnae_desc *desc = &ring->desc[ring->next_to_use]; struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; @@ -64,7 +64,7 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, desc_cb->type = type; desc->addr = cpu_to_le64(dma); - desc->tx.send_size = cpu_to_le16((u16)size); + desc->tx.send_size = cpu_to_le16((u16)send_sz); /* config bd buffer end */ hnae_set_bit(rrcfv, HNSV2_TXD_VLD_B, 1); @@ -133,6 +133,14 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, ring_ptr_move_fw(ring, next_to_use); } +static void fill_v2_desc(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) +{ + fill_v2_desc_hw(ring, priv, size, size, dma, frag_end, + buf_num, type, mtu); +} + static const struct acpi_device_id hns_enet_acpi_match[] = { { "HISI00C1", 0 }, { "HISI00C2", 0 }, @@ -289,15 +297,15 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv, /* when the frag size is bigger than hardware, split this frag */ for (k = 0; k < frag_buf_num; k++) - fill_v2_desc(ring, priv, - (k == frag_buf_num - 1) ? + fill_v2_desc_hw(ring, priv, k == 0 ? size : 0, + (k == frag_buf_num - 1) ? sizeoflast : BD_MAX_SEND_SIZE, - dma + BD_MAX_SEND_SIZE * k, - frag_end && (k == frag_buf_num - 1) ? 1 : 0, - buf_num, - (type == DESC_TYPE_SKB && !k) ? + dma + BD_MAX_SEND_SIZE * k, + frag_end && (k == frag_buf_num - 1) ? 1 : 0, + buf_num, + (type == DESC_TYPE_SKB && !k) ? DESC_TYPE_SKB : DESC_TYPE_PAGE, - mtu); + mtu); } netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, @@ -1495,21 +1503,6 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, return phy_mii_ioctl(phy_dev, ifr, cmd); } -/* use only for netconsole to poll with the device without interrupt */ -#ifdef CONFIG_NET_POLL_CONTROLLER -static void hns_nic_poll_controller(struct net_device *ndev) -{ - struct hns_nic_priv *priv = netdev_priv(ndev); - unsigned long flags; - int i; - - local_irq_save(flags); - for (i = 0; i < priv->ae_handle->q_num * 2; i++) - napi_schedule(&priv->ring_data[i].napi); - local_irq_restore(flags); -} -#endif - static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb, struct net_device *ndev) { @@ -1962,9 +1955,6 @@ static const struct net_device_ops hns_nic_netdev_ops = { .ndo_set_features = hns_nic_set_features, .ndo_fix_features = hns_nic_fix_features, .ndo_get_stats64 = hns_nic_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = hns_nic_poll_controller, -#endif .ndo_set_rx_mode = hns_nic_set_rx_mode, .ndo_select_queue = hns_nic_select_queue, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index be9dc08ccf67..038326cfda93 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -46,9 +46,6 @@ enum hclge_mbx_mac_vlan_subcode { HCLGE_MBX_MAC_VLAN_MC_MODIFY, /* modify MC mac addr */ HCLGE_MBX_MAC_VLAN_MC_ADD, /* add new MC mac addr */ HCLGE_MBX_MAC_VLAN_MC_REMOVE, /* remove MC mac addr */ - HCLGE_MBX_MAC_VLAN_MC_FUNC_MTA_ENABLE, /* config func MTA enable */ - HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ, /* read func MTA type */ - HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE, /* update MTA status */ }; /* below are per-VF vlan cfg subcodes */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 591ee2ee4bf6..1b49c5d3340b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -355,8 +355,6 @@ struct hnae3_ae_ops { const unsigned char *addr); int (*rm_mc_addr)(struct hnae3_handle *handle, const unsigned char *addr); - int (*update_mta_status)(struct hnae3_handle *handle); - void (*set_tso_stats)(struct hnae3_handle *handle, int enable); void (*update_stats)(struct hnae3_handle *handle, struct net_device_stats *net_stats); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index c2692563a4d9..e9d4564b8ce1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -21,6 +21,7 @@ static void hns3_clear_all_ring(struct hnae3_handle *h); static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h); +static void hns3_remove_hw_addr(struct net_device *netdev); static const char hns3_driver_name[] = "hns3"; const char hns3_driver_version[] = VERMAGIC_STRING; @@ -475,9 +476,6 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev) if (netdev->flags & IFF_MULTICAST) { if (__dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync)) netdev_err(netdev, "sync mc address fail\n"); - - if (h->ae_algo->ops->update_mta_status) - h->ae_algo->ops->update_mta_status(h); } } @@ -2202,18 +2200,18 @@ static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb) napi_gro_receive(&ring->tqp_vector->napi, skb); } -static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring, - struct hns3_desc *desc, u32 l234info) +static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring, + struct hns3_desc *desc, u32 l234info, + u16 *vlan_tag) { struct pci_dev *pdev = ring->tqp->handle->pdev; - u16 vlan_tag; if (pdev->revision == 0x20) { - vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); - if (!(vlan_tag & VLAN_VID_MASK)) - vlan_tag = le16_to_cpu(desc->rx.vlan_tag); + *vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); + if (!(*vlan_tag & VLAN_VID_MASK)) + *vlan_tag = le16_to_cpu(desc->rx.vlan_tag); - return vlan_tag; + return (*vlan_tag != 0); } #define HNS3_STRP_OUTER_VLAN 0x1 @@ -2222,17 +2220,14 @@ static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring, switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M, HNS3_RXD_STRP_TAGP_S)) { case HNS3_STRP_OUTER_VLAN: - vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); - break; + *vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag); + return true; case HNS3_STRP_INNER_VLAN: - vlan_tag = le16_to_cpu(desc->rx.vlan_tag); - break; + *vlan_tag = le16_to_cpu(desc->rx.vlan_tag); + return true; default: - vlan_tag = 0; - break; + return false; } - - return vlan_tag; } static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, @@ -2334,8 +2329,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { u16 vlan_tag; - vlan_tag = hns3_parse_vlan_tag(ring, desc, l234info); - if (vlan_tag & VLAN_VID_MASK) + if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); @@ -3155,15 +3149,6 @@ static void hns3_init_mac_addr(struct net_device *netdev, bool init) } -static void hns3_uninit_mac_addr(struct net_device *netdev) -{ - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; - - if (h->ae_algo->ops->rm_uc_addr) - h->ae_algo->ops->rm_uc_addr(h, netdev->dev_addr); -} - static int hns3_restore_fd_rules(struct net_device *netdev) { struct hnae3_handle *h = hns3_get_handle(netdev); @@ -3296,6 +3281,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) struct hns3_nic_priv *priv = netdev_priv(netdev); int ret; + hns3_remove_hw_addr(netdev); + if (netdev->reg_state != NETREG_UNINITIALIZED) unregister_netdev(netdev); @@ -3319,8 +3306,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) priv->ring_data = NULL; - hns3_uninit_mac_addr(netdev); - free_netdev(netdev); } @@ -3392,6 +3377,25 @@ static void hns3_recover_hw_addr(struct net_device *ndev) hns3_nic_mc_sync(ndev, ha->addr); } +static void hns3_remove_hw_addr(struct net_device *netdev) +{ + struct netdev_hw_addr_list *list; + struct netdev_hw_addr *ha, *tmp; + + hns3_nic_uc_unsync(netdev, netdev->dev_addr); + + /* go through and unsync uc_addr entries to the device */ + list = &netdev->uc; + list_for_each_entry_safe(ha, tmp, &list->list, list) + hns3_nic_uc_unsync(netdev, ha->addr); + + /* go through and unsync mc_addr entries to the device */ + list = &netdev->mc; + list_for_each_entry_safe(ha, tmp, &list->list, list) + if (ha->refcount > 1) + hns3_nic_mc_unsync(netdev, ha->addr); +} + static void hns3_clear_tx_ring(struct hns3_enet_ring *ring) { while (ring->next_to_clean != ring->next_to_use) { @@ -3637,14 +3641,14 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) if (ret) netdev_err(netdev, "uninit ring error\n"); - hns3_uninit_mac_addr(netdev); - - /* it is cumbersome for hardware to pick-and-choose rules for deletion - * from TCAM. Hence, for function reset software intervention is - * required to delete the rules + /* it is cumbersome for hardware to pick-and-choose entries for deletion + * from table space. Hence, for function reset software intervention is + * required to delete the entries */ - if (hns3_dev_ongoing_func_reset(ae_dev)) + if (hns3_dev_ongoing_func_reset(ae_dev)) { + hns3_remove_hw_addr(netdev); hns3_del_all_fd_rules(netdev, false); + } return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index e5e66b27e03e..1ccde67db770 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -175,15 +175,9 @@ enum hclge_opcode_type { HCLGE_OPC_MAC_VLAN_REMOVE = 0x1001, HCLGE_OPC_MAC_VLAN_TYPE_ID = 0x1002, HCLGE_OPC_MAC_VLAN_INSERT = 0x1003, + HCLGE_OPC_MAC_VLAN_ALLOCATE = 0x1004, HCLGE_OPC_MAC_ETHTYPE_ADD = 0x1010, HCLGE_OPC_MAC_ETHTYPE_REMOVE = 0x1011, - HCLGE_OPC_MAC_VLAN_MASK_SET = 0x1012, - - /* Multicast linear table commands */ - HCLGE_OPC_MTA_MAC_MODE_CFG = 0x1020, - HCLGE_OPC_MTA_MAC_FUNC_CFG = 0x1021, - HCLGE_OPC_MTA_TBL_ITEM_CFG = 0x1022, - HCLGE_OPC_MTA_TBL_ITEM_QUERY = 0x1023, /* VLAN commands */ HCLGE_OPC_VLAN_FILTER_CTRL = 0x1100, @@ -402,6 +396,8 @@ struct hclge_pf_res_cmd { #define HCLGE_CFG_RSS_SIZE_M GENMASK(31, 24) #define HCLGE_CFG_SPEED_ABILITY_S 0 #define HCLGE_CFG_SPEED_ABILITY_M GENMASK(7, 0) +#define HCLGE_CFG_UMV_TBL_SPACE_S 16 +#define HCLGE_CFG_UMV_TBL_SPACE_M GENMASK(31, 16) struct hclge_cfg_param_cmd { __le32 offset; @@ -591,13 +587,12 @@ struct hclge_mac_vlan_tbl_entry_cmd { u8 rsv2[6]; }; -#define HCLGE_VLAN_MASK_EN_B 0 -struct hclge_mac_vlan_mask_entry_cmd { - u8 rsv0[2]; - u8 vlan_mask; - u8 rsv1; - u8 mac_mask[6]; - u8 rsv2[14]; +#define HCLGE_UMV_SPC_ALC_B 0 +struct hclge_umv_spc_alc_cmd { + u8 allocate; + u8 rsv1[3]; + __le32 space_size; + u8 rsv2[16]; }; #define HCLGE_MAC_MGR_MASK_VLAN_B BIT(0) @@ -622,30 +617,6 @@ struct hclge_mac_mgr_tbl_entry_cmd { u8 rsv3[2]; }; -#define HCLGE_CFG_MTA_MAC_SEL_S 0 -#define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) -#define HCLGE_CFG_MTA_MAC_EN_B 7 -struct hclge_mta_filter_mode_cmd { - u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ - u8 rsv[23]; -}; - -#define HCLGE_CFG_FUNC_MTA_ACCEPT_B 0 -struct hclge_cfg_func_mta_filter_cmd { - u8 accept; /* Only used lowest 1 bit */ - u8 function_id; - u8 rsv[22]; -}; - -#define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0 -#define HCLGE_CFG_MTA_ITEM_IDX_S 0 -#define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) -struct hclge_cfg_func_mta_item_cmd { - __le16 item_idx; /* Only used lowest 12 bit */ - u8 accept; /* Only used lowest 1 bit */ - u8 rsv[21]; -}; - struct hclge_mac_vlan_add_cmd { __le16 flags; __le16 mac_addr_hi16; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 21ca4af3b37a..ca1a93664d0e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -25,12 +25,11 @@ #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) -static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, - enum hclge_mta_dmac_sel_type mta_mac_sel, - bool enable); static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu); static int hclge_init_vlan_config(struct hclge_dev *hdev); static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev); +static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, + u16 *allocated_size, bool is_alloc); static struct hnae3_ae_algo ae_algo; @@ -778,6 +777,11 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]), HCLGE_CFG_SPEED_ABILITY_M, HCLGE_CFG_SPEED_ABILITY_S); + cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_UMV_TBL_SPACE_M, + HCLGE_CFG_UMV_TBL_SPACE_S); + if (!cfg->umv_space) + cfg->umv_space = HCLGE_DEFAULT_UMV_SPACE_PER_PF; } /* hclge_get_cfg: query the static parameter from flash @@ -856,6 +860,7 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->tm_info.num_pg = 1; hdev->tc_max = cfg.tc_num; hdev->tm_info.hw_pfc_map = 0; + hdev->wanted_umv_size = cfg.umv_space; ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed); if (ret) { @@ -1939,40 +1944,13 @@ static int hclge_get_autoneg(struct hnae3_handle *handle) return hdev->hw.mac.autoneg; } -static int hclge_set_default_mac_vlan_mask(struct hclge_dev *hdev, - bool mask_vlan, - u8 *mac_mask) -{ - struct hclge_mac_vlan_mask_entry_cmd *req; - struct hclge_desc desc; - int status; - - req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false); - - hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B, - mask_vlan ? 1 : 0); - ether_addr_copy(req->mac_mask, mac_mask); - - status = hclge_cmd_send(&hdev->hw, &desc, 1); - if (status) - dev_err(&hdev->pdev->dev, - "Config mac_vlan_mask failed for cmd_send, ret =%d\n", - status); - - return status; -} - static int hclge_mac_init(struct hclge_dev *hdev) { struct hnae3_handle *handle = &hdev->vport[0].nic; struct net_device *netdev = handle->kinfo.netdev; struct hclge_mac *mac = &hdev->hw.mac; - u8 mac_mask[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; - struct hclge_vport *vport; int mtu; int ret; - int i; hdev->hw.mac.duplex = HCLGE_MAC_FULL; ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, @@ -1985,39 +1963,6 @@ static int hclge_mac_init(struct hclge_dev *hdev) mac->link = 0; - /* Initialize the MTA table work mode */ - hdev->enable_mta = true; - hdev->mta_mac_sel_type = HCLGE_MAC_ADDR_47_36; - - ret = hclge_set_mta_filter_mode(hdev, - hdev->mta_mac_sel_type, - hdev->enable_mta); - if (ret) { - dev_err(&hdev->pdev->dev, "set mta filter mode failed %d\n", - ret); - return ret; - } - - for (i = 0; i < hdev->num_alloc_vport; i++) { - vport = &hdev->vport[i]; - vport->accept_mta_mc = false; - - memset(vport->mta_shadow, 0, sizeof(vport->mta_shadow)); - ret = hclge_cfg_func_mta_filter(hdev, vport->vport_id, false); - if (ret) { - dev_err(&hdev->pdev->dev, - "set mta filter mode fail ret=%d\n", ret); - return ret; - } - } - - ret = hclge_set_default_mac_vlan_mask(hdev, true, mac_mask); - if (ret) { - dev_err(&hdev->pdev->dev, - "set default mac_vlan_mask fail ret=%d\n", ret); - return ret; - } - if (netdev) mtu = netdev->mtu; else @@ -4978,174 +4923,6 @@ static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); } -static u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, - const u8 *addr) -{ - u16 high_val = addr[1] | (addr[0] << 8); - struct hclge_dev *hdev = vport->back; - u32 rsh = 4 - hdev->mta_mac_sel_type; - u16 ret_val = (high_val >> rsh) & 0xfff; - - return ret_val; -} - -static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, - enum hclge_mta_dmac_sel_type mta_mac_sel, - bool enable) -{ - struct hclge_mta_filter_mode_cmd *req; - struct hclge_desc desc; - int ret; - - req = (struct hclge_mta_filter_mode_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); - - hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, - enable); - hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M, - HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "Config mat filter mode failed for cmd_send, ret =%d.\n", - ret); - - return ret; -} - -int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, - u8 func_id, - bool enable) -{ - struct hclge_cfg_func_mta_filter_cmd *req; - struct hclge_desc desc; - int ret; - - req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); - - hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, - enable); - req->function_id = func_id; - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "Config func_id enable failed for cmd_send, ret =%d.\n", - ret); - - return ret; -} - -static int hclge_set_mta_table_item(struct hclge_vport *vport, - u16 idx, - bool enable) -{ - struct hclge_dev *hdev = vport->back; - struct hclge_cfg_func_mta_item_cmd *req; - struct hclge_desc desc; - u16 item_idx = 0; - int ret; - - req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); - hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); - - hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, - HCLGE_CFG_MTA_ITEM_IDX_S, idx); - req->item_idx = cpu_to_le16(item_idx); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, - "Config mta table item failed for cmd_send, ret =%d.\n", - ret); - return ret; - } - - if (enable) - set_bit(idx, vport->mta_shadow); - else - clear_bit(idx, vport->mta_shadow); - - return 0; -} - -static int hclge_update_mta_status(struct hnae3_handle *handle) -{ - unsigned long mta_status[BITS_TO_LONGS(HCLGE_MTA_TBL_SIZE)]; - struct hclge_vport *vport = hclge_get_vport(handle); - struct net_device *netdev = handle->kinfo.netdev; - struct netdev_hw_addr *ha; - u16 tbl_idx; - - memset(mta_status, 0, sizeof(mta_status)); - - /* update mta_status from mc addr list */ - netdev_for_each_mc_addr(ha, netdev) { - tbl_idx = hclge_get_mac_addr_to_mta_index(vport, ha->addr); - set_bit(tbl_idx, mta_status); - } - - return hclge_update_mta_status_common(vport, mta_status, - 0, HCLGE_MTA_TBL_SIZE, true); -} - -int hclge_update_mta_status_common(struct hclge_vport *vport, - unsigned long *status, - u16 idx, - u16 count, - bool update_filter) -{ - struct hclge_dev *hdev = vport->back; - u16 update_max = idx + count; - u16 check_max; - int ret = 0; - bool used; - u16 i; - - /* setup mta check range */ - if (update_filter) { - i = 0; - check_max = HCLGE_MTA_TBL_SIZE; - } else { - i = idx; - check_max = update_max; - } - - used = false; - /* check and update all mta item */ - for (; i < check_max; i++) { - /* ignore unused item */ - if (!test_bit(i, vport->mta_shadow)) - continue; - - /* if i in update range then update it */ - if (i >= idx && i < update_max) - if (!test_bit(i - idx, status)) - hclge_set_mta_table_item(vport, i, false); - - if (!used && test_bit(i, vport->mta_shadow)) - used = true; - } - - /* no longer use mta, disable it */ - if (vport->accept_mta_mc && update_filter && !used) { - ret = hclge_cfg_func_mta_filter(hdev, - vport->vport_id, - false); - if (ret) - dev_err(&hdev->pdev->dev, - "disable func mta filter fail ret=%d\n", - ret); - else - vport->accept_mta_mc = false; - } - - return ret; -} - static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, struct hclge_mac_vlan_tbl_entry_cmd *req) { @@ -5269,6 +5046,118 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, return cfg_status; } +static int hclge_init_umv_space(struct hclge_dev *hdev) +{ + u16 allocated_size = 0; + int ret; + + ret = hclge_set_umv_space(hdev, hdev->wanted_umv_size, &allocated_size, + true); + if (ret) + return ret; + + if (allocated_size < hdev->wanted_umv_size) + dev_warn(&hdev->pdev->dev, + "Alloc umv space failed, want %d, get %d\n", + hdev->wanted_umv_size, allocated_size); + + mutex_init(&hdev->umv_mutex); + hdev->max_umv_size = allocated_size; + hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_req_vfs + 2); + hdev->share_umv_size = hdev->priv_umv_size + + hdev->max_umv_size % (hdev->num_req_vfs + 2); + + return 0; +} + +static int hclge_uninit_umv_space(struct hclge_dev *hdev) +{ + int ret; + + if (hdev->max_umv_size > 0) { + ret = hclge_set_umv_space(hdev, hdev->max_umv_size, NULL, + false); + if (ret) + return ret; + hdev->max_umv_size = 0; + } + mutex_destroy(&hdev->umv_mutex); + + return 0; +} + +static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size, + u16 *allocated_size, bool is_alloc) +{ + struct hclge_umv_spc_alc_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_umv_spc_alc_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ALLOCATE, false); + hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, !is_alloc); + req->space_size = cpu_to_le32(space_size); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "%s umv space failed for cmd_send, ret =%d\n", + is_alloc ? "allocate" : "free", ret); + return ret; + } + + if (is_alloc && allocated_size) + *allocated_size = le32_to_cpu(desc.data[1]); + + return 0; +} + +static void hclge_reset_umv_space(struct hclge_dev *hdev) +{ + struct hclge_vport *vport; + int i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + vport = &hdev->vport[i]; + vport->used_umv_num = 0; + } + + mutex_lock(&hdev->umv_mutex); + hdev->share_umv_size = hdev->priv_umv_size + + hdev->max_umv_size % (hdev->num_req_vfs + 2); + mutex_unlock(&hdev->umv_mutex); +} + +static bool hclge_is_umv_space_full(struct hclge_vport *vport) +{ + struct hclge_dev *hdev = vport->back; + bool is_full; + + mutex_lock(&hdev->umv_mutex); + is_full = (vport->used_umv_num >= hdev->priv_umv_size && + hdev->share_umv_size == 0); + mutex_unlock(&hdev->umv_mutex); + + return is_full; +} + +static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free) +{ + struct hclge_dev *hdev = vport->back; + + mutex_lock(&hdev->umv_mutex); + if (is_free) { + if (vport->used_umv_num > hdev->priv_umv_size) + hdev->share_umv_size++; + vport->used_umv_num--; + } else { + if (vport->used_umv_num >= hdev->priv_umv_size) + hdev->share_umv_size--; + vport->used_umv_num++; + } + mutex_unlock(&hdev->umv_mutex); +} + static int hclge_add_uc_addr(struct hnae3_handle *handle, const unsigned char *addr) { @@ -5314,8 +5203,19 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, * is not allowed in the mac vlan table. */ ret = hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false); - if (ret == -ENOENT) - return hclge_add_mac_vlan_tbl(vport, &req, NULL); + if (ret == -ENOENT) { + if (!hclge_is_umv_space_full(vport)) { + ret = hclge_add_mac_vlan_tbl(vport, &req, NULL); + if (!ret) + hclge_update_umv_space(vport, false); + return ret; + } + + dev_err(&hdev->pdev->dev, "UC MAC table full(%u)\n", + hdev->priv_umv_size); + + return -ENOSPC; + } /* check if we just hit the duplicate */ if (!ret) @@ -5358,6 +5258,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hclge_prepare_mac_addr(&req, addr); ret = hclge_remove_mac_vlan_tbl(vport, &req); + if (!ret) + hclge_update_umv_space(vport, true); return ret; } @@ -5376,7 +5278,6 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_mac_vlan_tbl_entry_cmd req; struct hclge_desc desc[3]; - u16 tbl_idx; int status; /* mac addr check */ @@ -5406,25 +5307,8 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, status = hclge_add_mac_vlan_tbl(vport, &req, desc); } - /* If mc mac vlan table is full, use MTA table */ - if (status == -ENOSPC) { - if (!vport->accept_mta_mc) { - status = hclge_cfg_func_mta_filter(hdev, - vport->vport_id, - true); - if (status) { - dev_err(&hdev->pdev->dev, - "set mta filter mode fail ret=%d\n", - status); - return status; - } - vport->accept_mta_mc = true; - } - - /* Set MTA table for this MAC address */ - tbl_idx = hclge_get_mac_addr_to_mta_index(vport, addr); - status = hclge_set_mta_table_item(vport, tbl_idx, true); - } + if (status == -ENOSPC) + dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); return status; } @@ -5639,7 +5523,7 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, } static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, - bool filter_en) + u8 fe_type, bool filter_en) { struct hclge_vlan_filter_ctrl_cmd *req; struct hclge_desc desc; @@ -5649,7 +5533,7 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; - req->vlan_fe = filter_en; + req->vlan_fe = filter_en ? fe_type : 0; ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) @@ -5661,13 +5545,30 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, #define HCLGE_FILTER_TYPE_VF 0 #define HCLGE_FILTER_TYPE_PORT 1 +#define HCLGE_FILTER_FE_EGRESS_V1_B BIT(0) +#define HCLGE_FILTER_FE_NIC_INGRESS_B BIT(0) +#define HCLGE_FILTER_FE_NIC_EGRESS_B BIT(1) +#define HCLGE_FILTER_FE_ROCE_INGRESS_B BIT(2) +#define HCLGE_FILTER_FE_ROCE_EGRESS_B BIT(3) +#define HCLGE_FILTER_FE_EGRESS (HCLGE_FILTER_FE_NIC_EGRESS_B \ + | HCLGE_FILTER_FE_ROCE_EGRESS_B) +#define HCLGE_FILTER_FE_INGRESS (HCLGE_FILTER_FE_NIC_INGRESS_B \ + | HCLGE_FILTER_FE_ROCE_INGRESS_B) static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, enable); + if (hdev->pdev->revision >= 0x21) { + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS, enable); + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, + HCLGE_FILTER_FE_INGRESS, enable); + } else { + hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS_V1_B, enable); + } } static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, @@ -5969,13 +5870,23 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) int ret; int i; - ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, true); - if (ret) - return ret; + if (hdev->pdev->revision >= 0x21) { + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS, true); + if (ret) + return ret; - ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, true); - if (ret) - return ret; + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, + HCLGE_FILTER_FE_INGRESS, true); + if (ret) + return ret; + } else { + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS_V1_B, + true); + if (ret) + return ret; + } hdev->vlan_type_cfg.rx_in_fst_vlan_type = HCLGE_DEF_VLAN_TYPE; hdev->vlan_type_cfg.rx_in_sec_vlan_type = HCLGE_DEF_VLAN_TYPE; @@ -6746,6 +6657,12 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) } } + ret = hclge_init_umv_space(hdev); + if (ret) { + dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret); + goto err_msi_irq_uninit; + } + ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); @@ -6866,6 +6783,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + hclge_reset_umv_space(hdev); + ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); @@ -6919,6 +6838,8 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) if (mac->phydev) mdiobus_unregister(mac->mdio_bus); + hclge_uninit_umv_space(hdev); + /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); synchronize_irq(hdev->misc_vector.vector_irq); @@ -7317,7 +7238,6 @@ static const struct hnae3_ae_ops hclge_ops = { .rm_uc_addr = hclge_rm_uc_addr, .add_mc_addr = hclge_add_mc_addr, .rm_mc_addr = hclge_rm_mc_addr, - .update_mta_status = hclge_update_mta_status, .set_autoneg = hclge_set_autoneg, .get_autoneg = hclge_get_autoneg, .get_pauseparam = hclge_get_pauseparam, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 06adbdd27b95..e3dfd654eca9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -14,6 +14,8 @@ #define HCLGE_MOD_VERSION "1.0" #define HCLGE_DRIVER_NAME "hclge" +#define HCLGE_MAX_PF_NUM 8 + #define HCLGE_INVALID_VPORT 0xffff #define HCLGE_PF_CFG_BLOCK_SIZE 32 @@ -53,7 +55,9 @@ #define HCLGE_RSS_TC_SIZE_6 64 #define HCLGE_RSS_TC_SIZE_7 128 -#define HCLGE_MTA_TBL_SIZE 4096 +#define HCLGE_UMV_TBL_SIZE 3072 +#define HCLGE_DEFAULT_UMV_SPACE_PER_PF \ + (HCLGE_UMV_TBL_SIZE / HCLGE_MAX_PF_NUM) #define HCLGE_TQP_RESET_TRY_TIMES 10 @@ -162,13 +166,6 @@ enum HCLGE_MAC_DUPLEX { HCLGE_MAC_FULL }; -enum hclge_mta_dmac_sel_type { - HCLGE_MAC_ADDR_47_36, - HCLGE_MAC_ADDR_46_35, - HCLGE_MAC_ADDR_45_34, - HCLGE_MAC_ADDR_44_33, -}; - struct hclge_mac { u8 phy_addr; u8 flag; @@ -251,6 +248,7 @@ struct hclge_cfg { u8 default_speed; u32 numa_node_map; u8 speed_ability; + u16 umv_space; }; struct hclge_tm_info { @@ -670,9 +668,6 @@ struct hclge_dev { u32 pkt_buf_size; /* Total pf buf size for tx/rx */ u32 mps; /* Max packet size */ - enum hclge_mta_dmac_sel_type mta_mac_sel_type; - bool enable_mta; /* Multicast filter enable */ - struct hclge_vlan_type_cfg vlan_type_cfg; unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)]; @@ -680,6 +675,15 @@ struct hclge_dev { struct hclge_fd_cfg fd_cfg; struct hlist_head fd_rule_list; u16 hclge_fd_rule_num; + + u16 wanted_umv_size; + /* max available unicast mac vlan space */ + u16 max_umv_size; + /* private unicast mac vlan space, it's same for PF and its VFs */ + u16 priv_umv_size; + /* unicast mac vlan space shared by PF and its VFs */ + u16 share_umv_size; + struct mutex umv_mutex; /* protect share_umv_size */ }; /* VPort level vlan tag configuration for TX direction */ @@ -732,13 +736,12 @@ struct hclge_vport { struct hclge_tx_vtag_cfg txvlan_cfg; struct hclge_rx_vtag_cfg rxvlan_cfg; + u16 used_umv_num; + int vport_id; struct hclge_dev *back; /* Back reference to associated dev */ struct hnae3_handle nic; struct hnae3_handle roce; - - bool accept_mta_mc; /* whether to accept mta filter multicast */ - unsigned long mta_shadow[BITS_TO_LONGS(HCLGE_MTA_TBL_SIZE)]; }; void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, @@ -753,15 +756,6 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, int hclge_rm_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr); -int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, - u8 func_id, - bool enable); -int hclge_update_mta_status_common(struct hclge_vport *vport, - unsigned long *status, - u16 idx, - u16 count, - bool update_filter); - struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle); int hclge_bind_ring_with_vector(struct hclge_vport *vport, int vector_id, bool en, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index f34851c91eb3..04462a347a94 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -233,43 +233,6 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, return 0; } -static int hclge_set_vf_mc_mta_status(struct hclge_vport *vport, - u8 *msg, u8 idx, bool is_end) -{ -#define HCLGE_MTA_STATUS_MSG_SIZE 13 -#define HCLGE_MTA_STATUS_MSG_BITS \ - (HCLGE_MTA_STATUS_MSG_SIZE * BITS_PER_BYTE) -#define HCLGE_MTA_STATUS_MSG_END_BITS \ - (HCLGE_MTA_TBL_SIZE % HCLGE_MTA_STATUS_MSG_BITS) - unsigned long status[BITS_TO_LONGS(HCLGE_MTA_STATUS_MSG_BITS)]; - u16 tbl_cnt; - u16 tbl_idx; - u8 msg_ofs; - u8 msg_bit; - - tbl_cnt = is_end ? HCLGE_MTA_STATUS_MSG_END_BITS : - HCLGE_MTA_STATUS_MSG_BITS; - - /* set msg field */ - msg_ofs = 0; - msg_bit = 0; - memset(status, 0, sizeof(status)); - for (tbl_idx = 0; tbl_idx < tbl_cnt; tbl_idx++) { - if (msg[msg_ofs] & BIT(msg_bit)) - set_bit(tbl_idx, status); - - msg_bit++; - if (msg_bit == BITS_PER_BYTE) { - msg_bit = 0; - msg_ofs++; - } - } - - return hclge_update_mta_status_common(vport, - status, idx * HCLGE_MTA_STATUS_MSG_BITS, - tbl_cnt, is_end); -} - static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req, bool gen_resp) @@ -284,27 +247,6 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, status = hclge_add_mc_addr_common(vport, mac_addr); } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_REMOVE) { status = hclge_rm_mc_addr_common(vport, mac_addr); - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_FUNC_MTA_ENABLE) { - u8 func_id = vport->vport_id; - bool enable = mbx_req->msg[2]; - - status = hclge_cfg_func_mta_filter(hdev, func_id, enable); - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ) { - resp_data = hdev->mta_mac_sel_type; - resp_len = sizeof(u8); - gen_resp = true; - status = 0; - } else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE) { - /* mta status update msg format - * msg[2.6 : 2.0] msg index - * msg[2.7] msg is end - * msg[15 : 3] mta status bits[103 : 0] - */ - bool is_end = (mbx_req->msg[2] & 0x80) ? true : false; - - status = hclge_set_vf_mc_mta_status(vport, &mbx_req->msg[3], - mbx_req->msg[2] & 0x7F, - is_end); } else { dev_err(&hdev->pdev->dev, "failed to set mcast mac addr, unknown subcode %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 8f858cb2a67b..ca4a9f790917 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -746,126 +746,6 @@ static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle) } } -static int hclgevf_cfg_func_mta_type(struct hclgevf_dev *hdev) -{ - u8 resp_msg = HCLGEVF_MTA_TYPE_SEL_MAX; - int ret; - - ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MTA_TYPE_READ, - NULL, 0, true, &resp_msg, sizeof(u8)); - - if (ret) { - dev_err(&hdev->pdev->dev, - "Read mta type fail, ret=%d.\n", ret); - return ret; - } - - if (resp_msg > HCLGEVF_MTA_TYPE_SEL_MAX) { - dev_err(&hdev->pdev->dev, - "Read mta type invalid, resp=%d.\n", resp_msg); - return -EINVAL; - } - - hdev->mta_mac_sel_type = resp_msg; - - return 0; -} - -static u16 hclgevf_get_mac_addr_to_mta_index(struct hclgevf_dev *hdev, - const u8 *addr) -{ - u32 rsh = HCLGEVF_MTA_TYPE_SEL_MAX - hdev->mta_mac_sel_type; - u16 high_val = addr[1] | (addr[0] << 8); - - return (high_val >> rsh) & 0xfff; -} - -static int hclgevf_do_update_mta_status(struct hclgevf_dev *hdev, - unsigned long *status) -{ -#define HCLGEVF_MTA_STATUS_MSG_SIZE 13 -#define HCLGEVF_MTA_STATUS_MSG_BITS \ - (HCLGEVF_MTA_STATUS_MSG_SIZE * BITS_PER_BYTE) -#define HCLGEVF_MTA_STATUS_MSG_END_BITS \ - (HCLGEVF_MTA_TBL_SIZE % HCLGEVF_MTA_STATUS_MSG_BITS) - u16 tbl_cnt; - u16 tbl_idx; - u8 msg_cnt; - u8 msg_idx; - int ret; - - msg_cnt = DIV_ROUND_UP(HCLGEVF_MTA_TBL_SIZE, - HCLGEVF_MTA_STATUS_MSG_BITS); - tbl_idx = 0; - msg_idx = 0; - while (msg_cnt--) { - u8 msg[HCLGEVF_MTA_STATUS_MSG_SIZE + 1]; - u8 *p = &msg[1]; - u8 msg_ofs; - u8 msg_bit; - - memset(msg, 0, sizeof(msg)); - - /* set index field */ - msg[0] = 0x7F & msg_idx; - - /* set end flag field */ - if (msg_cnt == 0) { - msg[0] |= 0x80; - tbl_cnt = HCLGEVF_MTA_STATUS_MSG_END_BITS; - } else { - tbl_cnt = HCLGEVF_MTA_STATUS_MSG_BITS; - } - - /* set status field */ - msg_ofs = 0; - msg_bit = 0; - while (tbl_cnt--) { - if (test_bit(tbl_idx, status)) - p[msg_ofs] |= BIT(msg_bit); - - tbl_idx++; - - msg_bit++; - if (msg_bit == BITS_PER_BYTE) { - msg_bit = 0; - msg_ofs++; - } - } - - ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MULTICAST, - HCLGE_MBX_MAC_VLAN_MTA_STATUS_UPDATE, - msg, sizeof(msg), false, NULL, 0); - if (ret) - break; - - msg_idx++; - } - - return ret; -} - -static int hclgevf_update_mta_status(struct hnae3_handle *handle) -{ - unsigned long mta_status[BITS_TO_LONGS(HCLGEVF_MTA_TBL_SIZE)]; - struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - struct net_device *netdev = hdev->nic.kinfo.netdev; - struct netdev_hw_addr *ha; - u16 tbl_idx; - - /* clear status */ - memset(mta_status, 0, sizeof(mta_status)); - - /* update status from mc addr list */ - netdev_for_each_mc_addr(ha, netdev) { - tbl_idx = hclgevf_get_mac_addr_to_mta_index(hdev, ha->addr); - set_bit(tbl_idx, mta_status); - } - - return hclgevf_do_update_mta_status(hdev, mta_status); -} - static void hclgevf_get_mac_addr(struct hnae3_handle *handle, u8 *p) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); @@ -1871,14 +1751,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) goto err_config; } - /* Initialize mta type for this VF */ - ret = hclgevf_cfg_func_mta_type(hdev); - if (ret) { - dev_err(&hdev->pdev->dev, - "failed(%d) to initialize MTA type\n", ret); - goto err_config; - } - /* Initialize RSS for this VF */ ret = hclgevf_rss_init_hw(hdev); if (ret) { @@ -2038,7 +1910,6 @@ static const struct hnae3_ae_ops hclgevf_ops = { .rm_uc_addr = hclgevf_rm_uc_addr, .add_mc_addr = hclgevf_add_mc_addr, .rm_mc_addr = hclgevf_rm_mc_addr, - .update_mta_status = hclgevf_update_mta_status, .get_stats = hclgevf_get_stats, .update_stats = hclgevf_update_stats, .get_strings = hclgevf_get_strings, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 2af01f107c63..cf5fbf793c5e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -47,9 +47,6 @@ #define HCLGEVF_RSS_CFG_TBL_NUM \ (HCLGEVF_RSS_IND_TBL_SIZE / HCLGEVF_RSS_CFG_TBL_SIZE) -#define HCLGEVF_MTA_TBL_SIZE 4096 -#define HCLGEVF_MTA_TYPE_SEL_MAX 4 - /* states of hclgevf device & tasks */ enum hclgevf_states { /* device states */ @@ -157,8 +154,6 @@ struct hclgevf_dev { u16 *vector_status; int *vector_irq; - bool accept_mta_mc; /* whether to accept mta filter multicast */ - u8 mta_mac_sel_type; bool mbx_event_pending; struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */ struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 09e9da10b786..4a8f82938ed5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -789,23 +789,6 @@ static void hinic_get_stats64(struct net_device *netdev, stats->tx_errors = nic_tx_stats->tx_dropped; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void hinic_netpoll(struct net_device *netdev) -{ - struct hinic_dev *nic_dev = netdev_priv(netdev); - int i, num_qps; - - num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); - for (i = 0; i < num_qps; i++) { - struct hinic_txq *txq = &nic_dev->txqs[i]; - struct hinic_rxq *rxq = &nic_dev->rxqs[i]; - - napi_schedule(&txq->napi); - napi_schedule(&rxq->napi); - } -} -#endif - static const struct net_device_ops hinic_netdev_ops = { .ndo_open = hinic_open, .ndo_stop = hinic_close, @@ -818,9 +801,6 @@ static const struct net_device_ops hinic_netdev_ops = { .ndo_start_xmit = hinic_xmit_frame, .ndo_tx_timeout = hinic_tx_timeout, .ndo_get_stats64 = hinic_get_stats64, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = hinic_netpoll, -#endif }; static void netdev_features_init(struct net_device *netdev) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index aa0b89777e74..3baabdc89726 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -920,17 +920,6 @@ static int ehea_poll(struct napi_struct *napi, int budget) return rx; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ehea_netpoll(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - int i; - - for (i = 0; i < port->num_def_qps; i++) - napi_schedule(&port->port_res[i].napi); -} -#endif - static irqreturn_t ehea_recv_irq_handler(int irq, void *param) { struct ehea_port_res *pr = param; @@ -2952,9 +2941,6 @@ static const struct net_device_ops ehea_netdev_ops = { .ndo_open = ehea_open, .ndo_stop = ehea_stop, .ndo_start_xmit = ehea_start_xmit, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ehea_netpoll, -#endif .ndo_get_stats64 = ehea_get_stats64, .ndo_set_mac_address = ehea_set_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index ad898e8eaca1..7893beffcc71 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2207,19 +2207,6 @@ restart_poll: return frames_processed; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void ibmvnic_netpoll_controller(struct net_device *dev) -{ - struct ibmvnic_adapter *adapter = netdev_priv(dev); - int i; - - replenish_pools(netdev_priv(dev)); - for (i = 0; i < adapter->req_rx_queues; i++) - ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq, - adapter->rx_scrq[i]); -} -#endif - static int wait_for_reset(struct ibmvnic_adapter *adapter) { int rc, ret; @@ -2292,9 +2279,6 @@ static const struct net_device_ops ibmvnic_netdev_ops = { .ndo_set_mac_address = ibmvnic_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = ibmvnic_tx_timeout, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ibmvnic_netpoll_controller, -#endif .ndo_change_mtu = ibmvnic_change_mtu, .ndo_features_check = ibmvnic_features_check, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 56b911a5dd8b..a20d1cf058ad 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -132,8 +132,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlan_features = 0x%08lx\n", (unsigned long int)nd->vlan_features); } - dev_info(&pf->pdev->dev, " active_vlans is %s\n", - vsi->active_vlans ? "<valid>" : "<null>"); dev_info(&pf->pdev->dev, " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index f4bb2779f03a..81b0e1f8d14b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4256,7 +4256,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) vf->link_forced = true; vf->link_up = true; pfe.event_data.link_event.link_status = true; - pfe.event_data.link_event.link_speed = I40E_LINK_SPEED_40GB; + pfe.event_data.link_event.link_speed = VIRTCHNL_LINK_SPEED_40GB; break; case IFLA_VF_LINK_STATE_DISABLE: vf->link_forced = true; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a512f7521841..272d76b733aa 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -342,7 +342,7 @@ struct iavf_adapter { struct iavf_channel_config ch_config; u8 num_tc; struct list_head cloud_filter_list; - /* lock to protest access to the cloud filter list */ + /* lock to protect access to the cloud filter list */ spinlock_t cloud_filter_list_lock; u16 num_cloud_filters; }; diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 45125bd074d9..e5d6f684437e 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -16,3 +16,4 @@ ice-y := ice_main.o \ ice_lib.o \ ice_txrx.o \ ice_ethtool.o +ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 0b269c470343..4c4b5717a627 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -28,6 +28,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_bridge.h> +#include <linux/avf/virtchnl.h> #include <net/ipv6.h> #include "ice_devids.h" #include "ice_type.h" @@ -35,6 +36,8 @@ #include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_virtchnl_pf.h" +#include "ice_sriov.h" extern const char ice_drv_ver[]; #define ICE_BAR0 0 @@ -46,6 +49,7 @@ extern const char ice_drv_ver[]; #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) #define ICE_ETHTOOL_FWVER_LEN 32 #define ICE_AQ_LEN 64 +#define ICE_MBXQ_LEN 64 #define ICE_MIN_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_MAX_VSI_ALLOC 130 @@ -63,6 +67,14 @@ extern const char ice_drv_ver[]; #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 +#define ICE_MAX_VF_COUNT 256 +#define ICE_MAX_QS_PER_VF 256 +#define ICE_MIN_QS_PER_VF 1 +#define ICE_DFLT_QS_PER_VF 4 +#define ICE_MAX_BASE_QS_PER_VF 16 +#define ICE_MAX_INTR_PER_VF 65 +#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) +#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -133,9 +145,21 @@ enum ice_state { __ICE_EMPR_RECV, /* set by OICR handler */ __ICE_SUSPENDED, /* set on module remove path */ __ICE_RESET_FAILED, /* set by reset/rebuild */ + /* When checking for the PF to be in a nominal operating state, the + * bits that are grouped at the beginning of the list need to be + * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will + * be checked. If you need to add a bit into consideration for nominal + * operating state, it must be added before + * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position + * without appropriate consideration. + */ + __ICE_STATE_NOMINAL_CHECK_BITS, __ICE_ADMINQ_EVENT_PENDING, + __ICE_MAILBOXQ_EVENT_PENDING, __ICE_MDD_EVENT_PENDING, + __ICE_VFLR_EVENT_PENDING, __ICE_FLTR_OVERFLOW_PROMISC, + __ICE_VF_DIS, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, __ICE_SERVICE_DIS, @@ -181,6 +205,8 @@ struct ice_vsi { /* Interrupt thresholds */ u16 work_lmt; + s16 vf_id; /* VF ID for SR-IOV VSIs */ + /* RSS config */ u16 rss_table_size; /* HW RSS table size */ u16 rss_size; /* Allocated RSS queues */ @@ -240,6 +266,8 @@ enum ice_pf_flags { ICE_FLAG_MSIX_ENA, ICE_FLAG_FLTR_SYNC, ICE_FLAG_RSS_ENA, + ICE_FLAG_SRIOV_ENA, + ICE_FLAG_SRIOV_CAPABLE, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -255,6 +283,12 @@ struct ice_pf { struct ice_vsi **vsi; /* VSIs created by the driver */ struct ice_sw *first_sw; /* first switch created by firmware */ + /* Virtchnl/SR-IOV config info */ + struct ice_vf *vf; + int num_alloc_vfs; /* actual number of VFs allocated */ + u16 num_vfs_supported; /* num VFs supported for this PF */ + u16 num_vf_qps; /* num queue pairs per VF */ + u16 num_vf_msix; /* num vectors per VF */ DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS); DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index c100b4bda195..6653555f55dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -87,6 +87,8 @@ struct ice_aqc_list_caps { /* Device/Function buffer entry, repeated per reported capability */ struct ice_aqc_list_caps_elem { __le16 cap; +#define ICE_AQC_CAPS_SRIOV 0x0012 +#define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 #define ICE_AQC_CAPS_RSS 0x0040 #define ICE_AQC_CAPS_RXQS 0x0041 @@ -1075,6 +1077,19 @@ struct ice_aqc_nvm { __le32 addr_low; }; +/** + * Send to PF command (indirect 0x0801) id is only used by PF + * + * Send to VF command (indirect 0x0802) id is only used by PF + * + */ +struct ice_aqc_pf_vf_msg { + __le32 id; + u32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + /* Get/Set RSS key (indirect 0x0B04/0x0B02) */ struct ice_aqc_get_set_rss_key { #define ICE_AQC_GSET_RSS_KEY_VSI_VALID BIT(15) @@ -1332,6 +1347,7 @@ struct ice_aq_desc { struct ice_aqc_query_txsched_res query_sched_res; struct ice_aqc_add_move_delete_elem add_move_delete_elem; struct ice_aqc_nvm nvm; + struct ice_aqc_pf_vf_msg virt; struct ice_aqc_get_set_rss_lut get_set_rss_lut; struct ice_aqc_get_set_rss_key get_set_rss_key; struct ice_aqc_add_txqs add_txqs; @@ -1429,6 +1445,10 @@ enum ice_adminq_opc { /* NVM commands */ ice_aqc_opc_nvm_read = 0x0701, + /* PF/VF mailbox commands */ + ice_mbx_opc_send_msg_to_pf = 0x0801, + ice_mbx_opc_send_msg_to_vf = 0x0802, + /* RSS commands */ ice_aqc_opc_set_rss_key = 0x0B02, ice_aqc_opc_set_rss_lut = 0x0B03, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 68fbbb92d504..c52f450f2c0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1406,6 +1406,28 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, u16 cap = le16_to_cpu(cap_resp->cap); switch (cap) { + case ICE_AQC_CAPS_SRIOV: + caps->sr_iov_1_1 = (number == 1); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: SR-IOV = %d\n", caps->sr_iov_1_1); + break; + case ICE_AQC_CAPS_VF: + if (dev_p) { + dev_p->num_vfs_exposed = number; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs exposed = %d\n", + dev_p->num_vfs_exposed); + } else if (func_p) { + func_p->num_allocd_vfs = number; + func_p->vf_base_id = logical_id; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VFs allocated = %d\n", + func_p->num_allocd_vfs); + ice_debug(hw, ICE_DBG_INIT, + "HW caps: VF base_id = %d\n", + func_p->vf_base_id); + } + break; case ICE_AQC_CAPS_VSI: if (dev_p) { dev_p->num_vsi_allocd_to_host = number; @@ -2265,6 +2287,8 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, * @num_qgrps: number of groups in the list * @qg_list: the list of groups to disable * @buf_size: the total size of the qg_list buffer in bytes + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * Disable LAN Tx queue (0x0C31) @@ -2272,6 +2296,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, static enum ice_status ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *qg_list, u16 buf_size, + enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { struct ice_aqc_dis_txqs *cmd; @@ -2281,14 +2306,45 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, cmd = &desc.params.dis_txqs; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs); - if (!qg_list) + /* qg_list can be NULL only in VM/VF reset flow */ + if (!qg_list && !rst_src) return ICE_ERR_PARAM; if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS) return ICE_ERR_PARAM; - desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + cmd->num_entries = num_qgrps; + cmd->vmvf_and_timeout = cpu_to_le16((5 << ICE_AQC_Q_DIS_TIMEOUT_S) & + ICE_AQC_Q_DIS_TIMEOUT_M); + + switch (rst_src) { + case ICE_VM_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VM_RESET; + cmd->vmvf_and_timeout |= + cpu_to_le16(vmvf_num & ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_VF_RESET: + cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET; + /* In this case, FW expects vmvf_num to be absolute VF id */ + cmd->vmvf_and_timeout |= + cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) & + ICE_AQC_Q_DIS_VMVF_NUM_M); + break; + case ICE_NO_RESET: + default: + break; + } + + /* If no queue group info, we are in a reset flow. Issue the AQ */ + if (!qg_list) + goto do_aq; + + /* set RD bit to indicate that command buffer is provided by the driver + * and it needs to be read by the firmware + */ + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + for (i = 0; i < num_qgrps; ++i) { /* Calculate the size taken up by the queue IDs in this group */ sz += qg_list[i].num_qs * sizeof(qg_list[i].q_id); @@ -2304,6 +2360,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, if (buf_size != sz) return ICE_ERR_PARAM; +do_aq: return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd); } @@ -2610,13 +2667,16 @@ ena_txq_exit: * @num_queues: number of queues * @q_ids: pointer to the q_id array * @q_teids: pointer to queue node teids + * @rst_src: if called due to reset, specifies the RST source + * @vmvf_num: the relative VM or VF number that is undergoing the reset * @cd: pointer to command details structure or NULL * * This function removes queues and their corresponding nodes in SW DB */ enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cd) + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cd) { enum ice_status status = ICE_ERR_DOES_NOT_EXIST; struct ice_aqc_dis_txq_item qg_list; @@ -2625,6 +2685,15 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return ICE_ERR_CFG; + /* if queue is disabled already yet the disable queue command has to be + * sent to complete the VF reset, then call ice_aq_dis_lan_txq without + * any queue information + */ + + if (!num_queues && rst_src) + return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src, vmvf_num, + NULL); + mutex_lock(&pi->sched_lock); for (i = 0; i < num_queues; i++) { @@ -2637,7 +2706,8 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, qg_list.num_qs = 1; qg_list.q_id[0] = cpu_to_le16(q_ids[i]); status = ice_aq_dis_lan_txq(pi->hw, 1, &qg_list, - sizeof(qg_list), cd); + sizeof(qg_list), rst_src, vmvf_num, + cd); if (status) break; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 7b2a5bb2e550..1900681289a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -7,6 +7,7 @@ #include "ice.h" #include "ice_type.h" #include "ice_switch.h" +#include <linux/avf/virtchnl.h> void ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf, u16 buf_len); @@ -89,7 +90,8 @@ ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, struct ice_sq_cd *cd); enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, - u32 *q_teids, struct ice_sq_cd *cmd_details); + u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, + struct ice_sq_cd *cmd_details); enum ice_status ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index b25ce4f587f5..84c967294eaf 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -33,6 +33,36 @@ static void ice_adminq_init_regs(struct ice_hw *hw) } /** + * ice_mailbox_init_regs - Initialize Mailbox registers + * @hw: pointer to the hardware structure + * + * This assumes the alloc_sq and alloc_rq functions have already been called + */ +static void ice_mailbox_init_regs(struct ice_hw *hw) +{ + struct ice_ctl_q_info *cq = &hw->mailboxq; + + /* set head and tail registers in our local struct */ + cq->sq.head = PF_MBX_ATQH; + cq->sq.tail = PF_MBX_ATQT; + cq->sq.len = PF_MBX_ATQLEN; + cq->sq.bah = PF_MBX_ATQBAH; + cq->sq.bal = PF_MBX_ATQBAL; + cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M; + cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M; + cq->sq.head_mask = PF_MBX_ATQH_ATQH_M; + + cq->rq.head = PF_MBX_ARQH; + cq->rq.tail = PF_MBX_ARQT; + cq->rq.len = PF_MBX_ARQLEN; + cq->rq.bah = PF_MBX_ARQBAH; + cq->rq.bal = PF_MBX_ARQBAL; + cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M; + cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M; + cq->rq.head_mask = PF_MBX_ARQH_ARQH_M; +} + +/** * ice_check_sq_alive * @hw: pointer to the hw struct * @cq: pointer to the specific Control queue @@ -639,6 +669,10 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) ice_adminq_init_regs(hw); cq = &hw->adminq; break; + case ICE_CTL_Q_MAILBOX: + ice_mailbox_init_regs(hw); + cq = &hw->mailboxq; + break; default: return ICE_ERR_PARAM; } @@ -696,7 +730,12 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) if (ret_code) return ret_code; - return ice_init_check_adminq(hw); + ret_code = ice_init_check_adminq(hw); + if (ret_code) + return ret_code; + + /* Init Mailbox queue */ + return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** @@ -714,6 +753,9 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) if (ice_check_sq_alive(hw, cq)) ice_aq_q_shutdown(hw, true); break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + break; default: return; } @@ -736,6 +778,8 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { /* Shutdown FW admin queue */ ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + /* Shutdown PF-VF Mailbox */ + ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index ea02b89243e2..437f832fd7c4 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -8,6 +8,7 @@ /* Maximum buffer lengths for all control queue types */ #define ICE_AQ_MAX_BUF_LEN 4096 +#define ICE_MBXQ_MAX_BUF_LEN 4096 #define ICE_CTL_Q_DESC(R, i) \ (&(((struct ice_aq_desc *)((R).desc_buf.va))[i])) @@ -28,6 +29,7 @@ enum ice_ctl_q { ICE_CTL_Q_UNKNOWN = 0, ICE_CTL_Q_ADMIN, + ICE_CTL_Q_MAILBOX, }; /* Control Queue default settings */ diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 9a78d83eaa3e..a6679a9bfd3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -29,6 +29,22 @@ #define PF_FW_ATQLEN_ATQCRIT_M BIT(30) #define PF_FW_ATQLEN_ATQENABLE_M BIT(31) #define PF_FW_ATQT 0x00080400 +#define PF_MBX_ARQBAH 0x0022E400 +#define PF_MBX_ARQBAL 0x0022E380 +#define PF_MBX_ARQH 0x0022E500 +#define PF_MBX_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN 0x0022E480 +#define PF_MBX_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ARQLEN_ARQENABLE_M BIT(31) +#define PF_MBX_ARQT 0x0022E580 +#define PF_MBX_ATQBAH 0x0022E180 +#define PF_MBX_ATQBAL 0x0022E100 +#define PF_MBX_ATQH 0x0022E280 +#define PF_MBX_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN 0x0022E200 +#define PF_MBX_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_MBX_ATQLEN_ATQENABLE_M BIT(31) +#define PF_MBX_ATQT 0x0022E300 #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, 0) @@ -74,10 +90,16 @@ #define GLGEN_RTRIG_CORER_M BIT(0) #define GLGEN_RTRIG_GLOBR_M BIT(1) #define GLGEN_STAT 0x000B612C +#define GLGEN_VFLRSTAT(_i) (0x00093A04 + ((_i) * 4)) #define PFGEN_CTRL 0x00091000 #define PFGEN_CTRL_PFSWR_M BIT(0) #define PFGEN_STATE 0x00088000 #define PRTGEN_STATUS 0x000B8100 +#define VFGEN_RSTAT(_VF) (0x00074000 + ((_VF) * 4)) +#define VPGEN_VFRSTAT(_VF) (0x00090800 + ((_VF) * 4)) +#define VPGEN_VFRSTAT_VFRD_M BIT(0) +#define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4)) +#define VPGEN_VFRTRIG_VFSWR_M BIT(0) #define PFHMC_ERRORDATA 0x00520500 #define PFHMC_ERRORINFO 0x00520400 #define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) @@ -90,11 +112,23 @@ #define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) #define GLINT_RATE(_INT) (0x0015A000 + ((_INT) * 4)) #define GLINT_RATE_INTRL_ENA_M BIT(6) +#define GLINT_VECT2FUNC(_INT) (0x00162000 + ((_INT) * 4)) +#define GLINT_VECT2FUNC_VF_NUM_S 0 +#define GLINT_VECT2FUNC_VF_NUM_M ICE_M(0xFF, 0) +#define GLINT_VECT2FUNC_PF_NUM_S 12 +#define GLINT_VECT2FUNC_PF_NUM_M ICE_M(0x7, 12) +#define GLINT_VECT2FUNC_IS_PF_S 16 +#define GLINT_VECT2FUNC_IS_PF_M BIT(16) #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_MBX_CTL 0x0016B280 +#define PFINT_MBX_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_MBX_CTL_ITR_INDX_S 11 +#define PFINT_MBX_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_MBX_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) @@ -102,6 +136,7 @@ #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_VFLR_M BIT(29) #define PFINT_OICR_CTL 0x0016CA80 #define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) #define PFINT_OICR_CTL_ITR_INDX_S 11 @@ -116,6 +151,12 @@ #define QINT_TQCTL_MSIX_INDX_S 0 #define QINT_TQCTL_ITR_INDX_S 11 #define QINT_TQCTL_CAUSE_ENA_M BIT(30) +#define VPINT_ALLOC(_VF) (0x001D1000 + ((_VF) * 4)) +#define VPINT_ALLOC_FIRST_S 0 +#define VPINT_ALLOC_FIRST_M ICE_M(0x7FF, 0) +#define VPINT_ALLOC_LAST_S 12 +#define VPINT_ALLOC_LAST_M ICE_M(0x7FF, 12) +#define VPINT_ALLOC_VALID_M BIT(31) #define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) #define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) #define QRX_CTRL_MAX_INDEX 2047 @@ -128,6 +169,20 @@ #define QRX_TAIL_MAX_INDEX 2047 #define QRX_TAIL_TAIL_S 0 #define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0) +#define VPLAN_RX_QBASE(_VF) (0x00072000 + ((_VF) * 4)) +#define VPLAN_RX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_RX_QBASE_VFFIRSTQ_M ICE_M(0x7FF, 0) +#define VPLAN_RX_QBASE_VFNUMQ_S 16 +#define VPLAN_RX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_RXQ_MAPENA(_VF) (0x00073000 + ((_VF) * 4)) +#define VPLAN_RXQ_MAPENA_RX_ENA_M BIT(0) +#define VPLAN_TX_QBASE(_VF) (0x001D1800 + ((_VF) * 4)) +#define VPLAN_TX_QBASE_VFFIRSTQ_S 0 +#define VPLAN_TX_QBASE_VFFIRSTQ_M ICE_M(0x3FFF, 0) +#define VPLAN_TX_QBASE_VFNUMQ_S 16 +#define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) +#define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4)) +#define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0) #define GL_MDET_RX 0x00294C00 #define GL_MDET_RX_QNUM_S 0 #define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) @@ -164,6 +219,14 @@ #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 VP_MDET_RX(_VF) (0x00294400 + ((_VF) * 4)) +#define VP_MDET_RX_VALID_M BIT(0) +#define VP_MDET_TX_PQM(_VF) (0x002D2000 + ((_VF) * 4)) +#define VP_MDET_TX_PQM_VALID_M BIT(0) +#define VP_MDET_TX_TCLAN(_VF) (0x000FB800 + ((_VF) * 4)) +#define VP_MDET_TX_TCLAN_VALID_M BIT(0) +#define VP_MDET_TX_TDPU(_VF) (0x00040000 + ((_VF) * 4)) +#define VP_MDET_TX_TDPU_VALID_M BIT(0) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 @@ -175,6 +238,9 @@ #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 PF_PCI_CIAA 0x0009E580 +#define PF_PCI_CIAA_VF_NUM_S 12 +#define PF_PCI_CIAD 0x0009E500 #define GL_PWR_MODE_CTL 0x000B820C #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) @@ -255,5 +321,8 @@ #define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define VSIQF_HKEY_MAX_INDEX 12 +#define VSIQF_HLUT_MAX_INDEX 15 +#define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) +#define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) #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 94504023d86e..7d2a66739e3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -418,6 +418,7 @@ struct ice_tlan_ctx { u8 pf_num; u16 vmvf_num; u8 vmvf_type; +#define ICE_TLAN_CTX_VMVF_TYPE_VF 0 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ 1 #define ICE_TLAN_CTX_VMVF_TYPE_PF 2 u16 src_vsi; @@ -473,4 +474,16 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) { return ice_ptype_lkup[ptype]; } + +#define ICE_LINK_SPEED_UNKNOWN 0 +#define ICE_LINK_SPEED_10MBPS 10 +#define ICE_LINK_SPEED_100MBPS 100 +#define ICE_LINK_SPEED_1000MBPS 1000 +#define ICE_LINK_SPEED_2500MBPS 2500 +#define ICE_LINK_SPEED_5000MBPS 5000 +#define ICE_LINK_SPEED_10000MBPS 10000 +#define ICE_LINK_SPEED_20000MBPS 20000 +#define ICE_LINK_SPEED_25000MBPS 25000 +#define ICE_LINK_SPEED_40000MBPS 40000 + #endif /* _ICE_LAN_TX_RX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index acf3478a3f3b..49f1940772ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -68,18 +68,20 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) /* Enable Flexible Descriptors in the queue context which * allows this driver to select a specific receive descriptor format */ - regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); - regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & - QRXFLXP_CNTXT_RXDID_IDX_M; - - /* increasing context priority to pick up profile id; - * default is 0x01; setting to 0x03 to ensure profile - * is programming if prev context is of same priority - */ - regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & - QRXFLXP_CNTXT_RXDID_PRIO_M; + if (vsi->type != ICE_VSI_VF) { + regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); + regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & + QRXFLXP_CNTXT_RXDID_IDX_M; + + /* increasing context priority to pick up profile id; + * default is 0x01; setting to 0x03 to ensure profile + * is programming if prev context is of same priority + */ + regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & + QRXFLXP_CNTXT_RXDID_PRIO_M; - wr32(hw, QRXFLXP_CNTXT(pf_q), regval); + wr32(hw, QRXFLXP_CNTXT(pf_q), regval); + } /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); @@ -90,6 +92,9 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) return -EIO; } + if (vsi->type == ICE_VSI_VF) + return 0; + /* init queue specific tail register */ ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); @@ -132,6 +137,11 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) case ICE_VSI_PF: tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; break; + case ICE_VSI_VF: + /* Firmware expects vmvf_num to be absolute VF id */ + tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id; + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; + break; default: return; } @@ -285,6 +295,16 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE); vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); break; + case ICE_VSI_VF: + vsi->alloc_txq = pf->num_vf_qps; + vsi->alloc_rxq = pf->num_vf_qps; + /* pf->num_vf_msix includes (VF miscellaneous vector + + * data queue interrupts). Since vsi->num_q_vectors is number + * of queues vectors, subtract 1 from the original vector + * count + */ + vsi->num_q_vectors = pf->num_vf_msix - 1; + break; default: dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", vsi->type); @@ -331,6 +351,8 @@ void ice_vsi_delete(struct ice_vsi *vsi) struct ice_vsi_ctx ctxt; enum ice_status status; + if (vsi->type == ICE_VSI_VF) + ctxt.vf_num = vsi->vf_id; ctxt.vsi_num = vsi->vsi_num; memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); @@ -466,6 +488,10 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type) /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; break; + case ICE_VSI_VF: + if (ice_vsi_alloc_arrays(vsi, true)) + goto err_rings; + break; default: dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); goto unlock_pf; @@ -685,6 +711,15 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) BIT(cap->rss_table_entry_width)); vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table + * For VSI_LUT, LUT size should be set to 64 bytes + */ + vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_size = min_t(int, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + break; default: dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type); @@ -773,17 +808,17 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * Setup number and offset of Rx queues for all TCs for the VSI */ + qcount = numq_tc; /* qcount will change if RSS is enabled */ if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { - if (vsi->type == ICE_VSI_PF) - max_rss = ICE_MAX_LG_RSS_QS; - else - max_rss = ICE_MAX_SMALL_RSS_QS; - - qcount = min_t(int, numq_tc, max_rss); - qcount = min_t(int, qcount, vsi->rss_size); - } else { - qcount = numq_tc; + if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) { + if (vsi->type == ICE_VSI_PF) + max_rss = ICE_MAX_LG_RSS_QS; + else + max_rss = ICE_MAX_SMALL_RSS_QS; + qcount = min_t(int, numq_tc, max_rss); + qcount = min_t(int, qcount, vsi->rss_size); + } } /* find the (rounded up) power-of-2 of qcount */ @@ -813,6 +848,14 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->num_txq = qcount_tx; vsi->num_rxq = offset; + if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { + dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); + /* since there is a chance that num_rxq could have been changed + * in the above for loop, make num_txq equal to num_rxq. + */ + vsi->num_txq = vsi->num_rxq; + } + /* Rx queue mapping */ ctxt->info.mapping_flags |= cpu_to_le16(ICE_AQ_VSI_Q_MAP_CONTIG); /* q_mapping buffer holds the info for the first queue allocated for @@ -838,6 +881,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF; hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; break; + case ICE_VSI_VF: + /* VF VSI will gets a small RSS table which is a VSI LUT type */ + lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; + hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ; + break; default: dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", vsi->type); @@ -868,6 +916,11 @@ static int ice_vsi_init(struct ice_vsi *vsi) case ICE_VSI_PF: ctxt.flags = ICE_AQ_VSI_TYPE_PF; break; + case ICE_VSI_VF: + ctxt.flags = ICE_AQ_VSI_TYPE_VF; + /* VF number here is the absolute VF number (0-255) */ + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id; + break; default: return -ENODEV; } @@ -961,6 +1014,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) q_vector->vsi = vsi; q_vector->v_idx = v_idx; + if (vsi->type == ICE_VSI_VF) + goto out; /* only set affinity_mask if the CPU is online */ if (cpu_online(v_idx)) cpumask_set_cpu(v_idx, &q_vector->affinity_mask); @@ -973,6 +1028,7 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) netif_napi_add(vsi->netdev, &q_vector->napi, ice_napi_poll, NAPI_POLL_WEIGHT); +out: /* tie q_vector and VSI together */ vsi->q_vectors[v_idx] = q_vector; @@ -1067,6 +1123,13 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, num_q_vectors, vsi->idx); break; + case ICE_VSI_VF: + /* take VF misc vector and data vectors into account */ + num_q_vectors = pf->num_vf_msix; + /* For VF VSI, reserve slots only from HW interrupts */ + vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker, + num_q_vectors, vsi->idx); + break; default: dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n", vsi->type); @@ -1077,9 +1140,11 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) dev_err(&pf->pdev->dev, "Failed to get tracking for %d HW vectors for VSI %d, err=%d\n", num_q_vectors, vsi->vsi_num, vsi->hw_base_vector); - ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, - vsi->idx); - pf->num_avail_sw_msix += num_q_vectors; + if (vsi->type != ICE_VSI_VF) { + ice_free_res(vsi->back->sw_irq_tracker, + vsi->sw_base_vector, vsi->idx); + pf->num_avail_sw_msix += num_q_vectors; + } return -ENOENT; } @@ -1139,7 +1204,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->vsi = vsi; ring->dev = &pf->pdev->dev; ring->count = vsi->num_desc; - ring->itr_setting = ICE_DFLT_TX_ITR; vsi->tx_rings[i] = ring; } @@ -1159,7 +1223,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->netdev = vsi->netdev; ring->dev = &pf->pdev->dev; ring->count = vsi->num_desc; - ring->itr_setting = ICE_DFLT_RX_ITR; vsi->rx_rings[i] = ring; } @@ -1196,6 +1259,7 @@ static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) tx_rings_per_v = DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); q_vector->num_ring_tx = tx_rings_per_v; q_vector->tx.ring = NULL; + q_vector->tx.itr_idx = ICE_TX_ITR; q_base = vsi->num_txq - tx_rings_rem; for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { @@ -1211,6 +1275,7 @@ static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) rx_rings_per_v = DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); q_vector->num_ring_rx = rx_rings_per_v; q_vector->rx.ring = NULL; + q_vector->rx.itr_idx = ICE_RX_ITR; q_base = vsi->num_rxq - rx_rings_rem; for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { @@ -1512,6 +1577,9 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) int err = 0; u16 i; + if (vsi->type == ICE_VSI_VF) + goto setup_rings; + if (vsi->netdev && vsi->netdev->mtu > ETH_DATA_LEN) vsi->max_frame = vsi->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; @@ -1519,6 +1587,7 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) vsi->max_frame = ICE_RXBUF_2048; vsi->rx_buf_len = ICE_RXBUF_2048; +setup_rings: /* set up individual rings */ for (i = 0; i < vsi->num_rxq && !err; i++) err = ice_setup_rx_ctx(vsi->rx_rings[i]); @@ -1615,6 +1684,37 @@ static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran) } /** + * ice_cfg_itr - configure the initial interrupt throttle values + * @hw: pointer to the HW structure + * @q_vector: interrupt vector that's being configured + * @vector: HW vector index to apply the interrupt throttling to + * + * Configure interrupt throttling values for the ring containers that are + * associated with the interrupt vector passed in. + */ +static void +ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector) +{ + u8 itr_gran = hw->itr_gran; + + if (q_vector->num_ring_rx) { + struct ice_ring_container *rc = &q_vector->rx; + + rc->itr = ITR_TO_REG(ICE_DFLT_RX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } + + if (q_vector->num_ring_tx) { + struct ice_ring_container *rc = &q_vector->tx; + + rc->itr = ITR_TO_REG(ICE_DFLT_TX_ITR, itr_gran); + rc->latency_range = ICE_LOW_LATENCY; + wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr); + } +} + +/** * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW * @vsi: the VSI being configured */ @@ -1624,31 +1724,13 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) u16 vector = vsi->hw_base_vector; struct ice_hw *hw = &pf->hw; u32 txq = 0, rxq = 0; - int i, q, itr; - u8 itr_gran; + int i, q; for (i = 0; i < vsi->num_q_vectors; i++, vector++) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - itr_gran = hw->itr_gran; - - q_vector->intrl = ICE_DFLT_INTRL; - - if (q_vector->num_ring_rx) { - q_vector->rx.itr = - ITR_TO_REG(vsi->rx_rings[rxq]->itr_setting, - itr_gran); - q_vector->rx.latency_range = ICE_LOW_LATENCY; - } + ice_cfg_itr(hw, q_vector, vector); - if (q_vector->num_ring_tx) { - q_vector->tx.itr = - ITR_TO_REG(vsi->tx_rings[txq]->itr_setting, - itr_gran); - q_vector->tx.latency_range = ICE_LOW_LATENCY; - } - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), q_vector->rx.itr); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), q_vector->tx.itr); wr32(hw, GLINT_RATE(vector), ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran)); @@ -1664,23 +1746,33 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) * tracked for this PF. */ for (q = 0; q < q_vector->num_ring_tx; q++) { + int itr_idx = q_vector->tx.itr_idx; u32 val; - itr = ICE_ITR_NONE; - val = QINT_TQCTL_CAUSE_ENA_M | - (itr << QINT_TQCTL_ITR_INDX_S) | - (vector << QINT_TQCTL_MSIX_INDX_S); + if (vsi->type == ICE_VSI_VF) + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + ((i + 1) << QINT_TQCTL_MSIX_INDX_S); + else + val = QINT_TQCTL_CAUSE_ENA_M | + (itr_idx << QINT_TQCTL_ITR_INDX_S) | + (vector << QINT_TQCTL_MSIX_INDX_S); wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val); txq++; } for (q = 0; q < q_vector->num_ring_rx; q++) { + int itr_idx = q_vector->rx.itr_idx; u32 val; - itr = ICE_ITR_NONE; - val = QINT_RQCTL_CAUSE_ENA_M | - (itr << QINT_RQCTL_ITR_INDX_S) | - (vector << QINT_RQCTL_MSIX_INDX_S); + if (vsi->type == ICE_VSI_VF) + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + ((i + 1) << QINT_RQCTL_MSIX_INDX_S); + else + val = QINT_RQCTL_CAUSE_ENA_M | + (itr_idx << QINT_RQCTL_ITR_INDX_S) | + (vector << QINT_RQCTL_MSIX_INDX_S); wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val); rxq++; } @@ -1784,8 +1876,11 @@ int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) /** * ice_vsi_stop_tx_rings - Disable Tx rings * @vsi: the VSI being configured + * @rst_src: reset source + * @rel_vmvf_num: Relative id of VF/VM */ -int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num) { struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; @@ -1837,7 +1932,7 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M); } status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, - NULL); + rst_src, rel_vmvf_num, NULL); /* 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. @@ -1934,7 +2029,7 @@ err_out: */ struct ice_vsi * ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type type, u16 __always_unused vf_id) + enum ice_vsi_type type, u16 vf_id) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = &pf->pdev->dev; @@ -1949,6 +2044,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, vsi->port_info = pi; vsi->vsw = pf->first_sw; + if (vsi->type == ICE_VSI_VF) + vsi->vf_id = vf_id; if (ice_vsi_get_qs(vsi)) { dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", @@ -1987,6 +2084,34 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_vsi_cfg_rss_lut_key(vsi); break; + case ICE_VSI_VF: + /* VF driver will take care of creating netdev for this type and + * map queues to vectors through Virtchnl, PF driver only + * creates a VSI and corresponding structures for bookkeeping + * purpose + */ + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto unroll_vsi_init; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + + /* Setup Vector base only during VF init phase or when VF asks + * for more vectors than assigned number. In all other cases, + * assign hw_base_vector to the value given earlier. + */ + if (test_bit(ICE_VF_STATE_CFG_INTR, pf->vf[vf_id].vf_states)) { + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto unroll_vector_base; + } else { + vsi->hw_base_vector = pf->vf[vf_id].first_vector_idx; + } + pf->q_left_tx -= vsi->alloc_txq; + pf->q_left_rx -= vsi->alloc_rxq; + break; default: /* if VSI type is not recognized, clean up the resources and * exit @@ -2045,8 +2170,8 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++, vector++) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; - wr32(hw, GLINT_ITR(ICE_RX_ITR, vector), 0); - wr32(hw, GLINT_ITR(ICE_TX_ITR, vector), 0); + wr32(hw, GLINT_ITR(ICE_IDX_ITR0, vector), 0); + wr32(hw, GLINT_ITR(ICE_IDX_ITR1, vector), 0); for (q = 0; q < q_vector->num_ring_tx; q++) { wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0); txq++; @@ -2077,6 +2202,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; ice_vsi_release_msix(vsi); + if (vsi->type == ICE_VSI_VF) + return; vsi->irqs_ready = false; for (i = 0; i < vsi->num_q_vectors; i++) { @@ -2317,10 +2444,12 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) int ice_vsi_release(struct ice_vsi *vsi) { struct ice_pf *pf; + struct ice_vf *vf; if (!vsi->back) return -ENODEV; pf = vsi->back; + vf = &pf->vf[vsi->vf_id]; /* 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 @@ -2342,10 +2471,23 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_vsi_close(vsi); /* reclaim interrupt vectors back to PF */ - ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); - pf->num_avail_hw_msix += vsi->num_q_vectors; + if (vsi->type != ICE_VSI_VF) { + /* reclaim SW interrupts back to the common pool */ + ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, + vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + /* reclaim HW interrupts back to the common pool */ + ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, + vsi->idx); + pf->num_avail_hw_msix += vsi->num_q_vectors; + } else if (test_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states)) { + /* Reclaim VF resources back only while freeing all VFs or + * vector reassignment is requested + */ + ice_free_res(vsi->back->hw_irq_tracker, vf->first_vector_idx, + vsi->idx); + pf->num_avail_hw_msix += pf->num_vf_msix; + } ice_remove_vsi_fltr(&pf->hw, vsi->idx); ice_vsi_delete(vsi); @@ -2414,6 +2556,22 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) ice_vsi_map_rings_to_vectors(vsi); break; + case ICE_VSI_VF: + ret = ice_vsi_alloc_q_vectors(vsi); + if (ret) + goto err_rings; + + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto err_vectors; + + vsi->back->q_left_tx -= vsi->alloc_txq; + vsi->back->q_left_rx -= vsi->alloc_rxq; + break; default: break; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 2617afe01c82..677db40338f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -31,7 +31,8 @@ int ice_vsi_start_rx_rings(struct ice_vsi *vsi); int ice_vsi_stop_rx_rings(struct ice_vsi *vsi); -int ice_vsi_stop_tx_rings(struct ice_vsi *vsi); +int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num); int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 46ccf265c218..8f61b375e768 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8,7 +8,7 @@ #include "ice.h" #include "ice_lib.h" -#define DRV_VERSION "0.7.1-k" +#define DRV_VERSION "0.7.2-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; @@ -342,6 +342,10 @@ ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; + /* Notify VFs of impending reset */ + if (ice_check_sq_alive(hw, &hw->mailboxq)) + ice_vc_notify_reset(pf); + /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf); @@ -661,6 +665,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi) } } + ice_vc_notify_link_state(pf); + return 0; } @@ -711,6 +717,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) cq = &hw->adminq; qtype = "Admin"; break; + case ICE_CTL_Q_MAILBOX: + cq = &hw->mailboxq; + qtype = "Mailbox"; + break; default: dev_warn(&pf->pdev->dev, "Unknown control queue type 0x%x\n", q_type); @@ -792,6 +802,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) dev_err(&pf->pdev->dev, "Could not handle link event\n"); break; + case ice_mbx_opc_send_msg_to_pf: + ice_vc_process_vf_msg(pf, &event); + break; case ice_aqc_opc_fw_logging: ice_output_fw_log(hw, &event.desc, event.msg_buf); break; @@ -851,6 +864,28 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) } /** + * ice_clean_mailboxq_subtask - clean the MailboxQ rings + * @pf: board private structure + */ +static void ice_clean_mailboxq_subtask(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + if (!test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state)) + return; + + if (__ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX)) + return; + + clear_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); + + if (ice_ctrlq_pending(hw, &hw->mailboxq)) + __ice_clean_ctrlq(pf, ICE_CTL_Q_MAILBOX); + + ice_flush(hw); +} + +/** * ice_service_task_schedule - schedule the service task to wake up * @pf: board private structure * @@ -916,6 +951,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; bool mdd_detected = false; u32 reg; + int i; if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state)) return; @@ -1005,6 +1041,51 @@ static void ice_handle_mdd_event(struct ice_pf *pf) } } + /* see if one of the VFs needs to be reset */ + for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + struct ice_vf *vf = &pf->vf[i]; + + reg = rd32(hw, VP_MDET_TX_PQM(i)); + if (reg & VP_MDET_TX_PQM_VALID_M) { + wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TCLAN(i)); + if (reg & VP_MDET_TX_TCLAN_VALID_M) { + wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_TX_TDPU(i)); + if (reg & VP_MDET_TX_TDPU_VALID_M) { + wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", + i); + } + + reg = rd32(hw, VP_MDET_RX(i)); + if (reg & VP_MDET_RX_VALID_M) { + wr32(hw, VP_MDET_RX(i), 0xFFFF); + vf->num_mdd_events++; + dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", + i); + } + + if (vf->num_mdd_events > ICE_DFLT_NUM_MDD_EVENTS_ALLOWED) { + dev_info(&pf->pdev->dev, + "Too many MDD events on VF %d, disabled\n", i); + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + } + } + /* re-enable MDD interrupt cause */ clear_bit(__ICE_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, PFINT_OICR_ENA); @@ -1038,8 +1119,10 @@ static void ice_service_task(struct work_struct *work) ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); ice_handle_mdd_event(pf); + ice_process_vflr_event(pf); ice_watchdog_subtask(pf); ice_clean_adminq_subtask(pf); + ice_clean_mailboxq_subtask(pf); /* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */ ice_service_task_complete(pf); @@ -1050,6 +1133,8 @@ static void ice_service_task(struct work_struct *work) */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || + test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + test_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state) || test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -1064,6 +1149,10 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) hw->adminq.num_sq_entries = ICE_AQ_LEN; hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN; hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN; + hw->mailboxq.num_rq_entries = ICE_MBXQ_LEN; + hw->mailboxq.num_sq_entries = ICE_MBXQ_LEN; + hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN; + hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN; } /** @@ -1197,6 +1286,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf) PFINT_OICR_MAL_DETECT_M | PFINT_OICR_GRST_M | PFINT_OICR_PCI_EXCEPTION_M | + PFINT_OICR_VFLR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_CRITERR_M); @@ -1220,6 +1310,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) u32 oicr, ena_mask; set_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); + set_bit(__ICE_MAILBOXQ_EVENT_PENDING, pf->state); oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); @@ -1228,6 +1319,10 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) ena_mask &= ~PFINT_OICR_MAL_DETECT_M; set_bit(__ICE_MDD_EVENT_PENDING, pf->state); } + if (oicr & PFINT_OICR_VFLR_M) { + ena_mask &= ~PFINT_OICR_VFLR_M; + set_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + } if (oicr & PFINT_OICR_GRST_M) { u32 reset; @@ -1406,6 +1501,11 @@ skip_req_irq: PFINT_FW_CTL_CAUSE_ENA_M); wr32(hw, PFINT_FW_CTL, val); + /* This enables Mailbox queue Interrupt causes */ + val = ((pf->hw_oicr_idx & PFINT_MBX_CTL_MSIX_INDX_M) | + PFINT_MBX_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_MBX_CTL, val); + itr_gran = hw->itr_gran; wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx), @@ -1775,6 +1875,15 @@ static void ice_init_pf(struct ice_pf *pf) { bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS); set_bit(ICE_FLAG_MSIX_ENA, pf->flags); +#ifdef CONFIG_PCI_IOV + if (pf->hw.func_caps.common_cap.sr_iov_1_1) { + struct ice_hw *hw = &pf->hw; + + set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); + pf->num_vfs_supported = min_t(int, hw->func_caps.num_allocd_vfs, + ICE_MAX_VF_COUNT); + } +#endif /* CONFIG_PCI_IOV */ mutex_init(&pf->sw_mutex); mutex_init(&pf->avail_q_mutex); @@ -2138,6 +2247,8 @@ static void ice_remove(struct pci_dev *pdev) set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) + ice_free_vfs(pf); ice_vsi_release_all(pf); ice_free_irq_msix_misc(pf); ice_for_each_vsi(pf, i) { @@ -2173,6 +2284,7 @@ static struct pci_driver ice_driver = { .id_table = ice_pci_tbl, .probe = ice_probe, .remove = ice_remove, + .sriov_configure = ice_sriov_configure, }; /** @@ -2908,7 +3020,7 @@ int ice_down(struct ice_vsi *vsi) } ice_vsi_dis_irq(vsi); - tx_err = ice_vsi_stop_tx_rings(vsi); + tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0); if (tx_err) netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n", @@ -3102,13 +3214,14 @@ 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) { - rtnl_lock(); - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - rtnl_unlock(); - } else { - ice_vsi_close(vsi); + if (vsi->type == ICE_VSI_PF && vsi->netdev) { + if (netif_running(vsi->netdev)) { + rtnl_lock(); + vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + rtnl_unlock(); + } else { + ice_vsi_close(vsi); + } } } @@ -3120,12 +3233,16 @@ static int ice_ena_vsi(struct ice_vsi *vsi) { int err = 0; - if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) - if (vsi->netdev && netif_running(vsi->netdev)) { + if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state) && + vsi->netdev) { + if (netif_running(vsi->netdev)) { rtnl_lock(); err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev); rtnl_unlock(); + } else { + err = ice_vsi_open(vsi); } + } return err; } @@ -3174,6 +3291,10 @@ static int ice_vsi_rebuild_all(struct ice_pf *pf) if (!pf->vsi[i]) continue; + /* VF VSI rebuild isn't supported yet */ + if (pf->vsi[i]->type == ICE_VSI_VF) + continue; + err = ice_vsi_rebuild(pf->vsi[i]); if (err) { dev_err(&pf->pdev->dev, @@ -3310,6 +3431,7 @@ static void ice_rebuild(struct ice_pf *pf) goto err_vsi_rebuild; } + ice_reset_all_vfs(pf, true); /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; @@ -3818,6 +3940,12 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, + .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, + .ndo_set_vf_mac = ice_set_vf_mac, + .ndo_get_vf_config = ice_get_vf_cfg, + .ndo_set_vf_trust = ice_set_vf_trust, + .ndo_set_vf_vlan = ice_set_vf_port_vlan, + .ndo_set_vf_link_state = ice_set_vf_link_state, .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, diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c new file mode 100644 index 000000000000..027eba4e13f8 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_adminq_cmd.h" +#include "ice_sriov.h" + +/** + * ice_aq_send_msg_to_vf + * @hw: pointer to the hardware structure + * @vfid: VF ID to send msg + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cd: pointer to command details + * + * Send message to VF driver (0x0802) using mailbox + * queue and asynchronously sending message via + * ice_sq_send_cmd() function + */ +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd) +{ + struct ice_aqc_pf_vf_msg *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf); + + cmd = &desc.params.virt; + cmd->id = cpu_to_le32(vfid); + + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + + if (msglen) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); +} + +/** + * ice_conv_link_speed_to_virtchnl + * @adv_link_support: determines the format of the returned link speed + * @link_speed: variable containing the link_speed to be converted + * + * Convert link speed supported by HW to link speed supported by virtchnl. + * If adv_link_support is true, then return link speed in Mbps. Else return + * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller + * needs to cast back to an enum virtchnl_link_speed in the case where + * adv_link_support is false, but when adv_link_support is true the caller can + * expect the speed in Mbps. + */ +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) +{ + u32 speed; + + if (adv_link_support) + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + speed = ICE_LINK_SPEED_10MBPS; + break; + case ICE_AQ_LINK_SPEED_100MB: + speed = ICE_LINK_SPEED_100MBPS; + break; + case ICE_AQ_LINK_SPEED_1000MB: + speed = ICE_LINK_SPEED_1000MBPS; + break; + case ICE_AQ_LINK_SPEED_2500MB: + speed = ICE_LINK_SPEED_2500MBPS; + break; + case ICE_AQ_LINK_SPEED_5GB: + speed = ICE_LINK_SPEED_5000MBPS; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = ICE_LINK_SPEED_10000MBPS; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = ICE_LINK_SPEED_20000MBPS; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = ICE_LINK_SPEED_25000MBPS; + break; + case ICE_AQ_LINK_SPEED_40GB: + speed = ICE_LINK_SPEED_40000MBPS; + break; + default: + speed = ICE_LINK_SPEED_UNKNOWN; + break; + } + else + /* Virtchnl speeds are not defined for every speed supported in + * the hardware. To maintain compatibility with older AVF + * drivers, while reporting the speed the new speed values are + * resolved to the closest known virtchnl speeds + */ + switch (link_speed) { + case ICE_AQ_LINK_SPEED_10MB: + case ICE_AQ_LINK_SPEED_100MB: + speed = (u32)VIRTCHNL_LINK_SPEED_100MB; + break; + case ICE_AQ_LINK_SPEED_1000MB: + case ICE_AQ_LINK_SPEED_2500MB: + case ICE_AQ_LINK_SPEED_5GB: + speed = (u32)VIRTCHNL_LINK_SPEED_1GB; + break; + case ICE_AQ_LINK_SPEED_10GB: + speed = (u32)VIRTCHNL_LINK_SPEED_10GB; + break; + case ICE_AQ_LINK_SPEED_20GB: + speed = (u32)VIRTCHNL_LINK_SPEED_20GB; + break; + case ICE_AQ_LINK_SPEED_25GB: + speed = (u32)VIRTCHNL_LINK_SPEED_25GB; + break; + case ICE_AQ_LINK_SPEED_40GB: + /* fall through */ + speed = (u32)VIRTCHNL_LINK_SPEED_40GB; + break; + default: + speed = (u32)VIRTCHNL_LINK_SPEED_UNKNOWN; + break; + } + + return speed; +} diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h new file mode 100644 index 000000000000..3d78a0795138 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_SRIOV_H_ +#define _ICE_SRIOV_H_ + +#include "ice_common.h" + +#ifdef CONFIG_PCI_IOV +enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, + u8 *msg, u16 msglen, struct ice_sq_cd *cd); + +u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); +#else /* CONFIG_PCI_IOV */ +static inline enum ice_status +ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, + u16 __always_unused vfid, u32 __always_unused v_opcode, + u32 __always_unused v_retval, u8 __always_unused *msg, + u16 __always_unused msglen, + struct ice_sq_cd __always_unused *cd) +{ + return 0; +} + +static inline u32 +ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, + u16 __always_unused link_speed) +{ + return 0; +} + +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h index d2dae913d81e..f49f299ddf2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ b/drivers/net/ethernet/intel/ice/ice_status.h @@ -6,6 +6,9 @@ /* Error Codes */ enum ice_status { + ICE_SUCCESS = 0, + + /* Generic codes : Range -1..-49 */ ICE_ERR_PARAM = -1, ICE_ERR_NOT_IMPL = -2, ICE_ERR_NOT_READY = -3, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index e949224b5282..33403f39f1b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -187,6 +187,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, if (!vsi_ctx->alloc_from_pool) cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + cmd->vf_id = vsi_ctx->vf_num; cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags); @@ -655,6 +656,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, u8 *eth_hdr; u32 act = 0; __be16 *off; + u8 q_rgn; if (opc == ice_aqc_opc_remove_sw_rules) { s_rule->pdata.lkup_tx_rx.act = 0; @@ -693,14 +695,19 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & ICE_SINGLE_ACT_Q_INDEX_M; break; + case ICE_DROP_PACKET: + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | + ICE_SINGLE_ACT_VALID_BIT; + break; case ICE_FWD_TO_QGRP: + q_rgn = f_info->qgrp_size > 0 ? + (u8)ilog2(f_info->qgrp_size) : 0; act |= ICE_SINGLE_ACT_TO_Q; - act |= (f_info->qgrp_size << ICE_SINGLE_ACT_Q_REGION_S) & + act |= (f_info->fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & ICE_SINGLE_ACT_Q_REGION_M; break; - case ICE_DROP_PACKET: - act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP; - break; default: return; } @@ -1415,8 +1422,8 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, fm_list->vsi_count--; clear_bit(vsi_handle, 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)) { + if (fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) { + struct ice_fltr_info tmp_fltr_info = fm_list->fltr_info; struct ice_vsi_list_map_info *vsi_list_info = fm_list->vsi_list_info; u16 rem_vsi_handle; @@ -1425,6 +1432,8 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, ICE_MAX_VSI); if (!ice_is_vsi_valid(hw, rem_vsi_handle)) return ICE_ERR_OUT_OF_RANGE; + + /* Make sure VSI list is empty before removing it below */ status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, vsi_list_id, true, ice_aqc_opc_update_sw_rules, @@ -1432,16 +1441,34 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, if (status) return status; + tmp_fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + tmp_fltr_info.vsi_handle = rem_vsi_handle; + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr_info); + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n", + tmp_fltr_info.fwd_id.hw_vsi_id, status); + return status; + } + + fm_list->fltr_info = tmp_fltr_info; + } + + 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; + /* Remove the VSI list since it is no longer used */ status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); - if (status) + if (status) { + ice_debug(hw, ICE_DBG_SW, + "Failed to remove VSI list %d, error %d\n", + vsi_list_id, 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.hw_vsi_id = - ice_get_hw_vsi_num(hw, rem_vsi_handle); - fm_list->fltr_info.vsi_handle = rem_vsi_handle; + } list_del(&vsi_list_info->list_entry); devm_kfree(ice_hw_to_dev(hw), vsi_list_info); @@ -1983,12 +2010,12 @@ out: enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_fltr_list_entry *list_itr; + struct ice_fltr_list_entry *list_itr, *tmp; if (!m_list) return ICE_ERR_PARAM; - list_for_each_entry(list_itr, m_list, list_entry) { + list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; if (l_type != ICE_SW_LKUP_MAC) @@ -2010,12 +2037,12 @@ ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { - struct ice_fltr_list_entry *v_list_itr; + struct ice_fltr_list_entry *v_list_itr, *tmp; if (!v_list || !hw) return ICE_ERR_PARAM; - list_for_each_entry(v_list_itr, v_list, list_entry) { + list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) { enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; if (l_type != ICE_SW_LKUP_VLAN) @@ -2115,7 +2142,7 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct ice_fltr_info *fi; fi = &fm_entry->fltr_info; - if (!ice_vsi_uses_fltr(fm_entry, vsi_handle)) + if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle)) continue; status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle, @@ -2232,7 +2259,8 @@ ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, goto end; continue; } - if (!test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) + if (!itr->vsi_list_info || + !test_bit(vsi_handle, itr->vsi_list_info->vsi_map)) continue; /* Clearing it so that the logic can add it back */ clear_bit(vsi_handle, itr->vsi_list_info->vsi_map); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 7706e9b6003c..b88d96a1ef69 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -19,6 +19,7 @@ struct ice_vsi_ctx { struct ice_aqc_vsi_props info; struct ice_sched_vsi_info sched; u8 alloc_from_pool; + u8 vf_num; }; enum ice_sw_fwd_act_type { diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index a9b92974e041..1d0f58bd389b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -105,8 +105,9 @@ enum ice_rx_dtype { #define ICE_TX_ITR ICE_IDX_ITR1 #define ICE_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define ICE_ITR_8K 125 -#define ICE_DFLT_TX_ITR ICE_ITR_8K -#define ICE_DFLT_RX_ITR ICE_ITR_8K +#define ICE_ITR_20K 50 +#define ICE_DFLT_TX_ITR ICE_ITR_20K +#define ICE_DFLT_RX_ITR ICE_ITR_20K /* apply ITR granularity translation to program the register. itr_gran is either * 2 or 4 usecs so we need to divide by 2 first then shift by that value */ @@ -135,13 +136,6 @@ struct ice_ring { u16 q_index; /* Queue number of ring */ u32 txq_teid; /* Added Tx queue TEID */ - /* high bit set means dynamic, use accessor routines to read/write. - * hardware supports 4us/2us resolution for the ITR registers. - * these values always store the USER setting, and must be converted - * before programming to a register. - */ - u16 itr_setting; - u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -178,6 +172,7 @@ struct ice_ring_container { unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_pkts; /* total packets processed this int */ enum ice_latency_range latency_range; + int itr_idx; /* index in the interrupt vector */ u16 itr; }; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index f5c8de0ed0eb..12f9432abf11 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -84,6 +84,7 @@ enum ice_media_type { enum ice_vsi_type { ICE_VSI_PF = 0, + ICE_VSI_VF, }; struct ice_link_status { @@ -103,6 +104,15 @@ struct ice_link_status { u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE]; }; +/* Different reset sources for which a disable queue AQ call has to be made in + * order to clean the TX scheduler as a part of the reset + */ +enum ice_disq_rst_src { + ICE_NO_RESET = 0, + ICE_VM_RESET, + ICE_VF_RESET, +}; + /* PHY info such as phy_type, etc... */ struct ice_phy_info { struct ice_link_status link_info; @@ -127,6 +137,9 @@ struct ice_hw_common_caps { /* Max MTU for function or device */ u16 max_mtu; + /* Virtualization support */ + u8 sr_iov_1_1; /* SR-IOV enabled */ + /* RSS related capabilities */ u16 rss_table_size; /* 512 for PFs and 64 for VFs */ u8 rss_table_entry_width; /* RSS Entry width in bits */ @@ -135,12 +148,15 @@ struct ice_hw_common_caps { /* Function specific capabilities */ struct ice_hw_func_caps { struct ice_hw_common_caps common_cap; + u32 num_allocd_vfs; /* Number of allocated VFs */ + u32 vf_base_id; /* Logical ID of the first VF */ u32 guaranteed_num_vsi; }; /* Device wide capabilities */ struct ice_hw_dev_caps { struct ice_hw_common_caps common_cap; + u32 num_vfs_exposed; /* Total number of VFs exposed */ u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ }; @@ -321,6 +337,7 @@ struct ice_hw { /* Control Queue info */ struct ice_ctl_q_info adminq; + struct ice_ctl_q_info mailboxq; u8 api_branch; /* API branch version */ u8 api_maj_ver; /* API major version */ @@ -426,4 +443,7 @@ struct ice_hw_port_stats { #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 #define ICE_SR_WORDS_IN_1KB 512 +/* Hash redirection LUT for VSI - maximum array size */ +#define ICE_VSIQF_HLUT_ARRAY_SIZE ((VSIQF_HLUT_MAX_INDEX + 1) * 4) + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c new file mode 100644 index 000000000000..c25e486706f3 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -0,0 +1,2668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +/** + * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF + * @pf: pointer to the PF structure + * @v_opcode: operation code + * @v_retval: return value + * @msg: pointer to the msg buffer + * @msglen: msg length + */ +static void +ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vf = pf->vf; + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++, vf++) { + /* Not all vfs are enabled so skip the ones that are not */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + continue; + + /* Ignore return value on purpose - a given VF may fail, but + * we need to keep going and send to all of them + */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, v_opcode, v_retval, msg, + msglen, NULL); + } +} + +/** + * ice_set_pfe_link - Set the link speed/status of the virtchnl_pf_event + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @ice_link_speed: link speed specified by ICE_AQ_LINK_SPEED_* + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + int ice_link_speed, bool link_up) +{ + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) { + pfe->event_data.link_event_adv.link_status = link_up; + /* Speed in Mbps */ + pfe->event_data.link_event_adv.link_speed = + ice_conv_link_speed_to_virtchnl(true, ice_link_speed); + } else { + pfe->event_data.link_event.link_status = link_up; + /* Legacy method for virtchnl link speeds */ + pfe->event_data.link_event.link_speed = + (enum virtchnl_link_speed) + ice_conv_link_speed_to_virtchnl(false, ice_link_speed); + } +} + +/** + * ice_set_pfe_link_forced - Force the virtchnl_pf_event link speed/status + * @vf: pointer to the VF structure + * @pfe: pointer to the virtchnl_pf_event to set link speed/status for + * @link_up: whether or not to set the link up/down + */ +static void +ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe, + bool link_up) +{ + u16 link_speed; + + if (link_up) + link_speed = ICE_AQ_LINK_SPEED_40GB; + else + link_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + + ice_set_pfe_link(vf, pfe, link_speed, link_up); +} + +/** + * ice_vc_notify_vf_link_state - Inform a VF of link status + * @vf: pointer to the VF structure + * + * send a link status message to a single VF + */ +static void ice_vc_notify_vf_link_state(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + + hw = &pf->hw; + ls = &hw->port_info->phy.link_info; + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info & + ICE_AQ_LINK_UP); + + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); +} + +/** + * ice_get_vf_vector - get VF interrupt vector register offset + * @vf_msix: number of MSIx vector per VF on a PF + * @vf_id: VF identifier + * @i: index of MSIx vector + */ +static u32 ice_get_vf_vector(int vf_msix, int vf_id, int i) +{ + return ((i == 0) ? VFINT_DYN_CTLN(vf_id) : + VFINT_DYN_CTLN(((vf_msix - 1) * (vf_id)) + (i - 1))); +} + +/** + * ice_free_vf_res - Free a VF's resources + * @vf: pointer to the VF info + */ +static void ice_free_vf_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + int i, pf_vf_msix; + + /* First, disable VF's configuration API to prevent OS from + * accessing the VF's VSI after it's freed or invalidated. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* free vsi & disconnect it from the parent uplink */ + if (vf->lan_vsi_idx) { + ice_vsi_release(pf->vsi[vf->lan_vsi_idx]); + vf->lan_vsi_idx = 0; + vf->lan_vsi_num = 0; + vf->num_mac = 0; + } + + pf_vf_msix = pf->num_vf_msix; + /* Disable interrupts so that VF starts in a known state */ + for (i = 0; i < pf_vf_msix; i++) { + u32 reg_idx; + + reg_idx = ice_get_vf_vector(pf_vf_msix, vf->vf_id, i); + wr32(&pf->hw, reg_idx, VFINT_DYN_CTLN_CLEARPBA_M); + ice_flush(&pf->hw); + } + /* reset some of the state variables keeping track of the resources */ + clear_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states); + clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); +} + +/***********************enable_vf routines*****************************/ + +/** + * ice_dis_vf_mappings + * @vf: pointer to the VF structure + */ +static void ice_dis_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + + wr32(hw, VPINT_ALLOC(vf->vf_id), 0); + + first = vf->first_vector_idx; + last = first + pf->num_vf_msix - 1; + for (v = first; v <= last; v++) { + u32 reg; + + reg = (((1 << GLINT_VECT2FUNC_IS_PF_S) & + GLINT_VECT2FUNC_IS_PF_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), 0); + else + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); +} + +/** + * ice_free_vfs - Free all VFs + * @pf: pointer to the PF structure + */ +void ice_free_vfs(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int tmp, i; + + if (!pf->vf) + return; + + while (test_and_set_bit(__ICE_VF_DIS, pf->state)) + usleep_range(1000, 2000); + + /* Avoid wait time by stopping all VFs at the same time */ + for (i = 0; i < pf->num_alloc_vfs; i++) { + if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states)) + continue; + + /* stop rings without wait time */ + ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx], + ICE_NO_RESET, i); + ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]); + + clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); + } + + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + + tmp = pf->num_alloc_vfs; + pf->num_vf_qps = 0; + pf->num_alloc_vfs = 0; + for (i = 0; i < tmp; i++) { + if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + /* disable VF qp mappings */ + ice_dis_vf_mappings(&pf->vf[i]); + + /* Set this state so that assigned VF vectors can be + * reclaimed by PF for reuse in ice_vsi_release(). No + * need to clear this bit since pf->vf array is being + * freed anyways after this for loop + */ + set_bit(ICE_VF_STATE_CFG_INTR, pf->vf[i].vf_states); + ice_free_vf_res(&pf->vf[i]); + } + } + + devm_kfree(&pf->pdev->dev, pf->vf); + pf->vf = NULL; + + /* This check is for when the driver is unloaded while VFs are + * assigned. Setting the number of VFs to 0 through sysfs is caught + * before this function ever gets called. + */ + if (!pci_vfs_assigned(pf->pdev)) { + int vf_id; + + /* Acknowledge VFLR for all VFs. Without this, VFs will fail to + * work correctly when SR-IOV gets re-enabled. + */ + for (vf_id = 0; vf_id < tmp; vf_id++) { + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + } + } + clear_bit(__ICE_VF_DIS, pf->state); + clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); +} + +/** + * ice_trigger_vf_reset - Reset a VF on HW + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. + */ +static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + u32 reg, reg_idx, bit_idx; + struct ice_hw *hw; + int vf_abs_id, i; + + hw = &pf->hw; + vf_abs_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* Inform VF that it is no longer active, as a warning */ + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * in ice_alloc_vf_res(), when it's safe again to access VF's VSI. + * It's normally disabled in ice_free_vf_res(), but it's safer + * to do it earlier to give some time to finish to any VF config + * functions that may still be running at this point. + */ + clear_bit(ICE_VF_STATE_INIT, vf->vf_states); + + /* In the case of a VFLR, the HW has already reset the VF and we + * just need to clean up, so don't hit the VFRTRIG register. + */ + if (!is_vflr) { + /* reset VF using VPGEN_VFRTRIG reg */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg |= VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + } + /* clear the VFLR bit in GLGEN_VFLRSTAT */ + reg_idx = (vf_abs_id) / 32; + bit_idx = (vf_abs_id) % 32; + wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); + ice_flush(hw); + + wr32(hw, PF_PCI_CIAA, + VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); + for (i = 0; i < 100; i++) { + reg = rd32(hw, PF_PCI_CIAD); + if ((reg & VF_TRANS_PENDING_M) != 0) + dev_err(&pf->pdev->dev, + "VF %d PCI transactions stuck\n", vf->vf_id); + udelay(1); + } +} + +/** + * ice_vsi_set_pvid - Set port VLAN id for the VSI + * @vsi: the VSI being changed + * @vid: the VLAN id to set as a PVID + */ +static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ICE_AQ_VSI_PVLAN_INSERT_PVID | + ICE_AQ_VSI_VLAN_EMOD_STR; + ctxt.info.pvid = cpu_to_le16(vid); + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL); + if (status) { + dev_info(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + status, hw->adminq.sq_last_status); + return -EIO; + } + + vsi->info.pvid = ctxt.info.pvid; + vsi->info.vlan_flags = ctxt.info.vlan_flags; + return 0; +} + +/** + * ice_vsi_kill_pvid - Remove port VLAN id from the VSI + * @vsi: the VSI being changed + */ +static int ice_vsi_kill_pvid(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + + if (ice_vsi_manage_vlan_stripping(vsi, false)) { + dev_err(&pf->pdev->dev, "Error removing Port VLAN on VSI %i\n", + vsi->vsi_num); + return -ENODEV; + } + + vsi->info.pvid = 0; + return 0; +} + +/** + * ice_vf_vsi_setup - Set up a VF VSI + * @pf: board private structure + * @pi: pointer to the port_info instance + * @vf_id: defines VF id to which this VSI connects. + * + * Returns pointer to the successfully allocated VSI struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi * +ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_VF, vf_id); +} + +/** + * ice_alloc_vsi_res - Setup VF VSI and its resources + * @vf: pointer to the VF structure + * + * Returns 0 on success, negative value on failure + */ +static int ice_alloc_vsi_res(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + LIST_HEAD(tmp_add_list); + u8 broadcast[ETH_ALEN]; + struct ice_vsi *vsi; + int status = 0; + + vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id); + + if (!vsi) { + dev_err(&pf->pdev->dev, "Failed to create VF VSI\n"); + return -ENOMEM; + } + + vf->lan_vsi_idx = vsi->idx; + vf->lan_vsi_num = vsi->vsi_num; + + /* first vector index is the VFs OICR index */ + vf->first_vector_idx = vsi->hw_base_vector; + /* Since hw_base_vector holds the vector where data queue interrupts + * starts, increment by 1 since VFs allocated vectors include OICR intr + * as well. + */ + vsi->hw_base_vector += 1; + + /* Check if port VLAN exist before, and restore it accordingly */ + if (vf->port_vlan_id) + ice_vsi_set_pvid(vsi, vf->port_vlan_id); + + eth_broadcast_addr(broadcast); + + status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); + if (status) + goto ice_alloc_vsi_res_exit; + + if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) { + status = ice_add_mac_to_list(vsi, &tmp_add_list, + vf->dflt_lan_addr.addr); + if (status) + goto ice_alloc_vsi_res_exit; + } + + status = ice_add_mac(&pf->hw, &tmp_add_list); + if (status) + dev_err(&pf->pdev->dev, "could not add mac filters\n"); + + /* Clear this bit after VF initialization since we shouldn't reclaim + * and reassign interrupts for synchronous or asynchronous VFR events. + * We don't want to reconfigure interrupts since AVF driver doesn't + * expect vector assignment to be changed unless there is a request for + * more vectors. + */ + clear_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states); +ice_alloc_vsi_res_exit: + ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; +} + +/** + * ice_alloc_vf_res - Allocate VF resources + * @vf: pointer to the VF structure + */ +static int ice_alloc_vf_res(struct ice_vf *vf) +{ + int status; + + /* setup VF VSI and necessary resources */ + status = ice_alloc_vsi_res(vf); + if (status) + goto ice_alloc_vf_res_exit; + + if (vf->trusted) + set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + else + clear_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); + + /* VF is now completely initialized */ + set_bit(ICE_VF_STATE_INIT, vf->vf_states); + + return status; + +ice_alloc_vf_res_exit: + ice_free_vf_res(vf); + return status; +} + +/** + * ice_ena_vf_mappings + * @vf: pointer to the VF structure + * + * Enable VF vectors and queues allocation by writing the details into + * respective registers. + */ +static void ice_ena_vf_mappings(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int first, last, v; + struct ice_hw *hw; + int abs_vf_id; + u32 reg; + + hw = &pf->hw; + vsi = pf->vsi[vf->lan_vsi_idx]; + first = vf->first_vector_idx; + last = (first + pf->num_vf_msix) - 1; + abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + + /* VF Vector allocation */ + reg = (((first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) | + ((last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) | + VPINT_ALLOC_VALID_M); + wr32(hw, VPINT_ALLOC(vf->vf_id), reg); + + /* map the interrupts to its functions */ + for (v = first; v <= last; v++) { + reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & + GLINT_VECT2FUNC_VF_NUM_M) | + ((hw->pf_id << GLINT_VECT2FUNC_PF_NUM_S) & + GLINT_VECT2FUNC_PF_NUM_M)); + wr32(hw, GLINT_VECT2FUNC(v), reg); + } + + /* VF Tx queues allocation */ + if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { + wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), + VPLAN_TXQ_MAPENA_TX_ENA_M); + /* set the VF PF Tx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->txq_map[0] << VPLAN_TX_QBASE_VFFIRSTQ_S) & + VPLAN_TX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_TX_QBASE_VFNUMQ_S) & + VPLAN_TX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_TX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Tx queues is not yet implemented\n"); + } + + /* VF Rx queues allocation */ + if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { + wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), + VPLAN_RXQ_MAPENA_RX_ENA_M); + /* set the VF PF Rx queue range + * VFNUMQ value should be set to (number of queues - 1). A value + * of 0 means 1 queue and a value of 255 means 256 queues + */ + reg = (((vsi->rxq_map[0] << VPLAN_RX_QBASE_VFFIRSTQ_S) & + VPLAN_RX_QBASE_VFFIRSTQ_M) | + (((vsi->alloc_txq - 1) << VPLAN_RX_QBASE_VFNUMQ_S) & + VPLAN_RX_QBASE_VFNUMQ_M)); + wr32(hw, VPLAN_RX_QBASE(vf->vf_id), reg); + } else { + dev_err(&pf->pdev->dev, + "Scattered mode for VF Rx queues is not yet implemented\n"); + } +} + +/** + * ice_determine_res + * @pf: pointer to the PF structure + * @avail_res: available resources in the PF structure + * @max_res: maximum resources that can be given per VF + * @min_res: minimum resources that can be given per VF + * + * Returns non-zero value if resources (queues/vectors) are available or + * returns zero if PF cannot accommodate for all num_alloc_vfs. + */ +static int +ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res) +{ + bool checked_min_res = false; + int res; + + /* start by checking if PF can assign max number of resources for + * all num_alloc_vfs. + * if yes, return number per VF + * If no, divide by 2 and roundup, check again + * repeat the loop till we reach a point where even minimum resources + * are not available, in that case return 0 + */ + res = max_res; + while ((res >= min_res) && !checked_min_res) { + int num_all_res; + + num_all_res = pf->num_alloc_vfs * res; + if (num_all_res <= avail_res) + return res; + + if (res == min_res) + checked_min_res = true; + + res = DIV_ROUND_UP(res, 2); + } + return 0; +} + +/** + * ice_check_avail_res - check if vectors and queues are available + * @pf: pointer to the PF structure + * + * This function is where we calculate actual number of resources for VF VSIs, + * we don't reserve ahead of time during probe. Returns success if vectors and + * queues resources are available, otherwise returns error code + */ +static int ice_check_avail_res(struct ice_pf *pf) +{ + u16 num_msix, num_txq, num_rxq; + + if (!pf->num_alloc_vfs) + return -EINVAL; + + /* Grab from HW interrupts common pool + * Note: By the time the user decides it needs more vectors in a VF + * its already too late since one must decide this prior to creating the + * VF interface. So the best we can do is take a guess as to what the + * user might want. + * + * We have two policies for vector allocation: + * 1. if num_alloc_vfs is from 1 to 16, then we consider this as small + * number of NFV VFs used for NFV appliances, since this is a special + * case, we try to assign maximum vectors per VF (65) as much as + * possible, based on determine_resources algorithm. + * 2. if num_alloc_vfs is from 17 to 256, then its large number of + * regular VFs which are not used for any special purpose. Hence try to + * grab default interrupt vectors (5 as supported by AVF driver). + */ + if (pf->num_alloc_vfs <= 16) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_MAX_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else if (pf->num_alloc_vfs <= ICE_MAX_VF_COUNT) { + num_msix = ice_determine_res(pf, pf->num_avail_hw_msix, + ICE_DFLT_INTR_PER_VF, + ICE_MIN_INTR_PER_VF); + } else { + dev_err(&pf->pdev->dev, + "Number of VFs %d exceeds max VF count %d\n", + pf->num_alloc_vfs, ICE_MAX_VF_COUNT); + return -EIO; + } + + if (!num_msix) + return -EIO; + + /* Grab from the common pool + * start by requesting Default queues (4 as supported by AVF driver), + * Note that, the main difference between queues and vectors is, latter + * can only be reserved at init time but queues can be requested by VF + * at runtime through Virtchnl, that is the reason we start by reserving + * few queues. + */ + num_txq = ice_determine_res(pf, pf->q_left_tx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + num_rxq = ice_determine_res(pf, pf->q_left_rx, ICE_DFLT_QS_PER_VF, + ICE_MIN_QS_PER_VF); + + if (!num_txq || !num_rxq) + return -EIO; + + /* since AVF driver works with only queue pairs which means, it expects + * to have equal number of Rx and Tx queues, so take the minimum of + * available Tx or Rx queues + */ + pf->num_vf_qps = min_t(int, num_txq, num_rxq); + pf->num_vf_msix = num_msix; + + return 0; +} + +/** + * ice_cleanup_and_realloc_vf - Clean up VF and reallocate resources after reset + * @vf: pointer to the VF structure + * + * Cleanup a VF after the hardware reset is finished. Expects the caller to + * have verified whether the reset is finished properly, and ensure the + * minimum amount of wait time has passed. Reallocate VF resources back to make + * VF state active + */ +static void ice_cleanup_and_realloc_vf(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw; + u32 reg; + + hw = &pf->hw; + + /* PF software completes the flow by notifying VF that reset flow is + * completed. This is done by enabling hardware by clearing the reset + * bit in the VPGEN_VFRTRIG reg and setting VFR_STATE in the VFGEN_RSTAT + * register to VFR completed (done at the end of this function) + * By doing this we allow HW to access VF memory at any point. If we + * did it any sooner, HW could access memory while it was being freed + * in ice_free_vf_res(), causing an IOMMU fault. + * + * On the other hand, this needs to be done ASAP, because the VF driver + * is waiting for this to happen and may report a timeout. It's + * harmless, but it gets logged into Guest OS kernel log, so best avoid + * it. + */ + reg = rd32(hw, VPGEN_VFRTRIG(vf->vf_id)); + reg &= ~VPGEN_VFRTRIG_VFSWR_M; + wr32(hw, VPGEN_VFRTRIG(vf->vf_id), reg); + + /* reallocate VF resources to finish resetting the VSI state */ + if (!ice_alloc_vf_res(vf)) { + ice_ena_vf_mappings(vf); + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + clear_bit(ICE_VF_STATE_DIS, vf->vf_states); + vf->num_vlan = 0; + } + + /* Tell the VF driver the reset is done. This needs to be done only + * after VF has been fully initialized, because the VF driver may + * request resources immediately after setting this flag. + */ + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); +} + +/** + * ice_reset_all_vfs - reset all allocated VFs in one go + * @pf: pointer to the PF structure + * @is_vflr: true if VFLR was issued, false if not + * + * First, tell the hardware to reset each VF, then do all the waiting in one + * chunk, and finally finish restoring each VF after the wait. This is useful + * during PF routines which need to reset all VFs, as otherwise it must perform + * these resets in a serialized fashion. + * + * Returns true if any VFs were reset, and false otherwise. + */ +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) +{ + struct ice_hw *hw = &pf->hw; + int v, i; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!pf->num_alloc_vfs) + return false; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + /* Begin reset on all VFs at once */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_trigger_vf_reset(&pf->vf[v], is_vflr); + + /* Call Disable LAN Tx queue AQ call with VFR bit set and 0 + * queues to inform Firmware about VF reset. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_dis_vsi_txq(pf->vsi[0]->port_info, 0, NULL, NULL, + ICE_VF_RESET, v, NULL); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in + * sequence to make sure that it has completed. We'll keep track of + * the VFs using a simple iterator that increments once that VF has + * finished resetting. + */ + for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + usleep_range(10000, 20000); + + /* Check each VF in sequence */ + while (v < pf->num_alloc_vfs) { + struct ice_vf *vf = &pf->vf[v]; + u32 reg; + + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & VPGEN_VFRSTAT_VFRD_M)) + break; + + /* If the current VF has finished resetting, move on + * to the next VF in sequence. + */ + v++; + } + } + + /* Display a warning if at least one VF didn't manage to reset in + * time, but continue on with the operation. + */ + if (v < pf->num_alloc_vfs) + dev_warn(&pf->pdev->dev, "VF reset check timeout\n"); + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_free_vf_res(&pf->vf[v]); + + if (ice_check_avail_res(pf)) { + dev_err(&pf->pdev->dev, + "Cannot allocate VF resources, try with fewer number of VFs\n"); + return false; + } + + /* Finish the reset on each VF */ + for (v = 0; v < pf->num_alloc_vfs; v++) + ice_cleanup_and_realloc_vf(&pf->vf[v]); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_reset_vf - Reset a particular VF + * @vf: pointer to the VF structure + * @is_vflr: true if VFLR was issued, false if not + * + * Returns true if the VF is reset, false otherwise. + */ +static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) +{ + struct ice_pf *pf = vf->pf; + struct ice_hw *hw = &pf->hw; + bool rsd = false; + u32 reg; + int i; + + /* If the VFs have been disabled, this means something else is + * resetting the VF, so we shouldn't continue. + */ + if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + return false; + + ice_trigger_vf_reset(vf, is_vflr); + + if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET, + vf->vf_id); + ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]); + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + } else { + /* Call Disable LAN Tx queue AQ call even when queues are not + * enabled. This is needed for successful completiom of VFR + */ + ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0, + NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL); + } + + /* poll VPGEN_VFRSTAT reg to make sure + * that reset is complete + */ + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. + */ + usleep_range(10000, 20000); + reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); + if (reg & VPGEN_VFRSTAT_VFRD_M) { + rsd = true; + break; + } + } + + /* Display a warning if VF didn't manage to reset in time, but need to + * continue on with the operation. + */ + if (!rsd) + dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + vf->vf_id); + + usleep_range(10000, 20000); + + /* free VF resources to begin resetting the VSI state */ + ice_free_vf_res(vf); + + ice_cleanup_and_realloc_vf(vf); + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** + * ice_vc_notify_link_state - Inform all VFs on a PF of link status + * @pf: pointer to the PF structure + */ +void ice_vc_notify_link_state(struct ice_pf *pf) +{ + int i; + + for (i = 0; i < pf->num_alloc_vfs; i++) + ice_vc_notify_vf_link_state(&pf->vf[i]); +} + +/** + * ice_vc_notify_reset - Send pending reset message to all VFs + * @pf: pointer to the PF structure + * + * indicate a pending reset to all VFs on a given PF + */ +void ice_vc_notify_reset(struct ice_pf *pf) +{ + struct virtchnl_pf_event pfe; + + if (!pf->num_alloc_vfs) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, ICE_SUCCESS, + (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); +} + +/** + * ice_vc_notify_vf_reset - Notify VF of a reset event + * @vf: pointer to the VF structure + */ +static void ice_vc_notify_vf_reset(struct ice_vf *vf) +{ + struct virtchnl_pf_event pfe; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return; + + /* verify if the VF is in either init or active before proceeding */ + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states) && + !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + return; + + pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING; + pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM; + ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, + (u8 *)&pfe, sizeof(pfe), NULL); +} + +/** + * ice_alloc_vfs - Allocate and set up VFs resources + * @pf: pointer to the PF structure + * @num_alloc_vfs: number of VFs to allocate + */ +static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) +{ + struct ice_hw *hw = &pf->hw; + struct ice_vf *vfs; + int i, ret; + + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ + wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx), + ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); + + ice_flush(hw); + + ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); + if (ret) { + pf->num_alloc_vfs = 0; + goto err_unroll_intr; + } + /* allocate memory */ + vfs = devm_kcalloc(&pf->pdev->dev, num_alloc_vfs, sizeof(*vfs), + GFP_KERNEL); + if (!vfs) { + ret = -ENOMEM; + goto err_unroll_sriov; + } + pf->vf = vfs; + + /* apply default profile */ + for (i = 0; i < num_alloc_vfs; i++) { + vfs[i].pf = pf; + vfs[i].vf_sw_id = pf->first_sw; + vfs[i].vf_id = i; + + /* assign default capabilities */ + set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); + vfs[i].spoofchk = true; + + /* Set this state so that PF driver does VF vector assignment */ + set_bit(ICE_VF_STATE_CFG_INTR, vfs[i].vf_states); + } + pf->num_alloc_vfs = num_alloc_vfs; + + /* VF resources get allocated during reset */ + if (!ice_reset_all_vfs(pf, false)) + goto err_unroll_sriov; + + goto err_unroll_intr; + +err_unroll_sriov: + pci_disable_sriov(pf->pdev); +err_unroll_intr: + /* rearm interrupts here */ + ice_irq_dynamic_ena(hw, NULL, NULL); + return ret; +} + +/** + * ice_pf_state_is_nominal - checks the pf for nominal state + * @pf: pointer to pf to check + * + * Check the PF's state for a collection of bits that would indicate + * the PF is in a state that would inhibit normal operation for + * driver functionality. + * + * Returns true if PF is in a nominal state. + * Returns false otherwise + */ +static bool ice_pf_state_is_nominal(struct ice_pf *pf) +{ + DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; + + if (!pf) + return false; + + bitmap_set(check_bits, 0, __ICE_STATE_NOMINAL_CHECK_BITS); + if (bitmap_intersects(pf->state, check_bits, __ICE_STATE_NBITS)) + return false; + + return true; +} + +/** + * ice_pci_sriov_ena - Enable or change number of VFs + * @pf: pointer to the PF structure + * @num_vfs: number of VFs to allocate + */ +static int ice_pci_sriov_ena(struct ice_pf *pf, int num_vfs) +{ + int pre_existing_vfs = pci_num_vf(pf->pdev); + struct device *dev = &pf->pdev->dev; + int err; + + if (!ice_pf_state_is_nominal(pf)) { + dev_err(dev, "Cannot enable SR-IOV, device not ready\n"); + return -EBUSY; + } + + if (!test_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags)) { + dev_err(dev, "This device is not capable of SR-IOV\n"); + return -ENODEV; + } + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + ice_free_vfs(pf); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + return num_vfs; + + if (num_vfs > pf->num_vfs_supported) { + dev_err(dev, "Can't enable %d VFs, max VFs supported is %d\n", + num_vfs, pf->num_vfs_supported); + return -ENOTSUPP; + } + + dev_info(dev, "Allocating %d VFs\n", num_vfs); + err = ice_alloc_vfs(pf, num_vfs); + if (err) { + dev_err(dev, "Failed to enable SR-IOV: %d\n", err); + return err; + } + + set_bit(ICE_FLAG_SRIOV_ENA, pf->flags); + return num_vfs; +} + +/** + * ice_sriov_configure - Enable or change number of VFs via sysfs + * @pdev: pointer to a pci_dev structure + * @num_vfs: number of VFs to allocate + * + * This function is called when the user updates the number of VFs in sysfs. + */ +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + if (num_vfs) + return ice_pci_sriov_ena(pf, num_vfs); + + if (!pci_vfs_assigned(pdev)) { + ice_free_vfs(pf); + } else { + dev_err(&pf->pdev->dev, + "can't free VFs because some are assigned to VMs.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * ice_process_vflr_event - Free VF resources via IRQ calls + * @pf: pointer to the PF structure + * + * called from the VLFR IRQ handler to + * free up VF resources and state variables + */ +void ice_process_vflr_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int vf_id; + u32 reg; + + if (!test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) || + !pf->num_alloc_vfs) + return; + + /* Re-enable the VFLR interrupt cause here, before looking for which + * VF got reset. Otherwise, if another VF gets a reset while the + * first one is being processed, that interrupt will be lost, and + * that VF will be stuck in reset forever. + */ + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_VFLR_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); + + clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state); + for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) { + struct ice_vf *vf = &pf->vf[vf_id]; + u32 reg_idx, bit_idx; + + reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; + bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; + /* read GLGEN_VFLRSTAT register to find out the flr VFs */ + reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); + if (reg & BIT(bit_idx)) + /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + ice_reset_vf(vf, true); + } +} + +/** + * ice_vc_dis_vf - Disable a given VF via SW reset + * @vf: pointer to the VF info + * + * Disable the VF through a SW reset + */ +static void ice_vc_dis_vf(struct ice_vf *vf) +{ + ice_vc_notify_vf_reset(vf); + ice_reset_vf(vf, false); +} + +/** + * ice_vc_send_msg_to_vf - Send message to VF + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + */ +static int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, + enum ice_status v_retval, u8 *msg, u16 msglen) +{ + enum ice_status aq_ret; + struct ice_pf *pf; + + /* validate the request */ + if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) + return -EINVAL; + + pf = vf->pf; + + /* single place to detect unsuccessful return values */ + if (v_retval) { + vf->num_inval_msgs++; + dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", + vf->vf_id, v_opcode, v_retval); + if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { + dev_err(&pf->pdev->dev, + "Number of invalid messages exceeded for VF %d\n", + vf->vf_id); + dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + return -EIO; + } + } else { + vf->num_valid_msgs++; + /* reset the invalid counter, if a valid message is received. */ + vf->num_inval_msgs = 0; + } + + aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, + msg, msglen, NULL); + if (aq_ret) { + dev_info(&pf->pdev->dev, + "Unable to send the message to VF %d aq_err %d\n", + vf->vf_id, pf->hw.mailboxq.sq_last_status); + return -EIO; + } + + return 0; +} + +/** + * ice_vc_get_ver_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request the API version used by the PF + */ +static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_version_info info = { + VIRTCHNL_VERSION_MAJOR, VIRTCHNL_VERSION_MINOR + }; + + vf->vf_ver = *(struct virtchnl_version_info *)msg; + /* VFs running the 1.0 API expect to get 1.0 back or they will cry. */ + if (VF_IS_V10(&vf->vf_ver)) + info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS; + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, ICE_SUCCESS, + (u8 *)&info, + sizeof(struct virtchnl_version_info)); +} + +/** + * ice_vc_get_vf_res_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to request its resources + */ +static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_resource *vfres = NULL; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_vf_resource); + + vfres = devm_kzalloc(&pf->pdev->dev, len, GFP_KERNEL); + if (!vfres) { + aq_ret = ICE_ERR_NO_MEMORY; + len = 0; + goto err; + } + if (VF_IS_V11(&vf->vf_ver)) + vf->driver_caps = *(u32 *)msg; + else + vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | + VIRTCHNL_VF_OFFLOAD_RSS_REG | + VIRTCHNL_VF_OFFLOAD_VLAN; + + vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi->info.pvid) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; + } else { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; + else + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; + } + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; + + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + + if (vf->driver_caps & VIRTCHNL_VF_CAP_ADV_LINK_SPEED) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + + vfres->num_vsis = 1; + /* Tx and Rx queue are equal for VF */ + vfres->num_queue_pairs = vsi->num_txq; + vfres->max_vectors = pf->num_vf_msix; + vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; + vfres->rss_lut_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + + vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; + vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; + ether_addr_copy(vfres->vsi_res[0].default_mac_addr, + vf->dflt_lan_addr.addr); + + set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, aq_ret, + (u8 *)vfres, len); + + devm_kfree(&pf->pdev->dev, vfres); + return ret; +} + +/** + * ice_vc_reset_vf_msg + * @vf: pointer to the VF info + * + * called from the VF to reset itself, + * unlike other virtchnl messages, PF driver + * doesn't send the response back to the VF + */ +static void ice_vc_reset_vf_msg(struct ice_vf *vf) +{ + if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ice_reset_vf(vf, false); +} + +/** + * ice_find_vsi_from_id + * @pf: the pf structure to search for the VSI + * @id: id of the VSI it is searching for + * + * searches for the VSI with the given id + */ +static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id) +{ + int i; + + for (i = 0; i < pf->num_alloc_vsi; i++) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == id) + return pf->vsi[i]; + + return NULL; +} + +/** + * ice_vc_isvalid_vsi_id + * @vf: pointer to the VF info + * @vsi_id: VF relative VSI id + * + * check for the valid VSI id + */ +static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = ice_find_vsi_from_id(pf, vsi_id); + + return (vsi && (vsi->vf_id == vf->vf_id)); +} + +/** + * ice_vc_isvalid_q_id + * @vf: pointer to the VF info + * @vsi_id: VSI id + * @qid: VSI relative queue id + * + * check for the valid queue id + */ +static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +{ + struct ice_vsi *vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + /* allocated Tx and Rx queues should be always equal for VF VSI */ + return (vsi && (qid < vsi->alloc_txq)); +} + +/** + * ice_vc_config_rss_key + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS key + */ +static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_key *vrk = + (struct virtchnl_rss_key *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrk->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, vrk->key, NULL, 0); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, aq_ret, + NULL, 0); +} + +/** + * ice_vc_config_rss_lut + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Configure the VF's RSS LUT + */ +static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + struct ice_vsi *vsi = NULL; + enum ice_status aq_ret; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vrl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + ret = ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE); + aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS; +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, aq_ret, + NULL, 0); +} + +/** + * ice_vc_get_stats_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to get VSI stats + */ +static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_eth_stats stats; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + memset(&stats, 0, sizeof(struct ice_eth_stats)); + ice_update_eth_stats(vsi); + + stats = vsi->eth_stats; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, aq_ret, + (u8 *)&stats, sizeof(stats)); +} + +/** + * ice_vc_ena_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to enable all or specific queue(s) + */ +static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* Enable only Rx rings, Tx rings were enabled by the FW when the + * Tx queue group list was configured and the context bits were + * programmed using ice_vsi_cfg_txqs + */ + if (ice_vsi_start_rx_rings(vsi)) + aq_ret = ICE_ERR_PARAM; + + /* Set flag to indicate that queues are enabled */ + if (!aq_ret) + set_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_dis_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to disable all or specific + * queue(s) + */ +static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_queue_select *vqs = + (struct virtchnl_queue_select *)msg; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && + !test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!vqs->rx_queues && !vqs->tx_queues) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop tx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + if (ice_vsi_stop_rx_rings(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop rx rings on VSI %d\n", + vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + } + + /* Clear enabled queues flag */ + if (!aq_ret) + clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_irq_map_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the IRQ to queue map + */ +static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_irq_map_info *irqmap_info = + (struct virtchnl_irq_map_info *)msg; + u16 vsi_id, vsi_q_id, vector_id; + struct virtchnl_vector_map *map; + struct ice_vsi *vsi = NULL; + struct ice_pf *pf = vf->pf; + enum ice_status aq_ret = 0; + unsigned long qmap; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < irqmap_info->num_vectors; i++) { + map = &irqmap_info->vecmap[i]; + + vector_id = map->vector_id; + vsi_id = map->vsi_id; + /* validate msg params */ + if (!(vector_id < pf->hw.func_caps.common_cap + .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + /* lookout for the invalid queue index */ + qmap = map->rxq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_rx++; + q_vector->rx.itr_idx = map->rxitr_idx; + vsi->rx_rings[vsi_q_id]->q_vector = q_vector; + } + + qmap = map->txq_map; + for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) { + struct ice_q_vector *q_vector; + + if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + q_vector = vsi->q_vectors[i]; + q_vector->num_ring_tx++; + q_vector->tx.itr_idx = map->txitr_idx; + vsi->tx_rings[vsi_q_id]->q_vector = q_vector; + } + } + + if (vsi) + ice_vsi_cfg_msix(vsi); +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, aq_ret, + NULL, 0); +} + +/** + * ice_vc_cfg_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * called from the VF to configure the Rx/Tx queues + */ +static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vsi_queue_config_info *qci = + (struct virtchnl_vsi_queue_config_info *)msg; + struct virtchnl_queue_pair_info *qpi; + enum ice_status aq_ret = 0; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = ice_find_vsi_from_id(vf->pf, qci->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < qci->num_queue_pairs; i++) { + qpi = &qci->qpair[i]; + if (qpi->txq.vsi_id != qci->vsi_id || + qpi->rxq.vsi_id != qci->vsi_id || + qpi->rxq.queue_id != qpi->txq.queue_id || + !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + /* copy Tx queue info from VF into VSI */ + vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[i]->count = qpi->txq.ring_len; + /* copy Rx queue info from VF into vsi */ + vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; + vsi->rx_rings[i]->count = qpi->rxq.ring_len; + if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->rx_buf_len = qpi->rxq.databuffer_size; + if (qpi->rxq.max_pkt_size >= (16 * 1024) || + qpi->rxq.max_pkt_size < 64) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + vsi->max_frame = qpi->rxq.max_pkt_size; + } + + /* VF can request to configure less than allocated queues + * or default allocated queues. So update the VSI with new number + */ + vsi->num_txq = qci->num_queue_pairs; + vsi->num_rxq = qci->num_queue_pairs; + + if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi)) + aq_ret = 0; + else + aq_ret = ICE_ERR_PARAM; + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, aq_ret, + NULL, 0); +} + +/** + * ice_is_vf_trusted + * @vf: pointer to the VF info + */ +static bool ice_is_vf_trusted(struct ice_vf *vf) +{ + return test_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); +} + +/** + * ice_can_vf_change_mac + * @vf: pointer to the VF info + * + * Return true if the VF is allowed to change its MAC filters, false otherwise + */ +static bool ice_can_vf_change_mac(struct ice_vf *vf) +{ + /* If the VF MAC address has been set administratively (via the + * ndo_set_vf_mac command), then deny permission to the VF to + * add/delete unicast MAC addresses, unless the VF is trusted + */ + if (vf->pf_set_mac && !ice_is_vf_trusted(vf)) + return false; + + return true; +} + +/** + * ice_vc_handle_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @set: true if mac filters are being set, false otherwise + * + * add guest mac address filter + */ +static int +ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) +{ + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_pf *pf = vf->pf; + enum virtchnl_ops vc_op; + enum ice_status ret; + LIST_HEAD(mac_list); + struct ice_vsi *vsi; + int mac_count = 0; + int i; + + if (set) + vc_op = VIRTCHNL_OP_ADD_ETH_ADDR; + else + vc_op = VIRTCHNL_OP_DEL_ETH_ADDR; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (set && !ice_is_vf_trusted(vf) && + (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) { + dev_err(&pf->pdev->dev, + "Can't add more MAC addresses, because VF is not trusted, switch the VF to trusted mode in order to add more functionalities\n"); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + + for (i = 0; i < al->num_elements; i++) { + u8 *maddr = al->list[i].addr; + + if (ether_addr_equal(maddr, vf->dflt_lan_addr.addr) || + is_broadcast_ether_addr(maddr)) { + if (set) { + /* VF is trying to add filters that the PF + * already added. Just continue. + */ + dev_info(&pf->pdev->dev, + "mac %pM already set for VF %d\n", + maddr, vf->vf_id); + continue; + } else { + /* VF can't remove dflt_lan_addr/bcast mac */ + dev_err(&pf->pdev->dev, + "can't remove mac %pM for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + } + + /* check for the invalid cases and bail if necessary */ + if (is_zero_ether_addr(maddr)) { + dev_err(&pf->pdev->dev, + "invalid mac %pM provided for VF %d\n", + maddr, vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + if (is_unicast_ether_addr(maddr) && + !ice_can_vf_change_mac(vf)) { + dev_err(&pf->pdev->dev, + "can't change unicast mac for untrusted VF %d\n", + vf->vf_id); + ret = ICE_ERR_PARAM; + goto handle_mac_exit; + } + + /* get here if maddr is multicast or if VF can change mac */ + if (ice_add_mac_to_list(vsi, &mac_list, al->list[i].addr)) { + ret = ICE_ERR_NO_MEMORY; + goto handle_mac_exit; + } + mac_count++; + } + + /* program the updated filter list */ + if (set) + ret = ice_add_mac(&pf->hw, &mac_list); + else + ret = ice_remove_mac(&pf->hw, &mac_list); + + if (ret) { + dev_err(&pf->pdev->dev, + "can't update mac filters for VF %d, error %d\n", + vf->vf_id, ret); + } else { + if (set) + vf->num_mac += mac_count; + else + vf->num_mac -= mac_count; + } + +handle_mac_exit: + ice_free_fltr_list(&pf->pdev->dev, &mac_list); + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, vc_op, ret, NULL, 0); +} + +/** + * ice_vc_add_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * add guest MAC address filter + */ +static int ice_vc_add_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, true); +} + +/** + * ice_vc_del_mac_addr_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove guest MAC address filter + */ +static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_handle_mac_addr_msg(vf, msg, false); +} + +/** + * ice_vc_request_qs_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * VFs get a default number of queues but can use this message to request a + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queue pairs via virtchnl message response to VF. + */ +static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + int req_queues = vfres->num_queue_pairs; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + int tx_rx_queue_left; + int cur_queues; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + cur_queues = pf->num_vf_qps; + tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); + if (req_queues <= 0) { + dev_err(&pf->pdev->dev, + "VF %d tried to request %d queues. Ignoring.\n", + vf->vf_id, req_queues); + } else if (req_queues > ICE_MAX_QS_PER_VF) { + dev_err(&pf->pdev->dev, + "VF %d tried to request more than %d queues.\n", + vf->vf_id, ICE_MAX_QS_PER_VF); + vfres->num_queue_pairs = ICE_MAX_QS_PER_VF; + } else if (req_queues - cur_queues > tx_rx_queue_left) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but only %d left.\n", + vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); + vfres->num_queue_pairs = tx_rx_queue_left + cur_queues; + } else { + /* request is successful, then reset VF */ + vf->num_req_qs = req_queues; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, + "VF %d granted request of %d queues.\n", + vf->vf_id, req_queues); + return 0; + } + +error_param: + /* send the response to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, + aq_ret, (u8 *)vfres, sizeof(*vfres)); +} + +/** + * ice_set_vf_port_vlan + * @netdev: network interface device structure + * @vf_id: VF identifier + * @vlan_id: VLAN id being set + * @qos: priority setting + * @vlan_proto: VLAN protocol + * + * program VF Port VLAN id and/or qos + */ +int +ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, + __be16 vlan_proto) +{ + u16 vlanprio = vlan_id | (qos << ICE_VLAN_PRIORITY_S); + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct ice_vsi *vsi; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + if (vlan_id > ICE_MAX_VLANID || qos > 7) { + dev_err(&pf->pdev->dev, "Invalid VF Parameters\n"); + return -EINVAL; + } + + if (vlan_proto != htons(ETH_P_8021Q)) { + dev_err(&pf->pdev->dev, "VF VLAN protocol is not supported\n"); + return -EPROTONOSUPPORT; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (le16_to_cpu(vsi->info.pvid) == vlanprio) { + /* duplicate request, so just return success */ + dev_info(&pf->pdev->dev, + "Duplicate pvid %d request\n", vlanprio); + return ret; + } + + /* If pvid, then remove all filters on the old VLAN */ + if (vsi->info.pvid) + ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) & + VLAN_VID_MASK)); + + if (vlan_id || qos) { + ret = ice_vsi_set_pvid(vsi, vlanprio); + if (ret) + goto error_set_pvid; + } else { + ice_vsi_kill_pvid(vsi); + } + + if (vlan_id) { + dev_info(&pf->pdev->dev, "Setting VLAN %d, QOS 0x%x on VF %d\n", + vlan_id, qos, vf_id); + + /* add new VLAN filter for each MAC */ + ret = ice_vsi_add_vlan(vsi, vlan_id); + if (ret) + goto error_set_pvid; + } + + /* The Port VLAN needs to be saved across resets the same as the + * default LAN MAC address. + */ + vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + +error_set_pvid: + return ret; +} + +/** + * ice_vc_process_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @add_v: Add VLAN if true, otherwise delete VLAN + * + * Process virtchnl op to add or remove programmed guest VLAN id + */ +static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) +{ + struct virtchnl_vlan_filter_list *vfl = + (struct virtchnl_vlan_filter_list *)msg; + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v && !ice_is_vf_trusted(vf) && + vf->num_vlan >= ICE_MAX_VLAN_PER_VF) { + dev_info(&pf->pdev->dev, + "VF is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n"); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + for (i = 0; i < vfl->num_elements; i++) { + if (vfl->vlan_id[i] > ICE_MAX_VLANID) { + aq_ret = ICE_ERR_PARAM; + dev_err(&pf->pdev->dev, + "invalid VF VLAN id %d\n", vfl->vlan_id[i]); + goto error_param; + } + } + + vsi = ice_find_vsi_from_id(vf->pf, vfl->vsi_id); + if (!vsi) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (vsi->info.pvid) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (ice_vsi_manage_vlan_stripping(vsi, add_v)) { + dev_err(&pf->pdev->dev, + "%sable VLAN stripping failed for VSI %i\n", + add_v ? "en" : "dis", vsi->vsi_num); + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + if (add_v) { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + if (!ice_vsi_add_vlan(vsi, vid)) { + vf->num_vlan++; + set_bit(vid, vsi->active_vlans); + + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) + if (ice_cfg_vlan_pruning(vsi, true)) + aq_ret = ICE_ERR_PARAM; + } else { + aq_ret = ICE_ERR_PARAM; + } + } + } else { + for (i = 0; i < vfl->num_elements; i++) { + u16 vid = vfl->vlan_id[i]; + + /* Make sure ice_vsi_kill_vlan is successful before + * updating VLAN information + */ + if (!ice_vsi_kill_vlan(vsi, vid)) { + vf->num_vlan--; + clear_bit(vid, vsi->active_vlans); + + /* Disable VLAN pruning when removing VLAN 0 */ + if (unlikely(!vid)) + ice_cfg_vlan_pruning(vsi, false); + } + } + } + +error_param: + /* send the response to the VF */ + if (add_v) + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, aq_ret, + NULL, 0); + else + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, aq_ret, + NULL, 0); +} + +/** + * ice_vc_add_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * Add and program guest VLAN id + */ +static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, true); +} + +/** + * ice_vc_remove_vlan_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * + * remove programmed guest VLAN id + */ +static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg) +{ + return ice_vc_process_vlan_msg(vf, msg, false); +} + +/** + * ice_vc_ena_vlan_stripping + * @vf: pointer to the VF info + * + * Enable VLAN header stripping for a given VF + */ +static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, true)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping + * @vf: pointer to the VF info + * + * Disable VLAN header stripping for a given VF + */ +static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) +{ + enum ice_status aq_ret = 0; + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + aq_ret = ICE_ERR_PARAM; + goto error_param; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + if (ice_vsi_manage_vlan_stripping(vsi, false)) + aq_ret = ICE_ERR_AQ_ERROR; + +error_param: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + aq_ret, NULL, 0); +} + +/** + * ice_vc_process_vf_msg - Process request from VF + * @pf: pointer to the PF structure + * @event: pointer to the AQ event + * + * called from the common asq/arq handler to + * process request from VF + */ +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 v_opcode = le32_to_cpu(event->desc.cookie_high); + s16 vf_id = le16_to_cpu(event->desc.retval); + u16 msglen = event->msg_len; + u8 *msg = event->msg_buf; + struct ice_vf *vf = NULL; + int err = 0; + + if (vf_id >= pf->num_alloc_vfs) { + err = -EINVAL; + goto error_handler; + } + + vf = &pf->vf[vf_id]; + + /* Check if VF is disabled. */ + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { + err = -EPERM; + goto error_handler; + } + + /* Perform basic checks on the msg */ + err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); + if (err) { + if (err == VIRTCHNL_ERR_PARAM) + err = -EPERM; + else + err = -EINVAL; + goto error_handler; + } + + /* Perform additional checks specific to RSS and Virtchnl */ + if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) { + struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; + + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) + err = -EINVAL; + } else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) { + struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; + + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) + err = -EINVAL; + } + +error_handler: + if (err) { + ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_PARAM, NULL, 0); + dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", + vf_id, v_opcode, msglen, err); + return; + } + + switch (v_opcode) { + case VIRTCHNL_OP_VERSION: + err = ice_vc_get_ver_msg(vf, msg); + break; + case VIRTCHNL_OP_GET_VF_RESOURCES: + err = ice_vc_get_vf_res_msg(vf, msg); + break; + case VIRTCHNL_OP_RESET_VF: + ice_vc_reset_vf_msg(vf); + break; + case VIRTCHNL_OP_ADD_ETH_ADDR: + err = ice_vc_add_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_ETH_ADDR: + err = ice_vc_del_mac_addr_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_VSI_QUEUES: + err = ice_vc_cfg_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_QUEUES: + err = ice_vc_ena_qs_msg(vf, msg); + ice_vc_notify_vf_link_state(vf); + break; + case VIRTCHNL_OP_DISABLE_QUEUES: + err = ice_vc_dis_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_REQUEST_QUEUES: + err = ice_vc_request_qs_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_IRQ_MAP: + err = ice_vc_cfg_irq_map_msg(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_KEY: + err = ice_vc_config_rss_key(vf, msg); + break; + case VIRTCHNL_OP_CONFIG_RSS_LUT: + err = ice_vc_config_rss_lut(vf, msg); + break; + case VIRTCHNL_OP_GET_STATS: + err = ice_vc_get_stats_msg(vf, msg); + break; + case VIRTCHNL_OP_ADD_VLAN: + err = ice_vc_add_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN: + err = ice_vc_remove_vlan_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + err = ice_vc_ena_vlan_stripping(vf); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + err = ice_vc_dis_vlan_stripping(vf); + break; + case VIRTCHNL_OP_UNKNOWN: + default: + dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n", + v_opcode, vf_id); + err = ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_NOT_IMPL, + NULL, 0); + break; + } + if (err) { + /* Helper function cares less about error return values here + * as it is busy with pending work. + */ + dev_info(&pf->pdev->dev, + "PF failed to honor VF %d, opcode %d\n, error %d\n", + vf_id, v_opcode, err); + } +} + +/** + * ice_get_vf_cfg + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ivi: VF configuration structure + * + * return VF configuration + */ +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + ivi->vf = vf_id; + ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr); + + /* VF configuration for VLAN and applicable QoS */ + ivi->vlan = le16_to_cpu(vsi->info.pvid) & ICE_VLAN_M; + ivi->qos = (le16_to_cpu(vsi->info.pvid) & ICE_PRIORITY_M) >> + ICE_VLAN_PRIORITY_S; + + ivi->trusted = vf->trusted; + ivi->spoofchk = vf->spoofchk; + if (!vf->link_forced) + ivi->linkstate = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE; + else + ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE; + ivi->max_tx_rate = vf->tx_rate; + ivi->min_tx_rate = 0; + return 0; +} + +/** + * ice_set_vf_spoofchk + * @netdev: network interface device structure + * @vf_id: VF identifier + * @ena: flag to enable or disable feature + * + * Enable or disable VF spoof checking + */ +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_ctx ctx = { 0 }; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int status; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (ena == vf->spoofchk) { + dev_dbg(&pf->pdev->dev, "VF spoofchk already %s\n", + ena ? "ON" : "OFF"); + return 0; + } + + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (ena) { + ctx.info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + ctx.info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M; + } + + status = ice_update_vsi(&pf->hw, vsi->idx, &ctx, NULL); + if (status) { + dev_dbg(&pf->pdev->dev, + "Error %d, failed to update VSI* parameters\n", status); + return -EIO; + } + + vf->spoofchk = ena; + vsi->info.sec_flags = ctx.info.sec_flags; + vsi->info.sw_flags2 = ctx.info.sw_flags2; + + return status; +} + +/** + * ice_set_vf_mac + * @netdev: network interface device structure + * @vf_id: VF identifier + * @mac: mac address + * + * program VF mac address + */ +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + int ret = 0; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + netdev_err(netdev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + netdev_err(netdev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { + netdev_err(netdev, "%pM not a valid unicast address\n", mac); + return -EINVAL; + } + + /* copy mac into dflt_lan_addr and trigger a VF reset. The reset + * flow will use the updated dflt_lan_addr and add a MAC filter + * using ice_add_mac. Also set pf_set_mac to indicate that the PF has + * set the MAC address for this VF. + */ + ether_addr_copy(vf->dflt_lan_addr.addr, mac); + vf->pf_set_mac = true; + netdev_info(netdev, + "mac on VF %d set to %pM\n. VF driver will be reinitialized\n", + vf_id, mac); + + ice_vc_dis_vf(vf); + return ret; +} + +/** + * ice_set_vf_trust + * @netdev: network interface device structure + * @vf_id: VF identifier + * @trusted: Boolean value to enable/disable trusted VF + * + * Enable or disable a given VF as trusted + */ +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + /* validate the request */ + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "invalid VF id: %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "VF %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + /* Check if already trusted */ + if (trusted == vf->trusted) + return 0; + + vf->trusted = trusted; + ice_vc_dis_vf(vf); + dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", + vf_id, trusted ? "" : "un"); + + return 0; +} + +/** + * ice_set_vf_link_state + * @netdev: network interface device structure + * @vf_id: VF identifier + * @link_state: required link state + * + * Set VF's link state, irrespective of physical link state status + */ +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + struct virtchnl_pf_event pfe = { 0 }; + struct ice_link_status *ls; + struct ice_vf *vf; + struct ice_hw *hw; + + if (vf_id >= pf->num_alloc_vfs) { + dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); + return -EINVAL; + } + + vf = &pf->vf[vf_id]; + hw = &pf->hw; + ls = &pf->hw.port_info->phy.link_info; + + if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { + dev_err(&pf->pdev->dev, "vf %d in reset. Try again.\n", vf_id); + return -EBUSY; + } + + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; + pfe.severity = PF_EVENT_SEVERITY_INFO; + + switch (link_state) { + case IFLA_VF_LINK_STATE_AUTO: + vf->link_forced = false; + vf->link_up = ls->link_info & ICE_AQ_LINK_UP; + break; + case IFLA_VF_LINK_STATE_ENABLE: + vf->link_forced = true; + vf->link_up = true; + break; + case IFLA_VF_LINK_STATE_DISABLE: + vf->link_forced = true; + vf->link_up = false; + break; + default: + return -EINVAL; + } + + if (vf->link_forced) + ice_set_pfe_link_forced(vf, &pfe, vf->link_up); + else + ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up); + + /* Notify the VF of its new link state */ + ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, + sizeof(pfe), NULL); + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h new file mode 100644 index 000000000000..10131e0180f9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -0,0 +1,173 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _ICE_VIRTCHNL_PF_H_ +#define _ICE_VIRTCHNL_PF_H_ +#include "ice.h" + +#define ICE_MAX_VLANID 4095 +#define ICE_VLAN_PRIORITY_S 12 +#define ICE_VLAN_M 0xFFF +#define ICE_PRIORITY_M 0x7000 + +/* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ +#define ICE_MAX_VLAN_PER_VF 8 +#define ICE_MAX_MACADDR_PER_VF 12 + +/* Malicious Driver Detection */ +#define ICE_DFLT_NUM_MDD_EVENTS_ALLOWED 3 +#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 + +/* Static VF transaction/status register def */ +#define VF_DEVICE_STATUS 0xAA +#define VF_TRANS_PENDING_M 0x20 + +/* Specific VF states */ +enum ice_vf_states { + ICE_VF_STATE_INIT = 0, + ICE_VF_STATE_ACTIVE, + ICE_VF_STATE_ENA, + ICE_VF_STATE_DIS, + ICE_VF_STATE_MC_PROMISC, + ICE_VF_STATE_UC_PROMISC, + /* state to indicate if PF needs to do vector assignment for VF. + * This needs to be set during first time VF initialization or later + * when VF asks for more Vectors through virtchnl OP. + */ + ICE_VF_STATE_CFG_INTR, + ICE_VF_STATES_NBITS +}; + +/* VF capabilities */ +enum ice_virtchnl_cap { + ICE_VIRTCHNL_VF_CAP_L2 = 0, + ICE_VIRTCHNL_VF_CAP_PRIVILEGE, +}; + +/* VF information structure */ +struct ice_vf { + struct ice_pf *pf; + + s16 vf_id; /* VF id in the PF space */ + u32 driver_caps; /* reported by VF driver */ + int first_vector_idx; /* first vector index of this VF */ + struct ice_sw *vf_sw_id; /* switch id the VF VSIs connect to */ + struct virtchnl_version_info vf_ver; + struct virtchnl_ether_addr dflt_lan_addr; + u16 port_vlan_id; + u8 pf_set_mac; /* VF MAC address set by VMM admin */ + u8 trusted; + u16 lan_vsi_idx; /* index into PF struct */ + u16 lan_vsi_num; /* ID as used by firmware */ + u64 num_mdd_events; /* number of mdd events detected */ + u64 num_inval_msgs; /* number of continuous invalid msgs */ + u64 num_valid_msgs; /* number of valid msgs detected */ + unsigned long vf_caps; /* vf's adv. capabilities */ + DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ + unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ + u8 link_forced; + u8 link_up; /* only valid if VF link is forced */ + u8 spoofchk; + u16 num_mac; + u16 num_vlan; + u8 num_req_qs; /* num of queue pairs requested by VF */ +}; + +#ifdef CONFIG_PCI_IOV +void ice_process_vflr_event(struct ice_pf *pf); +int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); +int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); +int ice_get_vf_cfg(struct net_device *netdev, int vf_id, + struct ifla_vf_info *ivi); + +void ice_free_vfs(struct ice_pf *pf); +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_vc_notify_link_state(struct ice_pf *pf); +void ice_vc_notify_reset(struct ice_pf *pf); +bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); + +int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, + u16 vlan_id, u8 qos, __be16 vlan_proto); + +int ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); + +int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); + +int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); + +int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); +#else /* CONFIG_PCI_IOV */ +#define ice_process_vflr_event(pf) do {} while (0) +#define ice_free_vfs(pf) do {} while (0) +#define ice_vc_process_vf_msg(pf, event) do {} while (0) +#define ice_vc_notify_link_state(pf) do {} while (0) +#define ice_vc_notify_reset(pf) do {} while (0) + +static inline bool +ice_reset_all_vfs(struct ice_pf __always_unused *pf, + bool __always_unused is_vflr) +{ + return true; +} + +static inline int +ice_sriov_configure(struct pci_dev __always_unused *pdev, + int __always_unused num_vfs) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_mac(struct net_device __always_unused *netdev, + int __always_unused vf_id, u8 __always_unused *mac) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_get_vf_cfg(struct net_device __always_unused *netdev, + int __always_unused vf_id, + struct ifla_vf_info __always_unused *ivi) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_trust(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused trusted) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_port_vlan(struct net_device __always_unused *netdev, + int __always_unused vf_id, u16 __always_unused vid, + u8 __always_unused qos, __be16 __always_unused v_proto) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_spoofchk(struct net_device __always_unused *netdev, + int __always_unused vf_id, bool __always_unused ena) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_link_state(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused link_state) +{ + return -EOPNOTSUPP; +} + +static inline int +ice_set_vf_bw(struct net_device __always_unused *netdev, + int __always_unused vf_id, int __always_unused min_tx_rate, + int __always_unused max_tx_rate) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_VIRTCHNL_PF_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 5414685189ce..ca6b0c458e4a 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -8,7 +8,8 @@ obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ - ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o + ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ + ixgbe_xsk.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 5c6fd42e90ed..7a7679e7be84 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -228,13 +228,17 @@ struct ixgbe_tx_buffer { struct ixgbe_rx_buffer { struct sk_buff *skb; 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 ixgbe_queue_stats { @@ -271,6 +275,7 @@ enum ixgbe_ring_state_t { __IXGBE_TX_DETECT_HANG, __IXGBE_HANG_CHECK_ARMED, __IXGBE_TX_XDP_RING, + __IXGBE_TX_DISABLED, }; #define ring_uses_build_skb(ring) \ @@ -347,6 +352,10 @@ struct ixgbe_ring { struct ixgbe_rx_queue_stats rx_stats; }; struct xdp_rxq_info xdp_rxq; + struct xdp_umem *xsk_umem; + struct zero_copy_allocator zca; /* ZC allocator anchor */ + u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ + u16 rx_buf_len; } ____cacheline_internodealigned_in_smp; enum ixgbe_ring_f_enum { @@ -764,6 +773,11 @@ struct ixgbe_adapter { #ifdef CONFIG_XFRM_OFFLOAD struct ixgbe_ipsec *ipsec; #endif /* CONFIG_XFRM_OFFLOAD */ + + /* AF_XDP zero-copy */ + struct xdp_umem **xsk_umems; + u16 num_xsk_umems_used; + u16 num_xsk_umems; }; static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 970f71d5da04..0bd1294ba517 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3485,17 +3485,6 @@ 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_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index d361f570ca37..62e6499e4146 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1055,7 +1055,7 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) int txr_remaining = adapter->num_tx_queues; int xdp_remaining = adapter->num_xdp_queues; int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0; - int err; + int err, i; /* only one q_vector if MSI-X is disabled. */ if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) @@ -1097,6 +1097,21 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) xdp_idx += xqpv; } + for (i = 0; i < adapter->num_rx_queues; i++) { + if (adapter->rx_ring[i]) + adapter->rx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->tx_ring[i]) + adapter->tx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + if (adapter->xdp_ring[i]) + adapter->xdp_ring[i]->ring_idx = i; + } + return 0; err_out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 140e87a10ff5..51268772a999 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -34,12 +34,14 @@ #include <net/tc_act/tc_mirred.h> #include <net/vxlan.h> #include <net/mpls.h> +#include <net/xdp_sock.h> #include "ixgbe.h" #include "ixgbe_common.h" #include "ixgbe_dcb_82599.h" #include "ixgbe_sriov.h" #include "ixgbe_model.h" +#include "ixgbe_txrx_common.h" char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = @@ -893,8 +895,8 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, } } -static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, - u64 qmask) +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, + u64 qmask) { u32 mask; @@ -1673,9 +1675,9 @@ static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; u32 flags = rx_ring->q_vector->adapter->flags; @@ -1708,8 +1710,8 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, skb->protocol = eth_type_trans(skb, dev); } -static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, - struct sk_buff *skb) +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) { napi_gro_receive(&q_vector->napi, skb); } @@ -1868,9 +1870,9 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, * * Returns true if an error was encountered and skb was freed. **/ -static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, - union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *netdev = rx_ring->netdev; @@ -2186,14 +2188,6 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED BIT(0) -#define IXGBE_XDP_TX BIT(1) -#define IXGBE_XDP_REDIR BIT(2) - -static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_frame *xdpf); - static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, struct xdp_buff *xdp) @@ -3167,7 +3161,11 @@ int ixgbe_poll(struct napi_struct *napi, int budget) #endif ixgbe_for_each_ring(ring, q_vector->tx) { - if (!ixgbe_clean_tx_irq(q_vector, ring, budget)) + bool wd = ring->xsk_umem ? + ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : + ixgbe_clean_tx_irq(q_vector, ring, budget); + + if (!wd) clean_complete = false; } @@ -3183,7 +3181,10 @@ int ixgbe_poll(struct napi_struct *napi, int budget) per_ring_budget = budget; ixgbe_for_each_ring(ring, q_vector->rx) { - int cleaned = ixgbe_clean_rx_irq(q_vector, ring, + int cleaned = ring->xsk_umem ? + ixgbe_clean_rx_irq_zc(q_vector, ring, + per_ring_budget) : + ixgbe_clean_rx_irq(q_vector, ring, per_ring_budget); work_done += cleaned; @@ -3196,11 +3197,13 @@ int ixgbe_poll(struct napi_struct *napi, int budget) return budget; /* all work done, exit the polling mode */ - napi_complete_done(napi, work_done); - if (adapter->rx_itr_setting & 1) - ixgbe_set_itr(q_vector); - if (!test_bit(__IXGBE_DOWN, &adapter->state)) - ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx)); + if (likely(napi_complete_done(napi, work_done))) { + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + BIT_ULL(q_vector->v_idx)); + } return min(work_done, budget - 1); } @@ -3473,6 +3476,10 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, u32 txdctl = IXGBE_TXDCTL_ENABLE; u8 reg_idx = ring->reg_idx; + ring->xsk_umem = NULL; + if (ring_is_xdp(ring)) + ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + /* disable queue to avoid issues while updating state */ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); IXGBE_WRITE_FLUSH(hw); @@ -3577,12 +3584,18 @@ static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) else mtqc |= IXGBE_MTQC_64VF; } else { - if (tcs > 4) + if (tcs > 4) { mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; - else if (tcs > 1) + } else if (tcs > 1) { mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; - else - mtqc = IXGBE_MTQC_64Q_1PB; + } else { + u8 max_txq = adapter->num_tx_queues + + adapter->num_xdp_queues; + if (max_txq > 63) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else + mtqc = IXGBE_MTQC_64Q_1PB; + } } IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); @@ -3705,10 +3718,27 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; /* configure the packet buffer length */ - if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) + if (rx_ring->xsk_umem) { + u32 xsk_buf_len = rx_ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + + /* If the MAC support setting RXDCTL.RLPML, the + * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and + * RXDCTL.RLPML is set to the actual UMEM buffer + * size. If not, then we are stuck with a 1k buffer + * size resolution. In this case frames larger than + * the UMEM buffer size viewed in a 1k resolution will + * be dropped. + */ + if (hw->mac.type != ixgbe_mac_82599EB) + srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) { srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; - else + } else { srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } /* configure descriptor type */ srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; @@ -4031,6 +4061,19 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->xsk_umem = ixgbe_xsk_umem(adapter, ring); + if (ring->xsk_umem) { + ring->zca.free = ixgbe_zca_free; + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_ZERO_COPY, + &ring->zca)); + + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL)); + } + /* disable queue to avoid use of these values while updating state */ rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); rxdctl &= ~IXGBE_RXDCTL_ENABLE; @@ -4080,6 +4123,17 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } + if (ring->xsk_umem && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN; + + ring->rx_buf_len = xsk_buf_len; + } + /* initialize rx_buffer_info */ memset(ring->rx_buffer_info, 0, sizeof(struct ixgbe_rx_buffer) * ring->count); @@ -4093,7 +4147,10 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); ixgbe_rx_desc_queue_enable(adapter, ring); - ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); + if (ring->xsk_umem) + ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); + else + ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); } static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) @@ -5173,6 +5230,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct hlist_node *node2; struct ixgbe_fdir_filter *filter; + u64 action; spin_lock(&adapter->fdir_perfect_lock); @@ -5181,12 +5239,17 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { + action = filter->action; + if (action != IXGBE_FDIR_DROP_QUEUE && action != 0) + action = + (action >> ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF) - 1; + ixgbe_fdir_write_perfect_filter_82599(hw, &filter->filter, filter->sw_idx, - (filter->action == IXGBE_FDIR_DROP_QUEUE) ? + (action == IXGBE_FDIR_DROP_QUEUE) ? IXGBE_FDIR_DROP_QUEUE : - adapter->rx_ring[filter->action]->reg_idx); + adapter->rx_ring[action]->reg_idx); } spin_unlock(&adapter->fdir_perfect_lock); @@ -5201,6 +5264,11 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) u16 i = rx_ring->next_to_clean; struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; + if (rx_ring->xsk_umem) { + ixgbe_xsk_clean_rx_ring(rx_ring); + goto skip_free; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { if (rx_buffer->skb) { @@ -5239,6 +5307,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) } } +skip_free: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -5883,6 +5952,11 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) u16 i = tx_ring->next_to_clean; struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + if (tx_ring->xsk_umem) { + ixgbe_xsk_clean_tx_ring(tx_ring); + goto out; + } + while (i != tx_ring->next_to_use) { union ixgbe_adv_tx_desc *eop_desc, *tx_desc; @@ -5934,6 +6008,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) if (!ring_is_xdp(tx_ring)) netdev_tx_reset_queue(txring_txq(tx_ring)); +out: /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -6434,7 +6509,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); int ring_node = -1; - int size, err; + int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; @@ -6471,13 +6546,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->queue_index) < 0) goto err; - err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err) { - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - goto err; - } - rx_ring->xdp_prog = adapter->xdp_prog; return 0; @@ -8102,9 +8170,6 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) return __ixgbe_maybe_stop_tx(tx_ring, size); } -#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ - IXGBE_TXD_CMD_RS) - static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, const u8 hdr_len) @@ -8457,8 +8522,8 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, } #endif -static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_frame *xdpf) +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; struct ixgbe_tx_buffer *tx_buffer; @@ -8680,6 +8745,8 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state))) + return NETDEV_TX_BUSY; return ixgbe_xmit_frame_ring(skb, adapter, tx_ring); } @@ -10191,12 +10258,19 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; + case XDP_QUERY_XSK_UMEM: + return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem, + xdp->xsk.queue_id); + case XDP_SETUP_XSK_UMEM: + return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, + xdp->xsk.queue_id); + default: return -EINVAL; } } -static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) { /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. @@ -10226,6 +10300,9 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, if (unlikely(!ring)) return -ENXIO; + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state))) + return -ENXIO; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -10287,8 +10364,162 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, + .ndo_xsk_async_xmit = ixgbe_xsk_async_xmit, }; +static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = tx_ring->reg_idx; + int wait_loop; + u32 txdctl; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + + /* delay mechanism from ixgbe_disable_tx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + + if (!(txdctl & IXGBE_TXDCTL_ENABLE)) + return; + } + + e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_disable_txr(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + set_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + ixgbe_disable_txr_hw(adapter, tx_ring); +} + +static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = rx_ring->reg_idx; + int wait_loop; + u32 rxdctl; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + rxdctl |= IXGBE_RXDCTL_SWFLSH; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + + /* RXDCTL.EN may not change on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* delay mechanism from ixgbe_disable_rx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + + if (!(rxdctl & IXGBE_RXDCTL_ENABLE)) + return; + } + + e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring) +{ + memset(&tx_ring->stats, 0, sizeof(tx_ring->stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) +{ + memset(&rx_ring->stats, 0, sizeof(rx_ring->stats)); + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); +} + +/** + * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function disables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + ixgbe_disable_txr(adapter, tx_ring); + if (xdp_ring) + ixgbe_disable_txr(adapter, xdp_ring); + ixgbe_disable_rxr_hw(adapter, rx_ring); + + if (xdp_ring) + synchronize_sched(); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + ixgbe_clean_tx_ring(tx_ring); + if (xdp_ring) + ixgbe_clean_tx_ring(xdp_ring); + ixgbe_clean_rx_ring(rx_ring); + + ixgbe_reset_txr_stats(tx_ring); + if (xdp_ring) + ixgbe_reset_txr_stats(xdp_ring); + ixgbe_reset_rxr_stats(rx_ring); +} + +/** + * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function enables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + + ixgbe_configure_tx_ring(adapter, tx_ring); + if (xdp_ring) + ixgbe_configure_tx_ring(adapter, xdp_ring); + ixgbe_configure_rx_ring(adapter, rx_ring); + + clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); +} + /** * ixgbe_enumerate_functions - Get the number of ports this device has * @adapter: adapter structure diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h new file mode 100644 index 000000000000..53d4089f5644 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef _IXGBE_TXRX_COMMON_H_ +#define _IXGBE_TXRX_COMMON_H_ + +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) + +#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ + IXGBE_TXD_CMD_RS) + +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf); +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb); +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring); +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask); + +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring); +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); + +struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring); +int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, + u16 qid); +int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, + u16 qid); + +void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); + +void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count); +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget); +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring); +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget); +int ixgbe_xsk_async_xmit(struct net_device *dev, u32 queue_id); +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); + +#endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c new file mode 100644 index 000000000000..65c3e2c979d4 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -0,0 +1,801 @@ +// 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 "ixgbe.h" +#include "ixgbe_txrx_common.h" + +struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + bool xdp_on = READ_ONCE(adapter->xdp_prog); + int qid = ring->ring_idx; + + if (!adapter->xsk_umems || !adapter->xsk_umems[qid] || + qid >= adapter->num_xsk_umems || !xdp_on) + return NULL; + + return adapter->xsk_umems[qid]; +} + +static int ixgbe_alloc_xsk_umems(struct ixgbe_adapter *adapter) +{ + if (adapter->xsk_umems) + return 0; + + adapter->num_xsk_umems_used = 0; + adapter->num_xsk_umems = adapter->num_rx_queues; + adapter->xsk_umems = kcalloc(adapter->num_xsk_umems, + sizeof(*adapter->xsk_umems), + GFP_KERNEL); + if (!adapter->xsk_umems) { + adapter->num_xsk_umems = 0; + return -ENOMEM; + } + + return 0; +} + +static int ixgbe_add_xsk_umem(struct ixgbe_adapter *adapter, + struct xdp_umem *umem, + u16 qid) +{ + int err; + + err = ixgbe_alloc_xsk_umems(adapter); + if (err) + return err; + + adapter->xsk_umems[qid] = umem; + adapter->num_xsk_umems_used++; + + return 0; +} + +static void ixgbe_remove_xsk_umem(struct ixgbe_adapter *adapter, u16 qid) +{ + adapter->xsk_umems[qid] = NULL; + adapter->num_xsk_umems_used--; + + if (adapter->num_xsk_umems == 0) { + kfree(adapter->xsk_umems); + adapter->xsk_umems = NULL; + adapter->num_xsk_umems = 0; + } +} + +static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter, + struct xdp_umem *umem) +{ + struct device *dev = &adapter->pdev->dev; + unsigned int i, j; + dma_addr_t dma; + + for (i = 0; i < umem->npgs; i++) { + dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL, IXGBE_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, IXGBE_RX_DMA_ATTR); + umem->pages[i].dma = 0; + } + + return -1; +} + +static void ixgbe_xsk_umem_dma_unmap(struct ixgbe_adapter *adapter, + struct xdp_umem *umem) +{ + struct device *dev = &adapter->pdev->dev; + unsigned int i; + + for (i = 0; i < umem->npgs; i++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, IXGBE_RX_DMA_ATTR); + + umem->pages[i].dma = 0; + } +} + +static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, + struct xdp_umem *umem, + u16 qid) +{ + struct xdp_umem_fq_reuse *reuseq; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (adapter->xsk_umems) { + if (qid >= adapter->num_xsk_umems) + return -EINVAL; + if (adapter->xsk_umems[qid]) + return -EBUSY; + } + + reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count); + if (!reuseq) + return -ENOMEM; + + xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); + + err = ixgbe_xsk_umem_dma_map(adapter, umem); + if (err) + return err; + + if_running = netif_running(adapter->netdev) && + READ_ONCE(adapter->xdp_prog); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + err = ixgbe_add_xsk_umem(adapter, umem, qid); + + if (if_running) + ixgbe_txrx_ring_enable(adapter, qid); + + return err; +} + +static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) +{ + bool if_running; + + if (!adapter->xsk_umems || qid >= adapter->num_xsk_umems || + !adapter->xsk_umems[qid]) + return -EINVAL; + + if_running = netif_running(adapter->netdev) && + READ_ONCE(adapter->xdp_prog); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + ixgbe_xsk_umem_dma_unmap(adapter, adapter->xsk_umems[qid]); + ixgbe_remove_xsk_umem(adapter, qid); + + if (if_running) + ixgbe_txrx_ring_enable(adapter, qid); + + return 0; +} + +int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, + u16 qid) +{ + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (adapter->xsk_umems) { + if (qid >= adapter->num_xsk_umems) + return -EINVAL; + *umem = adapter->xsk_umems[qid]; + return 0; + } + + *umem = NULL; + return 0; +} + +int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, + u16 qid) +{ + return umem ? ixgbe_xsk_umem_enable(adapter, umem, qid) : + ixgbe_xsk_umem_disable(adapter, qid); +} + +static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; + u32 act; + + rcu_read_lock(); + 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: + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) { + result = IXGBE_XDP_CONSUMED; + break; + } + result = ixgbe_xmit_xdp_ring(adapter, xdpf); + break; + case XDP_REDIRECT: + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED; + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fallthrough */ + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } + rcu_read_unlock(); + return result; +} + +static struct +ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring, + unsigned int size) +{ + struct ixgbe_rx_buffer *bi; + + bi = &rx_ring->rx_buffer_info[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; +} + +static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *obi) +{ + 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; + struct ixgbe_rx_buffer *nbi; + + nbi = &rx_ring->rx_buffer_info[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 */ + nbi->dma = obi->dma & mask; + nbi->dma += hr; + + nbi->addr = (void *)((unsigned long)obi->addr & mask); + nbi->addr += hr; + + nbi->handle = obi->handle & mask; + nbi->handle += rx_ring->xsk_umem->headroom; + + obi->addr = NULL; + obi->skb = NULL; +} + +void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) +{ + struct ixgbe_rx_buffer *bi; + struct ixgbe_ring *rx_ring; + u64 hr, mask; + u16 nta; + + rx_ring = container_of(alloc, struct ixgbe_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_buffer_info; + + 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; +} + +static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + void *addr = bi->addr; + u64 handle, hr; + + if (addr) + return true; + + if (!xsk_umem_peek_addr(umem, &handle)) { + rx_ring->rx_stats.alloc_rx_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; +} + +static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + u64 handle, hr; + + if (!xsk_umem_peek_addr_rq(umem, &handle)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + handle &= rx_ring->xsk_umem->chunk_mask; + + 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_rq(umem); + return true; +} + +static __always_inline bool +__ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count, + bool alloc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi)) +{ + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + bool ok = true; + + /* nothing to do */ + if (!cleaned_count) + return true; + + rx_desc = IXGBE_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + if (!alloc(rx_ring, bi)) { + ok = false; + break; + } + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + rx_ring->rx_buf_len, + DMA_BIDIRECTIONAL); + + /* Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBE_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, rx_ring->tail); + } + + return ok; +} + +void ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) +{ + __ixgbe_alloc_rx_buffers_zc(rx_ring, count, + ixgbe_alloc_buffer_slow_zc); +} + +static bool ixgbe_alloc_rx_buffers_fast_zc(struct ixgbe_ring *rx_ring, + u16 count) +{ + return __ixgbe_alloc_rx_buffers_zc(rx_ring, count, + ixgbe_alloc_buffer_zc); +} + +static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_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); + + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + return skb; +} + +static void ixgbe_inc_ntc(struct ixgbe_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(IXGBE_RX_DESC(rx_ring, ntc)); +} + +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct ixgbe_adapter *adapter = q_vector->adapter; + u16 cleaned_count = ixgbe_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 < budget)) { + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + unsigned int size; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { + failure = failure || + !ixgbe_alloc_rx_buffers_fast_zc(rx_ring, + cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + bi = ixgbe_get_rx_buffer_zc(rx_ring, size); + + if (unlikely(!ixgbe_test_staterr(rx_desc, + IXGBE_RXD_STAT_EOP))) { + struct ixgbe_rx_buffer *next_bi; + + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + ixgbe_inc_ntc(rx_ring); + next_bi = + &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + next_bi->skb = ERR_PTR(-EINVAL); + continue; + } + + if (unlikely(bi->skb)) { + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + ixgbe_inc_ntc(rx_ring); + continue; + } + + 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 = ixgbe_run_xdp_zc(adapter, rx_ring, &xdp); + + if (xdp_res) { + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; + bi->addr = NULL; + bi->skb = NULL; + } else { + ixgbe_reuse_rx_buffer_zc(rx_ring, bi); + } + total_rx_packets++; + total_rx_bytes += size; + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + continue; + } + + /* XDP_PASS path */ + skb = ixgbe_construct_skb_zc(rx_ring, bi, &xdp); + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + break; + } + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + + if (eth_skb_pad(skb)) + continue; + + total_rx_bytes += skb->len; + total_rx_packets++; + + ixgbe_process_skb_fields(rx_ring, rx_desc, skb); + ixgbe_rx_skb(q_vector, skb); + } + + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + + 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); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return failure ? budget : (int)total_rx_packets; +} + +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) +{ + u16 i = rx_ring->next_to_clean; + struct ixgbe_rx_buffer *bi = &rx_ring->rx_buffer_info[i]; + + while (i != rx_ring->next_to_alloc) { + xsk_umem_fq_reuse(rx_ring->xsk_umem, bi->handle); + i++; + bi++; + if (i == rx_ring->count) { + i = 0; + bi = rx_ring->rx_buffer_info; + } + } +} + +static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) +{ + union ixgbe_adv_tx_desc *tx_desc = NULL; + struct ixgbe_tx_buffer *tx_bi; + bool work_done = true; + u32 len, cmd_type; + dma_addr_t dma; + + while (budget-- > 0) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + 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_buffer_info[xdp_ring->next_to_use]; + tx_bi->bytecount = len; + tx_bi->xdpf = NULL; + + tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + xdp_ring->next_to_use++; + if (xdp_ring->next_to_use == xdp_ring->count) + xdp_ring->next_to_use = 0; + } + + if (tx_desc) { + ixgbe_xdp_ring_update_tail(xdp_ring); + xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + } + + return !!budget && work_done; +} + +static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring, + struct ixgbe_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); +} + +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget) +{ + unsigned int total_packets = 0, total_bytes = 0; + u32 i = tx_ring->next_to_clean, xsk_frames = 0; + unsigned int budget = q_vector->tx.work_limit; + struct xdp_umem *umem = tx_ring->xsk_umem; + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_bi; + bool xmit_done; + + tx_bi = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + total_bytes += tx_bi->bytecount; + total_packets += tx_bi->gso_segs; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + total_bytes += tx_bi->bytecount; + + tx_bi++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_bi = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + 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); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); + + xmit_done = ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); + return budget > 0 && xmit_done; +} + +int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!READ_ONCE(adapter->xdp_prog)) + return -ENXIO; + + if (qid >= adapter->num_xdp_queues) + return -ENXIO; + + if (!adapter->xsk_umems || !adapter->xsk_umems[qid]) + return -ENXIO; + + ring = adapter->xdp_ring[qid]; + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + u64 eics = BIT_ULL(ring->q_vector->v_idx); + + ixgbe_irq_rearm_queues(adapter, eics); + } + + return 0; +} + +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) +{ + u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; + struct xdp_umem *umem = tx_ring->xsk_umem; + struct ixgbe_tx_buffer *tx_bi; + u32 xsk_frames = 0; + + while (ntc != ntu) { + tx_bi = &tx_ring->tx_buffer_info[ntc]; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + + ntc++; + if (ntc == tx_ring->count) + ntc = 0; + } + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); +} diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index 997cea675a37..e8a3231be0bf 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -21,7 +21,6 @@ static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, 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 */ @@ -38,16 +37,14 @@ static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, 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); + ret = hw->mbx.ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE); if (ret) goto out; - msglen = sizeof(msgbuf[0]) * 2; - ret = hw->mbx.ops.read_posted(hw, msgbuf, msglen); + ret = hw->mbx.ops.read_posted(hw, msgbuf, 2); if (ret) goto out; @@ -80,11 +77,11 @@ static int ixgbevf_ipsec_del_pf_sa(struct ixgbevf_adapter *adapter, int pfsa) spin_lock_bh(&adapter->mbx_lock); - err = hw->mbx.ops.write_posted(hw, msgbuf, sizeof(msgbuf)); + err = hw->mbx.ops.write_posted(hw, msgbuf, 2); if (err) goto out; - err = hw->mbx.ops.read_posted(hw, msgbuf, sizeof(msgbuf)); + err = hw->mbx.ops.read_posted(hw, msgbuf, 2); if (err) goto out; @@ -470,7 +467,7 @@ int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, } sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; - if (unlikely(sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + 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; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2373cd41a625..14f9679c957c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -1755,7 +1755,7 @@ static void mvpp2_txq_desc_put(struct mvpp2_tx_queue *txq) } /* Set Tx descriptors fields relevant for CSUM calculation */ -static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto, +static u32 mvpp2_txq_desc_csum(int l3_offs, __be16 l3_proto, int ip_hdr_len, int l4_proto) { u32 command; @@ -2645,14 +2645,15 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; u8 l4_proto; + __be16 l3_proto = vlan_get_protocol(skb); - if (skb->protocol == htons(ETH_P_IP)) { + if (l3_proto == htons(ETH_P_IP)) { struct iphdr *ip4h = ip_hdr(skb); /* Calculate IPv4 checksum and L4 checksum */ ip_hdr_len = ip4h->ihl; l4_proto = ip4h->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (l3_proto == htons(ETH_P_IPV6)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); /* Read l4_protocol from one of IPv6 extra headers */ @@ -2664,7 +2665,7 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) } return mvpp2_txq_desc_csum(skb_network_offset(skb), - skb->protocol, ip_hdr_len, l4_proto); + l3_proto, ip_hdr_len, l4_proto); } return MVPP2_TXD_L4_CSUM_NOT | MVPP2_TXD_IP_CSUM_DISABLE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index ef7a44eb9adb..1d743bd5d212 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -54,6 +54,7 @@ #include "en_stats.h" #include "en/fs.h" +extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; #define MLX5E_METADATA_ETHER_TYPE (0x8CE4) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index bbf69e859b78..1431232c9a09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -16,6 +16,8 @@ struct mlx5e_tc_table { DECLARE_HASHTABLE(mod_hdr_tbl, 8); DECLARE_HASHTABLE(hairpin_tbl, 8); + + struct notifier_block netdevice_nb; }; struct mlx5e_flow_table { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 45cdde694d20..8657e0f26995 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -543,8 +543,11 @@ static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv, rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); - netdev_err(priv->netdev, "%s: add rule(filter id=%d, rq idx=%d) failed, err=%d\n", - __func__, arfs_rule->filter_id, arfs_rule->rxq, err); + priv->channel_stats[arfs_rule->rxq].rq.arfs_err++; + mlx5e_dbg(HW, priv, + "%s: add rule(filter id=%d, rq idx=%d, ip proto=0x%x) failed,err=%d\n", + __func__, arfs_rule->filter_id, arfs_rule->rxq, + tuple->ip_proto, err); } out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 35aca9a8e3d6..bc034958c846 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4318,7 +4318,7 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static const struct net_device_ops mlx5e_netdev_ops = { +const struct net_device_ops mlx5e_netdev_ops = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 90c7607b1f44..b7d4896c7c7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -93,6 +93,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) }, @@ -170,6 +171,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_cache_busy += rq_stats->cache_busy; s->rx_cache_waive += rq_stats->cache_waive; s->rx_congst_umr += rq_stats->congst_umr; + s->rx_arfs_err += rq_stats->arfs_err; s->ch_events += ch_stats->events; s->ch_poll += ch_stats->poll; s->ch_arm += ch_stats->arm; @@ -1161,6 +1163,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) }, }; static const struct counter_desc sq_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index a5fb3dc27f50..77f74ce11280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -106,6 +106,7 @@ struct mlx5e_sw_stats { u64 rx_cache_busy; u64 rx_cache_waive; u64 rx_congst_umr; + u64 rx_arfs_err; u64 ch_events; u64 ch_poll; u64 ch_arm; @@ -202,6 +203,7 @@ struct mlx5e_rq_stats { u64 cache_busy; u64 cache_waive; u64 congst_umr; + u64 arfs_err; }; struct mlx5e_sq_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 82723a0e509a..6de21d9f4fad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -532,7 +532,8 @@ static struct mlx5e_hairpin_entry *mlx5e_hairpin_get(struct mlx5e_priv *priv, #define UNKNOWN_MATCH_PRIO 8 static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, u8 *match_prio) + struct mlx5_flow_spec *spec, u8 *match_prio, + struct netlink_ext_ack *extack) { void *headers_c, *headers_v; u8 prio_val, prio_mask = 0; @@ -540,8 +541,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, #ifdef CONFIG_MLX5_CORE_EN_DCB if (priv->dcbx_dp.trust_state != MLX5_QPTS_TRUST_PCP) { - netdev_warn(priv->netdev, - "only PCP trust state supported for hairpin\n"); + NL_SET_ERR_MSG_MOD(extack, + "only PCP trust state supported for hairpin"); return -EOPNOTSUPP; } #endif @@ -557,8 +558,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, if (!vlan_present || !prio_mask) { prio_val = UNKNOWN_MATCH_PRIO; } else if (prio_mask != 0x7) { - netdev_warn(priv->netdev, - "masked priority match not supported for hairpin\n"); + NL_SET_ERR_MSG_MOD(extack, + "masked priority match not supported for hairpin"); return -EOPNOTSUPP; } @@ -568,7 +569,8 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { int peer_ifindex = parse_attr->mirred_ifindex; struct mlx5_hairpin_params params; @@ -583,12 +585,13 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex); if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) { - netdev_warn(priv->netdev, "hairpin is not supported\n"); + NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported"); return -EOPNOTSUPP; } peer_id = MLX5_CAP_GEN(peer_mdev, vhca_id); - err = mlx5e_hairpin_get_prio(priv, &parse_attr->spec, &match_prio); + err = mlx5e_hairpin_get_prio(priv, &parse_attr->spec, &match_prio, + extack); if (err) return err; hpe = mlx5e_hairpin_get(priv, peer_id, match_prio); @@ -677,7 +680,8 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, static struct mlx5_flow_handle * mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_nic_flow_attr *attr = flow->nic_attr; struct mlx5_core_dev *dev = priv->mdev; @@ -694,7 +698,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, int err, dest_ix = 0; if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) { - err = mlx5e_hairpin_flow_add(priv, flow, parse_attr); + err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); if (err) { rule = ERR_PTR(err); goto err_add_hairpin_flow; @@ -753,6 +757,8 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, MLX5E_TC_TABLE_NUM_GROUPS, MLX5E_TC_FT_LEVEL, 0); if (IS_ERR(priv->fs.tc.t)) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to create tc offload table\n"); netdev_err(priv->netdev, "Failed to create tc offload table\n"); rule = ERR_CAST(priv->fs.tc.t); @@ -819,12 +825,14 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct ip_tunnel_info *tun_info, struct net_device *mirred_dev, struct net_device **encap_dev, - struct mlx5e_tc_flow *flow); + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack); static struct mlx5_flow_handle * mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->esw_attr; @@ -838,7 +846,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, out_dev = __dev_get_by_index(dev_net(priv->netdev), attr->parse_attr->mirred_ifindex); err = mlx5e_attach_encap(priv, &parse_attr->tun_info, - out_dev, &encap_dev, flow); + out_dev, &encap_dev, flow, extack); if (err) { rule = ERR_PTR(err); if (err != -EAGAIN) @@ -1105,6 +1113,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f) { + struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, @@ -1133,6 +1142,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) parse_vxlan_attr(spec, f); else { + NL_SET_ERR_MSG_MOD(extack, + "port isn't an offloaded vxlan udp dport"); netdev_warn(priv->netdev, "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst)); return -EOPNOTSUPP; @@ -1149,6 +1160,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, udp_sport, ntohs(key->src)); } else { /* udp dst port must be given */ vxlan_match_offload_err: + NL_SET_ERR_MSG_MOD(extack, + "IP tunnel decap offload supported only for vxlan, must set UDP dport"); netdev_warn(priv->netdev, "IP tunnel decap offload supported only for vxlan, must set UDP dport\n"); return -EOPNOTSUPP; @@ -1225,6 +1238,16 @@ vxlan_match_offload_err: MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + + if (mask->ttl && + !MLX5_CAP_ESW_FLOWTABLE_FDB + (priv->mdev, + ft_field_support.outer_ipv4_ttl)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on TTL is not supported"); + return -EOPNOTSUPP; + } + } /* Enforce DMAC when offloading incoming tunneled flows. @@ -1247,6 +1270,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f, u8 *match_level) { + struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, @@ -1277,6 +1301,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_TCP) | BIT(FLOW_DISSECTOR_KEY_IP) | BIT(FLOW_DISSECTOR_KEY_ENC_IP))) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", f->dissector->used_keys); return -EOPNOTSUPP; @@ -1368,6 +1393,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } + } else { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) { @@ -1550,8 +1578,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, - ft_field_support.outer_ipv4_ttl)) + ft_field_support.outer_ipv4_ttl)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on TTL is not supported"); return -EOPNOTSUPP; + } if (mask->tos || mask->ttl) *match_level = MLX5_MATCH_L3; @@ -1593,6 +1624,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, udp_dport, ntohs(key->dst)); break; default: + NL_SET_ERR_MSG_MOD(extack, + "Only UDP and TCP transports are supported for L4 matching"); netdev_err(priv->netdev, "Only UDP and TCP transport are supported\n"); return -EINVAL; @@ -1629,6 +1662,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f) { + struct netlink_ext_ack *extack = f->common.extack; struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1643,6 +1677,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, if (rep->vport != FDB_UPLINK_VPORT && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && esw->offloads.inline_mode < match_level)) { + NL_SET_ERR_MSG_MOD(extack, + "Flow is not offloaded due to min inline setting"); netdev_warn(priv->netdev, "Flow is not offloaded due to min inline setting, required %d actual %d\n", match_level, esw->offloads.inline_mode); @@ -1744,7 +1780,8 @@ static struct mlx5_fields fields[] = { */ static int offload_pedit_fields(struct pedit_headers *masks, struct pedit_headers *vals, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; int i, action_size, nactions, max_actions, first, last, next_z; @@ -1783,11 +1820,15 @@ static int offload_pedit_fields(struct pedit_headers *masks, continue; if (s_mask && a_mask) { + NL_SET_ERR_MSG_MOD(extack, + "can't set and add to the same HW field"); printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field); return -EOPNOTSUPP; } if (nactions == max_actions) { + NL_SET_ERR_MSG_MOD(extack, + "too many pedit actions, can't offload"); printk(KERN_WARNING "mlx5: parsed %d pedit actions, can't do more\n", nactions); return -EOPNOTSUPP; } @@ -1820,6 +1861,8 @@ static int offload_pedit_fields(struct pedit_headers *masks, next_z = find_next_zero_bit(&mask, field_bsize, first); last = find_last_bit(&mask, field_bsize); if (first < next_z && next_z < last) { + NL_SET_ERR_MSG_MOD(extack, + "rewrite of few sub-fields isn't supported"); printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n", mask); return -EOPNOTSUPP; @@ -1878,7 +1921,8 @@ static const struct pedit_headers zero_masks = {}; static int parse_tc_pedit_action(struct mlx5e_priv *priv, const struct tc_action *a, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr) + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks; int nkeys, i, err = -EOPNOTSUPP; @@ -1896,12 +1940,13 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, err = -EOPNOTSUPP; /* can't be all optimistic */ if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) { - netdev_warn(priv->netdev, "legacy pedit isn't offloaded\n"); + NL_SET_ERR_MSG_MOD(extack, + "legacy pedit isn't offloaded"); goto out_err; } if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) { - netdev_warn(priv->netdev, "pedit cmd %d isn't offloaded\n", cmd); + NL_SET_ERR_MSG_MOD(extack, "pedit cmd isn't offloaded"); goto out_err; } @@ -1918,13 +1963,15 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, if (err) goto out_err; - err = offload_pedit_fields(masks, vals, parse_attr); + err = offload_pedit_fields(masks, vals, parse_attr, extack); if (err < 0) goto out_dealloc_parsed_actions; for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { cmd_masks = &masks[cmd]; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { + NL_SET_ERR_MSG_MOD(extack, + "attempt to offload an unsupported field"); netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd); print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS, 16, 1, cmd_masks, sizeof(zero_masks), true); @@ -1941,19 +1988,26 @@ out_err: return err; } -static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 update_flags) +static bool csum_offload_supported(struct mlx5e_priv *priv, + u32 action, + u32 update_flags, + struct netlink_ext_ack *extack) { u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP; /* The HW recalcs checksums only if re-writing headers */ if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) { + NL_SET_ERR_MSG_MOD(extack, + "TC csum action is only offloaded with pedit"); netdev_warn(priv->netdev, "TC csum action is only offloaded with pedit\n"); return false; } if (update_flags & ~prot_flags) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload TC csum action for some header/s"); netdev_warn(priv->netdev, "can't offload TC csum action for some header/s - flags %#x\n", update_flags); @@ -1964,7 +2018,8 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 upda } static bool modify_header_match_supported(struct mlx5_flow_spec *spec, - struct tcf_exts *exts) + struct tcf_exts *exts, + struct netlink_ext_ack *extack) { const struct tc_action *a; bool modify_ip_header; @@ -2002,6 +2057,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload re-write of non TCP/UDP"); pr_info("can't offload re-write of ip proto %d\n", ip_proto); return false; } @@ -2013,7 +2070,8 @@ out_ok: static bool actions_match_supported(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { u32 actions; @@ -2027,7 +2085,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv, return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - return modify_header_match_supported(&parse_attr->spec, exts); + return modify_header_match_supported(&parse_attr->spec, exts, + extack); return true; } @@ -2048,7 +2107,8 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_nic_flow_attr *attr = flow->nic_attr; const struct tc_action *a; @@ -2072,7 +2132,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_pedit(a)) { err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr); + parse_attr, extack); if (err) return err; @@ -2083,7 +2143,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_csum(a)) { if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a))) + tcf_csum_update_flags(a), + extack)) continue; return -EOPNOTSUPP; @@ -2099,6 +2160,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; } else { + NL_SET_ERR_MSG_MOD(extack, + "device is not on same HW, can't offload"); netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", peer_dev->name); return -EINVAL; @@ -2110,8 +2173,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 mark = tcf_skbedit_mark(a); if (mark & ~MLX5E_TC_FLOW_ID_MASK) { - netdev_warn(priv->netdev, "Bad flow mark - only 16 bit is supported: 0x%x\n", - mark); + NL_SET_ERR_MSG_MOD(extack, + "Bad flow mark - only 16 bit is supported"); return -EINVAL; } @@ -2124,7 +2187,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow)) + if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) return -EOPNOTSUPP; return 0; @@ -2526,7 +2589,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct ip_tunnel_info *tun_info, struct net_device *mirred_dev, struct net_device **encap_dev, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; unsigned short family = ip_tunnel_info_af(tun_info); @@ -2544,6 +2608,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, /* setting udp src port isn't supported */ if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) { vxlan_encap_offload_err: + NL_SET_ERR_MSG_MOD(extack, + "must set udp dst port and not set udp src port"); netdev_warn(priv->netdev, "must set udp dst port and not set udp src port\n"); return -EOPNOTSUPP; @@ -2553,6 +2619,8 @@ vxlan_encap_offload_err: MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { tunnel_type = MLX5_HEADER_TYPE_VXLAN; } else { + NL_SET_ERR_MSG_MOD(extack, + "port isn't an offloaded vxlan udp dport"); netdev_warn(priv->netdev, "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst)); return -EOPNOTSUPP; @@ -2657,7 +2725,8 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -2683,7 +2752,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_pedit(a)) { err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB, - parse_attr); + parse_attr, extack); if (err) return err; @@ -2694,7 +2763,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (is_tcf_csum(a)) { if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a))) + tcf_csum_update_flags(a), + extack)) continue; return -EOPNOTSUPP; @@ -2707,6 +2777,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, out_dev = tcf_mirred_dev(a); if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { + NL_SET_ERR_MSG_MOD(extack, + "can't support more output ports, can't offload forwarding"); pr_err("can't support more than %d output ports, can't offload forwarding\n", attr->out_count); return -EOPNOTSUPP; @@ -2730,6 +2802,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, MLX5_FLOW_CONTEXT_ACTION_COUNT; /* attr->out_rep is resolved when we handle encap */ } else { + NL_SET_ERR_MSG_MOD(extack, + "devices are not on same switch HW, can't offload forwarding"); pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); return -EINVAL; @@ -2766,10 +2840,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow)) + if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) return -EOPNOTSUPP; if (attr->out_count > 1 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { + NL_SET_ERR_MSG_MOD(extack, + "current firmware doesn't support split rule for port mirroring"); netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n"); return -EOPNOTSUPP; } @@ -2811,6 +2887,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv) int mlx5e_configure_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f, int flags) { + struct netlink_ext_ack *extack = f->common.extack; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct rhashtable *tc_ht = get_tc_ht(priv); @@ -2822,6 +2899,8 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); if (flow) { + NL_SET_ERR_MSG_MOD(extack, + "flow cookie already exists, ignoring"); netdev_warn_once(priv->netdev, "flow cookie %lx already exists, ignoring\n", f->cookie); return 0; } @@ -2850,15 +2929,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, goto err_free; if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { - err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow); + err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow, + extack); if (err < 0) goto err_free; - flow->rule[0] = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, + extack); } else { - err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow); + err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, + extack); if (err < 0) goto err_free; - flow->rule[0] = mlx5e_tc_add_nic_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_nic_flow(priv, parse_attr, flow, + extack); } if (IS_ERR(flow->rule[0])) { @@ -2946,14 +3029,71 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, return 0; } +static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, + struct mlx5e_priv *peer_priv) +{ + struct mlx5_core_dev *peer_mdev = peer_priv->mdev; + struct mlx5e_hairpin_entry *hpe; + u16 peer_vhca_id; + int bkt; + + if (!same_hw_devs(priv, peer_priv)) + return; + + peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); + + hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) { + if (hpe->peer_vhca_id == peer_vhca_id) + hpe->hp->pair->peer_gone = true; + } +} + +static int mlx5e_tc_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct mlx5e_flow_steering *fs; + struct mlx5e_priv *peer_priv; + struct mlx5e_tc_table *tc; + struct mlx5e_priv *priv; + + if (ndev->netdev_ops != &mlx5e_netdev_ops || + event != NETDEV_UNREGISTER || + ndev->reg_state == NETREG_REGISTERED) + return NOTIFY_DONE; + + tc = container_of(this, struct mlx5e_tc_table, netdevice_nb); + fs = container_of(tc, struct mlx5e_flow_steering, tc); + priv = container_of(fs, struct mlx5e_priv, fs); + peer_priv = netdev_priv(ndev); + if (priv == peer_priv || + !(priv->netdev->features & NETIF_F_HW_TC)) + return NOTIFY_DONE; + + mlx5e_tc_hairpin_update_dead_peer(priv, peer_priv); + + return NOTIFY_DONE; +} + int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; + int err; hash_init(tc->mod_hdr_tbl); hash_init(tc->hairpin_tbl); - return rhashtable_init(&tc->ht, &tc_ht_params); + err = rhashtable_init(&tc->ht, &tc_ht_params); + if (err) + return err; + + tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event; + if (register_netdevice_notifier(&tc->netdevice_nb)) { + tc->netdevice_nb.notifier_call = NULL; + mlx5_core_warn(priv->mdev, "Failed to register netdev notifier\n"); + } + + return err; } static void _mlx5e_tc_del_flow(void *ptr, void *arg) @@ -2969,6 +3109,9 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; + if (tc->netdevice_nb.notifier_call) + unregister_netdevice_notifier(&tc->netdevice_nb); + rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL); if (!IS_ERR_OR_NULL(tc->t)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2b252cde5cc2..ea7dedc2d5ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2000,7 +2000,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i; - for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; @@ -2020,7 +2020,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i; - for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 0b05bf2b91f6..dfc642de4e6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -269,12 +269,15 @@ struct mlx5_esw_flow_attr { struct mlx5e_tc_flow_parse_attr *parse_attr; }; -int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode); +int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode); -int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode); +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode); int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode); -int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap); +int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap, + struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 21e957083f65..a35a2310f871 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -810,29 +810,35 @@ out: return flow_rule; } -static int esw_offloads_start(struct mlx5_eswitch *esw) +static int esw_offloads_start(struct mlx5_eswitch *esw, + struct netlink_ext_ack *extack) { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; if (esw->mode != SRIOV_LEGACY) { - esw_warn(esw->dev, "Can't set offloads mode, SRIOV legacy not enabled\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set offloads mode, SRIOV legacy not enabled"); return -EINVAL; } mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); if (err) { - esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch to offloads"); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); - if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1); + if (err1) { + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch back to legacy"); + } } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { if (mlx5_eswitch_inline_mode_get(esw, num_vfs, &esw->offloads.inline_mode)) { esw->offloads.inline_mode = MLX5_INLINE_MODE_L2; - esw_warn(esw->dev, "Inline mode is different between vports\n"); + NL_SET_ERR_MSG_MOD(extack, + "Inline mode is different between vports"); } } return err; @@ -973,17 +979,20 @@ create_ft_err: return err; } -static int esw_offloads_stop(struct mlx5_eswitch *esw) +static int esw_offloads_stop(struct mlx5_eswitch *esw, + struct netlink_ext_ack *extack) { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; mlx5_eswitch_disable_sriov(esw); err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY); if (err) { - esw_warn(esw->dev, "Failed setting eswitch to legacy, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS); - if (err1) - esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err); + if (err1) { + NL_SET_ERR_MSG_MOD(extack, + "Failed setting eswitch back to offloads"); + } } /* enable back PF RoCE */ @@ -1092,7 +1101,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) return 0; } -int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); u16 cur_mlx5_mode, mlx5_mode = 0; @@ -1111,9 +1121,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) return 0; if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) - return esw_offloads_start(dev->priv.eswitch); + return esw_offloads_start(dev->priv.eswitch, extack); else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) - return esw_offloads_stop(dev->priv.eswitch); + return esw_offloads_stop(dev->priv.eswitch, extack); else return -EINVAL; } @@ -1130,7 +1140,8 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } -int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1147,14 +1158,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) return 0; /* fall through */ case MLX5_CAP_INLINE_MODE_L2: - esw_warn(dev, "Inline mode can't be set\n"); + NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set"); return -EOPNOTSUPP; case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: break; } if (esw->offloads.num_flows > 0) { - esw_warn(dev, "Can't set inline mode when flows are configured\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set inline mode when flows are configured"); return -EOPNOTSUPP; } @@ -1165,8 +1177,8 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) for (vport = 1; vport < esw->enabled_vports; vport++) { err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode); if (err) { - esw_warn(dev, "Failed to set min inline on vport %d\n", - vport); + NL_SET_ERR_MSG_MOD(extack, + "Failed to set min inline on vport"); goto revert_inline_mode; } } @@ -1232,7 +1244,8 @@ out: return 0; } -int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) +int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1259,7 +1272,8 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) return 0; if (esw->offloads.num_flows > 0) { - esw_warn(dev, "Can't set encapsulation when flows are configured\n"); + NL_SET_ERR_MSG_MOD(extack, + "Can't set encapsulation when flows are configured"); return -EOPNOTSUPP; } @@ -1268,7 +1282,8 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) esw->offloads.encap = encap; err = esw_create_offloads_fast_fdb_table(esw); if (err) { - esw_warn(esw->dev, "Failed re-creating fast FDB table, err %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "Failed re-creating fast FDB table"); esw->offloads.encap = !encap; (void)esw_create_offloads_fast_fdb_table(esw); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 41ad24f0de2c..1ab6f7e3bec6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -250,7 +250,7 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) if (ret) return ret; - force_state = MLX5_GET(teardown_hca_out, out, force_state); + force_state = MLX5_GET(teardown_hca_out, out, state); if (force_state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { mlx5_core_warn(dev, "teardown with force mode failed, doing normal teardown\n"); return -EIO; @@ -259,6 +259,54 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } +#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) +{ + unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {0}; + int state; + int ret; + + if (!MLX5_CAP_GEN(dev, fast_teardown)) { + mlx5_core_dbg(dev, "fast teardown is not supported in the firmware\n"); + return -EOPNOTSUPP; + } + + MLX5_SET(teardown_hca_in, in, opcode, MLX5_CMD_OP_TEARDOWN_HCA); + MLX5_SET(teardown_hca_in, in, profile, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) + return ret; + + state = MLX5_GET(teardown_hca_out, out, state); + if (state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { + mlx5_core_warn(dev, "teardown with fast mode failed\n"); + return -EIO; + } + + mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED); + + /* Loop until device state turns to disable */ + end = jiffies + msecs_to_jiffies(delay_ms); + do { + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + break; + + cond_resched(); + } while (!time_after(jiffies, end)); + + if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", + mlx5_get_nic_state(dev), delay_ms); + return -EIO; + } + + return 0; +} + enum mlxsw_reg_mcc_instruction { MLX5_REG_MCC_INSTRUCTION_LOCK_UPDATE_HANDLE = 0x01, MLX5_REG_MCC_INSTRUCTION_RELEASE_UPDATE_HANDLE = 0x02, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9f39aeca863f..43118de8ee99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -59,22 +59,25 @@ enum { }; enum { - MLX5_NIC_IFC_FULL = 0, - MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2, - MLX5_NIC_IFC_INVALID = 3 -}; - -enum { MLX5_DROP_NEW_HEALTH_WORK, MLX5_DROP_NEW_RECOVERY_WORK, }; -static u8 get_nic_state(struct mlx5_core_dev *dev) +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3; } +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state) +{ + u32 cur_cmdq_addr_l_sz; + + cur_cmdq_addr_l_sz = ioread32be(&dev->iseg->cmdq_addr_l_sz); + iowrite32be((cur_cmdq_addr_l_sz & 0xFFFFF000) | + state << MLX5_NIC_IFC_OFFSET, + &dev->iseg->cmdq_addr_l_sz); +} + static void trigger_cmd_completions(struct mlx5_core_dev *dev) { unsigned long flags; @@ -103,7 +106,7 @@ static int in_fatal(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) return 1; if (ioread32be(&h->fw_ver) == 0xffffffff) @@ -133,7 +136,7 @@ unlock: static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) { - u8 nic_interface = get_nic_state(dev); + u8 nic_interface = mlx5_get_nic_state(dev); switch (nic_interface) { case MLX5_NIC_IFC_FULL: @@ -168,7 +171,7 @@ static void health_recover(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); - nic_state = get_nic_state(dev); + nic_state = mlx5_get_nic_state(dev); if (nic_state == MLX5_NIC_IFC_INVALID) { dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n"); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b5e9f664fc66..28132c7dc05f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1594,12 +1594,17 @@ static const struct pci_error_handlers mlx5_err_handler = { static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) { - int ret; + bool fast_teardown = false, force_teardown = false; + int ret = 1; + + fast_teardown = MLX5_CAP_GEN(dev, fast_teardown); + force_teardown = MLX5_CAP_GEN(dev, force_teardown); + + mlx5_core_dbg(dev, "force teardown firmware support=%d\n", force_teardown); + mlx5_core_dbg(dev, "fast teardown firmware support=%d\n", fast_teardown); - if (!MLX5_CAP_GEN(dev, force_teardown)) { - mlx5_core_dbg(dev, "force teardown is not supported in the firmware\n"); + if (!fast_teardown && !force_teardown) return -EOPNOTSUPP; - } if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5_core_dbg(dev, "Device in internal error state, giving up\n"); @@ -1612,13 +1617,19 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); + ret = mlx5_cmd_fast_teardown_hca(dev); + if (!ret) + goto succeed; + ret = mlx5_cmd_force_teardown_hca(dev); - if (ret) { - mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); - mlx5_start_health_poll(dev); - return ret; - } + if (!ret) + goto succeed; + + mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); + mlx5_start_health_poll(dev); + return ret; +succeed: mlx5_enter_error_state(dev, true); /* Some platforms requiring freeing the IRQ's in the shutdown diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b4134fa0bba3..cc298527baf1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -95,6 +95,8 @@ int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev); +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev); + void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, @@ -214,4 +216,14 @@ int mlx5_lag_allow(struct mlx5_core_dev *dev); int mlx5_lag_forbid(struct mlx5_core_dev *dev); void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); + +enum { + MLX5_NIC_IFC_FULL = 0, + MLX5_NIC_IFC_DISABLED = 1, + MLX5_NIC_IFC_NO_DRAM_NIC = 2, + MLX5_NIC_IFC_INVALID = 3 +}; + +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); #endif /* __MLX5_CORE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index d2f76070ea7c..a1ee9a8a769e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -475,7 +475,8 @@ static void mlx5_hairpin_destroy_queues(struct mlx5_hairpin *hp) for (i = 0; i < hp->num_channels; i++) { mlx5_core_destroy_rq(hp->func_mdev, hp->rqn[i]); - mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); + if (!hp->peer_gone) + mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]); } } @@ -567,6 +568,8 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp) MLX5_RQC_STATE_RST, 0, 0); /* unset peer SQs */ + if (hp->peer_gone) + return; for (i = 0; i < hp->num_channels; i++) mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_RST, 0, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 4d271fb3de3d..5890fdfd62c3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -718,14 +718,17 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) memset(&active_cqns, 0, sizeof(active_cqns)); while ((eqe = mlxsw_pci_eq_sw_eqe_get(q))) { - u8 event_type = mlxsw_pci_eqe_event_type_get(eqe); - switch (event_type) { - case MLXSW_PCI_EQE_EVENT_TYPE_CMD: + /* Command interface completion events are always received on + * queue MLXSW_PCI_EQ_ASYNC_NUM (EQ0) and completion events + * are mapped to queue MLXSW_PCI_EQ_COMP_NUM (EQ1). + */ + switch (q->num) { + case MLXSW_PCI_EQ_ASYNC_NUM: mlxsw_pci_eq_cmd_event(mlxsw_pci, eqe); q->u.eq.ev_cmd_count++; break; - case MLXSW_PCI_EQE_EVENT_TYPE_COMP: + case MLXSW_PCI_EQ_COMP_NUM: cqn = mlxsw_pci_eqe_cqn_get(eqe); set_bit(cqn, active_cqns); cq_handle = true; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 88c33a8474eb..2b14fd0dcc42 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4855,6 +4855,8 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, upper_dev = info->upper_dev; if (info->linking) break; + if (is_vlan_dev(upper_dev)) + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, upper_dev); if (netif_is_macvlan(upper_dev)) mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev); break; diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig index 36c84625d54e..bcec0587cf61 100644 --- a/drivers/net/ethernet/mscc/Kconfig +++ b/drivers/net/ethernet/mscc/Kconfig @@ -23,6 +23,8 @@ config MSCC_OCELOT_SWITCH config MSCC_OCELOT_SWITCH_OCELOT tristate "Ocelot switch driver on Ocelot" depends on MSCC_OCELOT_SWITCH + depends on GENERIC_PHY + depends on OF_NET help This driver supports the Ocelot network switch device as present on the Ocelot SoCs. diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 1a4f2bb48ead..8f11fdba8d0e 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -472,6 +472,7 @@ static int ocelot_port_open(struct net_device *dev) { struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; + enum phy_mode phy_mode; int err; /* Enable receiving frames on the port, and activate auto-learning of @@ -482,8 +483,21 @@ static int ocelot_port_open(struct net_device *dev) ANA_PORT_PORT_CFG_PORTID_VAL(port->chip_port), ANA_PORT_PORT_CFG, port->chip_port); + if (port->serdes) { + if (port->phy_mode == PHY_INTERFACE_MODE_SGMII) + phy_mode = PHY_MODE_SGMII; + else + phy_mode = PHY_MODE_QSGMII; + + err = phy_set_mode(port->serdes, phy_mode); + if (err) { + netdev_err(dev, "Could not set mode of SerDes\n"); + return err; + } + } + err = phy_connect_direct(dev, port->phy, &ocelot_port_adjust_link, - PHY_INTERFACE_MODE_NA); + port->phy_mode); if (err) { netdev_err(dev, "Could not attach to PHY\n"); return err; diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 616bec30dfa3..62c7c8eb00d9 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -11,12 +11,13 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include <linux/phy.h> +#include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/regmap.h> #include "ocelot_ana.h" #include "ocelot_dev.h" -#include "ocelot_hsio.h" #include "ocelot_qsys.h" #include "ocelot_rew.h" #include "ocelot_sys.h" @@ -333,79 +334,6 @@ enum ocelot_reg { SYS_CM_DATA_RD, SYS_CM_OP, SYS_CM_DATA, - HSIO_PLL5G_CFG0 = HSIO << TARGET_OFFSET, - HSIO_PLL5G_CFG1, - HSIO_PLL5G_CFG2, - HSIO_PLL5G_CFG3, - HSIO_PLL5G_CFG4, - HSIO_PLL5G_CFG5, - HSIO_PLL5G_CFG6, - HSIO_PLL5G_STATUS0, - HSIO_PLL5G_STATUS1, - HSIO_PLL5G_BIST_CFG0, - HSIO_PLL5G_BIST_CFG1, - HSIO_PLL5G_BIST_CFG2, - HSIO_PLL5G_BIST_STAT0, - HSIO_PLL5G_BIST_STAT1, - HSIO_RCOMP_CFG0, - HSIO_RCOMP_STATUS, - HSIO_SYNC_ETH_CFG, - HSIO_SYNC_ETH_PLL_CFG, - HSIO_S1G_DES_CFG, - HSIO_S1G_IB_CFG, - HSIO_S1G_OB_CFG, - HSIO_S1G_SER_CFG, - HSIO_S1G_COMMON_CFG, - HSIO_S1G_PLL_CFG, - HSIO_S1G_PLL_STATUS, - HSIO_S1G_DFT_CFG0, - HSIO_S1G_DFT_CFG1, - HSIO_S1G_DFT_CFG2, - HSIO_S1G_TP_CFG, - HSIO_S1G_RC_PLL_BIST_CFG, - HSIO_S1G_MISC_CFG, - HSIO_S1G_DFT_STATUS, - HSIO_S1G_MISC_STATUS, - HSIO_MCB_S1G_ADDR_CFG, - HSIO_S6G_DIG_CFG, - HSIO_S6G_DFT_CFG0, - HSIO_S6G_DFT_CFG1, - HSIO_S6G_DFT_CFG2, - HSIO_S6G_TP_CFG0, - HSIO_S6G_TP_CFG1, - HSIO_S6G_RC_PLL_BIST_CFG, - HSIO_S6G_MISC_CFG, - HSIO_S6G_OB_ANEG_CFG, - HSIO_S6G_DFT_STATUS, - HSIO_S6G_ERR_CNT, - HSIO_S6G_MISC_STATUS, - HSIO_S6G_DES_CFG, - HSIO_S6G_IB_CFG, - HSIO_S6G_IB_CFG1, - HSIO_S6G_IB_CFG2, - HSIO_S6G_IB_CFG3, - HSIO_S6G_IB_CFG4, - HSIO_S6G_IB_CFG5, - HSIO_S6G_OB_CFG, - HSIO_S6G_OB_CFG1, - HSIO_S6G_SER_CFG, - HSIO_S6G_COMMON_CFG, - HSIO_S6G_PLL_CFG, - HSIO_S6G_ACJTAG_CFG, - HSIO_S6G_GP_CFG, - HSIO_S6G_IB_STATUS0, - HSIO_S6G_IB_STATUS1, - HSIO_S6G_ACJTAG_STATUS, - HSIO_S6G_PLL_STATUS, - HSIO_S6G_REVID, - HSIO_MCB_S6G_ADDR_CFG, - HSIO_HW_CFG, - HSIO_HW_QSGMII_CFG, - HSIO_HW_QSGMII_STAT, - HSIO_CLK_CFG, - HSIO_TEMP_SENSOR_CTRL, - HSIO_TEMP_SENSOR_CFG, - HSIO_TEMP_SENSOR_STAT, }; enum ocelot_regfield { @@ -527,6 +455,9 @@ struct ocelot_port { u8 vlan_aware; u64 *stats; + + phy_interface_t phy_mode; + struct phy *serdes; }; u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 3cdf63e35b53..953b32677383 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -6,9 +6,11 @@ */ #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/of_net.h> #include <linux/netdevice.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> +#include <linux/mfd/syscon.h> #include <linux/skbuff.h> #include "ocelot.h" @@ -168,6 +170,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct device_node *ports, *portnp; struct ocelot *ocelot; + struct regmap *hsio; u32 val; struct { @@ -179,7 +182,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) { QSYS, "qsys" }, { ANA, "ana" }, { QS, "qs" }, - { HSIO, "hsio" }, }; if (!np && !pdev->dev.platform_data) @@ -202,6 +204,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ocelot->targets[res[i].id] = target; } + hsio = syscon_regmap_lookup_by_compatible("mscc,ocelot-hsio"); + if (IS_ERR(hsio)) { + dev_err(&pdev->dev, "missing hsio syscon\n"); + return PTR_ERR(hsio); + } + + ocelot->targets[HSIO] = hsio; + err = ocelot_chip_init(ocelot); if (err) return err; @@ -244,18 +254,12 @@ static int mscc_ocelot_probe(struct platform_device *pdev) INIT_LIST_HEAD(&ocelot->multicast); ocelot_init(ocelot); - ocelot_rmw(ocelot, HSIO_HW_CFG_DEV1G_4_MODE | - HSIO_HW_CFG_DEV1G_6_MODE | - HSIO_HW_CFG_DEV1G_9_MODE, - HSIO_HW_CFG_DEV1G_4_MODE | - HSIO_HW_CFG_DEV1G_6_MODE | - HSIO_HW_CFG_DEV1G_9_MODE, - HSIO_HW_CFG); - for_each_available_child_of_node(ports, portnp) { struct device_node *phy_node; struct phy_device *phy; struct resource *res; + struct phy *serdes; + enum phy_mode phy_mode; void __iomem *regs; char res_name[8]; u32 port; @@ -280,10 +284,45 @@ static int mscc_ocelot_probe(struct platform_device *pdev) continue; err = ocelot_probe_port(ocelot, port, regs, phy); - if (err) { - dev_err(&pdev->dev, "failed to probe ports\n"); + if (err) + return err; + + err = of_get_phy_mode(portnp); + if (err < 0) + ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA; + else + ocelot->ports[port]->phy_mode = err; + + switch (ocelot->ports[port]->phy_mode) { + case PHY_INTERFACE_MODE_NA: + continue; + case PHY_INTERFACE_MODE_SGMII: + phy_mode = PHY_MODE_SGMII; + break; + case PHY_INTERFACE_MODE_QSGMII: + phy_mode = PHY_MODE_QSGMII; + break; + default: + dev_err(ocelot->dev, + "invalid phy mode for port%d, (Q)SGMII only\n", + port); + return -EINVAL; + } + + serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = PTR_ERR(serdes); + if (err == -EPROBE_DEFER) + dev_dbg(ocelot->dev, "deferring probe\n"); + else + dev_err(ocelot->dev, + "missing SerDes phys for port%d\n", + port); + goto err_probe_ports; } + + ocelot->ports[port]->serdes = serdes; } register_netdevice_notifier(&ocelot_netdevice_nb); diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index e334b406c40c..9271af18b93b 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -5,6 +5,7 @@ * Copyright (c) 2017 Microsemi Corporation */ #include "ocelot.h" +#include <soc/mscc/ocelot_hsio.h> static const u32 ocelot_ana_regmap[] = { REG(ANA_ADVLEARN, 0x009000), @@ -102,82 +103,6 @@ static const u32 ocelot_qs_regmap[] = { REG(QS_INH_DBG, 0x000048), }; -static const u32 ocelot_hsio_regmap[] = { - REG(HSIO_PLL5G_CFG0, 0x000000), - REG(HSIO_PLL5G_CFG1, 0x000004), - REG(HSIO_PLL5G_CFG2, 0x000008), - REG(HSIO_PLL5G_CFG3, 0x00000c), - REG(HSIO_PLL5G_CFG4, 0x000010), - REG(HSIO_PLL5G_CFG5, 0x000014), - REG(HSIO_PLL5G_CFG6, 0x000018), - REG(HSIO_PLL5G_STATUS0, 0x00001c), - REG(HSIO_PLL5G_STATUS1, 0x000020), - REG(HSIO_PLL5G_BIST_CFG0, 0x000024), - REG(HSIO_PLL5G_BIST_CFG1, 0x000028), - REG(HSIO_PLL5G_BIST_CFG2, 0x00002c), - REG(HSIO_PLL5G_BIST_STAT0, 0x000030), - REG(HSIO_PLL5G_BIST_STAT1, 0x000034), - REG(HSIO_RCOMP_CFG0, 0x000038), - REG(HSIO_RCOMP_STATUS, 0x00003c), - REG(HSIO_SYNC_ETH_CFG, 0x000040), - REG(HSIO_SYNC_ETH_PLL_CFG, 0x000048), - REG(HSIO_S1G_DES_CFG, 0x00004c), - REG(HSIO_S1G_IB_CFG, 0x000050), - REG(HSIO_S1G_OB_CFG, 0x000054), - REG(HSIO_S1G_SER_CFG, 0x000058), - REG(HSIO_S1G_COMMON_CFG, 0x00005c), - REG(HSIO_S1G_PLL_CFG, 0x000060), - REG(HSIO_S1G_PLL_STATUS, 0x000064), - REG(HSIO_S1G_DFT_CFG0, 0x000068), - REG(HSIO_S1G_DFT_CFG1, 0x00006c), - REG(HSIO_S1G_DFT_CFG2, 0x000070), - REG(HSIO_S1G_TP_CFG, 0x000074), - REG(HSIO_S1G_RC_PLL_BIST_CFG, 0x000078), - REG(HSIO_S1G_MISC_CFG, 0x00007c), - REG(HSIO_S1G_DFT_STATUS, 0x000080), - REG(HSIO_S1G_MISC_STATUS, 0x000084), - REG(HSIO_MCB_S1G_ADDR_CFG, 0x000088), - REG(HSIO_S6G_DIG_CFG, 0x00008c), - REG(HSIO_S6G_DFT_CFG0, 0x000090), - REG(HSIO_S6G_DFT_CFG1, 0x000094), - REG(HSIO_S6G_DFT_CFG2, 0x000098), - REG(HSIO_S6G_TP_CFG0, 0x00009c), - REG(HSIO_S6G_TP_CFG1, 0x0000a0), - REG(HSIO_S6G_RC_PLL_BIST_CFG, 0x0000a4), - REG(HSIO_S6G_MISC_CFG, 0x0000a8), - REG(HSIO_S6G_OB_ANEG_CFG, 0x0000ac), - REG(HSIO_S6G_DFT_STATUS, 0x0000b0), - REG(HSIO_S6G_ERR_CNT, 0x0000b4), - REG(HSIO_S6G_MISC_STATUS, 0x0000b8), - REG(HSIO_S6G_DES_CFG, 0x0000bc), - REG(HSIO_S6G_IB_CFG, 0x0000c0), - REG(HSIO_S6G_IB_CFG1, 0x0000c4), - REG(HSIO_S6G_IB_CFG2, 0x0000c8), - REG(HSIO_S6G_IB_CFG3, 0x0000cc), - REG(HSIO_S6G_IB_CFG4, 0x0000d0), - REG(HSIO_S6G_IB_CFG5, 0x0000d4), - REG(HSIO_S6G_OB_CFG, 0x0000d8), - REG(HSIO_S6G_OB_CFG1, 0x0000dc), - REG(HSIO_S6G_SER_CFG, 0x0000e0), - REG(HSIO_S6G_COMMON_CFG, 0x0000e4), - REG(HSIO_S6G_PLL_CFG, 0x0000e8), - REG(HSIO_S6G_ACJTAG_CFG, 0x0000ec), - REG(HSIO_S6G_GP_CFG, 0x0000f0), - REG(HSIO_S6G_IB_STATUS0, 0x0000f4), - REG(HSIO_S6G_IB_STATUS1, 0x0000f8), - REG(HSIO_S6G_ACJTAG_STATUS, 0x0000fc), - REG(HSIO_S6G_PLL_STATUS, 0x000100), - REG(HSIO_S6G_REVID, 0x000104), - REG(HSIO_MCB_S6G_ADDR_CFG, 0x000108), - REG(HSIO_HW_CFG, 0x00010c), - REG(HSIO_HW_QSGMII_CFG, 0x000110), - REG(HSIO_HW_QSGMII_STAT, 0x000114), - REG(HSIO_CLK_CFG, 0x000118), - REG(HSIO_TEMP_SENSOR_CTRL, 0x00011c), - REG(HSIO_TEMP_SENSOR_CFG, 0x000120), - REG(HSIO_TEMP_SENSOR_STAT, 0x000124), -}; - static const u32 ocelot_qsys_regmap[] = { REG(QSYS_PORT_MODE, 0x011200), REG(QSYS_SWITCH_PORT_MODE, 0x011234), @@ -302,7 +227,6 @@ static const u32 ocelot_sys_regmap[] = { static const u32 *ocelot_regmap[] = { [ANA] = ocelot_ana_regmap, [QS] = ocelot_qs_regmap, - [HSIO] = ocelot_hsio_regmap, [QSYS] = ocelot_qsys_regmap, [REW] = ocelot_rew_regmap, [SYS] = ocelot_sys_regmap, @@ -453,9 +377,11 @@ static void ocelot_pll5_init(struct ocelot *ocelot) /* Configure PLL5. This will need a proper CCF driver * The values are coming from the VTSS API for Ocelot */ - ocelot_write(ocelot, HSIO_PLL5G_CFG4_IB_CTRL(0x7600) | - HSIO_PLL5G_CFG4_IB_BIAS_CTRL(0x8), HSIO_PLL5G_CFG4); - ocelot_write(ocelot, HSIO_PLL5G_CFG0_CORE_CLK_DIV(0x11) | + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG4, + HSIO_PLL5G_CFG4_IB_CTRL(0x7600) | + HSIO_PLL5G_CFG4_IB_BIAS_CTRL(0x8)); + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG0, + HSIO_PLL5G_CFG0_CORE_CLK_DIV(0x11) | HSIO_PLL5G_CFG0_CPU_CLK_DIV(2) | HSIO_PLL5G_CFG0_ENA_BIAS | HSIO_PLL5G_CFG0_ENA_VCO_BUF | @@ -465,13 +391,14 @@ static void ocelot_pll5_init(struct ocelot *ocelot) HSIO_PLL5G_CFG0_SELBGV820(4) | HSIO_PLL5G_CFG0_DIV4 | HSIO_PLL5G_CFG0_ENA_CLKTREE | - HSIO_PLL5G_CFG0_ENA_LANE, HSIO_PLL5G_CFG0); - ocelot_write(ocelot, HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET | + HSIO_PLL5G_CFG0_ENA_LANE); + regmap_write(ocelot->targets[HSIO], HSIO_PLL5G_CFG2, + HSIO_PLL5G_CFG2_EN_RESET_FRQ_DET | HSIO_PLL5G_CFG2_EN_RESET_OVERRUN | HSIO_PLL5G_CFG2_GAIN_TEST(0x8) | HSIO_PLL5G_CFG2_ENA_AMPCTRL | HSIO_PLL5G_CFG2_PWD_AMPCTRL_N | - HSIO_PLL5G_CFG2_AMPC_SEL(0x10), HSIO_PLL5G_CFG2); + HSIO_PLL5G_CFG2_AMPC_SEL(0x10)); } int ocelot_chip_init(struct ocelot *ocelot) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index db463e20a876..4213fe42ac4d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -177,7 +177,8 @@ static int nfp_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) return nfp_app_eswitch_mode_get(pf->app, mode); } -static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) +static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct nfp_pf *pf = devlink_priv(devlink); int ret; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index d05e37fcc1b2..24c8f5bb1eb4 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2077,14 +2077,17 @@ nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp, return true; } -static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) +static bool nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) { struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring; struct nfp_net *nn = r_vec->nfp_net; struct nfp_net_dp *dp = &nn->dp; + unsigned int budget = 512; - while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring)) + while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring) && budget--) continue; + + return budget; } static void nfp_ctrl_poll(unsigned long arg) @@ -2096,9 +2099,13 @@ static void nfp_ctrl_poll(unsigned long arg) __nfp_ctrl_tx_queued(r_vec); spin_unlock(&r_vec->lock); - nfp_ctrl_rx(r_vec); - - nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + if (nfp_ctrl_rx(r_vec)) { + nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + } else { + tasklet_schedule(&r_vec->tasklet); + nn_dp_warn(&r_vec->nfp_net->dp, + "control message budget exceeded!\n"); + } } /* Setup and Configuration diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 69aa7fc392c5..59c70be22a84 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -72,9 +72,6 @@ static void netxen_schedule_work(struct netxen_adapter *adapter, work_func_t func, int delay); static void netxen_cancel_fw_work(struct netxen_adapter *adapter); static int netxen_nic_poll(struct napi_struct *napi, int budget); -#ifdef CONFIG_NET_POLL_CONTROLLER -static void netxen_nic_poll_controller(struct net_device *netdev); -#endif static void netxen_create_sysfs_entries(struct netxen_adapter *adapter); static void netxen_remove_sysfs_entries(struct netxen_adapter *adapter); @@ -581,9 +578,6 @@ static const struct net_device_ops netxen_netdev_ops = { .ndo_tx_timeout = netxen_tx_timeout, .ndo_fix_features = netxen_fix_features, .ndo_set_features = netxen_set_features, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = netxen_nic_poll_controller, -#endif }; static inline bool netxen_function_zero(struct pci_dev *pdev) @@ -2402,23 +2396,6 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget) return work_done; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void netxen_nic_poll_controller(struct net_device *netdev) -{ - int ring; - struct nx_host_sds_ring *sds_ring; - struct netxen_adapter *adapter = netdev_priv(netdev); - struct netxen_recv_context *recv_ctx = &adapter->recv_ctx; - - disable_irq(adapter->irq); - for (ring = 0; ring < adapter->max_sds_rings; ring++) { - sds_ring = &recv_ctx->sds_rings[ring]; - netxen_intr(adapter->irq, sds_ring); - } - enable_irq(adapter->irq); -} -#endif - static int nx_incr_dev_ref_cnt(struct netxen_adapter *adapter) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 56578f888b70..bf431ab86864 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12102,6 +12102,7 @@ struct public_global { u32 running_bundle_id; s32 external_temperature; u32 mdump_reason; + u64 reserved; u32 data_ptr; u32 data_size; }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index f99797a149a4..beb8e5d6401a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1709,7 +1709,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, cm_info->local_ip[0] = ntohl(iph->daddr); cm_info->remote_ip[0] = ntohl(iph->saddr); - cm_info->ip_version = TCP_IPV4; + cm_info->ip_version = QED_TCP_IPV4; ip_hlen = (iph->ihl) * sizeof(u32); *payload_len = ntohs(iph->tot_len) - ip_hlen; @@ -1729,7 +1729,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, cm_info->remote_ip[i] = ntohl(ip6h->saddr.in6_u.u6_addr32[i]); } - cm_info->ip_version = TCP_IPV6; + cm_info->ip_version = QED_TCP_IPV6; ip_hlen = sizeof(*ip6h); *payload_len = ntohs(ip6h->payload_len); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index da13117a604a..aa633381aa47 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -796,7 +796,18 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn, tx_pkt.vlan = p_buffer->vlan; tx_pkt.bd_flags = bd_flags; tx_pkt.l4_hdr_offset_w = l4_hdr_offset_w; - tx_pkt.tx_dest = p_ll2_conn->tx_dest; + switch (p_ll2_conn->tx_dest) { + case CORE_TX_DEST_NW: + tx_pkt.tx_dest = QED_LL2_TX_DEST_NW; + break; + case CORE_TX_DEST_LB: + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + break; + case CORE_TX_DEST_DROP: + default: + tx_pkt.tx_dest = QED_LL2_TX_DEST_DROP; + break; + } tx_pkt.first_frag = first_frag; tx_pkt.first_frag_len = p_buffer->packet_length; tx_pkt.cookie = p_buffer; diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index be941cfaa2d4..c71391b9c757 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -228,7 +228,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, num_cons, "Toggle"); if (rc) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, - "Failed to allocate toogle bits, rc = %d\n", rc); + "Failed to allocate toggle bits, rc = %d\n", rc); goto free_cq_map; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index 7d7a64c55ff1..f9167d1354bb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -140,23 +140,16 @@ static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid, static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) { - enum roce_flavor flavor; - switch (roce_mode) { case ROCE_V1: - flavor = PLAIN_ROCE; - break; + return PLAIN_ROCE; case ROCE_V2_IPV4: - flavor = RROCE_IPV4; - break; + return RROCE_IPV4; case ROCE_V2_IPV6: - flavor = ROCE_V2_IPV6; - break; + return RROCE_IPV6; default: - flavor = MAX_ROCE_MODE; - break; + return MAX_ROCE_FLAVOR; } - return flavor; } static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 8de644b4721e..77b6248ad3b9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -154,7 +154,7 @@ qed_set_pf_update_tunn_mode(struct qed_tunnel_info *p_tun, static void qed_set_tunn_cls_info(struct qed_tunnel_info *p_tun, struct qed_tunnel_info *p_src) { - enum tunnel_clss type; + int type; p_tun->b_update_rx_cls = p_src->b_update_rx_cls; p_tun->b_update_tx_cls = p_src->b_update_tx_cls; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 3d4269659820..be118d057b92 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -413,7 +413,6 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) } if (!p_iov->b_pre_fp_hsi && - ETH_HSI_VER_MINOR && (resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) { DP_INFO(p_hwfn, "PF is using older fastpath HSI; %02x.%02x is configured\n", @@ -572,7 +571,7 @@ free_p_iov: static void __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, u8 *p_cls) + enum qed_tunn_mode mask, u8 *p_cls) { if (p_src->b_update_mode) { p_req->tun_mode_update_mask |= BIT(mask); @@ -587,7 +586,7 @@ __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, static void qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, + enum qed_tunn_mode mask, u8 *p_cls, struct qed_tunn_update_udp_port *p_port, u8 *p_update_port, u16 *p_udp_port) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 81312924df14..0c443ea98479 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1800,7 +1800,8 @@ struct qlcnic_hardware_ops { int (*config_loopback) (struct qlcnic_adapter *, u8); int (*clear_loopback) (struct qlcnic_adapter *, u8); int (*config_promisc_mode) (struct qlcnic_adapter *, u32); - void (*change_l2_filter) (struct qlcnic_adapter *, u64 *, u16); + void (*change_l2_filter)(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *tx_ring); int (*get_board_info) (struct qlcnic_adapter *); void (*set_mac_filter_count) (struct qlcnic_adapter *); void (*free_mac_list) (struct qlcnic_adapter *); @@ -2064,9 +2065,10 @@ static inline int qlcnic_nic_set_promisc(struct qlcnic_adapter *adapter, } static inline void qlcnic_change_filter(struct qlcnic_adapter *adapter, - u64 *addr, u16 id) + u64 *addr, u16 vlan, + struct qlcnic_host_tx_ring *tx_ring) { - adapter->ahw->hw_ops->change_l2_filter(adapter, addr, id); + adapter->ahw->hw_ops->change_l2_filter(adapter, addr, vlan, tx_ring); } static inline int qlcnic_get_board_info(struct qlcnic_adapter *adapter) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 569d54ededec..a79d84f99102 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -2135,7 +2135,8 @@ out: } void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, - u16 vlan_id) + u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring) { u8 mac[ETH_ALEN]; memcpy(&mac, addr, ETH_ALEN); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index b75a81246856..73fe2f64491d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -550,7 +550,8 @@ int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *, ulong, u32); int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *, u32); int qlcnic_83xx_config_hw_lro(struct qlcnic_adapter *, int); int qlcnic_83xx_config_rss(struct qlcnic_adapter *, int); -void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *, u64 *, u16); +void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *ring); int qlcnic_83xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info *); int qlcnic_83xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *); void qlcnic_83xx_initialize_nic(struct qlcnic_adapter *, int); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 4bb33af8e2b3..56a3bd9e37dc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -173,7 +173,8 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, struct net_device *netdev); void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *); void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, - u64 *uaddr, u16 vlan_id); + u64 *uaddr, u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring); int qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *, struct ethtool_coalesce *); int qlcnic_82xx_set_rx_coalesce(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 84dd83031a1b..9647578cbe6a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -268,13 +268,12 @@ static void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, } void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, - u16 vlan_id) + u16 vlan_id, struct qlcnic_host_tx_ring *tx_ring) { struct cmd_desc_type0 *hwdesc; struct qlcnic_nic_req *req; struct qlcnic_mac_req *mac_req; struct qlcnic_vlan_req *vlan_req; - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; u32 producer; u64 word; @@ -301,7 +300,8 @@ void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, static void qlcnic_send_filter(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, - struct sk_buff *skb) + struct sk_buff *skb, + struct qlcnic_host_tx_ring *tx_ring) { struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data); struct ethhdr *phdr = (struct ethhdr *)(skb->data); @@ -335,7 +335,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, tmp_fil->vlan_id == vlan_id) { if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime)) qlcnic_change_filter(adapter, &src_addr, - vlan_id); + vlan_id, tx_ring); tmp_fil->ftime = jiffies; return; } @@ -350,7 +350,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, if (!fil) return; - qlcnic_change_filter(adapter, &src_addr, vlan_id); + qlcnic_change_filter(adapter, &src_addr, vlan_id, tx_ring); fil->ftime = jiffies; fil->vlan_id = vlan_id; memcpy(fil->faddr, &src_addr, ETH_ALEN); @@ -766,7 +766,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) } if (adapter->drv_mac_learn) - qlcnic_send_filter(adapter, first_desc, skb); + qlcnic_send_filter(adapter, first_desc, skb, tx_ring); tx_ring->tx_stats.tx_bytes += skb->len; tx_ring->tx_stats.xmit_called++; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 2d38d1ac2aae..dbd48012224f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -59,9 +59,6 @@ static int qlcnic_close(struct net_device *netdev); static void qlcnic_tx_timeout(struct net_device *netdev); static void qlcnic_attach_work(struct work_struct *work); static void qlcnic_fwinit_work(struct work_struct *work); -#ifdef CONFIG_NET_POLL_CONTROLLER -static void qlcnic_poll_controller(struct net_device *netdev); -#endif static void qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding); static int qlcnic_can_start_firmware(struct qlcnic_adapter *adapter); @@ -545,9 +542,6 @@ static const struct net_device_ops qlcnic_netdev_ops = { .ndo_udp_tunnel_add = qlcnic_add_vxlan_port, .ndo_udp_tunnel_del = qlcnic_del_vxlan_port, .ndo_features_check = qlcnic_features_check, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = qlcnic_poll_controller, -#endif #ifdef CONFIG_QLCNIC_SRIOV .ndo_set_vf_mac = qlcnic_sriov_set_vf_mac, .ndo_set_vf_rate = qlcnic_sriov_set_vf_tx_rate, @@ -3200,45 +3194,6 @@ static irqreturn_t qlcnic_msix_tx_intr(int irq, void *data) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void qlcnic_poll_controller(struct net_device *netdev) -{ - struct qlcnic_adapter *adapter = netdev_priv(netdev); - struct qlcnic_host_sds_ring *sds_ring; - struct qlcnic_recv_context *recv_ctx; - struct qlcnic_host_tx_ring *tx_ring; - int ring; - - if (!test_bit(__QLCNIC_DEV_UP, &adapter->state)) - return; - - recv_ctx = adapter->recv_ctx; - - for (ring = 0; ring < adapter->drv_sds_rings; ring++) { - sds_ring = &recv_ctx->sds_rings[ring]; - qlcnic_disable_sds_intr(adapter, sds_ring); - napi_schedule(&sds_ring->napi); - } - - if (adapter->flags & QLCNIC_MSIX_ENABLED) { - /* Only Multi-Tx queue capable devices need to - * schedule NAPI for TX rings - */ - if ((qlcnic_83xx_check(adapter) && - (adapter->flags & QLCNIC_TX_INTR_SHARED)) || - (qlcnic_82xx_check(adapter) && - !qlcnic_check_multi_tx(adapter))) - return; - - for (ring = 0; ring < adapter->drv_tx_rings; ring++) { - tx_ring = &adapter->tx_ring[ring]; - qlcnic_disable_tx_intr(adapter, tx_ring); - napi_schedule(&tx_ring->napi); - } - } -} -#endif - static void qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding) { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 7fd86d40a337..11167abe5934 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -113,7 +113,7 @@ rmnet_map_ingress_handler(struct sk_buff *skb, struct sk_buff *skbn; if (skb->dev->type == ARPHRD_ETHER) { - if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_KERNEL)) { + if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_ATOMIC)) { kfree_skb(skb); return; } @@ -147,7 +147,7 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, } if (skb_headroom(skb) < required_headroom) { - if (pskb_expand_head(skb, required_headroom, 0, GFP_KERNEL)) + if (pskb_expand_head(skb, required_headroom, 0, GFP_ATOMIC)) return -ENOMEM; } @@ -189,6 +189,9 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) if (!skb) goto done; + if (skb->pkt_type == PACKET_LOOPBACK) + return RX_HANDLER_PASS; + dev = skb->dev; port = rmnet_get_port(dev); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index ed8ffd498c88..7d3f671e1bb3 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4059,13 +4059,12 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp) genphy_soft_reset(dev->phydev); - /* It was reported that chip version 33 ends up with 10MBit/Half on a + /* It was reported that several chips end up with 10MBit/Half on a * 1GBit link after resuming from S3. For whatever reason the PHY on - * this chip doesn't properly start a renegotiation when soft-reset. + * these chips doesn't properly start a renegotiation when soft-reset. * Explicitly requesting a renegotiation fixes this. */ - if (tp->mac_version == RTL_GIGA_MAC_VER_33 && - dev->phydev->autoneg == AUTONEG_ENABLE) + if (dev->phydev->autoneg == AUTONEG_ENABLE) phy_restart_aneg(dev->phydev); } @@ -4523,9 +4522,14 @@ static void rtl8169_hw_reset(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) | - (InterFrameGap << TxInterFrameGapShift)); + u32 val = TX_DMA_BURST << TxDMAShift | + InterFrameGap << TxInterFrameGapShift; + + if (tp->mac_version >= RTL_GIGA_MAC_VER_34 && + tp->mac_version != RTL_GIGA_MAC_VER_39) + val |= TXCFG_AUTO_FIFO; + + RTL_W32(tp, TxConfig, val); } static void rtl_set_rx_max_size(struct rtl8169_private *tp) @@ -5020,7 +5024,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_disable_clock_request(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); /* Adjust EEE LED frequency */ @@ -5054,7 +5057,6 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) rtl_disable_clock_request(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); @@ -5099,8 +5101,6 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static void rtl_hw_start_8168g(struct rtl8169_private *tp) { - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); @@ -5198,8 +5198,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1)); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC); @@ -5282,8 +5280,6 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) { rtl8168ep_stop_cmac(tp); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); - rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x2f, ERIAR_EXGMAC); rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC); @@ -5605,7 +5601,6 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); - RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402)); @@ -6856,8 +6851,10 @@ static int rtl8169_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct net_device *dev = pci_get_drvdata(pdev); + struct rtl8169_private *tp = netdev_priv(dev); rtl8169_net_suspend(dev); + clk_disable_unprepare(tp->clk); return 0; } @@ -6885,6 +6882,9 @@ static int rtl8169_resume(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct net_device *dev = pci_get_drvdata(pdev); + struct rtl8169_private *tp = netdev_priv(dev); + + clk_prepare_enable(tp->clk); if (netif_running(dev)) __rtl8169_resume(dev); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 330233286e78..3d0dd39c289e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2208,29 +2208,6 @@ static void efx_fini_napi(struct efx_nic *efx) /************************************************************************** * - * Kernel netpoll interface - * - *************************************************************************/ - -#ifdef CONFIG_NET_POLL_CONTROLLER - -/* Although in the common case interrupts will be disabled, this is not - * guaranteed. However, all our work happens inside the NAPI callback, - * so no locking is required. - */ -static void efx_netpoll(struct net_device *net_dev) -{ - struct efx_nic *efx = netdev_priv(net_dev); - struct efx_channel *channel; - - efx_for_each_channel(channel, efx) - efx_schedule_channel(channel); -} - -#endif - -/************************************************************************** - * * Kernel net device interface * *************************************************************************/ @@ -2509,9 +2486,6 @@ static const struct net_device_ops efx_netdev_ops = { #endif .ndo_get_phys_port_id = efx_get_phys_port_id, .ndo_get_phys_port_name = efx_get_phys_port_name, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = efx_netpoll, -#endif .ndo_setup_tc = efx_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = efx_filter_rfs, diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index dd5530a4f8c8..03e2455c502e 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2054,29 +2054,6 @@ static void ef4_fini_napi(struct ef4_nic *efx) /************************************************************************** * - * Kernel netpoll interface - * - *************************************************************************/ - -#ifdef CONFIG_NET_POLL_CONTROLLER - -/* Although in the common case interrupts will be disabled, this is not - * guaranteed. However, all our work happens inside the NAPI callback, - * so no locking is required. - */ -static void ef4_netpoll(struct net_device *net_dev) -{ - struct ef4_nic *efx = netdev_priv(net_dev); - struct ef4_channel *channel; - - ef4_for_each_channel(channel, efx) - ef4_schedule_channel(channel); -} - -#endif - -/************************************************************************** - * * Kernel net device interface * *************************************************************************/ @@ -2250,9 +2227,6 @@ static const struct net_device_ops ef4_netdev_ops = { .ndo_set_mac_address = ef4_set_mac_address, .ndo_set_rx_mode = ef4_set_rx_mode, .ndo_set_features = ef4_set_features, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = ef4_netpoll, -#endif .ndo_setup_tc = ef4_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = ef4_filter_rfs, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6625fabe2c88..82eccc930c5c 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1325,11 +1325,15 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], info->key.tun_id = tunid; } - if (data[IFLA_GENEVE_TTL]) + if (data[IFLA_GENEVE_TTL_INHERIT]) { + if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) + *ttl_inherit = true; + else + *ttl_inherit = false; + } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); - - if (data[IFLA_GENEVE_TTL_INHERIT]) - *ttl_inherit = true; + *ttl_inherit = false; + } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 16ec7af6ab7b..ba9df430fca6 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -966,6 +966,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); + if (ym->cmd != SIOCYAMSMCS) + return -EINVAL; if (ym->bitrate > YAM_MAXBITRATE) { kfree(ym); return -EINVAL; @@ -981,6 +983,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_from_user(&yi, ifr->ifr_data, sizeof(struct yamdrv_ioctl_cfg))) return -EFAULT; + if (yi.cmd != SIOCYAMSCFG) + return -EINVAL; if ((yi.cfg.mask & YAM_IOBASE) && netif_running(dev)) return -EINVAL; /* Cannot change this parameter when up */ if ((yi.cfg.mask & YAM_IRQ) && netif_running(dev)) diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 23a52b9293f3..cd1d8faccca5 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1308,8 +1308,7 @@ static int adf7242_remove(struct spi_device *spi) { struct adf7242_local *lp = spi_get_drvdata(spi); - if (!IS_ERR_OR_NULL(lp->debugfs_root)) - debugfs_remove_recursive(lp->debugfs_root); + debugfs_remove_recursive(lp->debugfs_root); cancel_delayed_work_sync(&lp->work); destroy_workqueue(lp->wqueue); diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 58299fb666ed..0ff5a403a8dc 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -634,10 +634,9 @@ static int ca8210_test_int_driver_write( for (i = 0; i < len; i++) dev_dbg(&priv->spi->dev, "%#03x\n", buf[i]); - fifo_buffer = kmalloc(len, GFP_KERNEL); + fifo_buffer = kmemdup(buf, len, GFP_KERNEL); if (!fifo_buffer) return -ENOMEM; - memcpy(fifo_buffer, buf, len); kfifo_in(&test->up_fifo, &fifo_buffer, 4); wake_up_interruptible(&priv->test.readq); @@ -3044,8 +3043,7 @@ static void ca8210_test_interface_clear(struct ca8210_priv *priv) { struct ca8210_test *test = &priv->test; - if (!IS_ERR(test->ca8210_dfs_spi_int)) - debugfs_remove(test->ca8210_dfs_spi_int); + debugfs_remove(test->ca8210_dfs_spi_int); kfifo_free(&test->up_fifo); dev_info(&priv->spi->dev, "Test interface removed\n"); } diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index bf70ab892e69..51b5198d5943 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -37,8 +37,6 @@ MODULE_LICENSE("GPL"); static LIST_HEAD(hwsim_phys); static DEFINE_MUTEX(hwsim_phys_lock); -static LIST_HEAD(hwsim_ifup_phys); - static struct platform_device *mac802154hwsim_dev; /* MAC802154_HWSIM netlink family */ @@ -85,7 +83,6 @@ struct hwsim_phy { struct list_head edges; struct list_head list; - struct list_head list_ifup; }; static int hwsim_add_one(struct genl_info *info, struct device *dev, @@ -159,9 +156,6 @@ static int hwsim_hw_start(struct ieee802154_hw *hw) struct hwsim_phy *phy = hw->priv; phy->suspended = false; - list_add_rcu(&phy->list_ifup, &hwsim_ifup_phys); - synchronize_rcu(); - return 0; } @@ -170,8 +164,6 @@ static void hwsim_hw_stop(struct ieee802154_hw *hw) struct hwsim_phy *phy = hw->priv; phy->suspended = true; - list_del_rcu(&phy->list_ifup); - synchronize_rcu(); } static int diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index e428277781ac..44de81e5f140 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -132,11 +132,6 @@ static const struct reg_sequence mar20a_iar_overwrites[] = { }; #define MCR20A_VALID_CHANNELS (0x07FFF800) - -struct mcr20a_platform_data { - int rst_gpio; -}; - #define MCR20A_MAX_BUF (127) #define printdev(X) (&X->spi->dev) @@ -412,7 +407,6 @@ struct mcr20a_local { struct spi_device *spi; struct ieee802154_hw *hw; - struct mcr20a_platform_data *pdata; struct regmap *regmap_dar; struct regmap *regmap_iar; @@ -903,19 +897,19 @@ mcr20a_irq_clean_complete(void *context) switch (seq_state) { /* TX IRQ, RX IRQ and SEQ IRQ */ - case (0x03): + case (DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { lp->is_tx = 0; dev_dbg(printdev(lp), "TX is done. No ACK\n"); mcr20a_handle_tx_complete(lp); } break; - case (0x05): + case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ): /* rx is starting */ dev_dbg(printdev(lp), "RX is starting\n"); mcr20a_handle_rx(lp); break; - case (0x07): + case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { /* tx is done */ lp->is_tx = 0; @@ -927,7 +921,7 @@ mcr20a_irq_clean_complete(void *context) mcr20a_handle_rx(lp); } break; - case (0x01): + case (DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { dev_dbg(printdev(lp), "TX is starting\n"); mcr20a_handle_tx(lp); @@ -976,20 +970,6 @@ static irqreturn_t mcr20a_irq_isr(int irq, void *data) return IRQ_HANDLED; } -static int mcr20a_get_platform_data(struct spi_device *spi, - struct mcr20a_platform_data *pdata) -{ - int ret = 0; - - if (!spi->dev.of_node) - return -EINVAL; - - pdata->rst_gpio = of_get_named_gpio(spi->dev.of_node, "rst_b-gpio", 0); - dev_dbg(&spi->dev, "rst_b-gpio: %d\n", pdata->rst_gpio); - - return ret; -} - static void mcr20a_hw_setup(struct mcr20a_local *lp) { u8 i; @@ -1249,7 +1229,7 @@ mcr20a_probe(struct spi_device *spi) { struct ieee802154_hw *hw; struct mcr20a_local *lp; - struct mcr20a_platform_data *pdata; + struct gpio_desc *rst_b; int irq_type; int ret = -ENOMEM; @@ -1260,48 +1240,32 @@ mcr20a_probe(struct spi_device *spi) return -EINVAL; } - pdata = kmalloc(sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return -ENOMEM; - - /* set mcr20a platform data */ - ret = mcr20a_get_platform_data(spi, pdata); - if (ret < 0) { - dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n"); - goto free_pdata; - } - - /* init reset gpio */ - if (gpio_is_valid(pdata->rst_gpio)) { - ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio, - GPIOF_OUT_INIT_HIGH, "reset"); - if (ret) - goto free_pdata; + rst_b = devm_gpiod_get(&spi->dev, "rst_b", GPIOD_OUT_HIGH); + if (IS_ERR(rst_b)) { + ret = PTR_ERR(rst_b); + if (ret != -EPROBE_DEFER) + dev_err(&spi->dev, "Failed to get 'rst_b' gpio: %d", ret); + return ret; } /* reset mcr20a */ - if (gpio_is_valid(pdata->rst_gpio)) { - usleep_range(10, 20); - gpio_set_value_cansleep(pdata->rst_gpio, 0); - usleep_range(10, 20); - gpio_set_value_cansleep(pdata->rst_gpio, 1); - usleep_range(120, 240); - } + usleep_range(10, 20); + gpiod_set_value_cansleep(rst_b, 1); + usleep_range(10, 20); + gpiod_set_value_cansleep(rst_b, 0); + usleep_range(120, 240); /* allocate ieee802154_hw and private data */ hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops); if (!hw) { dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n"); - ret = -ENOMEM; - goto free_pdata; + return ret; } /* init mcr20a local data */ lp = hw->priv; lp->hw = hw; lp->spi = spi; - lp->spi->dev.platform_data = pdata; - lp->pdata = pdata; /* init ieee802154_hw */ hw->parent = &spi->dev; @@ -1370,8 +1334,6 @@ mcr20a_probe(struct spi_device *spi) free_dev: ieee802154_free_hw(lp->hw); -free_pdata: - kfree(pdata); return ret; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index f53ce65f45c5..43cb08dcce81 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -237,7 +237,12 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (!netdev) return !phydev->suspended; - /* Don't suspend PHY if the attached netdev parent may wakeup. + if (netdev->wol_enabled) + return false; + + /* As long as not all affected network drivers support the + * wol_enabled flag, let's check for hints that WoL is enabled. + * Don't suspend PHY if the attached netdev parent may wake up. * The parent may point to a PCI device, as in tg3 driver. */ if (netdev->dev.parent && device_may_wakeup(netdev->dev.parent)) @@ -1274,9 +1279,9 @@ void phy_detach(struct phy_device *phydev) sysfs_remove_link(&dev->dev.kobj, "phydev"); sysfs_remove_link(&phydev->mdio.dev.kobj, "attached_dev"); } + phy_suspend(phydev); phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; - phy_suspend(phydev); phydev->phylink = NULL; phy_led_triggers_unregister(phydev); @@ -1310,12 +1315,13 @@ EXPORT_SYMBOL(phy_detach); int phy_suspend(struct phy_device *phydev) { struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver); + struct net_device *netdev = phydev->attached_dev; struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; int ret = 0; /* If the device has WOL enabled, we cannot suspend the PHY */ phy_ethtool_get_wol(phydev, &wol); - if (wol.wolopts) + if (wol.wolopts || (netdev && netdev->wol_enabled)) return -EBUSY; if (phydev->drv && phydrv->suspend) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index b6993af5c9e4..9b8dd0d0ee42 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -690,6 +690,30 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) return 0; } +static int __phylink_connect_phy(struct phylink *pl, struct phy_device *phy, + phy_interface_t interface) +{ + int ret; + + if (WARN_ON(pl->link_an_mode == MLO_AN_FIXED || + (pl->link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(interface)))) + return -EINVAL; + + if (pl->phydev) + return -EBUSY; + + ret = phy_attach_direct(pl->netdev, phy, 0, interface); + if (ret) + return ret; + + ret = phylink_bringup_phy(pl, phy); + if (ret) + phy_detach(phy); + + return ret; +} + /** * phylink_connect_phy() - connect a PHY to the phylink instance * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -707,31 +731,13 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy) */ int phylink_connect_phy(struct phylink *pl, struct phy_device *phy) { - int ret; - - if (WARN_ON(pl->link_an_mode == MLO_AN_FIXED || - (pl->link_an_mode == MLO_AN_INBAND && - phy_interface_mode_is_8023z(pl->link_interface)))) - return -EINVAL; - - if (pl->phydev) - return -EBUSY; - /* Use PHY device/driver interface */ if (pl->link_interface == PHY_INTERFACE_MODE_NA) { pl->link_interface = phy->interface; pl->link_config.interface = pl->link_interface; } - ret = phy_attach_direct(pl->netdev, phy, 0, pl->link_interface); - if (ret) - return ret; - - ret = phylink_bringup_phy(pl, phy); - if (ret) - phy_detach(phy); - - return ret; + return __phylink_connect_phy(pl, phy, pl->link_interface); } EXPORT_SYMBOL_GPL(phylink_connect_phy); @@ -1648,7 +1654,9 @@ static void phylink_sfp_link_up(void *upstream) static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) { - return phylink_connect_phy(upstream, phy); + struct phylink *pl = upstream; + + return __phylink_connect_phy(upstream, phy, pl->link_config.interface); } static void phylink_sfp_disconnect_phy(void *upstream) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 52fffb98fde9..6e13b8832bc7 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -1098,8 +1098,11 @@ static int sfp_hwmon_insert(struct sfp *sfp) static void sfp_hwmon_remove(struct sfp *sfp) { - hwmon_device_unregister(sfp->hwmon_dev); - kfree(sfp->hwmon_name); + if (!IS_ERR_OR_NULL(sfp->hwmon_dev)) { + hwmon_device_unregister(sfp->hwmon_dev); + sfp->hwmon_dev = NULL; + kfree(sfp->hwmon_name); + } } #else static int sfp_hwmon_insert(struct sfp *sfp) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6a047d30e8c6..d887016e54b6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1167,6 +1167,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EBUSY; } + if (dev == port_dev) { + NL_SET_ERR_MSG(extack, "Cannot enslave team device to itself"); + netdev_err(dev, "Cannot enslave team device to itself\n"); + return -EINVAL; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3eb88b7147f0..b1743420939b 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -180,6 +180,7 @@ struct tun_file { }; struct napi_struct napi; bool napi_enabled; + bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; @@ -312,32 +313,32 @@ static int tun_napi_poll(struct napi_struct *napi, int budget) } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, - bool napi_en) + bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; + tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, NAPI_POLL_WEIGHT); napi_enable(&tfile->napi); - mutex_init(&tfile->napi_mutex); } } -static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile) +static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } -static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile) +static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } -static bool tun_napi_frags_enabled(const struct tun_struct *tun) +static bool tun_napi_frags_enabled(const struct tun_file *tfile) { - return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS; + return tfile->napi_frags_enabled; } #ifdef CONFIG_TUN_VNET_CROSS_LE @@ -689,8 +690,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun = rtnl_dereference(tfile->tun); if (tun && clean) { - tun_napi_disable(tun, tfile); - tun_napi_del(tun, tfile); + tun_napi_disable(tfile); + tun_napi_del(tfile); } if (tun && !tfile->detached) { @@ -757,7 +758,7 @@ static void tun_detach_all(struct net_device *dev) for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); - tun_napi_disable(tun, tfile); + tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); @@ -773,7 +774,7 @@ static void tun_detach_all(struct net_device *dev) synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - tun_napi_del(tun, tfile); + tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); @@ -792,7 +793,7 @@ static void tun_detach_all(struct net_device *dev) } static int tun_attach(struct tun_struct *tun, struct file *file, - bool skip_filter, bool napi) + bool skip_filter, bool napi, bool napi_frags) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; @@ -865,7 +866,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, tun_enable_queue(tfile); } else { sock_hold(&tfile->sk); - tun_napi_init(tun, tfile, napi); + tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) @@ -1743,7 +1744,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, int err; u32 rxhash = 0; int skb_xdp = 1; - bool frags = tun_napi_frags_enabled(tun); + bool frags = tun_napi_frags_enabled(tfile); if (!(tun->dev->flags & IFF_UP)) return -EIO; @@ -2683,7 +2684,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, - ifr->ifr_flags & IFF_NAPI); + ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS); if (err < 0) return err; @@ -2781,7 +2783,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI); + err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS); if (err < 0) goto err_free_flow; @@ -2930,7 +2933,8 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; - ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI); + ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, + tun->flags & IFF_NAPI_FRAGS); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) @@ -3348,6 +3352,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) return -ENOMEM; } + mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index e95dd12edec4..023b8d0bf175 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -607,6 +607,9 @@ int asix_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0; + if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= AX_MONITOR_LINK; if (wolinfo->wolopts & WAKE_MAGIC) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 9e8ad372f419..2207f7a7d1ff 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -566,6 +566,9 @@ ax88179_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0; + if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= AX_MONITOR_MODE_RWLC; if (wolinfo->wolopts & WAKE_MAGIC) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 656441d9a955..be1917be28f2 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1387,19 +1387,10 @@ static int lan78xx_set_wol(struct net_device *netdev, if (ret < 0) return ret; - pdata->wol = 0; - if (wol->wolopts & WAKE_UCAST) - pdata->wol |= WAKE_UCAST; - if (wol->wolopts & WAKE_MCAST) - pdata->wol |= WAKE_MCAST; - if (wol->wolopts & WAKE_BCAST) - pdata->wol |= WAKE_BCAST; - if (wol->wolopts & WAKE_MAGIC) - pdata->wol |= WAKE_MAGIC; - if (wol->wolopts & WAKE_PHY) - pdata->wol |= WAKE_PHY; - if (wol->wolopts & WAKE_ARP) - pdata->wol |= WAKE_ARP; + if (wol->wolopts & ~WAKE_ALL) + return -EINVAL; + + pdata->wol = wol->wolopts; device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2cd71bdb6484..f1b5201cc320 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4506,6 +4506,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (!rtl_can_wakeup(tp)) return -EOPNOTSUPP; + if (wol->wolopts & ~WAKE_ANY) + return -EINVAL; + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out_set_wol; diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 05553d252446..ec287c9741e8 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -731,6 +731,9 @@ static int smsc75xx_ethtool_set_wol(struct net_device *net, struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); int ret; + if (wolinfo->wolopts & ~SUPPORTED_WAKE) + return -EINVAL; + pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE; ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts); @@ -1517,6 +1520,7 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); if (pdata) { + cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); pdata = NULL; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 06b4d290784d..262e7a3c23cb 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -774,6 +774,9 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); int ret; + if (wolinfo->wolopts & ~SUPPORTED_WAKE) + return -EINVAL; + pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE; ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts); diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 9277a0f228df..35f39f23d881 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -421,6 +421,9 @@ sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0; + if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= SR_MONITOR_LINK; if (wolinfo->wolopts & WAKE_MAGIC) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 765920905226..dab504ec5e50 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1699,17 +1699,6 @@ static void virtnet_stats(struct net_device *dev, tot->rx_frame_errors = dev->stats.rx_frame_errors; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void virtnet_netpoll(struct net_device *dev) -{ - struct virtnet_info *vi = netdev_priv(dev); - int i; - - for (i = 0; i < vi->curr_queue_pairs; i++) - napi_schedule(&vi->rq[i].napi); -} -#endif - static void virtnet_ack_link_announce(struct virtnet_info *vi) { rtnl_lock(); @@ -2447,9 +2436,6 @@ static const struct net_device_ops virtnet_netdev = { .ndo_get_stats64 = virtnet_stats, .ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = virtnet_netpoll, -#endif .ndo_bpf = virtnet_xdp, .ndo_xdp_xmit = virtnet_xdp_xmit, .ndo_features_check = passthru_features_check, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e5d236595206..fb0cdbba8d76 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3539,6 +3539,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ @@ -3603,6 +3604,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || + nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, + !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c index 094cea775d0c..ef298d8525c5 100644 --- a/drivers/net/wimax/i2400m/control.c +++ b/drivers/net/wimax/i2400m/control.c @@ -257,7 +257,7 @@ static const struct [I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO }, [I2400M_MS_BUSY] = { "busy", -EBUSY }, [I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ }, - [I2400M_MS_UNINITIALIZED] = { "not unitialized", -EILSEQ }, + [I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ }, [I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO }, [I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO }, [I2400M_MS_NO_RF] = { "no RF", -EIO }, diff --git a/drivers/net/wireless/broadcom/b43/dma.c b/drivers/net/wireless/broadcom/b43/dma.c index d113bd997f4b..dfc4c34298d4 100644 --- a/drivers/net/wireless/broadcom/b43/dma.c +++ b/drivers/net/wireless/broadcom/b43/dma.c @@ -1518,13 +1518,15 @@ void b43_dma_handle_txstatus(struct b43_wldev *dev, } } else { /* More than a single header/data pair were missed. - * Report this error, and reset the controller to + * Report this error. If running with open-source + * firmware, then reset the controller to * revive operation. */ b43dbg(dev->wl, "Out of order TX status report on DMA ring %d. Expected %d, but got %d\n", ring->index, firstused, slot); - b43_controller_restart(dev, "Out of order TX"); + if (dev->fw.opensource) + b43_controller_restart(dev, "Out of order TX"); return; } } diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c index 46686ee88ff4..76b5ddb20248 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c @@ -47,6 +47,7 @@ static const struct iwl_base_params iwl1000_base_params = { .num_of_queues = IWLAGN_NUM_QUEUES, + .max_tfd_queue_size = 256, .eeprom_size = OTP_LOW_IMAGE_SIZE, .pll_cfg = true, .max_ll_items = OTP_MAX_LL_ITEMS_1000, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index f3863101af78..6f2730c7229b 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -521,7 +521,6 @@ struct mac80211_hwsim_data { int channels, idx; bool use_chanctx; bool destroy_on_close; - struct work_struct destroy_work; u32 portid; char alpha2[2]; const struct ieee80211_regdomain *regd; @@ -2931,8 +2930,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, hwsim_radios_generation++; spin_unlock_bh(&hwsim_radio_lock); - if (idx > 0) - hwsim_mcast_new_radio(idx, info, param); + hwsim_mcast_new_radio(idx, info, param); return idx; @@ -3561,30 +3559,27 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; -static void destroy_radio(struct work_struct *work) -{ - struct mac80211_hwsim_data *data = - container_of(work, struct mac80211_hwsim_data, destroy_work); - - hwsim_radios_generation++; - mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); -} - static void remove_user_radios(u32 portid) { struct mac80211_hwsim_data *entry, *tmp; + LIST_HEAD(list); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry_safe(entry, tmp, &hwsim_radios, list) { if (entry->destroy_on_close && entry->portid == portid) { - list_del(&entry->list); + list_move(&entry->list, &list); rhashtable_remove_fast(&hwsim_radios_rht, &entry->rht, hwsim_rht_params); - INIT_WORK(&entry->destroy_work, destroy_radio); - queue_work(hwsim_wq, &entry->destroy_work); + hwsim_radios_generation++; } } spin_unlock_bh(&hwsim_radio_lock); + + list_for_each_entry_safe(entry, tmp, &list, list) { + list_del(&entry->list); + mac80211_hwsim_del_radio(entry, wiphy_name(entry->hw->wiphy), + NULL); + } } static int mac80211_hwsim_netlink_notify(struct notifier_block *nb, @@ -3642,6 +3637,7 @@ static __net_init int hwsim_init_net(struct net *net) static void __net_exit hwsim_exit_net(struct net *net) { struct mac80211_hwsim_data *data, *tmp; + LIST_HEAD(list); spin_lock_bh(&hwsim_radio_lock); list_for_each_entry_safe(data, tmp, &hwsim_radios, list) { @@ -3652,17 +3648,19 @@ static void __net_exit hwsim_exit_net(struct net *net) if (data->netgroup == hwsim_net_get_netgroup(&init_net)) continue; - list_del(&data->list); + list_move(&data->list, &list); rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, hwsim_rht_params); hwsim_radios_generation++; - spin_unlock_bh(&hwsim_radio_lock); + } + spin_unlock_bh(&hwsim_radio_lock); + + list_for_each_entry_safe(data, tmp, &list, list) { + list_del(&data->list); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL); - spin_lock_bh(&hwsim_radio_lock); } - spin_unlock_bh(&hwsim_radio_lock); ida_simple_remove(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net)); } diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index a46a1e94505d..936c0b3e0ba2 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -241,8 +241,9 @@ struct xenvif_hash_cache { struct xenvif_hash { unsigned int alg; u32 flags; + bool mapping_sel; u8 key[XEN_NETBK_MAX_HASH_KEY_SIZE]; - u32 mapping[XEN_NETBK_MAX_HASH_MAPPING_SIZE]; + u32 mapping[2][XEN_NETBK_MAX_HASH_MAPPING_SIZE]; unsigned int size; struct xenvif_hash_cache cache; }; diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 3c4c58b9fe76..0ccb021f1e78 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -324,7 +324,8 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; vif->hash.size = size; - memset(vif->hash.mapping, 0, sizeof(u32) * size); + memset(vif->hash.mapping[vif->hash.mapping_sel], 0, + sizeof(u32) * size); return XEN_NETIF_CTRL_STATUS_SUCCESS; } @@ -332,31 +333,49 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size) u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len, u32 off) { - u32 *mapping = &vif->hash.mapping[off]; - struct gnttab_copy copy_op = { + u32 *mapping = vif->hash.mapping[!vif->hash.mapping_sel]; + unsigned int nr = 1; + struct gnttab_copy copy_op[2] = {{ .source.u.ref = gref, .source.domid = vif->domid, - .dest.u.gmfn = virt_to_gfn(mapping), .dest.domid = DOMID_SELF, - .dest.offset = xen_offset_in_page(mapping), - .len = len * sizeof(u32), + .len = len * sizeof(*mapping), .flags = GNTCOPY_source_gref - }; + }}; - if ((off + len > vif->hash.size) || copy_op.len > XEN_PAGE_SIZE) + if ((off + len < off) || (off + len > vif->hash.size) || + len > XEN_PAGE_SIZE / sizeof(*mapping)) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; - while (len-- != 0) - if (mapping[off++] >= vif->num_queues) - return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; + copy_op[0].dest.u.gmfn = virt_to_gfn(mapping + off); + copy_op[0].dest.offset = xen_offset_in_page(mapping + off); + if (copy_op[0].dest.offset + copy_op[0].len > XEN_PAGE_SIZE) { + copy_op[1] = copy_op[0]; + copy_op[1].source.offset = XEN_PAGE_SIZE - copy_op[0].dest.offset; + copy_op[1].dest.u.gmfn = virt_to_gfn(mapping + off + len); + copy_op[1].dest.offset = 0; + copy_op[1].len = copy_op[0].len - copy_op[1].source.offset; + copy_op[0].len = copy_op[1].source.offset; + nr = 2; + } - if (copy_op.len != 0) { - gnttab_batch_copy(©_op, 1); + memcpy(mapping, vif->hash.mapping[vif->hash.mapping_sel], + vif->hash.size * sizeof(*mapping)); - if (copy_op.status != GNTST_okay) + if (copy_op[0].len != 0) { + gnttab_batch_copy(copy_op, nr); + + if (copy_op[0].status != GNTST_okay || + copy_op[nr - 1].status != GNTST_okay) return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; } + while (len-- != 0) + if (mapping[off++] >= vif->num_queues) + return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER; + + vif->hash.mapping_sel = !vif->hash.mapping_sel; + return XEN_NETIF_CTRL_STATUS_SUCCESS; } @@ -408,6 +427,8 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m) } if (vif->hash.size != 0) { + const u32 *mapping = vif->hash.mapping[vif->hash.mapping_sel]; + seq_puts(m, "\nHash Mapping:\n"); for (i = 0; i < vif->hash.size; ) { @@ -420,7 +441,7 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m) seq_printf(m, "[%4u - %4u]: ", i, i + n - 1); for (j = 0; j < n; j++, i++) - seq_printf(m, "%4u ", vif->hash.mapping[i]); + seq_printf(m, "%4u ", mapping[i]); seq_puts(m, "\n"); } diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 7e3ea39a1b39..182d6770f102 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -162,7 +162,8 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, if (size == 0) return skb_get_hash_raw(skb) % dev->real_num_tx_queues; - return vif->hash.mapping[skb_get_hash_raw(skb) % size]; + return vif->hash.mapping[vif->hash.mapping_sel] + [skb_get_hash_raw(skb) % size]; } static netdev_tx_t diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5a9562881d4e..9fe3fff818b8 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -537,8 +537,10 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) INIT_WORK(&ctrl->ana_work, nvme_ana_work); ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); - if (!ctrl->ana_log_buf) + if (!ctrl->ana_log_buf) { + error = -ENOMEM; goto out; + } error = nvme_read_ana_log(ctrl, true); if (error) @@ -547,7 +549,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) out_free_ana_log_buf: kfree(ctrl->ana_log_buf); out: - return -ENOMEM; + return error; } void nvme_mpath_uninit(struct nvme_ctrl *ctrl) diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 778c4f76a884..2153956a0b20 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -135,7 +135,7 @@ static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, int index, if (val & PCIE_ATU_ENABLE) return; - usleep_range(LINK_WAIT_IATU_MIN, LINK_WAIT_IATU_MAX); + mdelay(LINK_WAIT_IATU); } dev_err(pci->dev, "Outbound iATU is not being enabled\n"); } @@ -178,7 +178,7 @@ void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type, if (val & PCIE_ATU_ENABLE) return; - usleep_range(LINK_WAIT_IATU_MIN, LINK_WAIT_IATU_MAX); + mdelay(LINK_WAIT_IATU); } dev_err(pci->dev, "Outbound iATU is not being enabled\n"); } @@ -236,7 +236,7 @@ static int dw_pcie_prog_inbound_atu_unroll(struct dw_pcie *pci, int index, if (val & PCIE_ATU_ENABLE) return 0; - usleep_range(LINK_WAIT_IATU_MIN, LINK_WAIT_IATU_MAX); + mdelay(LINK_WAIT_IATU); } dev_err(pci->dev, "Inbound iATU is not being enabled\n"); @@ -282,7 +282,7 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int bar, if (val & PCIE_ATU_ENABLE) return 0; - usleep_range(LINK_WAIT_IATU_MIN, LINK_WAIT_IATU_MAX); + mdelay(LINK_WAIT_IATU); } dev_err(pci->dev, "Inbound iATU is not being enabled\n"); diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 96126fd8403c..9f1a5e399b70 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -26,8 +26,7 @@ /* Parameters for the waiting for iATU enabled routine */ #define LINK_WAIT_MAX_IATU_RETRIES 5 -#define LINK_WAIT_IATU_MIN 9000 -#define LINK_WAIT_IATU_MAX 10000 +#define LINK_WAIT_IATU 9 /* Synopsys-specific PCIe configuration registers */ #define PCIE_PORT_LINK_CONTROL 0x710 diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 50eb0729385b..a41d79b8d46a 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1145,7 +1145,6 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) { struct device *dev = &pcie->pdev->dev; struct device_node *np = dev->of_node; - unsigned int i; int ret; INIT_LIST_HEAD(&pcie->resources); @@ -1179,13 +1178,58 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) resource_size(&pcie->io) - 1); pcie->realio.name = "PCI I/O"; + pci_add_resource(&pcie->resources, &pcie->realio); + } + + return devm_request_pci_bus_resources(dev, &pcie->resources); +} + +/* + * This is a copy of pci_host_probe(), except that it does the I/O + * remap as the last step, once we are sure we won't fail. + * + * It should be removed once the I/O remap error handling issue has + * been sorted out. + */ +static int mvebu_pci_host_probe(struct pci_host_bridge *bridge) +{ + struct mvebu_pcie *pcie; + struct pci_bus *bus, *child; + int ret; + + ret = pci_scan_root_bus_bridge(bridge); + if (ret < 0) { + dev_err(bridge->dev.parent, "Scanning root bridge failed"); + return ret; + } + + pcie = pci_host_bridge_priv(bridge); + if (resource_size(&pcie->io) != 0) { + unsigned int i; + for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K) pci_ioremap_io(i, pcie->io.start + i); + } - pci_add_resource(&pcie->resources, &pcie->realio); + bus = bridge->bus; + + /* + * We insert PCI resources into the iomem_resource and + * ioport_resource trees in either pci_bus_claim_resources() + * or pci_bus_assign_resources(). + */ + if (pci_has_flag(PCI_PROBE_ONLY)) { + pci_bus_claim_resources(bus); + } else { + pci_bus_size_bridges(bus); + pci_bus_assign_resources(bus); + + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } - return devm_request_pci_bus_resources(dev, &pcie->resources); + pci_bus_add_devices(bus); + return 0; } static int mvebu_pcie_probe(struct platform_device *pdev) @@ -1268,7 +1312,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev) bridge->align_resource = mvebu_pcie_align_resource; bridge->msi = pcie->msi; - return pci_host_probe(bridge); + return mvebu_pci_host_probe(bridge); } static const struct of_device_id mvebu_pcie_of_match_table[] = { diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index ef0b1b6ba86f..12afa7fdf77e 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -457,17 +457,18 @@ static void acpiphp_native_scan_bridge(struct pci_dev *bridge) /** * enable_slot - enable, configure a slot * @slot: slot to be enabled + * @bridge: true if enable is for the whole bridge (not a single slot) * * This function should be called per *physical slot*, * not per each slot object in ACPI namespace. */ -static void enable_slot(struct acpiphp_slot *slot) +static void enable_slot(struct acpiphp_slot *slot, bool bridge) { struct pci_dev *dev; struct pci_bus *bus = slot->bus; struct acpiphp_func *func; - if (bus->self && hotplug_is_native(bus->self)) { + if (bridge && bus->self && hotplug_is_native(bus->self)) { /* * If native hotplug is used, it will take care of hotplug * slot management and resource allocation for hotplug @@ -701,7 +702,7 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge) trim_stale_devices(dev); /* configure all functions */ - enable_slot(slot); + enable_slot(slot, true); } else { disable_slot(slot); } @@ -785,7 +786,7 @@ static void hotplug_event(u32 type, struct acpiphp_context *context) if (bridge) acpiphp_check_bridge(bridge); else if (!(slot->flags & SLOT_IS_GOING_AWAY)) - enable_slot(slot); + enable_slot(slot, false); break; @@ -973,7 +974,7 @@ int acpiphp_enable_slot(struct acpiphp_slot *slot) /* configure all functions */ if (!(slot->flags & SLOT_ENABLED)) - enable_slot(slot); + enable_slot(slot, false); pci_unlock_rescan_remove(); return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1835f3a7aa8d..51b6c81671c1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1289,12 +1289,12 @@ int pci_save_state(struct pci_dev *dev) EXPORT_SYMBOL(pci_save_state); static void pci_restore_config_dword(struct pci_dev *pdev, int offset, - u32 saved_val, int retry) + u32 saved_val, int retry, bool force) { u32 val; pci_read_config_dword(pdev, offset, &val); - if (val == saved_val) + if (!force && val == saved_val) return; for (;;) { @@ -1313,25 +1313,36 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset, } static void pci_restore_config_space_range(struct pci_dev *pdev, - int start, int end, int retry) + int start, int end, int retry, + bool force) { int index; for (index = end; index >= start; index--) pci_restore_config_dword(pdev, 4 * index, pdev->saved_config_space[index], - retry); + retry, force); } static void pci_restore_config_space(struct pci_dev *pdev) { if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) { - pci_restore_config_space_range(pdev, 10, 15, 0); + pci_restore_config_space_range(pdev, 10, 15, 0, false); /* Restore BARs before the command register. */ - pci_restore_config_space_range(pdev, 4, 9, 10); - pci_restore_config_space_range(pdev, 0, 3, 0); + pci_restore_config_space_range(pdev, 4, 9, 10, false); + pci_restore_config_space_range(pdev, 0, 3, 0, false); + } else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + pci_restore_config_space_range(pdev, 12, 15, 0, false); + + /* + * Force rewriting of prefetch registers to avoid S3 resume + * issues on Intel PCI bridges that occur when these + * registers are not explicitly written. + */ + pci_restore_config_space_range(pdev, 9, 11, 0, true); + pci_restore_config_space_range(pdev, 0, 8, 0, false); } else { - pci_restore_config_space_range(pdev, 0, 15, 0); + pci_restore_config_space_range(pdev, 0, 15, 0, false); } } diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 5c8d452e35e2..c89d3effd99d 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -48,6 +48,7 @@ source "drivers/phy/lantiq/Kconfig" source "drivers/phy/marvell/Kconfig" source "drivers/phy/mediatek/Kconfig" source "drivers/phy/motorola/Kconfig" +source "drivers/phy/mscc/Kconfig" source "drivers/phy/qualcomm/Kconfig" source "drivers/phy/ralink/Kconfig" source "drivers/phy/renesas/Kconfig" diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile index 84e3bd9c5665..ce8339ff0022 100644 --- a/drivers/phy/Makefile +++ b/drivers/phy/Makefile @@ -18,6 +18,7 @@ obj-y += broadcom/ \ hisilicon/ \ marvell/ \ motorola/ \ + mscc/ \ qualcomm/ \ ralink/ \ samsung/ \ diff --git a/drivers/phy/mscc/Kconfig b/drivers/phy/mscc/Kconfig new file mode 100644 index 000000000000..2e2a466efd66 --- /dev/null +++ b/drivers/phy/mscc/Kconfig @@ -0,0 +1,11 @@ +# +# Phy drivers for Microsemi devices +# + +config PHY_OCELOT_SERDES + tristate "SerDes PHY driver for Microsemi Ocelot" + select GENERIC_PHY + depends on OF + depends on MFD_SYSCON + help + Enable this for supporting SerDes muxing with Microsemi Ocelot. diff --git a/drivers/phy/mscc/Makefile b/drivers/phy/mscc/Makefile new file mode 100644 index 000000000000..e14749170fc9 --- /dev/null +++ b/drivers/phy/mscc/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Microsemi phy drivers. +# + +obj-$(CONFIG_PHY_OCELOT_SERDES) := phy-ocelot-serdes.o diff --git a/drivers/phy/mscc/phy-ocelot-serdes.c b/drivers/phy/mscc/phy-ocelot-serdes.c new file mode 100644 index 000000000000..8936abd22f0f --- /dev/null +++ b/drivers/phy/mscc/phy-ocelot-serdes.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * SerDes PHY driver for Microsemi Ocelot + * + * Copyright (c) 2018 Microsemi + * + */ + +#include <linux/err.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <soc/mscc/ocelot_hsio.h> +#include <dt-bindings/phy/phy-ocelot-serdes.h> + +struct serdes_ctrl { + struct regmap *regs; + struct device *dev; + struct phy *phys[SERDES_MAX]; +}; + +struct serdes_macro { + u8 idx; + /* Not used when in QSGMII or PCIe mode */ + int port; + struct serdes_ctrl *ctrl; +}; + +#define MCB_S1G_CFG_TIMEOUT 50 + +static int __serdes_write_mcb_s1g(struct regmap *regmap, u8 macro, u32 op) +{ + unsigned int regval; + + regmap_write(regmap, HSIO_MCB_S1G_ADDR_CFG, op | + HSIO_MCB_S1G_ADDR_CFG_SERDES1G_ADDR(BIT(macro))); + + return regmap_read_poll_timeout(regmap, HSIO_MCB_S1G_ADDR_CFG, regval, + (regval & op) != op, 100, + MCB_S1G_CFG_TIMEOUT * 1000); +} + +static int serdes_commit_mcb_s1g(struct regmap *regmap, u8 macro) +{ + return __serdes_write_mcb_s1g(regmap, macro, + HSIO_MCB_S1G_ADDR_CFG_SERDES1G_WR_ONE_SHOT); +} + +static int serdes_update_mcb_s1g(struct regmap *regmap, u8 macro) +{ + return __serdes_write_mcb_s1g(regmap, macro, + HSIO_MCB_S1G_ADDR_CFG_SERDES1G_RD_ONE_SHOT); +} + +static int serdes_init_s1g(struct regmap *regmap, u8 serdes) +{ + int ret; + + ret = serdes_update_mcb_s1g(regmap, serdes); + if (ret) + return ret; + + regmap_update_bits(regmap, HSIO_S1G_COMMON_CFG, + HSIO_S1G_COMMON_CFG_SYS_RST | + HSIO_S1G_COMMON_CFG_ENA_LANE | + HSIO_S1G_COMMON_CFG_ENA_ELOOP | + HSIO_S1G_COMMON_CFG_ENA_FLOOP, + HSIO_S1G_COMMON_CFG_ENA_LANE); + + regmap_update_bits(regmap, HSIO_S1G_PLL_CFG, + HSIO_S1G_PLL_CFG_PLL_FSM_ENA | + HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA_M, + HSIO_S1G_PLL_CFG_PLL_FSM_CTRL_DATA(200) | + HSIO_S1G_PLL_CFG_PLL_FSM_ENA); + + regmap_update_bits(regmap, HSIO_S1G_MISC_CFG, + HSIO_S1G_MISC_CFG_DES_100FX_CPMD_ENA | + HSIO_S1G_MISC_CFG_LANE_RST, + HSIO_S1G_MISC_CFG_LANE_RST); + + ret = serdes_commit_mcb_s1g(regmap, serdes); + if (ret) + return ret; + + regmap_update_bits(regmap, HSIO_S1G_COMMON_CFG, + HSIO_S1G_COMMON_CFG_SYS_RST, + HSIO_S1G_COMMON_CFG_SYS_RST); + + regmap_update_bits(regmap, HSIO_S1G_MISC_CFG, + HSIO_S1G_MISC_CFG_LANE_RST, 0); + + ret = serdes_commit_mcb_s1g(regmap, serdes); + if (ret) + return ret; + + return 0; +} + +struct serdes_mux { + u8 idx; + u8 port; + enum phy_mode mode; + u32 mask; + u32 mux; +}; + +#define SERDES_MUX(_idx, _port, _mode, _mask, _mux) { \ + .idx = _idx, \ + .port = _port, \ + .mode = _mode, \ + .mask = _mask, \ + .mux = _mux, \ +} + +#define SERDES_MUX_SGMII(i, p, m, c) SERDES_MUX(i, p, PHY_MODE_SGMII, m, c) +#define SERDES_MUX_QSGMII(i, p, m, c) SERDES_MUX(i, p, PHY_MODE_QSGMII, m, c) + +static const struct serdes_mux ocelot_serdes_muxes[] = { + SERDES_MUX_SGMII(SERDES1G(0), 0, 0, 0), + SERDES_MUX_SGMII(SERDES1G(1), 1, HSIO_HW_CFG_DEV1G_5_MODE, 0), + SERDES_MUX_SGMII(SERDES1G(1), 5, HSIO_HW_CFG_QSGMII_ENA | + HSIO_HW_CFG_DEV1G_5_MODE, HSIO_HW_CFG_DEV1G_5_MODE), + SERDES_MUX_SGMII(SERDES1G(2), 2, HSIO_HW_CFG_DEV1G_4_MODE, 0), + SERDES_MUX_SGMII(SERDES1G(2), 4, HSIO_HW_CFG_QSGMII_ENA | + HSIO_HW_CFG_DEV1G_4_MODE, HSIO_HW_CFG_DEV1G_4_MODE), + SERDES_MUX_SGMII(SERDES1G(3), 3, HSIO_HW_CFG_DEV1G_6_MODE, 0), + SERDES_MUX_SGMII(SERDES1G(3), 6, HSIO_HW_CFG_QSGMII_ENA | + HSIO_HW_CFG_DEV1G_6_MODE, HSIO_HW_CFG_DEV1G_6_MODE), + SERDES_MUX_SGMII(SERDES1G(4), 4, HSIO_HW_CFG_QSGMII_ENA | + HSIO_HW_CFG_DEV1G_4_MODE | HSIO_HW_CFG_DEV1G_9_MODE, + 0), + SERDES_MUX_SGMII(SERDES1G(4), 9, HSIO_HW_CFG_DEV1G_4_MODE | + HSIO_HW_CFG_DEV1G_9_MODE, HSIO_HW_CFG_DEV1G_4_MODE | + HSIO_HW_CFG_DEV1G_9_MODE), + SERDES_MUX_SGMII(SERDES1G(5), 5, HSIO_HW_CFG_QSGMII_ENA | + HSIO_HW_CFG_DEV1G_5_MODE | HSIO_HW_CFG_DEV2G5_10_MODE, + 0), + SERDES_MUX_SGMII(SERDES1G(5), 10, HSIO_HW_CFG_PCIE_ENA | + HSIO_HW_CFG_DEV1G_5_MODE | HSIO_HW_CFG_DEV2G5_10_MODE, + HSIO_HW_CFG_DEV1G_5_MODE | HSIO_HW_CFG_DEV2G5_10_MODE), + SERDES_MUX_QSGMII(SERDES6G(0), 4, HSIO_HW_CFG_QSGMII_ENA, + HSIO_HW_CFG_QSGMII_ENA), + SERDES_MUX_QSGMII(SERDES6G(0), 5, HSIO_HW_CFG_QSGMII_ENA, + HSIO_HW_CFG_QSGMII_ENA), + SERDES_MUX_QSGMII(SERDES6G(0), 6, HSIO_HW_CFG_QSGMII_ENA, + HSIO_HW_CFG_QSGMII_ENA), + SERDES_MUX_SGMII(SERDES6G(0), 7, HSIO_HW_CFG_QSGMII_ENA, 0), + SERDES_MUX_QSGMII(SERDES6G(0), 7, HSIO_HW_CFG_QSGMII_ENA, + HSIO_HW_CFG_QSGMII_ENA), + SERDES_MUX_SGMII(SERDES6G(1), 8, 0, 0), + SERDES_MUX_SGMII(SERDES6G(2), 10, HSIO_HW_CFG_PCIE_ENA | + HSIO_HW_CFG_DEV2G5_10_MODE, 0), + SERDES_MUX(SERDES6G(2), 10, PHY_MODE_PCIE, HSIO_HW_CFG_PCIE_ENA, + HSIO_HW_CFG_PCIE_ENA), +}; + +static int serdes_set_mode(struct phy *phy, enum phy_mode mode) +{ + struct serdes_macro *macro = phy_get_drvdata(phy); + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(ocelot_serdes_muxes); i++) { + if (macro->idx != ocelot_serdes_muxes[i].idx || + mode != ocelot_serdes_muxes[i].mode) + continue; + + if (mode != PHY_MODE_QSGMII && + macro->port != ocelot_serdes_muxes[i].port) + continue; + + ret = regmap_update_bits(macro->ctrl->regs, HSIO_HW_CFG, + ocelot_serdes_muxes[i].mask, + ocelot_serdes_muxes[i].mux); + if (ret) + return ret; + + if (macro->idx <= SERDES1G_MAX) + return serdes_init_s1g(macro->ctrl->regs, macro->idx); + + /* SERDES6G and PCIe not supported yet */ + return -EOPNOTSUPP; + } + + return -EINVAL; +} + +static const struct phy_ops serdes_ops = { + .set_mode = serdes_set_mode, + .owner = THIS_MODULE, +}; + +static struct phy *serdes_simple_xlate(struct device *dev, + struct of_phandle_args *args) +{ + struct serdes_ctrl *ctrl = dev_get_drvdata(dev); + unsigned int port, idx, i; + + if (args->args_count != 2) + return ERR_PTR(-EINVAL); + + port = args->args[0]; + idx = args->args[1]; + + for (i = 0; i <= SERDES_MAX; i++) { + struct serdes_macro *macro = phy_get_drvdata(ctrl->phys[i]); + + if (idx != macro->idx) + continue; + + /* SERDES6G(0) is the only SerDes capable of QSGMII */ + if (idx != SERDES6G(0) && macro->port >= 0) + return ERR_PTR(-EBUSY); + + macro->port = port; + return ctrl->phys[i]; + } + + return ERR_PTR(-ENODEV); +} + +static int serdes_phy_create(struct serdes_ctrl *ctrl, u8 idx, struct phy **phy) +{ + struct serdes_macro *macro; + + *phy = devm_phy_create(ctrl->dev, NULL, &serdes_ops); + if (IS_ERR(*phy)) + return PTR_ERR(*phy); + + macro = devm_kzalloc(ctrl->dev, sizeof(*macro), GFP_KERNEL); + if (!macro) + return -ENOMEM; + + macro->idx = idx; + macro->ctrl = ctrl; + macro->port = -1; + + phy_set_drvdata(*phy, macro); + + return 0; +} + +static int serdes_probe(struct platform_device *pdev) +{ + struct phy_provider *provider; + struct serdes_ctrl *ctrl; + unsigned int i; + int ret; + + ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL); + if (!ctrl) + return -ENOMEM; + + ctrl->dev = &pdev->dev; + ctrl->regs = syscon_node_to_regmap(pdev->dev.parent->of_node); + if (!ctrl->regs) + return -ENODEV; + + for (i = 0; i <= SERDES_MAX; i++) { + ret = serdes_phy_create(ctrl, i, &ctrl->phys[i]); + if (ret) + return ret; + } + + dev_set_drvdata(&pdev->dev, ctrl); + + provider = devm_of_phy_provider_register(ctrl->dev, + serdes_simple_xlate); + + return PTR_ERR_OR_ZERO(provider); +} + +static const struct of_device_id serdes_ids[] = { + { .compatible = "mscc,vsc7514-serdes", }, + {}, +}; +MODULE_DEVICE_TABLE(of, serdes_ids); + +static struct platform_driver mscc_ocelot_serdes = { + .probe = serdes_probe, + .driver = { + .name = "mscc,ocelot-serdes", + .of_match_table = of_match_ptr(serdes_ids), + }, +}; + +module_platform_driver(mscc_ocelot_serdes); + +MODULE_AUTHOR("Quentin Schulz <quentin.schulz@bootlin.com>"); +MODULE_DESCRIPTION("SerDes driver for Microsemi Ocelot"); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c index 8d48371caaa2..e7f45d96b0cb 100644 --- a/drivers/pinctrl/intel/pinctrl-cannonlake.c +++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c @@ -15,10 +15,11 @@ #include "pinctrl-intel.h" -#define CNL_PAD_OWN 0x020 -#define CNL_PADCFGLOCK 0x080 -#define CNL_HOSTSW_OWN 0x0b0 -#define CNL_GPI_IE 0x120 +#define CNL_PAD_OWN 0x020 +#define CNL_PADCFGLOCK 0x080 +#define CNL_LP_HOSTSW_OWN 0x0b0 +#define CNL_H_HOSTSW_OWN 0x0c0 +#define CNL_GPI_IE 0x120 #define CNL_GPP(r, s, e, g) \ { \ @@ -30,12 +31,12 @@ #define CNL_NO_GPIO -1 -#define CNL_COMMUNITY(b, s, e, g) \ +#define CNL_COMMUNITY(b, s, e, o, g) \ { \ .barno = (b), \ .padown_offset = CNL_PAD_OWN, \ .padcfglock_offset = CNL_PADCFGLOCK, \ - .hostown_offset = CNL_HOSTSW_OWN, \ + .hostown_offset = (o), \ .ie_offset = CNL_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ @@ -43,6 +44,12 @@ .ngpps = ARRAY_SIZE(g), \ } +#define CNLLP_COMMUNITY(b, s, e, g) \ + CNL_COMMUNITY(b, s, e, CNL_LP_HOSTSW_OWN, g) + +#define CNLH_COMMUNITY(b, s, e, g) \ + CNL_COMMUNITY(b, s, e, CNL_H_HOSTSW_OWN, g) + /* Cannon Lake-H */ static const struct pinctrl_pin_desc cnlh_pins[] = { /* GPP_A */ @@ -442,10 +449,10 @@ static const struct intel_function cnlh_functions[] = { }; static const struct intel_community cnlh_communities[] = { - CNL_COMMUNITY(0, 0, 50, cnlh_community0_gpps), - CNL_COMMUNITY(1, 51, 154, cnlh_community1_gpps), - CNL_COMMUNITY(2, 155, 248, cnlh_community3_gpps), - CNL_COMMUNITY(3, 249, 298, cnlh_community4_gpps), + CNLH_COMMUNITY(0, 0, 50, cnlh_community0_gpps), + CNLH_COMMUNITY(1, 51, 154, cnlh_community1_gpps), + CNLH_COMMUNITY(2, 155, 248, cnlh_community3_gpps), + CNLH_COMMUNITY(3, 249, 298, cnlh_community4_gpps), }; static const struct intel_pinctrl_soc_data cnlh_soc_data = { @@ -803,9 +810,9 @@ static const struct intel_padgroup cnllp_community4_gpps[] = { }; static const struct intel_community cnllp_communities[] = { - CNL_COMMUNITY(0, 0, 67, cnllp_community0_gpps), - CNL_COMMUNITY(1, 68, 180, cnllp_community1_gpps), - CNL_COMMUNITY(2, 181, 243, cnllp_community4_gpps), + CNLLP_COMMUNITY(0, 0, 67, cnllp_community0_gpps), + CNLLP_COMMUNITY(1, 68, 180, cnllp_community1_gpps), + CNLLP_COMMUNITY(2, 181, 243, cnllp_community4_gpps), }; static const struct intel_pinctrl_soc_data cnllp_soc_data = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index ec8dafc94694..1ea3438ea67e 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -887,36 +887,6 @@ static const struct gpio_chip intel_gpio_chip = { .set_config = gpiochip_generic_config, }; -static int intel_gpio_irq_reqres(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct intel_pinctrl *pctrl = gpiochip_get_data(gc); - int pin; - int ret; - - pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL); - if (pin >= 0) { - ret = gpiochip_lock_as_irq(gc, pin); - if (ret) { - dev_err(pctrl->dev, "unable to lock HW IRQ %d for IRQ\n", - pin); - return ret; - } - } - return 0; -} - -static void intel_gpio_irq_relres(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct intel_pinctrl *pctrl = gpiochip_get_data(gc); - int pin; - - pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL); - if (pin >= 0) - gpiochip_unlock_as_irq(gc, pin); -} - static void intel_gpio_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); @@ -1132,8 +1102,6 @@ static irqreturn_t intel_gpio_irq(int irq, void *data) static struct irq_chip intel_gpio_irqchip = { .name = "intel-gpio", - .irq_request_resources = intel_gpio_irq_reqres, - .irq_release_resources = intel_gpio_irq_relres, .irq_enable = intel_gpio_irq_enable, .irq_ack = intel_gpio_irq_ack, .irq_mask = intel_gpio_irq_mask, diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 41ccc759b8b8..1425c2874d40 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -348,21 +348,12 @@ static void amd_gpio_irq_enable(struct irq_data *d) unsigned long flags; struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); - u32 mask = BIT(INTERRUPT_ENABLE_OFF) | BIT(INTERRUPT_MASK_OFF); raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); pin_reg |= BIT(INTERRUPT_ENABLE_OFF); pin_reg |= BIT(INTERRUPT_MASK_OFF); writel(pin_reg, gpio_dev->base + (d->hwirq)*4); - /* - * When debounce logic is enabled it takes ~900 us before interrupts - * can be enabled. During this "debounce warm up" period the - * "INTERRUPT_ENABLE" bit will read as 0. Poll the bit here until it - * reads back as 1, signaling that interrupts are now enabled. - */ - while ((readl(gpio_dev->base + (d->hwirq)*4) & mask) != mask) - continue; raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } @@ -426,7 +417,7 @@ static void amd_gpio_irq_eoi(struct irq_data *d) static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) { int ret = 0; - u32 pin_reg; + u32 pin_reg, pin_reg_irq_en, mask; unsigned long flags, irq_flags; struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); @@ -495,6 +486,28 @@ static int amd_gpio_irq_set_type(struct irq_data *d, unsigned int type) } pin_reg |= CLR_INTR_STAT << INTERRUPT_STS_OFF; + /* + * If WAKE_INT_MASTER_REG.MaskStsEn is set, a software write to the + * debounce registers of any GPIO will block wake/interrupt status + * generation for *all* GPIOs for a lenght of time that depends on + * WAKE_INT_MASTER_REG.MaskStsLength[11:0]. During this period the + * INTERRUPT_ENABLE bit will read as 0. + * + * We temporarily enable irq for the GPIO whose configuration is + * changing, and then wait for it to read back as 1 to know when + * debounce has settled and then disable the irq again. + * We do this polling with the spinlock held to ensure other GPIO + * access routines do not read an incorrect value for the irq enable + * bit of other GPIOs. We keep the GPIO masked while polling to avoid + * spurious irqs, and disable the irq again after polling. + */ + mask = BIT(INTERRUPT_ENABLE_OFF); + pin_reg_irq_en = pin_reg; + pin_reg_irq_en |= mask; + pin_reg_irq_en &= ~BIT(INTERRUPT_MASK_OFF); + writel(pin_reg_irq_en, gpio_dev->base + (d->hwirq)*4); + while ((readl(gpio_dev->base + (d->hwirq)*4) & mask) != mask) + continue; writel(pin_reg, gpio_dev->base + (d->hwirq)*4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c index 0f8ac8dec3e1..a1bd8aaf4d98 100644 --- a/drivers/regulator/bd71837-regulator.c +++ b/drivers/regulator/bd71837-regulator.c @@ -569,6 +569,25 @@ static int bd71837_probe(struct platform_device *pdev) BD71837_REG_REGLOCK); } + /* + * There is a HW quirk in BD71837. The shutdown sequence timings for + * bucks/LDOs which are controlled via register interface are changed. + * At PMIC poweroff the voltage for BUCK6/7 is cut immediately at the + * beginning of shut-down sequence. As bucks 6 and 7 are parent + * supplies for LDO5 and LDO6 - this causes LDO5/6 voltage + * monitoring to errorneously detect under voltage and force PMIC to + * emergency state instead of poweroff. In order to avoid this we + * disable voltage monitoring for LDO5 and LDO6 + */ + err = regmap_update_bits(pmic->mfd->regmap, BD718XX_REG_MVRFLTMASK2, + BD718XX_LDO5_VRMON80 | BD718XX_LDO6_VRMON80, + BD718XX_LDO5_VRMON80 | BD718XX_LDO6_VRMON80); + if (err) { + dev_err(&pmic->pdev->dev, + "Failed to disable voltage monitoring\n"); + goto err; + } + for (i = 0; i < ARRAY_SIZE(pmic_regulator_inits); i++) { struct regulator_desc *desc; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index bb1324f93143..9577d8941846 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3161,7 +3161,7 @@ static inline int regulator_suspend_toggle(struct regulator_dev *rdev, if (!rstate->changeable) return -EPERM; - rstate->enabled = en; + rstate->enabled = (en) ? ENABLE_IN_SUSPEND : DISABLE_IN_SUSPEND; return 0; } @@ -4395,13 +4395,13 @@ regulator_register(const struct regulator_desc *regulator_desc, !rdev->desc->fixed_uV) rdev->is_switch = true; + dev_set_drvdata(&rdev->dev, rdev); ret = device_register(&rdev->dev); if (ret != 0) { put_device(&rdev->dev); goto unset_supplies; } - dev_set_drvdata(&rdev->dev, rdev); rdev_init_debugfs(rdev); /* try to resolve regulators supply since a new one was registered */ diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 638f17d4c848..210fc20f7de7 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -213,8 +213,6 @@ static void of_get_regulation_constraints(struct device_node *np, else if (of_property_read_bool(suspend_np, "regulator-off-in-suspend")) suspend_state->enabled = DISABLE_IN_SUSPEND; - else - suspend_state->enabled = DO_NOTHING_IN_SUSPEND; if (!of_property_read_u32(np, "regulator-suspend-min-microvolt", &pval)) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 0078b5d217cc..1771d0073c0c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -610,7 +610,7 @@ static void qeth_put_reply(struct qeth_reply *reply) static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, struct qeth_card *card) { - char *ipa_name; + const char *ipa_name; int com = cmd->hdr.command; ipa_name = qeth_get_ipa_cmd_name(com); if (rc) diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c index 5bcb8dafc3ee..e891c0b52f4c 100644 --- a/drivers/s390/net/qeth_core_mpc.c +++ b/drivers/s390/net/qeth_core_mpc.c @@ -148,10 +148,10 @@ EXPORT_SYMBOL_GPL(IPA_PDU_HEADER); struct ipa_rc_msg { enum qeth_ipa_return_codes rc; - char *msg; + const char *msg; }; -static struct ipa_rc_msg qeth_ipa_rc_msg[] = { +static const struct ipa_rc_msg qeth_ipa_rc_msg[] = { {IPA_RC_SUCCESS, "success"}, {IPA_RC_NOTSUPP, "Command not supported"}, {IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"}, @@ -219,23 +219,23 @@ static struct ipa_rc_msg qeth_ipa_rc_msg[] = { -char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc) +const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc) { - int x = 0; - qeth_ipa_rc_msg[sizeof(qeth_ipa_rc_msg) / - sizeof(struct ipa_rc_msg) - 1].rc = rc; - while (qeth_ipa_rc_msg[x].rc != rc) - x++; + int x; + + for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_msg) - 1; x++) + if (qeth_ipa_rc_msg[x].rc == rc) + return qeth_ipa_rc_msg[x].msg; return qeth_ipa_rc_msg[x].msg; } struct ipa_cmd_names { enum qeth_ipa_cmds cmd; - char *name; + const char *name; }; -static struct ipa_cmd_names qeth_ipa_cmd_names[] = { +static const struct ipa_cmd_names qeth_ipa_cmd_names[] = { {IPA_CMD_STARTLAN, "startlan"}, {IPA_CMD_STOPLAN, "stoplan"}, {IPA_CMD_SETVMAC, "setvmac"}, @@ -267,13 +267,12 @@ static struct ipa_cmd_names qeth_ipa_cmd_names[] = { {IPA_CMD_UNKNOWN, "unknown"}, }; -char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd) +const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd) { - int x = 0; - qeth_ipa_cmd_names[ - sizeof(qeth_ipa_cmd_names) / - sizeof(struct ipa_cmd_names)-1].cmd = cmd; - while (qeth_ipa_cmd_names[x].cmd != cmd) - x++; + int x; + + for (x = 0; x < ARRAY_SIZE(qeth_ipa_cmd_names) - 1; x++) + if (qeth_ipa_cmd_names[x].cmd == cmd) + return qeth_ipa_cmd_names[x].name; return qeth_ipa_cmd_names[x].name; } diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index aa8b9196b089..aa5de1fe01e1 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -797,8 +797,8 @@ enum qeth_ipa_arp_return_codes { QETH_IPA_ARP_RC_Q_NO_DATA = 0x0008, }; -extern char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); -extern char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); +extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); +extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); #define QETH_SETASS_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \ sizeof(struct qeth_ipacmd_setassparms_hdr)) diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index ecb22749df0b..8cc015183043 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -2729,6 +2729,9 @@ static int qman_alloc_range(struct gen_pool *p, u32 *result, u32 cnt) { unsigned long addr; + if (!p) + return -ENODEV; + addr = gen_pool_alloc(p, cnt); if (!addr) return -ENOMEM; diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c index c646d8713861..681f7d4b7724 100644 --- a/drivers/soc/fsl/qe/ucc.c +++ b/drivers/soc/fsl/qe/ucc.c @@ -626,7 +626,7 @@ static u32 ucc_get_tdm_sync_shift(enum comm_dir mode, u32 tdm_num) { u32 shift; - shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : RX_SYNC_SHIFT_BASE; + shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : TX_SYNC_SHIFT_BASE; shift -= tdm_num * 2; return shift; diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index 0626e6e3ea0c..421bfc7dda67 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -300,8 +300,8 @@ static int spi_gpio_request(struct device *dev, *mflags |= SPI_MASTER_NO_RX; spi_gpio->sck = devm_gpiod_get(dev, "sck", GPIOD_OUT_LOW); - if (IS_ERR(spi_gpio->mosi)) - return PTR_ERR(spi_gpio->mosi); + if (IS_ERR(spi_gpio->sck)) + return PTR_ERR(spi_gpio->sck); for (i = 0; i < num_chipselects; i++) { spi_gpio->cs_gpios[i] = devm_gpiod_get_index(dev, "cs", diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 95dc4d78618d..b37de1d991d6 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -598,11 +598,13 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx, ret = wait_event_interruptible_timeout(rspi->wait, rspi->dma_callbacked, HZ); - if (ret > 0 && rspi->dma_callbacked) + if (ret > 0 && rspi->dma_callbacked) { ret = 0; - else if (!ret) { - dev_err(&rspi->master->dev, "DMA timeout\n"); - ret = -ETIMEDOUT; + } else { + if (!ret) { + dev_err(&rspi->master->dev, "DMA timeout\n"); + ret = -ETIMEDOUT; + } if (tx) dmaengine_terminate_all(rspi->master->dma_tx); if (rx) @@ -1350,12 +1352,36 @@ static const struct platform_device_id spi_driver_ids[] = { MODULE_DEVICE_TABLE(platform, spi_driver_ids); +#ifdef CONFIG_PM_SLEEP +static int rspi_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct rspi_data *rspi = platform_get_drvdata(pdev); + + return spi_master_suspend(rspi->master); +} + +static int rspi_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct rspi_data *rspi = platform_get_drvdata(pdev); + + return spi_master_resume(rspi->master); +} + +static SIMPLE_DEV_PM_OPS(rspi_pm_ops, rspi_suspend, rspi_resume); +#define DEV_PM_OPS &rspi_pm_ops +#else +#define DEV_PM_OPS NULL +#endif /* CONFIG_PM_SLEEP */ + static struct platform_driver rspi_driver = { .probe = rspi_probe, .remove = rspi_remove, .id_table = spi_driver_ids, .driver = { .name = "renesas_spi", + .pm = DEV_PM_OPS, .of_match_table = of_match_ptr(rspi_of_match), }, }; diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 539d6d1a277a..101cd6aae2ea 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -397,7 +397,8 @@ static void sh_msiof_spi_set_mode_regs(struct sh_msiof_spi_priv *p, static void sh_msiof_reset_str(struct sh_msiof_spi_priv *p) { - sh_msiof_write(p, STR, sh_msiof_read(p, STR)); + sh_msiof_write(p, STR, + sh_msiof_read(p, STR) & ~(STR_TDREQ | STR_RDREQ)); } static void sh_msiof_spi_write_fifo_8(struct sh_msiof_spi_priv *p, @@ -1426,12 +1427,37 @@ static const struct platform_device_id spi_driver_ids[] = { }; MODULE_DEVICE_TABLE(platform, spi_driver_ids); +#ifdef CONFIG_PM_SLEEP +static int sh_msiof_spi_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct sh_msiof_spi_priv *p = platform_get_drvdata(pdev); + + return spi_master_suspend(p->master); +} + +static int sh_msiof_spi_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct sh_msiof_spi_priv *p = platform_get_drvdata(pdev); + + return spi_master_resume(p->master); +} + +static SIMPLE_DEV_PM_OPS(sh_msiof_spi_pm_ops, sh_msiof_spi_suspend, + sh_msiof_spi_resume); +#define DEV_PM_OPS &sh_msiof_spi_pm_ops +#else +#define DEV_PM_OPS NULL +#endif /* CONFIG_PM_SLEEP */ + static struct platform_driver sh_msiof_spi_drv = { .probe = sh_msiof_spi_probe, .remove = sh_msiof_spi_remove, .id_table = spi_driver_ids, .driver = { .name = "spi_sh_msiof", + .pm = DEV_PM_OPS, .of_match_table = of_match_ptr(sh_msiof_match), }, }; diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index 6f7b946b5ced..1427f343b39a 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -1063,6 +1063,24 @@ static int tegra_slink_probe(struct platform_device *pdev) goto exit_free_master; } + /* disabled clock may cause interrupt storm upon request */ + tspi->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(tspi->clk)) { + ret = PTR_ERR(tspi->clk); + dev_err(&pdev->dev, "Can not get clock %d\n", ret); + goto exit_free_master; + } + ret = clk_prepare(tspi->clk); + if (ret < 0) { + dev_err(&pdev->dev, "Clock prepare failed %d\n", ret); + goto exit_free_master; + } + ret = clk_enable(tspi->clk); + if (ret < 0) { + dev_err(&pdev->dev, "Clock enable failed %d\n", ret); + goto exit_free_master; + } + spi_irq = platform_get_irq(pdev, 0); tspi->irq = spi_irq; ret = request_threaded_irq(tspi->irq, tegra_slink_isr, @@ -1071,14 +1089,7 @@ static int tegra_slink_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n", tspi->irq); - goto exit_free_master; - } - - tspi->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(tspi->clk)) { - dev_err(&pdev->dev, "can not get clock\n"); - ret = PTR_ERR(tspi->clk); - goto exit_free_irq; + goto exit_clk_disable; } tspi->rst = devm_reset_control_get_exclusive(&pdev->dev, "spi"); @@ -1138,6 +1149,8 @@ exit_rx_dma_free: tegra_slink_deinit_dma_param(tspi, true); exit_free_irq: free_irq(spi_irq, tspi); +exit_clk_disable: + clk_disable(tspi->clk); exit_free_master: spi_master_put(master); return ret; @@ -1150,6 +1163,8 @@ static int tegra_slink_remove(struct platform_device *pdev) free_irq(tspi->irq, tspi); + clk_disable(tspi->clk); + if (tspi->tx_dma_chan) tegra_slink_deinit_dma_param(tspi, false); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 3946649b85c8..ba906876cc45 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -42,6 +42,7 @@ struct bmp_dib_header { u32 colors_important; } __packed; +static bool use_bgrt = true; static bool request_mem_succeeded = false; static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC; @@ -160,6 +161,9 @@ static void efifb_show_boot_graphics(struct fb_info *info) void *bgrt_image = NULL; u8 *dst = info->screen_base; + if (!use_bgrt) + return; + if (!bgrt_tab.image_address) { pr_info("efifb: No BGRT, not showing boot graphics\n"); return; @@ -290,6 +294,8 @@ static int efifb_setup(char *options) screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0); else if (!strcmp(this_opt, "nowc")) mem_flags &= ~EFI_MEMORY_WC; + else if (!strcmp(this_opt, "nobgrt")) + use_bgrt = false; } } diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index ef69273074ba..a3edb20ea4c3 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_info *fbi, if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size)) return -EFAULT; + if (mr->w > 4096 || mr->h > 4096) + return -EINVAL; + if (mr->w * mr->h * 3 > mr->buffer_size) return -EINVAL; @@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_info *fbi, mr->x, mr->y, mr->w, mr->h); if (r > 0) { - if (copy_to_user(mr->buffer, buf, mr->buffer_size)) + if (copy_to_user(mr->buffer, buf, r)) r = -EFAULT; } diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index def3a501acd6..d059d04c63ac 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -712,7 +712,7 @@ static int pxa168fb_probe(struct platform_device *pdev) /* * enable controller clock */ - clk_enable(fbi->clk); + clk_prepare_enable(fbi->clk); pxa168fb_set_par(info); @@ -767,7 +767,7 @@ static int pxa168fb_probe(struct platform_device *pdev) failed_free_cmap: fb_dealloc_cmap(&info->cmap); failed_free_clk: - clk_disable(fbi->clk); + clk_disable_unprepare(fbi->clk); failed_free_fbmem: dma_free_coherent(fbi->dev, info->fix.smem_len, info->screen_base, fbi->fb_start_dma); @@ -807,7 +807,7 @@ static int pxa168fb_remove(struct platform_device *pdev) dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), info->screen_base, info->fix.smem_start); - clk_disable(fbi->clk); + clk_disable_unprepare(fbi->clk); framebuffer_release(info); diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 045e8afe398b..9e88e3f594c2 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1157,7 +1157,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) dev_name); goto out_err0; } - /* fall though */ + /* fall through */ case S9000_ID_ARTIST: case S9000_ID_HCRX: case S9000_ID_TIMBER: diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 025a9a5e1c32..55a756c60746 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -17,11 +17,6 @@ #include "internal.h" #include "afs_fs.h" -//#define AFS_MAX_ADDRESSES -// ((unsigned int)((PAGE_SIZE - sizeof(struct afs_addr_list)) / -// sizeof(struct sockaddr_rxrpc))) -#define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8)) - /* * Release an address list. */ @@ -43,11 +38,15 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, _enter("%u,%u,%u", nr, service, port); + if (nr > AFS_MAX_ADDRESSES) + nr = AFS_MAX_ADDRESSES; + alist = kzalloc(struct_size(alist, addrs, nr), GFP_KERNEL); if (!alist) return NULL; refcount_set(&alist->usage, 1); + alist->max_addrs = nr; for (i = 0; i < nr; i++) { struct sockaddr_rxrpc *srx = &alist->addrs[i]; @@ -109,8 +108,6 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, } while (p < end); _debug("%u/%u addresses", nr, AFS_MAX_ADDRESSES); - if (nr > AFS_MAX_ADDRESSES) - nr = AFS_MAX_ADDRESSES; alist = afs_alloc_addrlist(nr, service, port); if (!alist) @@ -119,8 +116,10 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, /* Extract the addresses */ p = text; do { - struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs]; const char *q, *stop; + unsigned int xport = port; + __be32 x[4]; + int family; if (*p == delim) { p++; @@ -136,19 +135,12 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, break; } - if (in4_pton(p, q - p, - (u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3], - -1, &stop)) { - srx->transport.sin6.sin6_addr.s6_addr32[0] = 0; - srx->transport.sin6.sin6_addr.s6_addr32[1] = 0; - srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - } else if (in6_pton(p, q - p, - srx->transport.sin6.sin6_addr.s6_addr, - -1, &stop)) { - /* Nothing to do */ - } else { + if (in4_pton(p, q - p, (u8 *)&x[0], -1, &stop)) + family = AF_INET; + else if (in6_pton(p, q - p, (u8 *)x, -1, &stop)) + family = AF_INET6; + else goto bad_address; - } if (stop != q) goto bad_address; @@ -160,7 +152,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, if (p < end) { if (*p == '+') { /* Port number specification "+1234" */ - unsigned int xport = 0; + xport = 0; p++; if (p >= end || !isdigit(*p)) goto bad_address; @@ -171,7 +163,6 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, goto bad_address; p++; } while (p < end && isdigit(*p)); - srx->transport.sin6.sin6_port = htons(xport); } else if (*p == delim) { p++; } else { @@ -179,8 +170,12 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, } } - alist->nr_addrs++; - } while (p < end && alist->nr_addrs < AFS_MAX_ADDRESSES); + if (family == AF_INET) + afs_merge_fs_addr4(alist, x[0], xport); + else + afs_merge_fs_addr6(alist, x, xport); + + } while (p < end); _leave(" = [nr %u]", alist->nr_addrs); return alist; @@ -237,19 +232,23 @@ struct afs_addr_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry) */ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port) { - struct sockaddr_in6 *a; - __be16 xport = htons(port); + struct sockaddr_rxrpc *srx; + u32 addr = ntohl(xdr); int i; + if (alist->nr_addrs >= alist->max_addrs) + return; + for (i = 0; i < alist->nr_ipv4; i++) { - a = &alist->addrs[i].transport.sin6; - if (xdr == a->sin6_addr.s6_addr32[3] && - xport == a->sin6_port) + struct sockaddr_in *a = &alist->addrs[i].transport.sin; + u32 a_addr = ntohl(a->sin_addr.s_addr); + u16 a_port = ntohs(a->sin_port); + + if (addr == a_addr && port == a_port) return; - if (xdr == a->sin6_addr.s6_addr32[3] && - (u16 __force)xport < (u16 __force)a->sin6_port) + if (addr == a_addr && port < a_port) break; - if ((u32 __force)xdr < (u32 __force)a->sin6_addr.s6_addr32[3]) + if (addr < a_addr) break; } @@ -258,12 +257,11 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port) alist->addrs + i, sizeof(alist->addrs[0]) * (alist->nr_addrs - i)); - a = &alist->addrs[i].transport.sin6; - a->sin6_port = xport; - a->sin6_addr.s6_addr32[0] = 0; - a->sin6_addr.s6_addr32[1] = 0; - a->sin6_addr.s6_addr32[2] = htonl(0xffff); - a->sin6_addr.s6_addr32[3] = xdr; + srx = &alist->addrs[i]; + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.sin.sin_family = AF_INET; + srx->transport.sin.sin_port = htons(port); + srx->transport.sin.sin_addr.s_addr = xdr; alist->nr_ipv4++; alist->nr_addrs++; } @@ -273,18 +271,20 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port) */ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port) { - struct sockaddr_in6 *a; - __be16 xport = htons(port); + struct sockaddr_rxrpc *srx; int i, diff; + if (alist->nr_addrs >= alist->max_addrs) + return; + for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) { - a = &alist->addrs[i].transport.sin6; + struct sockaddr_in6 *a = &alist->addrs[i].transport.sin6; + u16 a_port = ntohs(a->sin6_port); + diff = memcmp(xdr, &a->sin6_addr, 16); - if (diff == 0 && - xport == a->sin6_port) + if (diff == 0 && port == a_port) return; - if (diff == 0 && - (u16 __force)xport < (u16 __force)a->sin6_port) + if (diff == 0 && port < a_port) break; if (diff < 0) break; @@ -295,12 +295,11 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port) alist->addrs + i, sizeof(alist->addrs[0]) * (alist->nr_addrs - i)); - a = &alist->addrs[i].transport.sin6; - a->sin6_port = xport; - a->sin6_addr.s6_addr32[0] = xdr[0]; - a->sin6_addr.s6_addr32[1] = xdr[1]; - a->sin6_addr.s6_addr32[2] = xdr[2]; - a->sin6_addr.s6_addr32[3] = xdr[3]; + srx = &alist->addrs[i]; + srx->transport_len = sizeof(srx->transport.sin6); + srx->transport.sin6.sin6_family = AF_INET6; + srx->transport.sin6.sin6_port = htons(port); + memcpy(&srx->transport.sin6.sin6_addr, xdr, 16); alist->nr_addrs++; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 871a228d7f37..8ae4e2ebb99a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -73,12 +73,14 @@ struct afs_addr_list { struct rcu_head rcu; /* Must be first */ refcount_t usage; u32 version; /* Version */ - unsigned short nr_addrs; - unsigned short index; /* Address currently in use */ - unsigned short nr_ipv4; /* Number of IPv4 addresses */ + unsigned char max_addrs; + unsigned char nr_addrs; + unsigned char index; /* Address currently in use */ + unsigned char nr_ipv4; /* Number of IPv4 addresses */ unsigned long probed; /* Mask of servers that have been probed */ unsigned long yfs; /* Mask of servers that are YFS */ struct sockaddr_rxrpc addrs[]; +#define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8)) }; /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 0c9ab62c3df4..9dcaed031843 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1553,6 +1553,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, /* Flags */ #define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ +#define MID_DELETED 2 /* Mid has been dequeued/deleted */ /* Types of response buffer returned from SendReceive2 */ #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 7aa08dba4719..52d71b64c0c6 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -659,7 +659,15 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed) mid->mid_state = MID_RESPONSE_RECEIVED; else mid->mid_state = MID_RESPONSE_MALFORMED; - list_del_init(&mid->qhead); + /* + * Trying to handle/dequeue a mid after the send_recv() + * function has finished processing it is a bug. + */ + if (mid->mid_flags & MID_DELETED) + printk_once(KERN_WARNING + "trying to dequeue a deleted mid\n"); + else + list_del_init(&mid->qhead); spin_unlock(&GlobalMid_Lock); } @@ -938,8 +946,7 @@ next_pdu: } else { mids[0] = server->ops->find_mid(server, buf); bufs[0] = buf; - if (mids[0]) - num_mids = 1; + num_mids = 1; if (!mids[0] || !mids[0]->receive) length = standard_receive3(server, mids[0]); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index d954ce36b473..89985a0a6819 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1477,7 +1477,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, } srch_inf->entries_in_buffer = 0; - srch_inf->index_of_last_entry = 0; + srch_inf->index_of_last_entry = 2; rc = SMB2_query_directory(xid, tcon, fid->persistent_fid, fid->volatile_fid, 0, srch_inf); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 78f96fa3d7d9..b48f43963da6 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -142,7 +142,8 @@ void cifs_delete_mid(struct mid_q_entry *mid) { spin_lock(&GlobalMid_Lock); - list_del(&mid->qhead); + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; spin_unlock(&GlobalMid_Lock); DeleteMidQEntry(mid); @@ -772,6 +773,11 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst) return mid; } +static void +cifs_noop_callback(struct mid_q_entry *mid) +{ +} + int compound_send_recv(const unsigned int xid, struct cifs_ses *ses, const int flags, const int num_rqst, struct smb_rqst *rqst, @@ -826,8 +832,13 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, } midQ[i]->mid_state = MID_REQUEST_SUBMITTED; + /* + * We don't invoke the callback compounds unless it is the last + * request. + */ + if (i < num_rqst - 1) + midQ[i]->callback = cifs_noop_callback; } - cifs_in_send_inc(ses->server); rc = smb_send_rqst(ses->server, num_rqst, rqst, flags); cifs_in_send_dec(ses->server); @@ -908,6 +919,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, midQ[i]->resp_buf = NULL; } out: + /* + * This will dequeue all mids. After this it is important that the + * demultiplex_thread will not process any of these mids any futher. + * This is prevented above by using a noop callback that will not + * wake this thread except for the very last PDU. + */ for (i = 0; i < num_rqst; i++) cifs_delete_mid(midQ[i]); add_credits(ses->server, credits, optype); @@ -447,6 +447,7 @@ bool dax_lock_mapping_entry(struct page *page) xa_unlock_irq(&mapping->i_pages); break; } else if (IS_ERR(entry)) { + xa_unlock_irq(&mapping->i_pages); WARN_ON_ONCE(PTR_ERR(entry) != -EAGAIN); continue; } @@ -1120,21 +1121,12 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry, { struct inode *inode = mapping->host; unsigned long vaddr = vmf->address; - vm_fault_t ret = VM_FAULT_NOPAGE; - struct page *zero_page; - pfn_t pfn; - - zero_page = ZERO_PAGE(0); - if (unlikely(!zero_page)) { - ret = VM_FAULT_OOM; - goto out; - } + pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); + vm_fault_t ret; - pfn = page_to_pfn_t(zero_page); dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE, false); ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); -out: trace_dax_load_hole(inode, vmf, ret); return ret; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 7f7ee18fe179..e4bb9386c045 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1448,6 +1448,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) } inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ext2_set_inode_flags(inode); ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); ei->i_frag_no = raw_inode->i_frag; ei->i_frag_size = raw_inode->i_fsize; @@ -1517,7 +1518,6 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } brelse (bh); - ext2_set_inode_flags(inode); unlock_new_inode(inode); return inode; diff --git a/fs/ioctl.c b/fs/ioctl.c index 3212c29235ce..2005529af560 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -230,7 +230,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; - ret = do_clone_file_range(src_file.file, off, dst_file, destoff, olen); + ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); fdput: fdput(src_file); return ret; diff --git a/fs/iomap.c b/fs/iomap.c index 74762b1ec233..ec15cf2ec696 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1051,6 +1051,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, } else { WARN_ON_ONCE(!PageUptodate(page)); iomap_page_create(inode, page); + set_page_dirty(page); } return length; @@ -1090,7 +1091,6 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) length -= ret; } - set_page_dirty(page); wait_for_stable_page(page); return VM_FAULT_LOCKED; out_unlock: diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 55a099e47ba2..b53e76391e52 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -541,7 +541,8 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { - return nfserrno(do_clone_file_range(src, src_pos, dst, dst_pos, count)); + return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, + count)); } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index aaca0949fe53..826f0567ec43 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -584,9 +584,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm, res->last_used = 0; - spin_lock(&dlm->spinlock); + spin_lock(&dlm->track_lock); list_add_tail(&res->tracking, &dlm->tracking_list); - spin_unlock(&dlm->spinlock); + spin_unlock(&dlm->track_lock); memset(res->lvb, 0, DLM_LVB_LEN); memset(res->refmap, 0, sizeof(res->refmap)); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7869622af22a..7a5ee145c733 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2946,6 +2946,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, if (map_end & (PAGE_SIZE - 1)) to = map_end & (PAGE_SIZE - 1); +retry: page = find_or_create_page(mapping, page_index, GFP_NOFS); if (!page) { ret = -ENOMEM; @@ -2954,11 +2955,18 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, } /* - * In case PAGE_SIZE <= CLUSTER_SIZE, This page - * can't be dirtied before we CoW it out. + * In case PAGE_SIZE <= CLUSTER_SIZE, we do not expect a dirty + * page, so write it back. */ - if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) - BUG_ON(PageDirty(page)); + if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { + if (PageDirty(page)) { + /* + * write_on_page will unlock the page on return + */ + ret = write_one_page(page); + goto retry; + } + } if (!PageUptodate(page)) { ret = block_read_full_page(page, ocfs2_get_block); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 296037afecdb..1cc797a08a5b 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -141,7 +141,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) } /* Try to use clone_file_range to clone up within the same fs */ - error = vfs_clone_file_range(old_file, 0, new_file, 0, len); + error = do_clone_file_range(old_file, 0, new_file, 0, len); if (!error) goto out; /* Couldn't clone, so now we try to copy the data */ diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index aeaefd2a551b..986313da0c88 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -240,8 +240,10 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); + file_start_write(real.file); ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, ovl_iocb_to_rwf(iocb)); + file_end_write(real.file); revert_creds(old_cred); /* Update size */ diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b6ac545b5a32..3b7ed5d2279c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -504,7 +504,7 @@ static const struct inode_operations ovl_special_inode_operations = { .update_time = ovl_update_time, }; -const struct address_space_operations ovl_aops = { +static const struct address_space_operations ovl_aops = { /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ .direct_IO = noop_direct_IO, }; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index f28711846dd6..9c0ca6a7becf 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -686,7 +686,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, index = NULL; goto out; } - pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" + pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, err); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index f61839e1054c..a3c0d9584312 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -152,8 +152,8 @@ static inline int ovl_do_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int err = vfs_setxattr(dentry, name, value, size, flags); - pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n", - dentry, name, (int) size, (char *) value, flags, err); + pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, 0x%x) = %i\n", + dentry, name, min((int)size, 48), value, size, flags, err); return err; } diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 8cfb62cc8672..ace4fe4c39a9 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -683,7 +683,7 @@ static void ovl_cleanup_index(struct dentry *dentry) struct dentry *upperdentry = ovl_dentry_upper(dentry); struct dentry *index = NULL; struct inode *inode; - struct qstr name; + struct qstr name = { }; int err; err = ovl_get_index_name(lowerdentry, &name); @@ -726,6 +726,7 @@ static void ovl_cleanup_index(struct dentry *dentry) goto fail; out: + kfree(name.name); dput(index); return; diff --git a/fs/proc/base.c b/fs/proc/base.c index ccf86f16d9f0..7e9f07bf260d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -407,6 +407,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, unsigned long *entries; int err; + /* + * The ability to racily run the kernel stack unwinder on a running task + * and then observe the unwinder output is scary; while it is useful for + * debugging kernel issues, it can also allow an attacker to leak kernel + * stack contents. + * Doing this in a manner that is at least safe from races would require + * some work to ensure that the remote task can not be scheduled; and + * even then, this would still expose the unwinder as local attack + * surface. + * Therefore, this interface is restricted to root. + */ + if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EACCES; + entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index bbd1e357c23d..f4fd2e72add4 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -898,8 +898,22 @@ static struct platform_driver ramoops_driver = { }, }; -static void ramoops_register_dummy(void) +static inline void ramoops_unregister_dummy(void) { + platform_device_unregister(dummy); + dummy = NULL; + + kfree(dummy_data); + dummy_data = NULL; +} + +static void __init ramoops_register_dummy(void) +{ + /* + * Prepare a dummy platform data structure to carry the module + * parameters. If mem_size isn't set, then there are no module + * parameters, and we can skip this. + */ if (!mem_size) return; @@ -932,21 +946,28 @@ static void ramoops_register_dummy(void) if (IS_ERR(dummy)) { pr_info("could not create platform device: %ld\n", PTR_ERR(dummy)); + dummy = NULL; + ramoops_unregister_dummy(); } } static int __init ramoops_init(void) { + int ret; + ramoops_register_dummy(); - return platform_driver_register(&ramoops_driver); + ret = platform_driver_register(&ramoops_driver); + if (ret != 0) + ramoops_unregister_dummy(); + + return ret; } late_initcall(ramoops_init); static void __exit ramoops_exit(void) { platform_driver_unregister(&ramoops_driver); - platform_device_unregister(dummy); - kfree(dummy_data); + ramoops_unregister_dummy(); } module_exit(ramoops_exit); diff --git a/fs/read_write.c b/fs/read_write.c index 39b4a21dd933..8a2737f0d61d 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1818,8 +1818,8 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, } EXPORT_SYMBOL(vfs_clone_file_prep_inodes); -int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -1866,6 +1866,19 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, return ret; } +EXPORT_SYMBOL(do_clone_file_range); + +int vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len) +{ + int ret; + + file_start_write(file_out); + ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len); + file_end_write(file_out); + + return ret; +} EXPORT_SYMBOL(vfs_clone_file_range); /* diff --git a/fs/xattr.c b/fs/xattr.c index daa732550088..0d6a6a4af861 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -948,17 +948,19 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, int err = 0; #ifdef CONFIG_FS_POSIX_ACL - if (inode->i_acl) { - err = xattr_list_one(&buffer, &remaining_size, - XATTR_NAME_POSIX_ACL_ACCESS); - if (err) - return err; - } - if (inode->i_default_acl) { - err = xattr_list_one(&buffer, &remaining_size, - XATTR_NAME_POSIX_ACL_DEFAULT); - if (err) - return err; + if (IS_POSIXACL(inode)) { + if (inode->i_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_ACCESS); + if (err) + return err; + } + if (inode->i_default_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_DEFAULT); + if (err) + return err; + } } #endif diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 1e671d4eb6fa..c6299f82a6e4 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -587,7 +587,7 @@ xfs_attr_leaf_addname( */ error = xfs_attr3_leaf_to_node(args); if (error) - goto out_defer_cancel; + return error; error = xfs_defer_finish(&args->trans); if (error) return error; @@ -675,7 +675,7 @@ xfs_attr_leaf_addname( error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (error) - goto out_defer_cancel; + return error; error = xfs_defer_finish(&args->trans); if (error) return error; @@ -693,9 +693,6 @@ xfs_attr_leaf_addname( error = xfs_attr3_leaf_clearflag(args); } return error; -out_defer_cancel: - xfs_defer_cancel(args->trans); - return error; } /* @@ -738,15 +735,12 @@ xfs_attr_leaf_removename( error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (error) - goto out_defer_cancel; + return error; error = xfs_defer_finish(&args->trans); if (error) return error; } return 0; -out_defer_cancel: - xfs_defer_cancel(args->trans); - return error; } /* @@ -864,7 +858,7 @@ restart: state = NULL; error = xfs_attr3_leaf_to_node(args); if (error) - goto out_defer_cancel; + goto out; error = xfs_defer_finish(&args->trans); if (error) goto out; @@ -888,7 +882,7 @@ restart: */ error = xfs_da3_split(state); if (error) - goto out_defer_cancel; + goto out; error = xfs_defer_finish(&args->trans); if (error) goto out; @@ -984,7 +978,7 @@ restart: if (retval && (state->path.active > 1)) { error = xfs_da3_join(state); if (error) - goto out_defer_cancel; + goto out; error = xfs_defer_finish(&args->trans); if (error) goto out; @@ -1013,9 +1007,6 @@ out: if (error) return error; return retval; -out_defer_cancel: - xfs_defer_cancel(args->trans); - goto out; } /* @@ -1107,7 +1098,7 @@ xfs_attr_node_removename( if (retval && (state->path.active > 1)) { error = xfs_da3_join(state); if (error) - goto out_defer_cancel; + goto out; error = xfs_defer_finish(&args->trans); if (error) goto out; @@ -1138,7 +1129,7 @@ xfs_attr_node_removename( error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (error) - goto out_defer_cancel; + goto out; error = xfs_defer_finish(&args->trans); if (error) goto out; @@ -1150,9 +1141,6 @@ xfs_attr_node_removename( out: xfs_da_state_free(state); return error; -out_defer_cancel: - xfs_defer_cancel(args->trans); - goto out; } /* diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index af094063e402..d89363c6b523 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -485,7 +485,7 @@ xfs_attr_rmtval_set( blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map, &nmap); if (error) - goto out_defer_cancel; + return error; error = xfs_defer_finish(&args->trans); if (error) return error; @@ -553,9 +553,6 @@ xfs_attr_rmtval_set( } ASSERT(valuelen == 0); return 0; -out_defer_cancel: - xfs_defer_cancel(args->trans); - return error; } /* @@ -625,7 +622,7 @@ xfs_attr_rmtval_remove( error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt, XFS_BMAPI_ATTRFORK, 1, &done); if (error) - goto out_defer_cancel; + return error; error = xfs_defer_finish(&args->trans); if (error) return error; @@ -638,7 +635,4 @@ xfs_attr_rmtval_remove( return error; } return 0; -out_defer_cancel: - xfs_defer_cancel(args->trans); - return error; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 2760314fdf7f..a47670332326 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -673,7 +673,8 @@ xfs_bmap_extents_to_btree( ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS); /* - * Make space in the inode incore. + * Make space in the inode incore. This needs to be undone if we fail + * to expand the root. */ xfs_iroot_realloc(ip, 1, whichfork); ifp->if_flags |= XFS_IFBROOT; @@ -711,16 +712,15 @@ xfs_bmap_extents_to_btree( args.minlen = args.maxlen = args.prod = 1; args.wasdel = wasdel; *logflagsp = 0; - if ((error = xfs_alloc_vextent(&args))) { - ASSERT(ifp->if_broot == NULL); - goto err1; - } + error = xfs_alloc_vextent(&args); + if (error) + goto out_root_realloc; if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { - ASSERT(ifp->if_broot == NULL); error = -ENOSPC; - goto err1; + goto out_root_realloc; } + /* * Allocation can't fail, the space was reserved. */ @@ -732,9 +732,10 @@ xfs_bmap_extents_to_btree( xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0); if (!abp) { - error = -ENOSPC; - goto err2; + error = -EFSCORRUPTED; + goto out_unreserve_dquot; } + /* * Fill in the child block. */ @@ -775,11 +776,12 @@ xfs_bmap_extents_to_btree( *logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork); return 0; -err2: +out_unreserve_dquot: xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); -err1: +out_root_realloc: xfs_iroot_realloc(ip, -1, whichfork); XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); + ASSERT(ifp->if_broot == NULL); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 059bc44c27e8..afbe336600e1 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1016,6 +1016,8 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) #define XFS_DIFLAG_EXTSZINHERIT_BIT 12 /* inherit inode extent size */ #define XFS_DIFLAG_NODEFRAG_BIT 13 /* do not reorganize/defragment */ #define XFS_DIFLAG_FILESTREAM_BIT 14 /* use filestream allocator */ +/* Do not use bit 15, di_flags is legacy and unchanging now */ + #define XFS_DIFLAG_REALTIME (1 << XFS_DIFLAG_REALTIME_BIT) #define XFS_DIFLAG_PREALLOC (1 << XFS_DIFLAG_PREALLOC_BIT) #define XFS_DIFLAG_NEWRTBM (1 << XFS_DIFLAG_NEWRTBM_BIT) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 30d1d60f1d46..09d9c8cfa4a0 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -415,6 +415,31 @@ xfs_dinode_verify_fork( return NULL; } +static xfs_failaddr_t +xfs_dinode_verify_forkoff( + struct xfs_dinode *dip, + struct xfs_mount *mp) +{ + if (!XFS_DFORK_Q(dip)) + return NULL; + + switch (dip->di_format) { + case XFS_DINODE_FMT_DEV: + if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3)) + return __this_address; + break; + case XFS_DINODE_FMT_LOCAL: /* fall through ... */ + case XFS_DINODE_FMT_EXTENTS: /* fall through ... */ + case XFS_DINODE_FMT_BTREE: + if (dip->di_forkoff >= (XFS_LITINO(mp, dip->di_version) >> 3)) + return __this_address; + break; + default: + return __this_address; + } + return NULL; +} + xfs_failaddr_t xfs_dinode_verify( struct xfs_mount *mp, @@ -470,6 +495,11 @@ xfs_dinode_verify( if (mode && (flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp) return __this_address; + /* check for illegal values of forkoff */ + fa = xfs_dinode_verify_forkoff(dip, mp); + if (fa) + return fa; + /* Do we have appropriate data fork formats for the mode? */ switch (mode & S_IFMT) { case S_IFIFO: diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 036b5c7021eb..376bcb585ae6 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -17,7 +17,6 @@ #include "xfs_sb.h" #include "xfs_alloc.h" #include "xfs_rmap.h" -#include "xfs_alloc.h" #include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 5b3b177c0fc9..e386c9b0b4ab 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -126,6 +126,7 @@ xchk_inode_flags( { struct xfs_mount *mp = sc->mp; + /* di_flags are all taken, last bit cannot be used */ if (flags & ~XFS_DIFLAG_ANY) goto bad; @@ -172,8 +173,9 @@ xchk_inode_flags2( { struct xfs_mount *mp = sc->mp; + /* Unknown di_flags2 could be from a future kernel */ if (flags2 & ~XFS_DIFLAG2_ANY) - goto bad; + xchk_ino_set_warning(sc, ino); /* reflink flag requires reflink feature */ if ((flags2 & XFS_DIFLAG2_REFLINK) && diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index addbd74ecd8e..6de8d90041ff 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -702,13 +702,9 @@ xfs_bmap_punch_delalloc_range( struct xfs_iext_cursor icur; int error = 0; - xfs_ilock(ip, XFS_ILOCK_EXCL); - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); - if (error) - goto out_unlock; - } + ASSERT(ifp->if_flags & XFS_IFEXTENTS); + xfs_ilock(ip, XFS_ILOCK_EXCL); if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got)) goto out_unlock; @@ -1584,7 +1580,7 @@ xfs_swap_extent_rmap( tirec.br_blockcount, &irec, &nimaps, 0); if (error) - goto out_defer; + goto out; ASSERT(nimaps == 1); ASSERT(tirec.br_startoff == irec.br_startoff); trace_xfs_swap_extent_rmap_remap_piece(ip, &irec); @@ -1599,22 +1595,22 @@ xfs_swap_extent_rmap( /* Remove the mapping from the donor file. */ error = xfs_bmap_unmap_extent(tp, tip, &uirec); if (error) - goto out_defer; + goto out; /* Remove the mapping from the source file. */ error = xfs_bmap_unmap_extent(tp, ip, &irec); if (error) - goto out_defer; + goto out; /* Map the donor file's blocks into the source file. */ error = xfs_bmap_map_extent(tp, ip, &uirec); if (error) - goto out_defer; + goto out; /* Map the source file's blocks into the donor file. */ error = xfs_bmap_map_extent(tp, tip, &irec); if (error) - goto out_defer; + goto out; error = xfs_defer_finish(tpp); tp = *tpp; @@ -1636,8 +1632,6 @@ xfs_swap_extent_rmap( tip->i_d.di_flags2 = tip_flags2; return 0; -out_defer: - xfs_defer_cancel(tp); out: trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_); tip->i_d.di_flags2 = tip_flags2; diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 1c9d1398980b..12d8455bfbb2 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -532,6 +532,49 @@ xfs_buf_item_push( } /* + * Drop the buffer log item refcount and take appropriate action. This helper + * determines whether the bli must be freed or not, since a decrement to zero + * does not necessarily mean the bli is unused. + * + * Return true if the bli is freed, false otherwise. + */ +bool +xfs_buf_item_put( + struct xfs_buf_log_item *bip) +{ + struct xfs_log_item *lip = &bip->bli_item; + bool aborted; + bool dirty; + + /* drop the bli ref and return if it wasn't the last one */ + if (!atomic_dec_and_test(&bip->bli_refcount)) + return false; + + /* + * We dropped the last ref and must free the item if clean or aborted. + * If the bli is dirty and non-aborted, the buffer was clean in the + * transaction but still awaiting writeback from previous changes. In + * that case, the bli is freed on buffer writeback completion. + */ + aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) || + XFS_FORCED_SHUTDOWN(lip->li_mountp); + dirty = bip->bli_flags & XFS_BLI_DIRTY; + if (dirty && !aborted) + return false; + + /* + * The bli is aborted or clean. An aborted item may be in the AIL + * regardless of dirty state. For example, consider an aborted + * transaction that invalidated a dirty bli and cleared the dirty + * state. + */ + if (aborted) + xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR); + xfs_buf_item_relse(bip->bli_buf); + return true; +} + +/* * Release the buffer associated with the buf log item. If there is no dirty * logged data associated with the buffer recorded in the buf log item, then * free the buf log item and remove the reference to it in the buffer. @@ -556,76 +599,42 @@ xfs_buf_item_unlock( { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; - bool aborted; - bool hold = !!(bip->bli_flags & XFS_BLI_HOLD); - bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY); + bool released; + bool hold = bip->bli_flags & XFS_BLI_HOLD; + bool stale = bip->bli_flags & XFS_BLI_STALE; #if defined(DEBUG) || defined(XFS_WARN) - bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED); + bool ordered = bip->bli_flags & XFS_BLI_ORDERED; + bool dirty = bip->bli_flags & XFS_BLI_DIRTY; #endif - aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags); - - /* Clear the buffer's association with this transaction. */ - bp->b_transp = NULL; - - /* - * The per-transaction state has been copied above so clear it from the - * bli. - */ - bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); - - /* - * If the buf item is marked stale, then don't do anything. We'll - * unlock the buffer and free the buf item when the buffer is unpinned - * for the last time. - */ - if (bip->bli_flags & XFS_BLI_STALE) { - trace_xfs_buf_item_unlock_stale(bip); - ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); - if (!aborted) { - atomic_dec(&bip->bli_refcount); - return; - } - } - trace_xfs_buf_item_unlock(bip); /* - * If the buf item isn't tracking any data, free it, otherwise drop the - * reference we hold to it. If we are aborting the transaction, this may - * be the only reference to the buf item, so we free it anyway - * regardless of whether it is dirty or not. A dirty abort implies a - * shutdown, anyway. - * * The bli dirty state should match whether the blf has logged segments * except for ordered buffers, where only the bli should be dirty. */ ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) || (ordered && dirty && !xfs_buf_item_dirty_format(bip))); + ASSERT(!stale || (bip->__bli_format.blf_flags & XFS_BLF_CANCEL)); /* - * Clean buffers, by definition, cannot be in the AIL. However, aborted - * buffers may be in the AIL regardless of dirty state. An aborted - * transaction that invalidates a buffer already in the AIL may have - * marked it stale and cleared the dirty state, for example. - * - * Therefore if we are aborting a buffer and we've just taken the last - * reference away, we have to check if it is in the AIL before freeing - * it. We need to free it in this case, because an aborted transaction - * has already shut the filesystem down and this is the last chance we - * will have to do so. + * Clear the buffer's association with this transaction and + * per-transaction state from the bli, which has been copied above. */ - if (atomic_dec_and_test(&bip->bli_refcount)) { - if (aborted) { - ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); - xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR); - xfs_buf_item_relse(bp); - } else if (!dirty) - xfs_buf_item_relse(bp); - } + bp->b_transp = NULL; + bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); - if (!hold) - xfs_buf_relse(bp); + /* + * Unref the item and unlock the buffer unless held or stale. Stale + * buffers remain locked until final unpin unless the bli is freed by + * the unref call. The latter implies shutdown because buffer + * invalidation dirties the bli and transaction. + */ + released = xfs_buf_item_put(bip); + if (hold || (stale && !released)) + return; + ASSERT(!stale || test_bit(XFS_LI_ABORTED, &lip->li_flags)); + xfs_buf_relse(bp); } /* diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 3f7d7b72e7e6..90f65f891fab 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -51,6 +51,7 @@ struct xfs_buf_log_item { int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *); void xfs_buf_item_relse(struct xfs_buf *); +bool xfs_buf_item_put(struct xfs_buf_log_item *); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_attach_iodone(struct xfs_buf *, diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index d957a46dc1cb..05db9540e459 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1563,7 +1563,7 @@ xfs_itruncate_extents_flags( error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags, XFS_ITRUNC_MAX_EXTENTS, &done); if (error) - goto out_bmap_cancel; + goto out; /* * Duplicate the transaction that has the permanent @@ -1599,14 +1599,6 @@ xfs_itruncate_extents_flags( out: *tpp = tp; return error; -out_bmap_cancel: - /* - * If the bunmapi call encounters an error, return to the caller where - * the transaction can be properly aborted. We just need to make sure - * we're not holding any resources that we were not when we came in. - */ - xfs_defer_cancel(tp); - goto out; } int diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index c3e74f9128e8..f48ffd7a8d3e 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -471,8 +471,18 @@ xfs_vn_get_link_inline( struct inode *inode, struct delayed_call *done) { + char *link; + ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE); - return XFS_I(inode)->i_df.if_u1.if_data; + + /* + * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if + * if_data is junk. + */ + link = XFS_I(inode)->i_df.if_u1.if_data; + if (!link) + return ERR_PTR(-EFSCORRUPTED); + return link; } STATIC int diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index a21dc61ec09e..1fc9e9042e0e 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1570,16 +1570,6 @@ xlog_find_zeroed( if (last_cycle != 0) { /* log completely written to */ xlog_put_bp(bp); return 0; - } else if (first_cycle != 1) { - /* - * If the cycle of the last block is zero, the cycle of - * the first block must be 1. If it's not, maybe we're - * not looking at a log... Bail out. - */ - xfs_warn(log->l_mp, - "Log inconsistent or not a log (last==0, first!=1)"); - error = -EINVAL; - goto bp_err; } /* we have a partially zeroed log */ diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 38f405415b88..5289e22cb081 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -352,6 +352,47 @@ xfs_reflink_convert_cow( return error; } +/* + * Find the extent that maps the given range in the COW fork. Even if the extent + * is not shared we might have a preallocation for it in the COW fork. If so we + * use it that rather than trigger a new allocation. + */ +static int +xfs_find_trim_cow_extent( + struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, + bool *shared, + bool *found) +{ + xfs_fileoff_t offset_fsb = imap->br_startoff; + xfs_filblks_t count_fsb = imap->br_blockcount; + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec got; + bool trimmed; + + *found = false; + + /* + * If we don't find an overlapping extent, trim the range we need to + * allocate to fit the hole we found. + */ + if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) || + got.br_startoff > offset_fsb) + return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); + + *shared = true; + if (isnullstartblock(got.br_startblock)) { + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); + return 0; + } + + /* real extent found - no need to allocate */ + xfs_trim_extent(&got, offset_fsb, count_fsb); + *imap = got; + *found = true; + return 0; +} + /* Allocate all CoW reservations covering a range of blocks in a file. */ int xfs_reflink_allocate_cow( @@ -363,78 +404,64 @@ xfs_reflink_allocate_cow( struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb = imap->br_startoff; xfs_filblks_t count_fsb = imap->br_blockcount; - struct xfs_bmbt_irec got; - struct xfs_trans *tp = NULL; + struct xfs_trans *tp; int nimaps, error = 0; - bool trimmed; + bool found; xfs_filblks_t resaligned; xfs_extlen_t resblks = 0; - struct xfs_iext_cursor icur; -retry: - ASSERT(xfs_is_reflink_inode(ip)); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(xfs_is_reflink_inode(ip)); - /* - * Even if the extent is not shared we might have a preallocation for - * it in the COW fork. If so use it. - */ - if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) && - got.br_startoff <= offset_fsb) { - *shared = true; - - /* If we have a real allocation in the COW fork we're done. */ - if (!isnullstartblock(got.br_startblock)) { - xfs_trim_extent(&got, offset_fsb, count_fsb); - *imap = got; - goto convert; - } + error = xfs_find_trim_cow_extent(ip, imap, shared, &found); + if (error || !*shared) + return error; + if (found) + goto convert; - xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); - } else { - error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); - if (error || !*shared) - goto out; - } + resaligned = xfs_aligned_fsb_count(imap->br_startoff, + imap->br_blockcount, xfs_get_cowextsz_hint(ip)); + resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); - if (!tp) { - resaligned = xfs_aligned_fsb_count(imap->br_startoff, - imap->br_blockcount, xfs_get_cowextsz_hint(ip)); - resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned); + xfs_iunlock(ip, *lockmode); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); + *lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, *lockmode); - xfs_iunlock(ip, *lockmode); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); - *lockmode = XFS_ILOCK_EXCL; - xfs_ilock(ip, *lockmode); + if (error) + return error; - if (error) - return error; + error = xfs_qm_dqattach_locked(ip, false); + if (error) + goto out_trans_cancel; - error = xfs_qm_dqattach_locked(ip, false); - if (error) - goto out; - goto retry; + /* + * Check for an overlapping extent again now that we dropped the ilock. + */ + error = xfs_find_trim_cow_extent(ip, imap, shared, &found); + if (error || !*shared) + goto out_trans_cancel; + if (found) { + xfs_trans_cancel(tp); + goto convert; } error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0, XFS_QMOPT_RES_REGBLKS); if (error) - goto out; + goto out_trans_cancel; xfs_trans_ijoin(tp, ip, 0); - nimaps = 1; - /* Allocate the entire reservation as unwritten blocks. */ + nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, resblks, imap, &nimaps); if (error) - goto out_trans_cancel; + goto out_unreserve; xfs_inode_set_cowblocks_tag(ip); - - /* Finish up. */ error = xfs_trans_commit(tp); if (error) return error; @@ -447,12 +474,12 @@ retry: return -ENOSPC; convert: return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb); -out_trans_cancel: + +out_unreserve: xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0, XFS_QMOPT_RES_REGBLKS); -out: - if (tp) - xfs_trans_cancel(tp); +out_trans_cancel: + xfs_trans_cancel(tp); return error; } @@ -666,14 +693,12 @@ xfs_reflink_end_cow( if (!del.br_blockcount) goto prev_extent; - ASSERT(!isnullstartblock(got.br_startblock)); - /* - * Don't remap unwritten extents; these are - * speculatively preallocated CoW extents that have been - * allocated but have not yet been involved in a write. + * Only remap real extent that contain data. With AIO + * speculatively preallocations can leak into the range we + * are called upon, and we need to skip them. */ - if (got.br_state == XFS_EXT_UNWRITTEN) + if (!xfs_bmap_is_real_extent(&got)) goto prev_extent; /* Unmap the old blocks in the data fork. */ diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ad315e83bc02..3043e5ed6495 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -473,7 +473,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index bedc5a5133a5..912b42f5fe4a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -259,6 +259,14 @@ xfs_trans_alloc( struct xfs_trans *tp; int error; + /* + * Allocate the handle before we do our freeze accounting and setting up + * GFP_NOFS allocation context so that we avoid lockdep false positives + * by doing GFP_KERNEL allocations inside sb_start_intwrite(). + */ + tp = kmem_zone_zalloc(xfs_trans_zone, + (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP); + if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); @@ -270,8 +278,6 @@ xfs_trans_alloc( mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); atomic_inc(&mp->m_active_trans); - tp = kmem_zone_zalloc(xfs_trans_zone, - (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP); tp->t_magic = XFS_TRANS_HEADER_MAGIC; tp->t_flags = flags; tp->t_mountp = mp; diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 15919f67a88f..286a287ac57a 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -322,49 +322,38 @@ xfs_trans_read_buf_map( } /* - * Release the buffer bp which was previously acquired with one of the - * xfs_trans_... buffer allocation routines if the buffer has not - * been modified within this transaction. If the buffer is modified - * within this transaction, do decrement the recursion count but do - * not release the buffer even if the count goes to 0. If the buffer is not - * modified within the transaction, decrement the recursion count and - * release the buffer if the recursion count goes to 0. + * Release a buffer previously joined to the transaction. If the buffer is + * modified within this transaction, decrement the recursion count but do not + * release the buffer even if the count goes to 0. If the buffer is not modified + * within the transaction, decrement the recursion count and release the buffer + * if the recursion count goes to 0. * - * If the buffer is to be released and it was not modified before - * this transaction began, then free the buf_log_item associated with it. + * If the buffer is to be released and it was not already dirty before this + * transaction began, then also free the buf_log_item associated with it. * - * If the transaction pointer is NULL, make this just a normal - * brelse() call. + * If the transaction pointer is NULL, this is a normal xfs_buf_relse() call. */ void xfs_trans_brelse( - xfs_trans_t *tp, - xfs_buf_t *bp) + struct xfs_trans *tp, + struct xfs_buf *bp) { - struct xfs_buf_log_item *bip; - int freed; + struct xfs_buf_log_item *bip = bp->b_log_item; - /* - * Default to a normal brelse() call if the tp is NULL. - */ - if (tp == NULL) { - ASSERT(bp->b_transp == NULL); + ASSERT(bp->b_transp == tp); + + if (!tp) { xfs_buf_relse(bp); return; } - ASSERT(bp->b_transp == tp); - bip = bp->b_log_item; + trace_xfs_trans_brelse(bip); ASSERT(bip->bli_item.li_type == XFS_LI_BUF); - ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); - ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL)); ASSERT(atomic_read(&bip->bli_refcount) > 0); - trace_xfs_trans_brelse(bip); - /* - * If the release is just for a recursive lock, - * then decrement the count and return. + * If the release is for a recursive lookup, then decrement the count + * and return. */ if (bip->bli_recur > 0) { bip->bli_recur--; @@ -372,64 +361,24 @@ xfs_trans_brelse( } /* - * If the buffer is dirty within this transaction, we can't + * If the buffer is invalidated or dirty in this transaction, we can't * release it until we commit. */ if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags)) return; - - /* - * If the buffer has been invalidated, then we can't release - * it until the transaction commits to disk unless it is re-dirtied - * as part of this transaction. This prevents us from pulling - * the item from the AIL before we should. - */ if (bip->bli_flags & XFS_BLI_STALE) return; - ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED)); - /* - * Free up the log item descriptor tracking the released item. + * Unlink the log item from the transaction and clear the hold flag, if + * set. We wouldn't want the next user of the buffer to get confused. */ + ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED)); xfs_trans_del_item(&bip->bli_item); + bip->bli_flags &= ~XFS_BLI_HOLD; - /* - * Clear the hold flag in the buf log item if it is set. - * We wouldn't want the next user of the buffer to - * get confused. - */ - if (bip->bli_flags & XFS_BLI_HOLD) { - bip->bli_flags &= ~XFS_BLI_HOLD; - } - - /* - * Drop our reference to the buf log item. - */ - freed = atomic_dec_and_test(&bip->bli_refcount); - - /* - * If the buf item is not tracking data in the log, then we must free it - * before releasing the buffer back to the free pool. - * - * If the fs has shutdown and we dropped the last reference, it may fall - * on us to release a (possibly dirty) bli if it never made it to the - * AIL (e.g., the aborted unpin already happened and didn't release it - * due to our reference). Since we're already shutdown and need - * ail_lock, just force remove from the AIL and release the bli here. - */ - if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) { - xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR); - xfs_buf_item_relse(bp); - } else if (!(bip->bli_flags & XFS_BLI_DIRTY)) { -/*** - ASSERT(bp->b_pincount == 0); -***/ - ASSERT(atomic_read(&bip->bli_refcount) == 0); - ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)); - ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF)); - xfs_buf_item_relse(bp); - } + /* drop the reference to the bli */ + xfs_buf_item_put(bip); bp->b_transp = NULL; xfs_buf_relse(bp); diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index 989f8e52864d..971bb7853776 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -87,9 +87,10 @@ struct drm_client_dev { struct drm_file *file; }; -int drm_client_new(struct drm_device *dev, struct drm_client_dev *client, - const char *name, const struct drm_client_funcs *funcs); +int drm_client_init(struct drm_device *dev, struct drm_client_dev *client, + const char *name, const struct drm_client_funcs *funcs); void drm_client_release(struct drm_client_dev *client); +void drm_client_add(struct drm_client_dev *client); void drm_client_dev_unregister(struct drm_device *dev); void drm_client_dev_hotplug(struct drm_device *dev); diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 582a0ec0aa70..777814755fa6 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -89,7 +89,6 @@ struct drm_panel { struct drm_device *drm; struct drm_connector *connector; struct device *dev; - struct device_link *link; const struct drm_panel_funcs *funcs; diff --git a/include/dt-bindings/phy/phy-ocelot-serdes.h b/include/dt-bindings/phy/phy-ocelot-serdes.h new file mode 100644 index 000000000000..bd28f21206f6 --- /dev/null +++ b/include/dt-bindings/phy/phy-ocelot-serdes.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* Copyright (c) 2018 Microsemi Corporation */ +#ifndef __PHY_OCELOT_SERDES_H__ +#define __PHY_OCELOT_SERDES_H__ + +#define SERDES1G(x) (x) +#define SERDES1G_MAX SERDES1G(5) +#define SERDES6G(x) (SERDES1G_MAX + 1 + (x)) +#define SERDES6G_MAX SERDES6G(2) +#define SERDES_MAX SERDES6G_MAX + +#endif diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b41f7bc958ef..2c9756bd9c4c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -252,6 +252,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 #define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 +/* Define below the capability flags that are not offloads */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -596,10 +598,23 @@ enum virtchnl_event_codes { struct virtchnl_pf_event { enum virtchnl_event_codes event; union { + /* If the PF driver does not support the new speed reporting + * capabilities then use link_event else use link_event_adv to + * get the speed and link information. The ability to understand + * new speeds is indicated by setting the capability flag + * VIRTCHNL_VF_CAP_ADV_LINK_SPEED in vf_cap_flags parameter + * in virtchnl_vf_resource struct and can be used to determine + * which link event struct to use below. + */ struct { enum virtchnl_link_speed link_speed; bool link_status; } link_event; + struct { + /* link_speed provided in Mbps */ + u32 link_speed; + u8 link_status; + } link_event_adv; } event_data; int severity; diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index 6ac3cad9aef1..34a744a1bafc 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -24,11 +24,9 @@ #ifndef _LINUX_DNS_RESOLVER_H #define _LINUX_DNS_RESOLVER_H -#ifdef __KERNEL__ +#include <uapi/linux/dns_resolver.h> extern int dns_query(const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry); -#endif /* KERNEL */ - #endif /* _LINUX_DNS_RESOLVER_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..897eae8faee1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1828,8 +1828,10 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, struct inode *inode_out, loff_t pos_out, u64 *len, bool is_dedupe); +extern int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); @@ -2773,19 +2775,6 @@ static inline void file_end_write(struct file *file) __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } -static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len) -{ - int ret; - - file_start_write(file_out); - ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); - file_end_write(file_out); - - return ret; -} - /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b68e345f0ca..087fd5f48c91 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index a528747f8aed..e8338e5dc10b 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -78,9 +78,9 @@ enum { BD71837_REG_TRANS_COND0 = 0x1F, BD71837_REG_TRANS_COND1 = 0x20, BD71837_REG_VRFAULTEN = 0x21, - BD71837_REG_MVRFLTMASK0 = 0x22, - BD71837_REG_MVRFLTMASK1 = 0x23, - BD71837_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, BD71837_REG_RCVCFG = 0x25, BD71837_REG_RCVNUM = 0x26, BD71837_REG_PWRONCONFIG0 = 0x27, @@ -159,6 +159,33 @@ enum { #define BUCK8_MASK 0x3F #define BUCK8_DEFAULT 0x1E +/* BD718XX Voltage monitoring masks */ +#define BD718XX_BUCK1_VRMON80 0x1 +#define BD718XX_BUCK1_VRMON130 0x2 +#define BD718XX_BUCK2_VRMON80 0x4 +#define BD718XX_BUCK2_VRMON130 0x8 +#define BD718XX_1ST_NODVS_BUCK_VRMON80 0x1 +#define BD718XX_1ST_NODVS_BUCK_VRMON130 0x2 +#define BD718XX_2ND_NODVS_BUCK_VRMON80 0x4 +#define BD718XX_2ND_NODVS_BUCK_VRMON130 0x8 +#define BD718XX_3RD_NODVS_BUCK_VRMON80 0x10 +#define BD718XX_3RD_NODVS_BUCK_VRMON130 0x20 +#define BD718XX_4TH_NODVS_BUCK_VRMON80 0x40 +#define BD718XX_4TH_NODVS_BUCK_VRMON130 0x80 +#define BD718XX_LDO1_VRMON80 0x1 +#define BD718XX_LDO2_VRMON80 0x2 +#define BD718XX_LDO3_VRMON80 0x4 +#define BD718XX_LDO4_VRMON80 0x8 +#define BD718XX_LDO5_VRMON80 0x10 +#define BD718XX_LDO6_VRMON80 0x20 + +/* BD71837 specific voltage monitoring masks */ +#define BD71837_BUCK3_VRMON80 0x10 +#define BD71837_BUCK3_VRMON130 0x20 +#define BD71837_BUCK4_VRMON80 0x40 +#define BD71837_BUCK4_VRMON130 0x80 +#define BD71837_LDO7_VRMON80 0x40 + /* BD71837_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..e9b502d5bcc1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -504,6 +504,10 @@ struct health_buffer { __be16 ext_synd; }; +enum mlx5_cmd_addr_l_sz_offset { + MLX5_NIC_IFC_OFFSET = 8, +}; + struct mlx5_init_seg { __be32 fw_rev; __be32 cmdif_rev_fw_sub; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..6e8a882052b1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -896,7 +896,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x8]; u8 dump_fill_mkey[0x1]; - u8 reserved_at_f9[0x3]; + u8 reserved_at_f9[0x2]; + u8 fast_teardown[0x1]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; @@ -3352,12 +3353,13 @@ struct mlx5_ifc_teardown_hca_out_bits { u8 reserved_at_40[0x3f]; - u8 force_state[0x1]; + u8 state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN = 0x2, }; struct mlx5_ifc_teardown_hca_in_bits { diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 83a33a1873a6..7f5ca2cd3a32 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -90,6 +90,8 @@ struct mlx5_hairpin { u32 *rqn; u32 *sqn; + + bool peer_gone; }; struct mlx5_hairpin * diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..0416a7204be3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2455,6 +2455,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e22d96734e0..3f4c0b167333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,12 +671,6 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; - - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; - - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; #endif /* * This is a per-node reserve of pages that are not available diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1cbbf77a685f..f5f1f145018d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1756,6 +1756,8 @@ enum netdev_priv_flags { * switch driver and used to set the phys state of the * switch port. * + * @wol_enabled: Wake-on-LAN is enabled + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2039,6 +2041,7 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; + unsigned wol_enabled:1; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 07efffd0c759..bbe99d2b28b4 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -215,6 +215,8 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP + if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) + break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 9713aebdd348..03b319f89a34 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -37,9 +37,11 @@ enum phy_mode { PHY_MODE_USB_OTG, PHY_MODE_SGMII, PHY_MODE_2500SGMII, + PHY_MODE_QSGMII, PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, + PHY_MODE_PCIE, }; /** diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 3468703d663a..a459a5e973a7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -48,9 +48,9 @@ struct regulator; * DISABLE_IN_SUSPEND - turn off regulator in suspend states * ENABLE_IN_SUSPEND - keep regulator on in suspend states */ -#define DO_NOTHING_IN_SUSPEND (-1) -#define DISABLE_IN_SUSPEND 0 -#define ENABLE_IN_SUSPEND 1 +#define DO_NOTHING_IN_SUSPEND 0 +#define DISABLE_IN_SUSPEND 1 +#define ENABLE_IN_SUSPEND 2 /* Regulator active discharge flags */ enum regulator_active_discharge { diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index b2bd4b4127c4..69ee30456864 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -81,8 +81,10 @@ enum spi_mem_data_dir { * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes * @data.buswidth: number of IO lanes used to send/receive the data * @data.dir: direction of the transfer - * @data.buf.in: input buffer - * @data.buf.out: output buffer + * @data.nbytes: number of data bytes to send/receive. Can be zero if the + * operation does not involve transferring data + * @data.buf.in: input buffer (must be DMA-able) + * @data.buf.out: output buffer (must be DMA-able) */ struct spi_mem_op { struct { @@ -105,7 +107,6 @@ struct spi_mem_op { u8 buswidth; enum spi_mem_data_dir dir; unsigned int nbytes; - /* buf.{in,out} must be DMA-able. */ union { void *in; const void *out; diff --git a/include/linux/uio.h b/include/linux/uio.h index 409c845d4cd3..422b1c01ee0d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -172,7 +172,7 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) + if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter_mcsafe(addr, bytes, i); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 9397628a1967..cb462f9ab7dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -5,6 +5,24 @@ #include <linux/if_vlan.h> #include <uapi/linux/virtio_net.h> +static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, + const struct virtio_net_hdr *hdr) +{ + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + case VIRTIO_NET_HDR_GSO_UDP: + skb->protocol = cpu_to_be16(ETH_P_IP); + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + skb->protocol = cpu_to_be16(ETH_P_IPV6); + break; + default: + return -EINVAL; + } + + return 0; +} + static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h index ea73fef8bdc0..8586cfb49828 100644 --- a/include/media/v4l2-fh.h +++ b/include/media/v4l2-fh.h @@ -38,10 +38,13 @@ struct v4l2_ctrl_handler; * @prio: priority of the file handler, as defined by &enum v4l2_priority * * @wait: event' s wait queue + * @subscribe_lock: serialise changes to the subscribed list; guarantee that + * the add and del event callbacks are orderly called * @subscribed: list of subscribed events * @available: list of events waiting to be dequeued * @navailable: number of available events at @available list * @sequence: event sequence number + * * @m2m_ctx: pointer to &struct v4l2_m2m_ctx */ struct v4l2_fh { @@ -52,6 +55,7 @@ struct v4l2_fh { /* Events */ wait_queue_head_t wait; + struct mutex subscribe_lock; struct list_head subscribed; struct list_head available; unsigned int navailable; diff --git a/include/net/act_api.h b/include/net/act_api.h index 1ddff3360592..05c7df41d737 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -13,7 +13,7 @@ #include <net/netns/generic.h> struct tcf_idrinfo { - spinlock_t lock; + struct mutex lock; struct idr action_idr; }; @@ -117,7 +117,7 @@ int tc_action_net_init(struct tc_action_net *tn, if (!tn->idrinfo) return -ENOMEM; tn->ops = ops; - spin_lock_init(&tn->idrinfo->lock); + mutex_init(&tn->idrinfo->lock); idr_init(&tn->idrinfo->action_idr); return err; } diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index f53edb3754bc..de587948042a 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -13,6 +13,7 @@ #define _NET_RXRPC_H #include <linux/rxrpc.h> +#include <linux/ktime.h> struct key; struct sock; @@ -77,5 +78,8 @@ int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *, int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *, enum rxrpc_call_completion *, u32 *); u32 rxrpc_kernel_check_life(struct socket *, struct rxrpc_call *); +u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *, + ktime_t *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h index a2d058170ea3..b46d68acf701 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -139,12 +139,6 @@ struct bond_parm_tbl { int mode; }; -struct netdev_notify_work { - struct delayed_work work; - struct net_device *dev; - struct netdev_bonding_info bonding_info; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ @@ -172,6 +166,7 @@ struct slave { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif + struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9f3ed79c39d7..1ec67536bbab 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4865,8 +4865,6 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * * @alpha2: the ISO/IEC 3166 alpha2 wmm rule to be queried. * @freq: the freqency(in MHz) to be queried. - * @ptr: pointer where the regdb wmm data is to be stored (or %NULL if - * irrelevant). This can be used later for deduplication. * @rule: pointer to store the wmm rule from the regulatory db. * * Self-managed wireless drivers can use this function to query diff --git a/include/net/devlink.h b/include/net/devlink.h index b9b89d6604d4..9a70755ad1c2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -362,6 +362,9 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MAX_MACS, DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT, + DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -380,6 +383,15 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable" #define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME "ignore_ari" +#define DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME "msix_vec_per_pf_max" +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE DEVLINK_PARAM_TYPE_U32 + +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min" +#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -451,11 +463,14 @@ struct devlink_ops { u32 *p_cur, u32 *p_max); int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); - int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); + int (*eswitch_mode_set)(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode); - int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode); + int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode, + struct netlink_ext_ack *extack); int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); - int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode); + int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index e03b93360f33..a80fd0ac4563 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -130,12 +130,6 @@ static inline int inet_request_bound_dev_if(const struct sock *sk, return sk->sk_bound_dev_if; } -static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq) -{ - return rcu_dereference_check(ireq->ireq_opt, - refcount_read(&ireq->req.rsk_refcnt) > 0); -} - struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/ip.h b/include/net/ip.h index e44b1a44f67a..72593e171d14 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -420,8 +420,35 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); } -int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, - u32 *metrics); +struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, + int fc_mx_len); +static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) +{ + if (fib_metrics != &dst_default_metrics && + refcount_dec_and_test(&fib_metrics->refcnt)) + kfree(fib_metrics); +} + +/* ipv4 and ipv6 both use refcounted metrics if it is not the default */ +static inline +void ip_dst_init_metrics(struct dst_entry *dst, struct dst_metrics *fib_metrics) +{ + dst_init_metrics(dst, fib_metrics->metrics, true); + + if (fib_metrics != &dst_default_metrics) { + dst->_metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&fib_metrics->refcnt); + } +} + +static inline +void ip_dst_metrics_put(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); +} u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); diff --git a/include/net/netlink.h b/include/net/netlink.h index 6a106ef5ca56..589683091f16 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -153,7 +153,7 @@ * nla_find() find attribute in stream of attributes * nla_find_nested() find attribute in nested attributes * nla_parse() parse and validate stream of attrs - * nla_parse_nested() parse nested attribuets + * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes * nla_for_each_nested() loop over the nested attributes *========================================================================= diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bbfe27f86d5f..72ffb3120ced 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -65,11 +65,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -static inline struct net_device *tcf_block_dev(struct tcf_block *block) -{ - return tcf_block_q(block)->dev_queue->dev; -} - void *tcf_block_cb_priv(struct tcf_block_cb *block_cb); struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); @@ -122,11 +117,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return NULL; } -static inline struct net_device *tcf_block_dev(struct tcf_block *block) -{ - return NULL; -} - static inline int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_priv) diff --git a/include/net/udp.h b/include/net/udp.h index 8482a990b0bb..9e82cb391dea 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -443,8 +443,10 @@ int udpv4_offload_init(void); void udp_init(void); +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); #if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif diff --git a/drivers/net/ethernet/mscc/ocelot_hsio.h b/include/soc/mscc/ocelot_hsio.h index d93ddec3931b..43112dd7313a 100644 --- a/drivers/net/ethernet/mscc/ocelot_hsio.h +++ b/include/soc/mscc/ocelot_hsio.h @@ -8,6 +8,80 @@ #ifndef _MSCC_OCELOT_HSIO_H_ #define _MSCC_OCELOT_HSIO_H_ +#define HSIO_PLL5G_CFG0 0x0000 +#define HSIO_PLL5G_CFG1 0x0004 +#define HSIO_PLL5G_CFG2 0x0008 +#define HSIO_PLL5G_CFG3 0x000c +#define HSIO_PLL5G_CFG4 0x0010 +#define HSIO_PLL5G_CFG5 0x0014 +#define HSIO_PLL5G_CFG6 0x0018 +#define HSIO_PLL5G_STATUS0 0x001c +#define HSIO_PLL5G_STATUS1 0x0020 +#define HSIO_PLL5G_BIST_CFG0 0x0024 +#define HSIO_PLL5G_BIST_CFG1 0x0028 +#define HSIO_PLL5G_BIST_CFG2 0x002c +#define HSIO_PLL5G_BIST_STAT0 0x0030 +#define HSIO_PLL5G_BIST_STAT1 0x0034 +#define HSIO_RCOMP_CFG0 0x0038 +#define HSIO_RCOMP_STATUS 0x003c +#define HSIO_SYNC_ETH_CFG 0x0040 +#define HSIO_SYNC_ETH_PLL_CFG 0x0048 +#define HSIO_S1G_DES_CFG 0x004c +#define HSIO_S1G_IB_CFG 0x0050 +#define HSIO_S1G_OB_CFG 0x0054 +#define HSIO_S1G_SER_CFG 0x0058 +#define HSIO_S1G_COMMON_CFG 0x005c +#define HSIO_S1G_PLL_CFG 0x0060 +#define HSIO_S1G_PLL_STATUS 0x0064 +#define HSIO_S1G_DFT_CFG0 0x0068 +#define HSIO_S1G_DFT_CFG1 0x006c +#define HSIO_S1G_DFT_CFG2 0x0070 +#define HSIO_S1G_TP_CFG 0x0074 +#define HSIO_S1G_RC_PLL_BIST_CFG 0x0078 +#define HSIO_S1G_MISC_CFG 0x007c +#define HSIO_S1G_DFT_STATUS 0x0080 +#define HSIO_S1G_MISC_STATUS 0x0084 +#define HSIO_MCB_S1G_ADDR_CFG 0x0088 +#define HSIO_S6G_DIG_CFG 0x008c +#define HSIO_S6G_DFT_CFG0 0x0090 +#define HSIO_S6G_DFT_CFG1 0x0094 +#define HSIO_S6G_DFT_CFG2 0x0098 +#define HSIO_S6G_TP_CFG0 0x009c +#define HSIO_S6G_TP_CFG1 0x00a0 +#define HSIO_S6G_RC_PLL_BIST_CFG 0x00a4 +#define HSIO_S6G_MISC_CFG 0x00a8 +#define HSIO_S6G_OB_ANEG_CFG 0x00ac +#define HSIO_S6G_DFT_STATUS 0x00b0 +#define HSIO_S6G_ERR_CNT 0x00b4 +#define HSIO_S6G_MISC_STATUS 0x00b8 +#define HSIO_S6G_DES_CFG 0x00bc +#define HSIO_S6G_IB_CFG 0x00c0 +#define HSIO_S6G_IB_CFG1 0x00c4 +#define HSIO_S6G_IB_CFG2 0x00c8 +#define HSIO_S6G_IB_CFG3 0x00cc +#define HSIO_S6G_IB_CFG4 0x00d0 +#define HSIO_S6G_IB_CFG5 0x00d4 +#define HSIO_S6G_OB_CFG 0x00d8 +#define HSIO_S6G_OB_CFG1 0x00dc +#define HSIO_S6G_SER_CFG 0x00e0 +#define HSIO_S6G_COMMON_CFG 0x00e4 +#define HSIO_S6G_PLL_CFG 0x00e8 +#define HSIO_S6G_ACJTAG_CFG 0x00ec +#define HSIO_S6G_GP_CFG 0x00f0 +#define HSIO_S6G_IB_STATUS0 0x00f4 +#define HSIO_S6G_IB_STATUS1 0x00f8 +#define HSIO_S6G_ACJTAG_STATUS 0x00fc +#define HSIO_S6G_PLL_STATUS 0x0100 +#define HSIO_S6G_REVID 0x0104 +#define HSIO_MCB_S6G_ADDR_CFG 0x0108 +#define HSIO_HW_CFG 0x010c +#define HSIO_HW_QSGMII_CFG 0x0110 +#define HSIO_HW_QSGMII_STAT 0x0114 +#define HSIO_CLK_CFG 0x0118 +#define HSIO_TEMP_SENSOR_CTRL 0x011c +#define HSIO_TEMP_SENSOR_CFG 0x0120 +#define HSIO_TEMP_SENSOR_STAT 0x0124 + #define HSIO_PLL5G_CFG0_ENA_ROT BIT(31) #define HSIO_PLL5G_CFG0_ENA_LANE BIT(30) #define HSIO_PLL5G_CFG0_ENA_CLKTREE BIT(29) diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 711372845945..705b33d1e395 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); - -TRACE_EVENT(mm_numa_migrate_ratelimit, - - TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages), - - TP_ARGS(p, dst_nid, nr_pages), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN) - __field( pid_t, pid) - __field( int, dst_nid) - __field( unsigned long, nr_pages) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->dst_nid = dst_nid; - __entry->nr_pages = nr_pages; - ), - - TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu", - __entry->comm, - __entry->pid, - __entry->dst_nid, - __entry->nr_pages) -); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 196587b8f204..837393fa897b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -56,7 +56,6 @@ enum rxrpc_peer_trace { rxrpc_peer_new, rxrpc_peer_processing, rxrpc_peer_put, - rxrpc_peer_queued_error, }; enum rxrpc_conn_trace { @@ -257,8 +256,7 @@ enum rxrpc_tx_point { EM(rxrpc_peer_got, "GOT") \ EM(rxrpc_peer_new, "NEW") \ EM(rxrpc_peer_processing, "PRO") \ - EM(rxrpc_peer_put, "PUT") \ - E_(rxrpc_peer_queued_error, "QER") + E_(rxrpc_peer_put, "PUT") #define rxrpc_conn_traces \ EM(rxrpc_conn_got, "GOT") \ diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h index e4732d3c2998..b0f8e87235bd 100644 --- a/include/uapi/asm-generic/hugetlb_encode.h +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -26,7 +26,9 @@ #define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_32MB (25 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512MB (29 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) diff --git a/include/uapi/linux/dns_resolver.h b/include/uapi/linux/dns_resolver.h new file mode 100644 index 000000000000..129745f9c794 --- /dev/null +++ b/include/uapi/linux/dns_resolver.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* DNS resolver interface definitions. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_DNS_RESOLVER_H +#define _UAPI_LINUX_DNS_RESOLVER_H + +#include <linux/types.h> + +/* + * Type of payload. + */ +enum dns_payload_content_type { + DNS_PAYLOAD_IS_SERVER_LIST = 0, /* List of servers, requested by srv=1 */ +}; + +/* + * Type of address that might be found in an address record. + */ +enum dns_payload_address_type { + DNS_ADDRESS_IS_IPV4 = 0, /* 4-byte AF_INET address */ + DNS_ADDRESS_IS_IPV6 = 1, /* 16-byte AF_INET6 address */ +}; + +/* + * Type of protocol used to access a server. + */ +enum dns_payload_protocol_type { + DNS_SERVER_PROTOCOL_UNSPECIFIED = 0, + DNS_SERVER_PROTOCOL_UDP = 1, /* Use UDP to talk to the server */ + DNS_SERVER_PROTOCOL_TCP = 2, /* Use TCP to talk to the server */ +}; + +/* + * Source of record included in DNS resolver payload. + */ +enum dns_record_source { + DNS_RECORD_UNAVAILABLE = 0, /* No source available (empty record) */ + DNS_RECORD_FROM_CONFIG = 1, /* From local configuration data */ + DNS_RECORD_FROM_DNS_A = 2, /* From DNS A or AAAA record */ + DNS_RECORD_FROM_DNS_AFSDB = 3, /* From DNS AFSDB record */ + DNS_RECORD_FROM_DNS_SRV = 4, /* From DNS SRV record */ + DNS_RECORD_FROM_NSS = 5, /* From NSS */ + NR__dns_record_source +}; + +/* + * Status of record included in DNS resolver payload. + */ +enum dns_lookup_status { + DNS_LOOKUP_NOT_DONE = 0, /* No lookup has been made */ + DNS_LOOKUP_GOOD = 1, /* Good records obtained */ + DNS_LOOKUP_GOOD_WITH_BAD = 2, /* Good records, some decoding errors */ + DNS_LOOKUP_BAD = 3, /* Couldn't decode results */ + DNS_LOOKUP_GOT_NOT_FOUND = 4, /* Got a "Not Found" result */ + DNS_LOOKUP_GOT_LOCAL_FAILURE = 5, /* Local failure during lookup */ + DNS_LOOKUP_GOT_TEMP_FAILURE = 6, /* Temporary failure during lookup */ + DNS_LOOKUP_GOT_NS_FAILURE = 7, /* Name server failure */ + NR__dns_lookup_status +}; + +/* + * Header at the beginning of binary format payload. + */ +struct dns_payload_header { + __u8 zero; /* Zero byte: marks this as not being text */ + __u8 content; /* enum dns_payload_content_type */ + __u8 version; /* Encoding version */ +} __packed; + +/* + * Header at the beginning of a V1 server list. This is followed directly by + * the server records. Each server records begins with a struct of type + * dns_server_list_v1_server. + */ +struct dns_server_list_v1_header { + struct dns_payload_header hdr; + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 nr_servers; /* Number of server records following this */ +} __packed; + +/* + * Header at the beginning of each V1 server record. This is followed by the + * characters of the name with no NUL-terminator, followed by the address + * records for that server. Each address record begins with a struct of type + * struct dns_server_list_v1_address. + */ +struct dns_server_list_v1_server { + __u16 name_len; /* Length of name (LE) */ + __u16 priority; /* Priority (as SRV record) (LE) */ + __u16 weight; /* Weight (as SRV record) (LE) */ + __u16 port; /* UDP/TCP port number (LE) */ + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 protocol; /* enum dns_payload_protocol_type */ + __u8 nr_addrs; +} __packed; + +/* + * Header at the beginning of each V1 address record. This is followed by the + * bytes of the address, 4 for IPV4 and 16 for IPV6. + */ +struct dns_server_list_v1_address { + __u8 address_type; /* enum dns_payload_address_type */ +} __packed; + +#endif /* _UAPI_LINUX_DNS_RESOLVER_H */ diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 015a4c0bbb47..7a8a26751c23 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -25,7 +25,9 @@ #define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index bfd5938fede6..d0f515d53299 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -28,7 +28,9 @@ #define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index e9b7244ac381..89ee47c2f17d 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1084,4 +1084,50 @@ enum { CAKE_ATM_MAX }; + +/* TAPRIO */ +enum { + TC_TAPRIO_CMD_SET_GATES = 0x00, + TC_TAPRIO_CMD_SET_AND_HOLD = 0x01, + TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02, +}; + +enum { + TCA_TAPRIO_SCHED_ENTRY_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */ + TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */ + __TCA_TAPRIO_SCHED_ENTRY_MAX, +}; +#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1) + +/* The format for schedule entry list is: + * [TCA_TAPRIO_SCHED_ENTRY_LIST] + * [TCA_TAPRIO_SCHED_ENTRY] + * [TCA_TAPRIO_SCHED_ENTRY_CMD] + * [TCA_TAPRIO_SCHED_ENTRY_GATES] + * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] + */ +enum { + TCA_TAPRIO_SCHED_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY, + __TCA_TAPRIO_SCHED_MAX, +}; + +#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1) + +enum { + TCA_TAPRIO_ATTR_UNSPEC, + TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ + TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */ + TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ + TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ + TCA_TAPRIO_PAD, + __TCA_TAPRIO_ATTR_MAX, +}; + +#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1) + #endif diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index dde1344f047c..6507ad0afc81 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -65,7 +65,9 @@ struct shmid_ds { #define SHM_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define SHM_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define SHM_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define SHM_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define SHM_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define SHM_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define SHM_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define SHM_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define SHM_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB diff --git a/ipc/shm.c b/ipc/shm.c index 4cd402e4cfeb..1c65fb357395 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -206,7 +206,7 @@ err: * Callers of shm_lock() must validate the status of the returned ipc * object pointer and error out as appropriate. */ - return (void *)ipcp; + return ERR_CAST(ipcp); } static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 22ad967d1e5f..830d7f095748 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -129,7 +129,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; - if (flags & BPF_NOEXIST) + if (flags != BPF_ANY && flags != BPF_EXIST) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, @@ -195,6 +195,9 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) if (attr->key_size != sizeof(struct bpf_cgroup_storage_key)) return ERR_PTR(-EINVAL); + if (attr->value_size == 0) + return ERR_PTR(-EINVAL); + if (attr->value_size > PAGE_SIZE) return ERR_PTR(-E2BIG); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e986518d7bc3..3584ab27d25c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2842,6 +2842,15 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, u64 umin_val, umax_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + if (insn_bitness == 32) { + /* Relevant for 32-bit RSH: Information can propagate towards + * LSB, so it isn't sufficient to only truncate the output to + * 32 bits. + */ + coerce_reg_to_size(dst_reg, 4); + coerce_reg_to_size(&src_reg, 4); + } + smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; @@ -3077,7 +3086,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops are (32,32)->32 */ coerce_reg_to_size(dst_reg, 4); - coerce_reg_to_size(&src_reg, 4); } __reg_deduce_bounds(dst_reg); diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 9bd54304446f..1b1d63b3634b 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -23,6 +23,9 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU bool select NEED_DMA_MAP_STATE +config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL + bool + config DMA_DIRECT_OPS bool depends on HAS_DMA diff --git a/kernel/events/core.c b/kernel/events/core.c index c80549bf82c6..5a97f34bc14c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3935,6 +3935,12 @@ int perf_event_read_local(struct perf_event *event, u64 *value, goto out; } + /* If this is a pinned event it must be running on this CPU */ + if (event->attr.pinned && event->oncpu != smp_processor_id()) { + ret = -EBUSY; + goto out; + } + /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise @@ -8308,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, goto unlock; list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->cpu != smp_processor_id()) + continue; if (event->attr.type != PERF_TYPE_TRACEPOINT) continue; if (event->attr.config != entry->type) @@ -9425,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu) if (pmu->task_ctx_nr > perf_invalid_context) return; - mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); - mutex_unlock(&pmus_lock); } /* @@ -9683,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register); void perf_pmu_unregister(struct pmu *pmu) { - int remove_device; - mutex_lock(&pmus_lock); - remove_device = pmu_bus_running; list_del_rcu(&pmu->entry); - mutex_unlock(&pmus_lock); /* * We dereference the pmu list under both SRCU and regular RCU, so @@ -9700,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu) free_percpu(pmu->pmu_disable_count); if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); - if (remove_device) { + if (pmu_bus_running) { if (pmu->nr_addr_filters) device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); device_del(pmu->dev); put_device(pmu->dev); } free_pmu_context(pmu); + mutex_unlock(&pmus_lock); } EXPORT_SYMBOL_GPL(perf_pmu_unregister); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0be047dbd897..65a3b7e55b9f 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work) { struct test_cycle *cycle = container_of(work, typeof(*cycle), work); struct ww_acquire_ctx ctx; - int err; + int err, erra = 0; ww_acquire_init(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); @@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work) err = ww_mutex_lock(cycle->b_mutex, &ctx); if (err == -EDEADLK) { + err = 0; ww_mutex_unlock(&cycle->a_mutex); ww_mutex_lock_slow(cycle->b_mutex, &ctx); - err = ww_mutex_lock(&cycle->a_mutex, &ctx); + erra = ww_mutex_lock(&cycle->a_mutex, &ctx); } if (!err) ww_mutex_unlock(cycle->b_mutex); - ww_mutex_unlock(&cycle->a_mutex); + if (!erra) + ww_mutex_unlock(&cycle->a_mutex); ww_acquire_fini(&ctx); - cycle->result = err; + cycle->result = err ?: erra; } static int __test_cycle(unsigned int nthreads) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 625bc9897f62..ad97f3ba5ec5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1167,7 +1167,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (task_cpu(p) != new_cpu) { if (p->sched_class->migrate_task_rq) - p->sched_class->migrate_task_rq(p); + p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; rseq_migrate(p); perf_event_task_migrate(p); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 997ea7b839fa..91e4202b0634 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1607,7 +1607,7 @@ out: return cpu; } -static void migrate_task_rq_dl(struct task_struct *p) +static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused) { struct rq *rq; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f808ddf2a868..7fc4a371bdd2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1392,6 +1392,17 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int last_cpupid, this_cpupid; this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + + /* + * Allow first faults or private faults to migrate immediately early in + * the lifetime of a task. The magic number 4 is based on waiting for + * two full passes of the "multi-stage node selection" test that is + * executed below. + */ + if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) + return true; /* * Multi-stage node selection is used in conjunction with a periodic @@ -1410,7 +1421,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * This quadric squishes small probabilities, making it less likely we * act on an unlikely task<->page relation. */ - last_cpupid = page_cpupid_xchg_last(page, this_cpupid); if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != dst_nid) return false; @@ -1514,6 +1524,21 @@ struct task_numa_env { static void task_numa_assign(struct task_numa_env *env, struct task_struct *p, long imp) { + struct rq *rq = cpu_rq(env->dst_cpu); + + /* Bail out if run-queue part of active NUMA balance. */ + if (xchg(&rq->numa_migrate_on, 1)) + return; + + /* + * Clear previous best_cpu/rq numa-migrate flag, since task now + * found a better CPU to move/swap. + */ + if (env->best_cpu != -1) { + rq = cpu_rq(env->best_cpu); + WRITE_ONCE(rq->numa_migrate_on, 0); + } + if (env->best_task) put_task_struct(env->best_task); if (p) @@ -1553,6 +1578,13 @@ static bool load_too_imbalanced(long src_load, long dst_load, } /* + * Maximum NUMA importance can be 1998 (2*999); + * SMALLIMP @ 30 would be close to 1998/64. + * Used to deter task migration. + */ +#define SMALLIMP 30 + +/* * This checks if the overall compute and NUMA accesses of the system would * be improved if the source tasks was migrated to the target dst_cpu taking * into account that it might be best if task running on the dst_cpu should @@ -1569,6 +1601,9 @@ static void task_numa_compare(struct task_numa_env *env, long moveimp = imp; int dist = env->dist; + if (READ_ONCE(dst_rq->numa_migrate_on)) + return; + rcu_read_lock(); cur = task_rcu_dereference(&dst_rq->curr); if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur))) @@ -1582,7 +1617,7 @@ static void task_numa_compare(struct task_numa_env *env, goto unlock; if (!cur) { - if (maymove || imp > env->best_imp) + if (maymove && moveimp >= env->best_imp) goto assign; else goto unlock; @@ -1625,16 +1660,22 @@ static void task_numa_compare(struct task_numa_env *env, task_weight(cur, env->dst_nid, dist); } - if (imp <= env->best_imp) - goto unlock; - if (maymove && moveimp > imp && moveimp > env->best_imp) { - imp = moveimp - 1; + imp = moveimp; cur = NULL; goto assign; } /* + * If the NUMA importance is less than SMALLIMP, + * task migration might only result in ping pong + * of tasks and also hurt performance due to cache + * misses. + */ + if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2) + goto unlock; + + /* * In the overloaded case, try and keep the load balanced. */ load = task_h_load(env->p) - task_h_load(cur); @@ -1710,6 +1751,7 @@ static int task_numa_migrate(struct task_struct *p) .best_cpu = -1, }; struct sched_domain *sd; + struct rq *best_rq; unsigned long taskweight, groupweight; int nid, ret, dist; long taskimp, groupimp; @@ -1805,20 +1847,17 @@ static int task_numa_migrate(struct task_struct *p) if (env.best_cpu == -1) return -EAGAIN; - /* - * Reset the scan period if the task is being rescheduled on an - * alternative node to recheck if the tasks is now properly placed. - */ - p->numa_scan_period = task_scan_start(p); - + best_rq = cpu_rq(env.best_cpu); if (env.best_task == NULL) { ret = migrate_task_to(p, env.best_cpu); + WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); return ret; } ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); @@ -2596,6 +2635,39 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) } } +static void update_scan_period(struct task_struct *p, int new_cpu) +{ + int src_nid = cpu_to_node(task_cpu(p)); + int dst_nid = cpu_to_node(new_cpu); + + if (!static_branch_likely(&sched_numa_balancing)) + return; + + if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING)) + return; + + if (src_nid == dst_nid) + return; + + /* + * Allow resets if faults have been trapped before one scan + * has completed. This is most likely due to a new task that + * is pulled cross-node due to wakeups or load balancing. + */ + if (p->numa_scan_seq) { + /* + * Avoid scan adjustments if moving to the preferred + * node or if the task was not previously running on + * the preferred node. + */ + if (dst_nid == p->numa_preferred_nid || + (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + return; + } + + p->numa_scan_period = task_scan_start(p); +} + #else static void task_tick_numa(struct rq *rq, struct task_struct *curr) { @@ -2609,6 +2681,10 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) { } +static inline void update_scan_period(struct task_struct *p, int new_cpu) +{ +} + #endif /* CONFIG_NUMA_BALANCING */ static void @@ -6275,7 +6351,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se); * cfs_rq_of(p) references at time of call are still valid and identify the * previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held. */ -static void migrate_task_rq_fair(struct task_struct *p) +static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) { /* * As blocked tasks retain absolute vruntime the migration needs to @@ -6328,6 +6404,8 @@ static void migrate_task_rq_fair(struct task_struct *p) /* We have migrated, no longer consider this task hot */ p->se.exec_start = 0; + + update_scan_period(p, new_cpu); } static void task_dead_fair(struct task_struct *p) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4a2e8cae63c4..455fa330de04 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -783,6 +783,7 @@ struct rq { #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; + unsigned int numa_migrate_on; #endif #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; @@ -1523,7 +1524,7 @@ struct sched_class { #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); - void (*migrate_task_rq)(struct task_struct *p); + void (*migrate_task_rq)(struct task_struct *p, int new_cpu); void (*task_woken)(struct rq *this_rq, struct task_struct *task); diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 6a473709e9b6..7405c9d89d65 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -19,7 +19,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd, struct gup_benchmark *gup) { ktime_t start_time, end_time; - unsigned long i, nr, nr_pages, addr, next; + unsigned long i, nr_pages, addr, next; + int nr; struct page **pages; nr_pages = gup->size / PAGE_SIZE; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 533f9b00147d..00704060b7f7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2931,7 +2931,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) else page_add_file_rmap(new, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c21775f196b..5c390f5a5207 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3326,8 +3326,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - const unsigned long mmun_start = start; /* For mmu_notifiers */ - const unsigned long mmun_end = end; /* For mmu_notifiers */ + unsigned long mmun_start = start; /* For mmu_notifiers */ + unsigned long mmun_end = end; /* For mmu_notifiers */ WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3339,6 +3339,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, */ tlb_remove_check_page_size_change(tlb, sz); tlb_start_vma(tlb, vma); + + /* + * If sharing possible, alert mmu notifiers of worst case. + */ + adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); address = start; for (; address < end; address += sz) { @@ -3349,6 +3354,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); + /* + * We just unmapped a page of PMDs by clearing a PUD. + * The caller's TLB flush range should cover this area. + */ continue; } @@ -3431,12 +3440,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm; struct mmu_gather tlb; + unsigned long tlb_start = start; + unsigned long tlb_end = end; + + /* + * If shared PMDs were possibly used within this vma range, adjust + * start/end for worst case tlb flushing. + * Note that we can not be sure if PMDs are shared until we try to + * unmap pages. However, we want to make sure TLB flushing covers + * the largest possible range. + */ + adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; - tlb_gather_mmu(&tlb, mm, start, end); + tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* @@ -4298,11 +4318,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; + unsigned long f_start = start; + unsigned long f_end = end; + bool shared_pmd = false; + + /* + * In the case of shared PMDs, the area to flush could be beyond + * start/end. Set f_start/f_end to cover the maximum possible + * range if PMD sharing is possible. + */ + adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end); BUG_ON(address >= end); - flush_cache_range(vma, address, end); + flush_cache_range(vma, f_start, f_end); - mmu_notifier_invalidate_range_start(mm, start, end); + mmu_notifier_invalidate_range_start(mm, f_start, f_end); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; @@ -4313,6 +4343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (huge_pmd_unshare(mm, &address, ptep)) { pages++; spin_unlock(ptl); + shared_pmd = true; continue; } pte = huge_ptep_get(ptep); @@ -4348,9 +4379,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. + * and that page table be reused and filled with junk. If we actually + * did unshare a page of pmds, flush the range corresponding to the pud. */ - flush_hugetlb_tlb_range(vma, start, end); + if (shared_pmd) + flush_hugetlb_tlb_range(vma, f_start, f_end); + else + flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. @@ -4358,7 +4393,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); - mmu_notifier_invalidate_range_end(mm, start, end); + mmu_notifier_invalidate_range_end(mm, f_start, f_end); return pages << h->order; } @@ -4545,13 +4580,41 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } /* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + +/* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the @@ -4648,6 +4711,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/madvise.c b/mm/madvise.c index 972a9eaa898b..71d21df2a3f3 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -96,7 +96,7 @@ static long madvise_behavior(struct vm_area_struct *vma, new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: - if (new_flags & VM_SPECIAL) { + if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) { error = -EINVAL; goto out; } diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..84381b55b2bd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -275,6 +275,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new); + if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } @@ -1411,7 +1414,7 @@ retry: * we encounter them after the rest of the list * is processed. */ - if (PageTransHuge(page)) { + if (PageTransHuge(page) && !PageHuge(page)) { lock_page(page); rc = split_huge_page_to_list(page, from); unlock_page(page); @@ -1855,46 +1858,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } -/* - * page migration rate limiting control. - * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs - * window of time. Default here says do not migrate more than 1280M per second. - */ -static unsigned int migrate_interval_millisecs __read_mostly = 100; -static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); - -/* Returns true if the node is migrate rate-limited after the update */ -static bool numamigrate_update_ratelimit(pg_data_t *pgdat, - unsigned long nr_pages) -{ - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { - spin_lock(&pgdat->numabalancing_migrate_lock); - pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies + - msecs_to_jiffies(migrate_interval_millisecs); - spin_unlock(&pgdat->numabalancing_migrate_lock); - } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { - trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, - nr_pages); - return true; - } - - /* - * This is an unlocked non-atomic update so errors are possible. - * The consequences are failing to migrate when we potentiall should - * have which is not severe enough to warrant locking. If it is ever - * a problem, it can be converted to a per-cpu counter. - */ - pgdat->numabalancing_migrate_nr_pages += nr_pages; - return false; -} - static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; @@ -1967,14 +1930,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, if (page_is_file_cache(page) && PageDirty(page)) goto out; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, 1)) - goto out; - isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) goto out; @@ -2021,14 +1976,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unsigned long mmun_start = address & HPAGE_PMD_MASK; unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR)) - goto out_dropref; - new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), HPAGE_PMD_ORDER); @@ -2125,7 +2072,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); -out_dropref: ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { entry = pmd_modify(entry, vma->vm_page_prot); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 89d2a2ab3fe6..706a738c0aee 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, static void pgdat_init_numabalancing(struct pglist_data *pgdat) { spin_lock_init(&pgdat->numabalancing_migrate_lock); - pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies; } #else static void pgdat_init_numabalancing(struct pglist_data *pgdat) {} diff --git a/mm/rmap.c b/mm/rmap.c index eb477809a5c0..1e79fac3186b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1362,11 +1362,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* - * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free in this function as call of try_to_unmap() - * must hold a reference on the page. + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. */ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &start, &end); + } mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { @@ -1409,6 +1419,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; + if (PageHuge(page)) { + if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, start, end); + flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..c5ef7240cbcb 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -580,8 +580,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; - unsigned long freed = 0; - int ret, i; + unsigned long ret, freed = 0; + int i; if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)) return 0; @@ -677,9 +677,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { + unsigned long ret, freed = 0; struct shrinker *shrinker; - unsigned long freed = 0; - int ret; if (!mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ba0870ecddd..7878da76abf2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1275,6 +1275,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", @@ -1283,7 +1286,6 @@ const char * const vmstat_text[] = { #ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", - "vmacache_full_flushes", #endif #ifdef CONFIG_SWAP "swap_ra", diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 3bdc8f3ca259..ccce954f8146 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2434,9 +2434,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* LE address type */ addr_type = le_addr_type(cp->addr.type); - hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type); - - err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type); + /* Abort any ongoing SMP pairing. Removes ltk and irk if they exist. */ + err = smp_cancel_and_remove_pairing(hdev, &cp->addr.bdaddr, addr_type); if (err < 0) { err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, MGMT_STATUS_NOT_PAIRED, &rp, @@ -2450,8 +2449,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto done; } - /* Abort any ongoing SMP pairing */ - smp_cancel_pairing(conn); /* Defer clearing up the connection parameters until closing to * give a chance of keeping them if a repairing happens. diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 090670fe385f..a1c1b7e8a45c 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2419,30 +2419,51 @@ unlock: return ret; } -void smp_cancel_pairing(struct hci_conn *hcon) +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type) { - struct l2cap_conn *conn = hcon->l2cap_data; + struct hci_conn *hcon; + struct l2cap_conn *conn; struct l2cap_chan *chan; struct smp_chan *smp; + int err; + + err = hci_remove_ltk(hdev, bdaddr, addr_type); + hci_remove_irk(hdev, bdaddr, addr_type); + + hcon = hci_conn_hash_lookup_le(hdev, bdaddr, addr_type); + if (!hcon) + goto done; + conn = hcon->l2cap_data; if (!conn) - return; + goto done; chan = conn->smp; if (!chan) - return; + goto done; l2cap_chan_lock(chan); smp = chan->data; if (smp) { + /* Set keys to NULL to make sure smp_failure() does not try to + * remove and free already invalidated rcu list entries. */ + smp->ltk = NULL; + smp->slave_ltk = NULL; + smp->remote_irk = NULL; + if (test_bit(SMP_FLAG_COMPLETE, &smp->flags)) smp_failure(conn, 0); else smp_failure(conn, SMP_UNSPECIFIED); + err = 0; } l2cap_chan_unlock(chan); + +done: + return err; } static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 0ff6247eaa6c..121edadd5f8d 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -181,7 +181,8 @@ enum smp_key_pref { }; /* SMP Commands */ -void smp_cancel_pairing(struct hci_conn *hcon); +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type); bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, enum smp_key_pref key_pref); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index f0fc182d3db7..b64e1649993b 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -59,7 +59,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, req.is_set = is_set; req.pid = current->pid; req.cmd = optname; - req.addr = (long)optval; + req.addr = (long __force __user)optval; req.len = optlen; mutex_lock(&bpfilter_lock); if (!info.pid) @@ -98,7 +98,7 @@ static int __init load_umh(void) pr_info("Loaded bpfilter_umh pid %d\n", info.pid); /* health check that usermode process started correctly */ - if (__bpfilter_process_sockopt(NULL, 0, 0, 0, 0) != 0) { + if (__bpfilter_process_sockopt(NULL, 0, NULL, 0, 0) != 0) { stop_umh(); return -EFAULT; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index e0a3b038d052..b1b5e8516724 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -836,7 +836,8 @@ static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) { + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev)) { state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ed225e280..938f68ee92f0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1626,7 +1626,7 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, if (!ops->eswitch_mode_set) return -EOPNOTSUPP; mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); - err = ops->eswitch_mode_set(devlink, mode); + err = ops->eswitch_mode_set(devlink, mode, info->extack); if (err) return err; } @@ -1636,7 +1636,8 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, return -EOPNOTSUPP; inline_mode = nla_get_u8( info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); - err = ops->eswitch_inline_mode_set(devlink, inline_mode); + err = ops->eswitch_inline_mode_set(devlink, inline_mode, + info->extack); if (err) return err; } @@ -1645,7 +1646,8 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, if (!ops->eswitch_encap_mode_set) return -EOPNOTSUPP; encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); - err = ops->eswitch_encap_mode_set(devlink, encap_mode); + err = ops->eswitch_encap_mode_set(devlink, encap_mode, + info->extack); if (err) return err; } @@ -2675,6 +2677,21 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME, .type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, + .name = DEVLINK_PARAM_GENERIC_IGNORE_ARI_NAME, + .type = DEVLINK_PARAM_GENERIC_IGNORE_ARI_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_NAME, + .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MAX_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + .name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME, + .type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 96afc55aa61e..3144ef2bf136 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1395,6 +1395,7 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol; + int ret; if (!dev->ethtool_ops->set_wol) return -EOPNOTSUPP; @@ -1402,7 +1403,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) if (copy_from_user(&wol, useraddr, sizeof(wol))) return -EFAULT; - return dev->ethtool_ops->set_wol(dev, &wol); + ret = dev->ethtool_ops->set_wol(dev, &wol); + if (ret) + return ret; + + dev->wol_enabled = !!wol.wolopts; + + return 0; } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 20e0d3308148..fb023df48b83 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2329,35 +2329,24 @@ static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) return false; } +struct neigh_dump_filter { + int master_idx; + int dev_idx; +}; + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + struct neigh_dump_filter *filter) { struct net *net = sock_net(skb->sk); - const struct nlmsghdr *nlh = cb->nlh; - struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; - int filter_master_idx = 0, filter_idx = 0; unsigned int flags = NLM_F_MULTI; - int err; - err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL); - if (!err) { - if (tb[NDA_IFINDEX]) { - if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) - return -EINVAL; - filter_idx = nla_get_u32(tb[NDA_IFINDEX]); - } - if (tb[NDA_MASTER]) { - if (nla_len(tb[NDA_MASTER]) != sizeof(u32)) - return -EINVAL; - filter_master_idx = nla_get_u32(tb[NDA_MASTER]); - } - if (filter_idx || filter_master_idx) - flags |= NLM_F_DUMP_FILTERED; - } + if (filter->dev_idx || filter->master_idx) + flags |= NLM_F_DUMP_FILTERED; rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2370,8 +2359,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (idx < s_idx || !net_eq(dev_net(n->dev), net)) goto next; - if (neigh_ifindex_filtered(n->dev, filter_idx) || - neigh_master_filtered(n->dev, filter_master_idx)) + if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || + neigh_master_filtered(n->dev, filter->master_idx)) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -2393,12 +2382,17 @@ out: } static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + struct neigh_dump_filter *filter) { struct pneigh_entry *n; struct net *net = sock_net(skb->sk); int rc, h, s_h = cb->args[3]; int idx, s_idx = idx = cb->args[4]; + unsigned int flags = NLM_F_MULTI; + + if (filter->dev_idx || filter->master_idx) + flags |= NLM_F_DUMP_FILTERED; read_lock_bh(&tbl->lock); @@ -2408,10 +2402,12 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { if (idx < s_idx || pneigh_net(n) != net) goto next; + if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || + neigh_master_filtered(n->dev, filter->master_idx)) + goto next; if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI, tbl) < 0) { + RTM_NEWNEIGH, flags, tbl) < 0) { read_unlock_bh(&tbl->lock); rc = -1; goto out; @@ -2432,20 +2428,36 @@ out: static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { + const struct nlmsghdr *nlh = cb->nlh; + struct neigh_dump_filter filter = {}; + struct nlattr *tb[NDA_MAX + 1]; struct neigh_table *tbl; int t, family, s_t; int proxy = 0; int err; - family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; /* check for full ndmsg structure presence, family member is * the same for both structures */ - if (nlmsg_len(cb->nlh) >= sizeof(struct ndmsg) && - ((struct ndmsg *) nlmsg_data(cb->nlh))->ndm_flags == NTF_PROXY) + if (nlmsg_len(nlh) >= sizeof(struct ndmsg) && + ((struct ndmsg *)nlmsg_data(nlh))->ndm_flags == NTF_PROXY) proxy = 1; + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL); + if (!err) { + if (tb[NDA_IFINDEX]) { + if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) + return -EINVAL; + filter.dev_idx = nla_get_u32(tb[NDA_IFINDEX]); + } + if (tb[NDA_MASTER]) { + if (nla_len(tb[NDA_MASTER]) != sizeof(u32)) + return -EINVAL; + filter.master_idx = nla_get_u32(tb[NDA_MASTER]); + } + } s_t = cb->args[0]; for (t = 0; t < NEIGH_NR_TABLES; t++) { @@ -2459,9 +2471,9 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (proxy) - err = pneigh_dump_table(tbl, skb, cb); + err = pneigh_dump_table(tbl, skb, cb, &filter); else - err = neigh_dump_table(tbl, skb, cb); + err = neigh_dump_table(tbl, skb, cb, &filter); if (err < 0) break; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3219a2932463..de1d1ba92f2d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -135,27 +135,9 @@ static void queue_process(struct work_struct *work) } } -/* - * Check whether delayed processing was scheduled for our NIC. If so, - * we attempt to grab the poll lock and use ->poll() to pump the card. - * If this fails, either we've recursed in ->poll() or it's already - * running on another CPU. - * - * Note: we don't mask interrupts with this lock because we're using - * trylock here and interrupts are already disabled in the softirq - * case. Further, we test the poll_owner to avoid recursion on UP - * systems where the lock doesn't exist. - */ static void poll_one_napi(struct napi_struct *napi) { - int work = 0; - - /* net_rx_action's ->poll() invocations and our's are - * synchronized by this test which is only made while - * holding the napi->poll_lock. - */ - if (!test_bit(NAPI_STATE_SCHED, &napi->state)) - return; + int work; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need @@ -330,6 +312,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; + rcu_read_lock_bh(); lockdep_assert_irqs_disabled(); npinfo = rcu_dereference_bh(np->dev->npinfo); @@ -374,6 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } + rcu_read_unlock_bh(); } EXPORT_SYMBOL(netpoll_send_skb_on_dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 35162e1b06ad..5564eee1e980 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1913,10 +1913,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) 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; - } + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); } if (tb[IFLA_EXT_MASK]) @@ -2852,6 +2850,12 @@ struct net_device *rtnl_create_link(struct net *net, else if (ops->get_num_rx_queues) num_rx_queues = ops->get_num_rx_queues(); + if (num_tx_queues < 1 || num_tx_queues > 4096) + return ERR_PTR(-EINVAL); + + if (num_rx_queues < 1 || num_rx_queues > 4096) + return ERR_PTR(-EINVAL); + dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, ops->setup, num_tx_queues, num_rx_queues); if (!dev) @@ -3759,16 +3763,27 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) int err = 0; int fidx = 0; - err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, - IFLA_MAX, ifla_policy, NULL); - if (err < 0) { - return -EINVAL; - } else if (err == 0) { - if (tb[IFLA_MASTER]) - br_idx = nla_get_u32(tb[IFLA_MASTER]); - } + /* A hack to preserve kernel<->userspace interface. + * Before Linux v4.12 this code accepted ndmsg since iproute2 v3.3.0. + * However, ndmsg is shorter than ifinfomsg thus nlmsg_parse() bails. + * So, check for ndmsg with an optional u32 attribute (not used here). + * Fortunately these sizes don't conflict with the size of ifinfomsg + * with an optional attribute. + */ + if (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) && + (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) + + nla_attr_size(sizeof(u32)))) { + err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, + IFLA_MAX, ifla_policy, NULL); + if (err < 0) { + return -EINVAL; + } else if (err == 0) { + if (tb[IFLA_MASTER]) + br_idx = nla_get_u32(tb[IFLA_MASTER]); + } - brport_idx = ifm->ifi_index; + brport_idx = ifm->ifi_index; + } if (br_idx) { br_dev = __dev_get_by_index(net, br_idx); diff --git a/net/dccp/input.c b/net/dccp/input.c index d28d46bff6ab..85d6c879383d 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -606,11 +606,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (sk->sk_state == DCCP_LISTEN) { if (dh->dccph_type == DCCP_PKT_REQUEST) { /* It is possible that we process SYN packets from backlog, - * so we need to make sure to disable BH right there. + * so we need to make sure to disable BH and RCU right there. */ + rcu_read_lock(); local_bh_disable(); acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0; local_bh_enable(); + rcu_read_unlock(); if (!acceptable) return 1; consume_skb(skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b08feb219b44..8e08cea6f178 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -493,9 +493,11 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq_opt_deref(ireq)); + rcu_dereference(ireq->ireq_opt)); + rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 7f4534828f6c..a65d553e730d 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -29,6 +29,7 @@ #include <linux/keyctl.h> #include <linux/err.h> #include <linux/seq_file.h> +#include <linux/dns_resolver.h> #include <keys/dns_resolver-type.h> #include <keys/user-type.h> #include "internal.h" @@ -48,27 +49,86 @@ const struct cred *dns_resolver_cache; /* * Preparse instantiation data for a dns_resolver key. * - * The data must be a NUL-terminated string, with the NUL char accounted in - * datalen. + * For normal hostname lookups, the data must be a NUL-terminated string, with + * the NUL char accounted in datalen. * * If the data contains a '#' characters, then we take the clause after each * one to be an option of the form 'key=value'. The actual data of interest is * the string leading up to the first '#'. For instance: * * "ip1,ip2,...#foo=bar" + * + * For server list requests, the data must begin with a NUL char and be + * followed by a byte indicating the version of the data format. Version 1 + * looks something like (note this is packed): + * + * u8 Non-string marker (ie. 0) + * u8 Content (DNS_PAYLOAD_IS_*) + * u8 Version (e.g. 1) + * u8 Source of server list + * u8 Lookup status of server list + * u8 Number of servers + * foreach-server { + * __le16 Name length + * __le16 Priority (as per SRV record, low first) + * __le16 Weight (as per SRV record, higher first) + * __le16 Port + * u8 Source of address list + * u8 Lookup status of address list + * u8 Protocol (DNS_SERVER_PROTOCOL_*) + * u8 Number of addresses + * char[] Name (not NUL-terminated) + * foreach-address { + * u8 Family (DNS_ADDRESS_IS_*) + * union { + * u8[4] ipv4_addr + * u8[16] ipv6_addr + * } + * } + * } + * */ static int dns_resolver_preparse(struct key_preparsed_payload *prep) { + const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; int datalen = prep->datalen, result_len = 0; const char *data = prep->data, *end, *opt; + if (datalen <= 1 || !data) + return -EINVAL; + + if (data[0] == 0) { + /* It may be a server list. */ + if (datalen <= sizeof(*bin)) + return -EINVAL; + + bin = (const struct dns_payload_header *)data; + kenter("[%u,%u],%u", bin->content, bin->version, datalen); + if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + pr_warn_ratelimited( + "dns_resolver: Unsupported content type (%u)\n", + bin->content); + return -EINVAL; + } + + if (bin->version != 1) { + pr_warn_ratelimited( + "dns_resolver: Unsupported server list version (%u)\n", + bin->version); + return -EINVAL; + } + + result_len = datalen; + goto store_result; + } + kenter("'%*.*s',%u", datalen, datalen, data, datalen); - if (datalen <= 1 || !data || data[datalen - 1] != '\0') + if (!data || data[datalen - 1] != '\0') return -EINVAL; datalen--; @@ -144,6 +204,7 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return 0; } +store_result: kdebug("store result"); prep->quotalen = result_len; diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index 49da67034f29..76338c38738a 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -148,12 +148,9 @@ int dns_query(const char *type, const char *name, size_t namelen, if (_result) { ret = -ENOMEM; - *_result = kmalloc(len + 1, GFP_KERNEL); + *_result = kmemdup_nul(upayload->data, len, GFP_KERNEL); if (!*_result) goto put; - - memcpy(*_result, upayload->data, len); - (*_result)[len] = '\0'; } if (_expiry) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index bee8db979195..f8c7ec8171a8 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -208,7 +208,6 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); - struct dst_metrics *m; change_nexthops(fi) { if (nexthop_nh->nh_dev) @@ -219,9 +218,8 @@ static void free_fib_info_rcu(struct rcu_head *head) rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); - m = fi->fib_metrics; - if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) - kfree(m); + ip_fib_metrics_put(fi->fib_metrics); + kfree(fi); } @@ -1020,13 +1018,6 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) return true; } -static int -fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) -{ - return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len, - fi->fib_metrics->metrics); -} - struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack) { @@ -1084,16 +1075,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (!fi) goto failure; - if (cfg->fc_mx) { - fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); - if (unlikely(!fi->fib_metrics)) { - kfree(fi); - return ERR_PTR(err); - } - refcount_set(&fi->fib_metrics->refcnt, 1); - } else { - fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; + fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx, + cfg->fc_mx_len); + if (unlikely(IS_ERR(fi->fib_metrics))) { + err = PTR_ERR(fi->fib_metrics); + kfree(fi); + return ERR_PTR(err); } + fib_info_cnt++; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; @@ -1112,10 +1101,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto failure; } endfor_nexthops(fi) - err = fib_convert_metrics(fi, cfg); - if (err) - goto failure; - if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index dfd5009f96ef..15e7f7915a21 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -544,7 +544,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, struct ip_options_rcu *opt; struct rtable *rt; - opt = ireq_opt_deref(ireq); + rcu_read_lock(); + opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, @@ -558,11 +559,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; + rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: + rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index c0fe5ad996f2..26c36cccabdc 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -149,7 +149,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; - const struct iphdr *iph = ip_hdr(skb); __be16 *ports; int end; @@ -164,7 +163,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; - sin.sin_addr.s_addr = iph->daddr; + sin.sin_addr.s_addr = ip_hdr(skb)->daddr; sin.sin_port = ports[1]; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 04311f7067e2..6d218f5a2e71 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -5,8 +5,8 @@ #include <net/net_namespace.h> #include <net/tcp.h> -int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, - u32 *metrics) +static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, + int fc_mx_len, u32 *metrics) { bool ecn_ca = false; struct nlattr *nla; @@ -52,4 +52,28 @@ int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, return 0; } -EXPORT_SYMBOL_GPL(ip_metrics_convert); + +struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, + int fc_mx_len) +{ + struct dst_metrics *fib_metrics; + int err; + + if (!fc_mx) + return (struct dst_metrics *)&dst_default_metrics; + + fib_metrics = kzalloc(sizeof(*fib_metrics), GFP_KERNEL); + if (unlikely(!fib_metrics)) + return ERR_PTR(-ENOMEM); + + err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics); + if (!err) { + refcount_set(&fib_metrics->refcnt, 1); + } else { + kfree(fib_metrics); + fib_metrics = ERR_PTR(err); + } + + return fib_metrics; +} +EXPORT_SYMBOL_GPL(ip_fib_metrics_init); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 048919713f4e..f71d2395c428 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1476,12 +1476,9 @@ void rt_del_uncached_list(struct rtable *rt) static void ipv4_dst_destroy(struct dst_entry *dst) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rtable *rt = (struct rtable *)dst; - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - + ip_dst_metrics_put(dst); rt_del_uncached_list(rt); } @@ -1528,11 +1525,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, rt->rt_gateway = nh->nh_gw; rt->rt_uses_gateway = 1; } - dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); - if (fi->fib_metrics != &dst_default_metrics) { - rt->dst._metrics |= DST_METRICS_REFCOUNTED; - refcount_inc(&fi->fib_metrics->refcnt); - } + ip_dst_init_metrics(&rt->dst, fi->fib_metrics); + #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b92f422f2fa8..891ed2f91467 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -48,6 +48,7 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; +static u32 u32_max_div_HZ = UINT_MAX / HZ; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -745,9 +746,10 @@ static struct ctl_table ipv4_net_table[] = { { .procname = "tcp_probe_interval", .data = &init_net.ipv4.sysctl_tcp_probe_interval, - .maxlen = sizeof(int), + .maxlen = sizeof(u32), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_douintvec_minmax, + .extra2 = &u32_max_div_HZ, }, { .procname = "igmp_link_local_mcast_reports", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bf1aac315490..188980c58f87 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6002,11 +6002,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (th->fin) goto discard; /* It is possible that we process SYN packets from backlog, - * so we need to make sure to disable BH right there. + * so we need to make sure to disable BH and RCU right there. */ + rcu_read_lock(); local_bh_disable(); acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; local_bh_enable(); + rcu_read_unlock(); if (!acceptable) return 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1f2496e8620d..de47038afdf0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -943,9 +943,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - ireq_opt_deref(ireq)); + rcu_dereference(ireq->ireq_opt)); + rcu_read_unlock(); err = net_xmit_eval(err); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5fc4beb1c336..1bec2203d558 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1889,7 +1889,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return 0; } -static DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void) { static_branch_enable(&udp_encap_needed_key); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 0c0522b79b43..802f2bc00d69 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -405,7 +405,7 @@ static struct sk_buff *udp4_gro_receive(struct list_head *head, { struct udphdr *uh = udp_gro_udphdr(skb); - if (unlikely(!uh)) + if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index bcfc00e88756..f8de2482a529 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c index 3d36644890bb..1ad2c2c4e250 100644 --- a/net/ipv4/xfrm4_mode_transport.c +++ b/net/ipv4/xfrm4_mode_transport.c @@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5516f55e214b..cf709eadc932 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -29,6 +29,7 @@ #include <linux/list.h> #include <linux/slab.h> +#include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> @@ -160,8 +161,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) } INIT_LIST_HEAD(&f6i->fib6_siblings); - f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; - atomic_inc(&f6i->fib6_ref); return f6i; @@ -171,7 +170,6 @@ void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); struct rt6_exception_bucket *bucket; - struct dst_metrics *m; WARN_ON(f6i->fib6_node); @@ -203,9 +201,7 @@ void fib6_info_destroy_rcu(struct rcu_head *head) if (f6i->fib6_nh.nh_dev) dev_put(f6i->fib6_nh.nh_dev); - m = f6i->fib6_metrics; - if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) - kfree(m); + ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 413d98bf24f4..5e0efd3954e9 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -651,8 +651,6 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb->tstamp = sockc->transmit_time; - skb_dst_set(skb, &rt->dst); - *dstp = NULL; skb_put(skb, length); skb_reset_network_header(skb); @@ -665,8 +663,14 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); - if (err) - goto error_fault; + if (err) { + err = -EFAULT; + kfree_skb(skb); + goto error; + } + + skb_dst_set(skb, &rt->dst); + *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -675,21 +679,28 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, if (unlikely(!skb)) return 0; + /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev + * in the error path. Since skb has been freed, the dst could + * have been queued for deletion. + */ + rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); - if (err) - goto error; + if (err) { + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); + goto error_check; + } + rcu_read_unlock(); out: return 0; -error_fault: - err = -EFAULT; - kfree_skb(skb); error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); +error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6311a7fc5f63..74d97addf1af 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -364,14 +364,11 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rt6_info *rt = (struct rt6_info *)dst; struct fib6_info *from; struct inet6_dev *idev; - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - + ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; @@ -978,11 +975,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); - dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); - if (from->fib6_metrics != &dst_default_metrics) { - rt->dst._metrics |= DST_METRICS_REFCOUNTED; - refcount_inc(&from->fib6_metrics->refcnt); - } + ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to @ort */ @@ -2705,24 +2698,6 @@ out: return entries > rt_max_size; } -static int ip6_convert_metrics(struct net *net, struct fib6_info *rt, - struct fib6_config *cfg) -{ - struct dst_metrics *p; - - if (!cfg->fc_mx) - return 0; - - p = kzalloc(sizeof(*rt->fib6_metrics), GFP_KERNEL); - if (unlikely(!p)) - return -ENOMEM; - - refcount_set(&p->refcnt, 1); - rt->fib6_metrics = p; - - return ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len, p->metrics); -} - static struct rt6_info *ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, @@ -2998,13 +2973,17 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (!rt) goto out; + rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len); + if (IS_ERR(rt->fib6_metrics)) { + err = PTR_ERR(rt->fib6_metrics); + /* Do not leave garbage there. */ + rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; + goto out; + } + if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; - err = ip6_convert_metrics(net, rt, cfg); - if (err < 0) - goto out; - if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); @@ -3727,6 +3706,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, if (!f6i) return ERR_PTR(-ENOMEM); + f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0); f6i->dst_nocount = true; f6i->dst_host = true; f6i->fib6_protocol = RTPROT_KERNEL; @@ -4289,11 +4269,6 @@ static int ip6_route_info_append(struct net *net, if (!nh) return -ENOMEM; nh->fib6_info = rt; - err = ip6_convert_metrics(net, rt, r_cfg); - if (err) { - kfree(nh); - return err; - } memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->next, rt6_nh_list); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 28c4aa5078fc..374e7d302f26 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -548,7 +548,7 @@ static __inline__ void udpv6_err(struct sk_buff *skb, __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } -static DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_enable(&udpv6_encap_needed_key); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 95dee9ca8d22..1b8e161ac527 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -119,7 +119,7 @@ static struct sk_buff *udp6_gro_receive(struct list_head *head, { struct udphdr *uh = udp_gro_udphdr(skb); - if (unlikely(!uh)) + if (unlikely(!uh) || !static_branch_unlikely(&udpv6_encap_needed_key)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841f4a07438e..9ef490dddcea 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -59,6 +59,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return -1; } diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 9ad07a91708e..3c29da5defe6 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -51,7 +51,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -60,8 +59,7 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - sizeof(struct ipv6hdr)); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5959ce9620eb..6a74080005cf 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -170,9 +170,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 504627e2117f..914aef7e7afd 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -425,7 +425,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ - if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP)) + if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5e6cf2cee965..5836ddeac9e3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1756,7 +1756,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if (local->ops->wake_tx_queue && type != NL80211_IFTYPE_AP_VLAN && - type != NL80211_IFTYPE_MONITOR) + (type != NL80211_IFTYPE_MONITOR || + (params->flags & MONITOR_FLAG_ACTIVE))) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index ee56f18cad3f..21526630bf65 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -217,7 +217,8 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb); + struct sta_info *sta, + struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index daf9db3c8f24..6950cd0bf594 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -295,15 +295,12 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, } void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb) + struct sta_info *sta, + struct ieee80211_tx_status *st) { - struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *txinfo = st->info; int failed; - if (!ieee80211_is_data(hdr->frame_control)) - return; - failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); /* moving average, scaled to 100. diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 9a6d7208bf4f..91d7c0cd1882 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -479,11 +479,6 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, if (!skb) return; - if (dropped) { - dev_kfree_skb_any(skb); - return; - } - if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; @@ -507,6 +502,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, rcu_read_unlock(); dev_kfree_skb_any(skb); + } else if (dropped) { + dev_kfree_skb_any(skb); } else { /* consumes skb */ skb_complete_wifi_ack(skb, acked); @@ -811,7 +808,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, rate_control_tx_status(local, sband, status); if (ieee80211_vif_is_mesh(&sta->sdata->vif)) - ieee80211s_update_metric(local, sta, skb); + ieee80211s_update_metric(local, sta, status); if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); @@ -972,6 +969,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, } rate_control_tx_status(local, sband, status); + if (ieee80211_vif_is_mesh(&sta->sdata->vif)) + ieee80211s_update_metric(local, sta, status); } if (acked || noack_success) { diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 5cd5e6e5834e..6c647f425e05 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -16,6 +16,7 @@ #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" +#include "wme.h" /* give usermode some time for retries in setting up the TDLS session */ #define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) @@ -1010,14 +1011,13 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: - skb_set_queue_mapping(skb, IEEE80211_AC_BK); - skb->priority = 2; + skb->priority = 256 + 2; break; default: - skb_set_queue_mapping(skb, IEEE80211_AC_VI); - skb->priority = 5; + skb->priority = 256 + 5; break; } + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb)); /* * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress. diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index c42bfa1dcd2c..e0ccee23fbcd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -214,6 +214,7 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) { struct ieee80211_local *local = tx->local; struct ieee80211_if_managed *ifmgd; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); /* driver doesn't support power save */ if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) @@ -242,6 +243,9 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx) if (tx->sdata->vif.type != NL80211_IFTYPE_STATION) return TX_CONTINUE; + if (unlikely(info->flags & IEEE80211_TX_INTFL_OFFCHAN_TX_OK)) + return TX_CONTINUE; + ifmgd = &tx->sdata->u.mgd; /* @@ -1915,7 +1919,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; if (invoke_tx_handlers_early(&tx)) - return false; + return true; if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb)) return true; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 8055e3965cef..3d0a33b874f5 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -68,6 +68,10 @@ enum { NCSI_MODE_MAX }; +/* OEM Vendor Manufacture ID */ +#define NCSI_OEM_MFR_MLX_ID 0x8119 +#define NCSI_OEM_MFR_BCM_ID 0x113d + struct ncsi_channel_version { u32 version; /* Supported BCD encoded NCSI version */ u32 alpha2; /* Supported BCD encoded NCSI version */ @@ -305,6 +309,7 @@ struct ncsi_cmd_arg { unsigned short words[8]; unsigned int dwords[4]; }; + unsigned char *data; /* NCSI OEM data */ }; extern struct list_head ncsi_dev_list; diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index 7567ca63aae2..82b7d9201db8 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -211,6 +211,25 @@ static int ncsi_cmd_handler_snfc(struct sk_buff *skb, return 0; } +static int ncsi_cmd_handler_oem(struct sk_buff *skb, + struct ncsi_cmd_arg *nca) +{ + struct ncsi_cmd_oem_pkt *cmd; + unsigned int len; + + len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; + if (nca->payload < 26) + len += 26; + else + len += nca->payload; + + cmd = skb_put_zero(skb, len); + memcpy(&cmd->mfr_id, nca->data, nca->payload); + ncsi_cmd_build_header(&cmd->cmd.common, nca); + + return 0; +} + static struct ncsi_cmd_handler { unsigned char type; int payload; @@ -244,7 +263,7 @@ static struct ncsi_cmd_handler { { NCSI_PKT_CMD_GNS, 0, ncsi_cmd_handler_default }, { NCSI_PKT_CMD_GNPTS, 0, ncsi_cmd_handler_default }, { NCSI_PKT_CMD_GPS, 0, ncsi_cmd_handler_default }, - { NCSI_PKT_CMD_OEM, 0, NULL }, + { NCSI_PKT_CMD_OEM, -1, ncsi_cmd_handler_oem }, { NCSI_PKT_CMD_PLDM, 0, NULL }, { NCSI_PKT_CMD_GPUUID, 0, ncsi_cmd_handler_default } }; @@ -316,8 +335,13 @@ int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) return -ENOENT; } - /* Get packet payload length and allocate the request */ - nca->payload = nch->payload; + /* Get packet payload length and allocate the request + * It is expected that if length set as negative in + * handler structure means caller is initializing it + * and setting length in nca before calling xmit function + */ + if (nch->payload >= 0) + nca->payload = nch->payload; nr = ncsi_alloc_command(nca); if (!nr) return -ENOMEM; diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index 91b4b66438df..0f2087c8d42a 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -151,6 +151,20 @@ struct ncsi_cmd_snfc_pkt { unsigned char pad[22]; }; +/* OEM Request Command as per NCSI Specification */ +struct ncsi_cmd_oem_pkt { + struct ncsi_cmd_pkt_hdr cmd; /* Command header */ + __be32 mfr_id; /* Manufacture ID */ + unsigned char data[]; /* OEM Payload Data */ +}; + +/* OEM Response Packet as per NCSI Specification */ +struct ncsi_rsp_oem_pkt { + struct ncsi_rsp_pkt_hdr rsp; /* Command header */ + __be32 mfr_id; /* Manufacture ID */ + unsigned char data[]; /* Payload data */ +}; + /* Get Link Status */ struct ncsi_rsp_gls_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 930c1d3796f0..d66b34749027 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -596,6 +596,47 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) return 0; } +static struct ncsi_rsp_oem_handler { + unsigned int mfr_id; + int (*handler)(struct ncsi_request *nr); +} ncsi_rsp_oem_handlers[] = { + { NCSI_OEM_MFR_MLX_ID, NULL }, + { NCSI_OEM_MFR_BCM_ID, NULL } +}; + +/* Response handler for OEM command */ +static int ncsi_rsp_handler_oem(struct ncsi_request *nr) +{ + struct ncsi_rsp_oem_pkt *rsp; + struct ncsi_rsp_oem_handler *nrh = NULL; + unsigned int mfr_id, i; + + /* Get the response header */ + rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); + mfr_id = ntohl(rsp->mfr_id); + + /* Check for manufacturer id and Find the handler */ + for (i = 0; i < ARRAY_SIZE(ncsi_rsp_oem_handlers); i++) { + if (ncsi_rsp_oem_handlers[i].mfr_id == mfr_id) { + if (ncsi_rsp_oem_handlers[i].handler) + nrh = &ncsi_rsp_oem_handlers[i]; + else + nrh = NULL; + + break; + } + } + + if (!nrh) { + netdev_err(nr->ndp->ndev.dev, "Received unrecognized OEM packet with MFR-ID (0x%x)\n", + mfr_id); + return -ENOENT; + } + + /* Process the packet */ + return nrh->handler(nr); +} + static int ncsi_rsp_handler_gvi(struct ncsi_request *nr) { struct ncsi_rsp_gvi_pkt *rsp; @@ -932,7 +973,7 @@ static struct ncsi_rsp_handler { { NCSI_PKT_RSP_GNS, 172, ncsi_rsp_handler_gns }, { NCSI_PKT_RSP_GNPTS, 172, ncsi_rsp_handler_gnpts }, { NCSI_PKT_RSP_GPS, 8, ncsi_rsp_handler_gps }, - { NCSI_PKT_RSP_OEM, 0, NULL }, + { NCSI_PKT_RSP_OEM, -1, ncsi_rsp_handler_oem }, { NCSI_PKT_RSP_PLDM, 0, NULL }, { NCSI_PKT_RSP_GPUUID, 20, ncsi_rsp_handler_gpuuid } }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index b4bdf9eda7b7..247b89784a6f 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1213,8 +1213,8 @@ static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { #define TCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ - NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))) + \ - NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags)))) + NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)) + \ + NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags))) static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct) { diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 5af74b37f423..a35fb59ace73 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -49,7 +49,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFTA_DATA_VALUE, NFT_OSF_MAXGENRELEN); + NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN); if (err < 0) return err; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 55e2d9215c0d..0e5ec126f6ad 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -355,12 +355,11 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { + struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; struct nft_set_gc_batch *gcb = NULL; - struct rb_node *node, *prev = NULL; - struct nft_rbtree_elem *rbe; struct nft_rbtree *priv; + struct rb_node *node; struct nft_set *set; - int i; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); @@ -371,7 +370,7 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(node, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe)) { - prev = node; + rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) @@ -379,29 +378,30 @@ static void nft_rbtree_gc(struct work_struct *work) if (nft_set_elem_mark_busy(&rbe->ext)) continue; + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + rbe_prev = NULL; + } gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + rbe_prev = rbe; - if (prev) { - rbe = rb_entry(prev, struct nft_rbtree_elem, node); + if (rbe_end) { atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - prev = NULL; + nft_set_gc_batch_add(gcb, rbe_end); + rb_erase(&rbe_end->node, &priv->root); + rbe_end = NULL; } node = rb_next(node); if (!node) break; } - if (gcb) { - for (i = 0; i < gcb->head.cnt; i++) { - rbe = gcb->elems[i]; - rb_erase(&rbe->node, &priv->root); - } - } + if (rbe_prev) + rb_erase(&rbe_prev->node, &priv->root); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 0472f3472842..ada144e5645b 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -56,7 +56,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; - if (!net_eq(xt_net(par), sock_net(sk))) + if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) @@ -117,7 +117,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sk_buff *pskb = (struct sk_buff *)skb; struct sock *sk = skb->sk; - if (!net_eq(xt_net(par), sock_net(sk))) + if (sk && !net_eq(xt_net(par), sock_net(sk))) sk = NULL; if (!sk) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 86a75105af1a..35ae64cbef33 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1312,6 +1312,10 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, rcu_assign_pointer(help->helper, helper); info->helper = helper; + + if (info->nat) + request_module("ip_nat_%s", name); + return 0; } @@ -1624,10 +1628,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; } - - __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); - if (helper) { err = ovs_ct_add_helper(&ct_info, helper, key, log); if (err) @@ -1639,6 +1639,8 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (err) goto err_free_ct; + __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); + nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f85f67b5c1f4..ec3095f13aae 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2715,10 +2715,12 @@ tpacket_error: } } - if (po->has_vnet_hdr && virtio_net_hdr_to_skb(skb, vnet_hdr, - vio_le())) { - tp_len = -EINVAL; - goto tpacket_error; + if (po->has_vnet_hdr) { + if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { + tp_len = -EINVAL; + goto tpacket_error; + } + virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; @@ -2915,6 +2917,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; len += sizeof(vnet_hdr); + virtio_net_hdr_set_proto(skb, &vnet_hdr); } skb_probe_transport_header(skb, reserve); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ac44d8afffb1..013dbcb052e5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -97,7 +97,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, srx->transport_len > len) return -EINVAL; - if (srx->transport.family != rx->family) + if (srx->transport.family != rx->family && + srx->transport.family == AF_INET && rx->family != AF_INET6) return -EAFNOSUPPORT; switch (srx->transport.family) { @@ -385,6 +386,20 @@ u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call) EXPORT_SYMBOL(rxrpc_kernel_check_life); /** + * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call. + * @sock: The socket the call is on + * @call: The call to query + * + * Allow a kernel service to retrieve the epoch value from a service call to + * see if the client at the other end rebooted. + */ +u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call) +{ + return call->conn->proto.epoch; +} +EXPORT_SYMBOL(rxrpc_kernel_get_epoch); + +/** * rxrpc_kernel_check_call - Check a call's state * @sock: The socket the call is on * @call: The call to check diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c97558710421..76569c178915 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -40,17 +40,12 @@ struct rxrpc_crypt { struct rxrpc_connection; /* - * Mark applied to socket buffers. + * Mark applied to socket buffers in skb->mark. skb->priority is used + * to pass supplementary information. */ enum rxrpc_skb_mark { - RXRPC_SKB_MARK_DATA, /* data message */ - RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ - RXRPC_SKB_MARK_BUSY, /* server busy message */ - RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ - RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */ - RXRPC_SKB_MARK_NET_ERROR, /* network error message */ - RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ - RXRPC_SKB_MARK_NEW_CALL, /* local error message */ + RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ + RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; /* @@ -293,7 +288,6 @@ struct rxrpc_peer { struct hlist_node hash_link; struct rxrpc_local *local; struct hlist_head error_targets; /* targets for net error distribution */ - struct work_struct error_distributor; struct rb_root service_conns; /* Service connections */ struct list_head keepalive_link; /* Link in net->peer_keepalive[] */ time64_t last_tx_at; /* Last time packet sent here */ @@ -304,8 +298,6 @@ struct rxrpc_peer { unsigned int maxdata; /* data size (MTU - hdrsize) */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ int debug_id; /* debug ID for printks */ - int error_report; /* Net (+0) or local (+1000000) to distribute */ -#define RXRPC_LOCAL_ERROR_OFFSET 1000000 struct sockaddr_rxrpc srx; /* remote address */ /* calculated RTT cache */ @@ -463,6 +455,16 @@ struct rxrpc_connection { u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ }; +static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp) +{ + return sp->hdr.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp) +{ + return !rxrpc_to_server(sp); +} + /* * Flags in call->flags. */ @@ -717,6 +719,8 @@ extern struct workqueue_struct *rxrpc_workqueue; int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, + struct rxrpc_sock *, + struct rxrpc_peer *, struct rxrpc_connection *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); @@ -908,7 +912,8 @@ extern unsigned int rxrpc_closed_conn_expiry; struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, - struct sk_buff *); + struct sk_buff *, + struct rxrpc_peer **); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); @@ -1031,7 +1036,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *); * peer_event.c */ void rxrpc_error_report(struct sock *); -void rxrpc_peer_error_distributor(struct work_struct *); void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); void rxrpc_peer_keepalive_worker(struct work_struct *); @@ -1044,13 +1048,11 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); -struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *, - struct rxrpc_peer *); +void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); -void __rxrpc_queue_peer_error(struct rxrpc_peer *); /* * proc.c @@ -1093,7 +1095,6 @@ void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); -void rxrpc_lose_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* @@ -1110,8 +1111,7 @@ static inline void rxrpc_sysctl_exit(void) {} /* * utils.c */ -int rxrpc_extract_addr_from_skb(struct rxrpc_local *, struct sockaddr_rxrpc *, - struct sk_buff *); +int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); static inline bool before(u32 seq1, u32 seq2) { diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 9d1e298b784c..8354cadbb839 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) */ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, + struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; - struct rxrpc_peer *peer, *xpeer; struct rxrpc_call *call; unsigned short call_head, conn_head, peer_head; unsigned short call_tail, conn_tail, peer_tail; @@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, return NULL; if (!conn) { - /* No connection. We're going to need a peer to start off - * with. If one doesn't yet exist, use a spare from the - * preallocation set. We dump the address into the spare in - * anticipation - and to save on stack space. - */ - xpeer = b->peer_backlog[peer_tail]; - if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0) - return NULL; - - peer = rxrpc_lookup_incoming_peer(local, xpeer); - if (peer == xpeer) { + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + peer = b->peer_backlog[peer_tail]; + if (rxrpc_extract_addr_from_skb(&peer->srx, skb) < 0) + return NULL; b->peer_backlog[peer_tail] = NULL; smp_store_release(&b->peer_backlog_tail, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); + + rxrpc_new_incoming_peer(local, peer); } /* Now allocate and set up the connection */ @@ -335,45 +332,31 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, * The call is returned with the user access mutex held. */ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_sock *rx, + struct rxrpc_peer *peer, struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_sock *rx; struct rxrpc_call *call; - u16 service_id = sp->hdr.serviceId; _enter(""); - /* Get the socket providing the service */ - rx = rcu_dereference(local->service); - if (rx && (service_id == rx->srx.srx_service || - service_id == rx->second_service)) - goto found_service; - - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; - skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [service]"); - return NULL; - -found_service: spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; _leave(" = NULL [close]"); call = NULL; goto out; } - call = rxrpc_alloc_incoming_call(rx, local, conn, skb); + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); if (!call) { - skb->mark = RXRPC_SKB_MARK_BUSY; + skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; _leave(" = NULL [busy]"); call = NULL; goto out; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9486293fef5c..799f75b6900d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -400,7 +400,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, rcu_assign_pointer(conn->channels[chan].call, call); spin_lock(&conn->params.peer->lock); - hlist_add_head(&call->error_link, &conn->params.peer->error_targets); + hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets); spin_unlock(&conn->params.peer->lock); _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f8f37188a932..8acf74fe24c0 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -710,8 +710,8 @@ int rxrpc_connect_call(struct rxrpc_call *call, } spin_lock_bh(&call->conn->params.peer->lock); - hlist_add_head(&call->error_link, - &call->conn->params.peer->error_targets); + hlist_add_head_rcu(&call->error_link, + &call->conn->params.peer->error_targets); spin_unlock_bh(&call->conn->params.peer->lock); out: diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 77440a356b14..c332722820c2 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) * If successful, a pointer to the connection is returned, but no ref is taken. * NULL is returned if there is no match. * + * When searching for a service call, if we find a peer but no connection, we + * return that through *_peer in case we need to create a new service call. + * * The caller must be holding the RCU read lock. */ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, - struct sk_buff *skb) + struct sk_buff *skb, + struct rxrpc_peer **_peer) { struct rxrpc_connection *conn; struct rxrpc_conn_proto k; @@ -82,14 +86,12 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); - if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0) + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) goto not_found; - k.epoch = sp->hdr.epoch; - k.cid = sp->hdr.cid & RXRPC_CIDMASK; - - /* We may have to handle mixing IPv4 and IPv6 */ - if (srx.transport.family != local->srx.transport.family) { + if (srx.transport.family != local->srx.transport.family && + (srx.transport.family == AF_INET && + local->srx.transport.family != AF_INET6)) { pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", srx.transport.family, local->srx.transport.family); @@ -99,7 +101,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) { + if (rxrpc_to_server(sp)) { /* We need to look up service connections by the full protocol * parameter set. We look up the peer first as an intermediate * step and then the connection from the peer's tree. @@ -107,6 +109,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, peer = rxrpc_lookup_peer_rcu(local, &srx); if (!peer) goto not_found; + *_peer = peer; conn = rxrpc_find_service_conn_rcu(peer, skb); if (!conn || atomic_read(&conn->usage) == 0) goto not_found; @@ -214,7 +217,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; spin_lock_bh(&conn->params.peer->lock); - hlist_del_init(&call->error_link); + hlist_del_rcu(&call->error_link); spin_unlock_bh(&conn->params.peer->lock); if (rxrpc_is_client_call(call)) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index ee8e7e1d5c0f..5b2626929822 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -622,13 +622,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call, if (!skb) continue; + sent_at = skb->tstamp; + smp_rmb(); /* Read timestamp before serial. */ sp = rxrpc_skb(skb); if (sp->hdr.serial != orig_serial) continue; - smp_rmb(); - sent_at = skb->tstamp; goto found; } + return; found: @@ -1124,12 +1125,14 @@ void rxrpc_data_ready(struct sock *udp_sk) { struct rxrpc_connection *conn; struct rxrpc_channel *chan; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_local *local = udp_sk->sk_user_data; + struct rxrpc_peer *peer = NULL; + struct rxrpc_sock *rx = NULL; struct sk_buff *skb; unsigned int channel; - int ret, skew; + int ret, skew = 0; _enter("%p", udp_sk); @@ -1143,6 +1146,9 @@ void rxrpc_data_ready(struct sock *udp_sk) return; } + if (skb->tstamp == 0) + skb->tstamp = ktime_get_real(); + rxrpc_new_skb(skb, rxrpc_skb_rx_received); _net("recv skb %p", skb); @@ -1170,53 +1176,82 @@ void rxrpc_data_ready(struct sock *udp_sk) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_lose_skb(skb, rxrpc_skb_rx_lost); + rxrpc_free_skb(skb, rxrpc_skb_rx_lost); return; } } trace_rxrpc_rx_packet(sp); - _net("Rx RxRPC %s ep=%x call=%x:%x", - sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient", - sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber); - - if (sp->hdr.type >= RXRPC_N_PACKET_TYPES || - !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) { - _proto("Rx Bad Packet Type %u", sp->hdr.type); - goto bad_message; - } - switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: - if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) + if (rxrpc_to_client(sp)) goto discard; rxrpc_post_packet_to_local(local, skb); goto out; case RXRPC_PACKET_TYPE_BUSY: - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + if (rxrpc_to_server(sp)) goto discard; /* Fall through */ + case RXRPC_PACKET_TYPE_ACK: + case RXRPC_PACKET_TYPE_ACKALL: + if (sp->hdr.callNumber == 0) + goto bad_message; + /* Fall through */ + case RXRPC_PACKET_TYPE_ABORT: + break; case RXRPC_PACKET_TYPE_DATA: - if (sp->hdr.callNumber == 0) + if (sp->hdr.callNumber == 0 || + sp->hdr.seq == 0) goto bad_message; if (sp->hdr.flags & RXRPC_JUMBO_PACKET && !rxrpc_validate_jumbo(skb)) goto bad_message; break; + case RXRPC_PACKET_TYPE_CHALLENGE: + if (rxrpc_to_server(sp)) + goto discard; + break; + case RXRPC_PACKET_TYPE_RESPONSE: + if (rxrpc_to_client(sp)) + goto discard; + break; + /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: goto discard; + + default: + _proto("Rx Bad Packet Type %u", sp->hdr.type); + goto bad_message; } + if (sp->hdr.serviceId == 0) + goto bad_message; + rcu_read_lock(); - conn = rxrpc_find_connection_rcu(local, skb); + if (rxrpc_to_server(sp)) { + /* Weed out packets to services we're not offering. Packets + * that would begin a call are explicitly rejected and the rest + * are just discarded. + */ + rx = rcu_dereference(local->service); + if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && + sp->hdr.serviceId != rx->second_service)) { + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + sp->hdr.seq == 1) + goto unsupported_service; + goto discard_unlock; + } + } + + conn = rxrpc_find_connection_rcu(local, skb, &peer); if (conn) { if (sp->hdr.securityIndex != conn->security_ix) goto wrong_security; @@ -1280,7 +1315,7 @@ void rxrpc_data_ready(struct sock *udp_sk) call = rcu_dereference(chan->call); if (sp->hdr.callNumber > chan->call_id) { - if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) { + if (rxrpc_to_client(sp)) { rcu_read_unlock(); goto reject_packet; } @@ -1297,19 +1332,15 @@ void rxrpc_data_ready(struct sock *udp_sk) if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) set_bit(RXRPC_CALL_RX_HEARD, &call->flags); } - } else { - skew = 0; - call = NULL; } if (!call || atomic_read(&call->usage) == 0) { - if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) || - sp->hdr.callNumber == 0 || + if (rxrpc_to_client(sp) || sp->hdr.type != RXRPC_PACKET_TYPE_DATA) goto bad_message_unlock; if (sp->hdr.seq != 1) goto discard_unlock; - call = rxrpc_new_incoming_call(local, conn, skb); + call = rxrpc_new_incoming_call(local, rx, peer, conn, skb); if (!call) { rcu_read_unlock(); goto reject_packet; @@ -1340,6 +1371,13 @@ wrong_security: skb->priority = RXKADINCONSISTENCY; goto post_abort; +unsupported_service: + rcu_read_unlock(); + trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EOPNOTSUPP); + skb->priority = RX_INVALID_OPERATION; + goto post_abort; + reupgrade: rcu_read_unlock(); trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, @@ -1354,7 +1392,7 @@ bad_message: protocol_error: skb->priority = RX_PROTOCOL_ERROR; post_abort: - skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 13bd8a4dfac7..927ead43df42 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -39,7 +39,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, _enter(""); - if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0) + if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) return; msg.msg_name = &srx.transport; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 777c3ed4cfc0..94d234e9c685 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -135,10 +135,10 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } switch (local->srx.transport.family) { - case AF_INET: - /* we want to receive ICMP errors */ + case AF_INET6: + /* we want to receive ICMPv6 errors */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); @@ -146,19 +146,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } /* we want to set the don't fragment bit */ - opt = IP_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + opt = IPV6_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); goto error; } - break; - case AF_INET6: + /* Fall through and set IPv4 options too otherwise we don't get + * errors from IPv4 packets sent through the IPv6 socket. + */ + + case AF_INET: /* we want to receive ICMP errors */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); @@ -166,13 +169,22 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, (char *) &opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); goto error; } + + /* We want receive timestamps. */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS, + (char *)&opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } break; default: diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index ccf5de160444..0f0b499d1202 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, struct kvec iov[2]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; - ktime_t now; size_t len, n; int ret; u8 reason; @@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, /* We need to stick a time in before we send the packet in case * the reply gets back before kernel_sendmsg() completes - but * asking UDP to send the packet can take a relatively long - * time, so we update the time after, on the assumption that - * the packet transmission is more likely to happen towards the - * end of the kernel_sendmsg() call. + * time. */ call->ping_time = ktime_get_real(); set_bit(RXRPC_CALL_PINGING, &call->flags); @@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - now = ktime_get_real(); - if (ping) - call->ping_time = now; conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, @@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. + * + * However, we mustn't request an ACK on the last reply packet of a + * service call, lest OpenAFS incorrectly send us an ACK with some + * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (!(sp->hdr.flags & RXRPC_LAST_PACKET) && + if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) || + rxrpc_to_server(sp) + ) && (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || retrans || call->cong_mode == RXRPC_CALL_SLOW_START || @@ -378,11 +378,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, if ((lose++ & 7) == 7) { ret = 0; lost = true; - goto done; } } - _proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq); + trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, + retrans, lost); + if (lost) + goto done; /* send the packet with the don't fragment bit set if we currently * think it's small enough */ @@ -390,6 +392,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, goto send_fragmentable; down_read(&conn->params.local->defrag_sem); + + sp->hdr.serial = serial; + smp_wmb(); /* Set serial before timestamp */ + skb->tstamp = ktime_get_real(); + /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -410,15 +417,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, goto send_fragmentable; done: - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, - retrans, lost); if (ret >= 0) { - ktime_t now = ktime_get_real(); - skb->tstamp = now; - smp_wmb(); - sp->hdr.serial = serial; if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = now; + call->peer->rtt_last_req = skb->tstamp; trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_usage > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -457,6 +458,10 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); + sp->hdr.serial = serial; + smp_wmb(); /* Set serial before timestamp */ + skb->tstamp = ktime_get_real(); + switch (conn->params.local->srx.transport.family) { case AF_INET: opt = IP_PMTUDISC_DONT; @@ -519,7 +524,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) struct kvec iov[2]; size_t size; __be32 code; - int ret; + int ret, ioc; _enter("%d", local->debug_id); @@ -527,7 +532,6 @@ void rxrpc_reject_packets(struct rxrpc_local *local) iov[0].iov_len = sizeof(whdr); iov[1].iov_base = &code; iov[1].iov_len = sizeof(code); - size = sizeof(whdr) + sizeof(code); msg.msg_name = &srx.transport; msg.msg_control = NULL; @@ -535,16 +539,30 @@ void rxrpc_reject_packets(struct rxrpc_local *local) msg.msg_flags = 0; memset(&whdr, 0, sizeof(whdr)); - whdr.type = RXRPC_PACKET_TYPE_ABORT; while ((skb = skb_dequeue(&local->reject_queue))) { rxrpc_see_skb(skb, rxrpc_skb_rx_seen); sp = rxrpc_skb(skb); - if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) { - msg.msg_namelen = srx.transport_len; - + switch (skb->mark) { + case RXRPC_SKB_MARK_REJECT_BUSY: + whdr.type = RXRPC_PACKET_TYPE_BUSY; + size = sizeof(whdr); + ioc = 1; + break; + case RXRPC_SKB_MARK_REJECT_ABORT: + whdr.type = RXRPC_PACKET_TYPE_ABORT; code = htonl(skb->priority); + size = sizeof(whdr) + sizeof(code); + ioc = 2; + break; + default: + rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + continue; + } + + if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { + msg.msg_namelen = srx.transport_len; whdr.epoch = htonl(sp->hdr.epoch); whdr.cid = htonl(sp->hdr.cid); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 4f9da2f51c69..81a7869325a6 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -23,6 +23,8 @@ #include "ar-internal.h" static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); +static void rxrpc_distribute_error(struct rxrpc_peer *, int, + enum rxrpc_call_completion); /* * Find the peer associated with an ICMP packet. @@ -45,6 +47,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, */ switch (srx->transport.family) { case AF_INET: + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.family = AF_INET; srx->transport.sin.sin_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP: @@ -68,20 +72,20 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: - srx->transport.sin6.sin6_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP6: _net("Rx ICMP6"); + srx->transport.sin6.sin6_port = serr->port; memcpy(&srx->transport.sin6.sin6_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in6_addr)); break; case SO_EE_ORIGIN_ICMP: _net("Rx ICMP on v6 sock"); - srx->transport.sin6.sin6_addr.s6_addr32[0] = 0; - srx->transport.sin6.sin6_addr.s6_addr32[1] = 0; - srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12, + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.family = AF_INET; + srx->transport.sin.sin_port = serr->port; + memcpy(&srx->transport.sin.sin_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in_addr)); break; @@ -194,8 +198,6 @@ void rxrpc_error_report(struct sock *sk) rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_rx_freed); - /* The ref we obtained is passed off to the work item */ - __rxrpc_queue_peer_error(peer); _leave(""); } @@ -205,6 +207,7 @@ void rxrpc_error_report(struct sock *sk) static void rxrpc_store_error(struct rxrpc_peer *peer, struct sock_exterr_skb *serr) { + enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR; struct sock_extended_err *ee; int err; @@ -255,7 +258,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: _proto("Rx Received local error { error=%d }", err); - err += RXRPC_LOCAL_ERROR_OFFSET; + compl = RXRPC_CALL_LOCAL_ERROR; break; case SO_EE_ORIGIN_ICMP6: @@ -264,48 +267,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; } - peer->error_report = err; + rxrpc_distribute_error(peer, err, compl); } /* - * Distribute an error that occurred on a peer + * Distribute an error that occurred on a peer. */ -void rxrpc_peer_error_distributor(struct work_struct *work) +static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, + enum rxrpc_call_completion compl) { - struct rxrpc_peer *peer = - container_of(work, struct rxrpc_peer, error_distributor); struct rxrpc_call *call; - enum rxrpc_call_completion compl; - int error; - - _enter(""); - - error = READ_ONCE(peer->error_report); - if (error < RXRPC_LOCAL_ERROR_OFFSET) { - compl = RXRPC_CALL_NETWORK_ERROR; - } else { - compl = RXRPC_CALL_LOCAL_ERROR; - error -= RXRPC_LOCAL_ERROR_OFFSET; - } - - _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error); - spin_lock_bh(&peer->lock); - - while (!hlist_empty(&peer->error_targets)) { - call = hlist_entry(peer->error_targets.first, - struct rxrpc_call, error_link); - hlist_del_init(&call->error_link); + hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) { rxrpc_see_call(call); - - if (rxrpc_set_call_completion(call, compl, 0, -error)) + if (call->state < RXRPC_CALL_COMPLETE && + rxrpc_set_call_completion(call, compl, 0, -error)) rxrpc_notify_socket(call); } - - spin_unlock_bh(&peer->lock); - - rxrpc_put_peer(peer); - _leave(""); } /* diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1dc7648e3eff..01a9febfa367 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( struct rxrpc_net *rxnet = local->rxnet; hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { - if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) { - if (atomic_read(&peer->usage) == 0) - return NULL; + if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 && + atomic_read(&peer->usage) > 0) return peer; - } } return NULL; @@ -222,8 +220,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) atomic_set(&peer->usage, 1); peer->local = local; INIT_HLIST_HEAD(&peer->error_targets); - INIT_WORK(&peer->error_distributor, - &rxrpc_peer_error_distributor); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); @@ -299,34 +295,23 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, } /* - * Set up a new incoming peer. The address is prestored in the preallocated - * peer. + * Set up a new incoming peer. There shouldn't be any other matching peers + * since we've already done a search in the list from the non-reentrant context + * (the data_ready handler) that is the only place we can add new peers. */ -struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, - struct rxrpc_peer *prealloc) +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) { - struct rxrpc_peer *peer; struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; - hash_key = rxrpc_peer_hash_key(local, &prealloc->srx); - prealloc->local = local; - rxrpc_init_peer(prealloc, hash_key); + hash_key = rxrpc_peer_hash_key(local, &peer->srx); + peer->local = local; + rxrpc_init_peer(peer, hash_key); spin_lock(&rxnet->peer_hash_lock); - - /* Need to check that we aren't racing with someone else */ - peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - peer = prealloc; - hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); - list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - } - + hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); + list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); spin_unlock(&rxnet->peer_hash_lock); - return peer; } /* @@ -416,21 +401,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) } /* - * Queue a peer record. This passes the caller's ref to the workqueue. - */ -void __rxrpc_queue_peer_error(struct rxrpc_peer *peer) -{ - const void *here = __builtin_return_address(0); - int n; - - n = atomic_read(&peer->usage); - if (rxrpc_queue_work(&peer->error_distributor)) - trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here); - else - rxrpc_put_peer(peer); -} - -/* * Discard a peer record. */ static void __rxrpc_put_peer(struct rxrpc_peer *peer) diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 93da73bf7098..f9cb83c938f3 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -50,7 +50,6 @@ struct rxrpc_wire_header { #define RXRPC_PACKET_TYPE_10 10 /* Ignored */ #define RXRPC_PACKET_TYPE_11 11 /* Ignored */ #define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ -#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ uint8_t flags; /* packet flags */ #define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ @@ -72,20 +71,6 @@ struct rxrpc_wire_header { } __packed; -#define RXRPC_SUPPORTED_PACKET_TYPES ( \ - (1 << RXRPC_PACKET_TYPE_DATA) | \ - (1 << RXRPC_PACKET_TYPE_ACK) | \ - (1 << RXRPC_PACKET_TYPE_BUSY) | \ - (1 << RXRPC_PACKET_TYPE_ABORT) | \ - (1 << RXRPC_PACKET_TYPE_ACKALL) | \ - (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ - (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ - /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ - (1 << RXRPC_PACKET_TYPE_PARAMS) | \ - (1 << RXRPC_PACKET_TYPE_10) | \ - (1 << RXRPC_PACKET_TYPE_11) | \ - (1 << RXRPC_PACKET_TYPE_VERSION)) - /*****************************************************************************/ /* * jumbo packet secondary header diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 816b19a78809..eaf19ebaa964 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -715,3 +715,46 @@ call_complete: goto out; } EXPORT_SYMBOL(rxrpc_kernel_recv_data); + +/** + * rxrpc_kernel_get_reply_time - Get timestamp on first reply packet + * @sock: The socket that the call exists on + * @call: The call to query + * @_ts: Where to put the timestamp + * + * Retrieve the timestamp from the first DATA packet of the reply if it is + * in the ring. Returns true if successful, false if not. + */ +bool rxrpc_kernel_get_reply_time(struct socket *sock, struct rxrpc_call *call, + ktime_t *_ts) +{ + struct sk_buff *skb; + rxrpc_seq_t hard_ack, top, seq; + bool success = false; + + mutex_lock(&call->user_mutex); + + if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_RECV_REPLY) + goto out; + + hard_ack = call->rx_hard_ack; + if (hard_ack != 0) + goto out; + + seq = hard_ack + 1; + top = smp_load_acquire(&call->rx_top); + if (after(seq, top)) + goto out; + + skb = call->rxtx_buffer[seq & RXRPC_RXTX_BUFF_MASK]; + if (!skb) + goto out; + + *_ts = skb_get_ktime(skb); + success = true; + +out: + mutex_unlock(&call->user_mutex); + return success; +} +EXPORT_SYMBOL(rxrpc_kernel_get_reply_time); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index b8985d01876a..913dca65cc65 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -69,21 +69,6 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) } /* - * Note the injected loss of a socket buffer. - */ -void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) -{ - const void *here = __builtin_return_address(0); - if (skb) { - int n; - CHECK_SLAB_OKAY(&skb->users); - n = atomic_dec_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); - kfree_skb(skb); - } -} - -/* * Clear a queue of socket buffers. */ void rxrpc_purge_queue(struct sk_buff_head *list) diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c index e801171fa351..ff7af71c4b49 100644 --- a/net/rxrpc/utils.c +++ b/net/rxrpc/utils.c @@ -17,28 +17,17 @@ /* * Fill out a peer address from a socket buffer containing a packet. */ -int rxrpc_extract_addr_from_skb(struct rxrpc_local *local, - struct sockaddr_rxrpc *srx, - struct sk_buff *skb) +int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *srx, struct sk_buff *skb) { memset(srx, 0, sizeof(*srx)); switch (ntohs(skb->protocol)) { case ETH_P_IP: - if (local->srx.transport.family == AF_INET6) { - srx->transport_type = SOCK_DGRAM; - srx->transport_len = sizeof(srx->transport.sin6); - srx->transport.sin6.sin6_family = AF_INET6; - srx->transport.sin6.sin6_port = udp_hdr(skb)->source; - srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - srx->transport.sin6.sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr; - } else { - srx->transport_type = SOCK_DGRAM; - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.sin.sin_family = AF_INET; - srx->transport.sin.sin_port = udp_hdr(skb)->source; - srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; - } + srx->transport_type = SOCK_DGRAM; + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.sin.sin_family = AF_INET; + srx->transport.sin.sin_port = udp_hdr(skb)->source; + srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; return 0; #ifdef CONFIG_AF_RXRPC_IPV6 diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e95741388311..1b9afdee5ba9 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -194,6 +194,17 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_TAPRIO + tristate "Time Aware Priority (taprio) Scheduler" + help + Say Y here if you want to use the Time Aware Priority (taprio) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_taprio.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_taprio. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index f0403f49edcb..8a40431d7b5c 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o +obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3c7c23421885..55153da00278 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -104,11 +104,11 @@ static int __tcf_action_put(struct tc_action *p, bool bind) { struct tcf_idrinfo *idrinfo = p->idrinfo; - if (refcount_dec_and_lock(&p->tcfa_refcnt, &idrinfo->lock)) { + if (refcount_dec_and_mutex_lock(&p->tcfa_refcnt, &idrinfo->lock)) { if (bind) atomic_dec(&p->tcfa_bindcnt); idr_remove(&idrinfo->action_idr, p->tcfa_index); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); tcf_action_cleanup(p); return 1; @@ -200,7 +200,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct tc_action *p; unsigned long id = 1; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); s_i = cb->args[0]; @@ -235,7 +235,7 @@ done: if (index >= 0) cb->args[0] = index + 1; - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); if (n_i) { if (act_flags & TCA_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; @@ -277,18 +277,18 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, id) { ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); n_i++; } else if (ret < 0) { - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); goto nla_put_failure; } } - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); if (nla_put_u32(skb, TCA_FCNT, n_i)) goto nla_put_failure; @@ -324,13 +324,13 @@ 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); + mutex_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); if (IS_ERR(p)) p = NULL; else if (p) refcount_inc(&p->tcfa_refcnt); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); if (p) { *a = p; @@ -345,10 +345,10 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) struct tc_action *p; int ret = 0; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); if (!p) { - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return -ENOENT; } @@ -358,7 +358,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) WARN_ON(p != idr_remove(&idrinfo->action_idr, p->tcfa_index)); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); tcf_action_cleanup(p); module_put(owner); @@ -369,7 +369,7 @@ static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) ret = -EPERM; } - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return ret; } @@ -431,10 +431,10 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) { struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_insert); @@ -444,10 +444,10 @@ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) { struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index))); - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_cleanup); @@ -465,14 +465,14 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, int ret; again: - spin_lock(&idrinfo->lock); + mutex_lock(&idrinfo->lock); if (*index) { p = idr_find(&idrinfo->action_idr, *index); if (IS_ERR(p)) { /* This means that another process allocated * index but did not assign the pointer yet. */ - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); goto again; } @@ -485,7 +485,7 @@ again: } else { *a = NULL; ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - *index, GFP_ATOMIC); + *index, GFP_KERNEL); if (!ret) idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), *index); @@ -494,12 +494,12 @@ again: *index = 1; *a = NULL; ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - UINT_MAX, GFP_ATOMIC); + UINT_MAX, GFP_KERNEL); if (!ret) idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), *index); } - spin_unlock(&idrinfo->lock); + mutex_unlock(&idrinfo->lock); return ret; } EXPORT_SYMBOL(tcf_idr_check_alloc); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 1efbfb10b1fc..8af6c11d2482 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -135,7 +135,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, } td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]); - if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) { + if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) { if (exists) tcf_idr_release(*a, bind); else diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 92dd5071a708..9aada2d0ef06 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -79,7 +79,6 @@ struct fl_flow_tmplt { struct fl_flow_key mask; struct flow_dissector dissector; struct tcf_chain *chain; - struct rcu_work rwork; }; struct cls_fl_head { @@ -1438,20 +1437,12 @@ errout_tb: return ERR_PTR(err); } -static void fl_tmplt_destroy_work(struct work_struct *work) -{ - struct fl_flow_tmplt *tmplt = container_of(to_rcu_work(work), - struct fl_flow_tmplt, rwork); - - fl_hw_destroy_tmplt(tmplt->chain, tmplt); - kfree(tmplt); -} - static void fl_tmplt_destroy(void *tmplt_priv) { struct fl_flow_tmplt *tmplt = tmplt_priv; - tcf_queue_work(&tmplt->rwork, fl_tmplt_destroy_work); + fl_hw_destroy_tmplt(tmplt->chain, tmplt); + kfree(tmplt); } static int fl_dump_key_val(struct sk_buff *skb, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 22e9799e5b69..da1963b19dec 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1322,6 +1322,18 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) * Delete/get qdisc. */ +const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { + [TCA_KIND] = { .type = NLA_STRING }, + [TCA_OPTIONS] = { .type = NLA_NESTED }, + [TCA_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct tc_estimator) }, + [TCA_STAB] = { .type = NLA_NESTED }, + [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, + [TCA_CHAIN] = { .type = NLA_U32 }, + [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, + [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, +}; + static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1338,7 +1350,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; @@ -1422,7 +1435,8 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, replay: /* Reinit, just in case something touches this. */ - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; @@ -1656,7 +1670,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, + rtm_tca_policy, NULL); if (err < 0) return err; @@ -1875,7 +1890,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL, extack); + err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, + extack); if (err < 0) return err; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c new file mode 100644 index 000000000000..206e4dbed12f --- /dev/null +++ b/net/sched/sch_taprio.c @@ -0,0 +1,962 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_taprio.c Time Aware Priority Scheduler + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + * + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/list.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/pkt_cls.h> +#include <net/sch_generic.h> + +#define TAPRIO_ALL_GATES_OPEN -1 + +struct sched_entry { + struct list_head list; + + /* The instant that this entry "closes" and the next one + * should open, the qdisc will make some effort so that no + * packet leaves after this time. + */ + ktime_t close_time; + atomic_t budget; + int index; + u32 gate_mask; + u32 interval; + u8 command; +}; + +struct taprio_sched { + struct Qdisc **qdiscs; + struct Qdisc *root; + s64 base_time; + int clockid; + int picos_per_byte; /* Using picoseconds because for 10Gbps+ + * speeds it's sub-nanoseconds per byte + */ + size_t num_entries; + + /* Protects the update side of the RCU protected current_entry */ + spinlock_t current_entry_lock; + struct sched_entry __rcu *current_entry; + struct list_head entries; + ktime_t (*get_time)(void); + struct hrtimer advance_timer; +}; + +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct Qdisc *child; + int queue; + + queue = skb_get_queue_mapping(skb); + + child = q->qdiscs[queue]; + if (unlikely(!child)) + return qdisc_drop(skb, sch, to_free); + + qdisc_qstats_backlog_inc(sch, skb); + sch->q.qlen++; + + return qdisc_enqueue(skb, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + gate_mask = entry ? entry->gate_mask : -1; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + int prio; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + return NULL; + + return skb; + } + + return NULL; +} + +static inline int length_to_duration(struct taprio_sched *q, int len) +{ + return (len * q->picos_per_byte) / 1000; +} + +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + /* if there's no entry, it means that the schedule didn't + * start yet, so force all gates to be open, this is in + * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 + * "AdminGateSates" + */ + gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + ktime_t guard; + int prio; + int len; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + continue; + + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(q->get_time(), + length_to_duration(q, len)); + + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + ktime_after(guard, entry->close_time)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + atomic_sub_return(len, &entry->budget) < 0) + return NULL; + + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; + } + + return NULL; +} + +static bool should_restart_cycle(const struct taprio_sched *q, + const struct sched_entry *entry) +{ + WARN_ON(!entry); + + return list_is_last(&entry->list, &q->entries); +} + +static enum hrtimer_restart advance_sched(struct hrtimer *timer) +{ + struct taprio_sched *q = container_of(timer, struct taprio_sched, + advance_timer); + struct sched_entry *entry, *next; + struct Qdisc *sch = q->root; + ktime_t close_time; + + spin_lock(&q->current_entry_lock); + entry = rcu_dereference_protected(q->current_entry, + lockdep_is_held(&q->current_entry_lock)); + + /* This is the case that it's the first time that the schedule + * runs, so it only happens once per schedule. The first entry + * is pre-calculated during the schedule initialization. + */ + if (unlikely(!entry)) { + next = list_first_entry(&q->entries, struct sched_entry, + list); + close_time = next->close_time; + goto first_run; + } + + if (should_restart_cycle(q, entry)) + next = list_first_entry(&q->entries, struct sched_entry, + list); + else + next = list_next_entry(entry, list); + + close_time = ktime_add_ns(entry->close_time, next->interval); + + next->close_time = close_time; + atomic_set(&next->budget, + (next->interval * 1000) / q->picos_per_byte); + +first_run: + rcu_assign_pointer(q->current_entry, next); + spin_unlock(&q->current_entry_lock); + + hrtimer_set_expires(&q->advance_timer, close_time); + + rcu_read_lock(); + __netif_schedule(sch); + rcu_read_unlock(); + + return HRTIMER_RESTART; +} + +static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, + [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, +}; + +static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { + [TCA_TAPRIO_ATTR_PRIOMAP] = { + .len = sizeof(struct tc_mqprio_qopt) + }, + [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) + entry->command = nla_get_u8( + tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) + entry->gate_mask = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) + interval = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + return 0; +} + +static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_sched_entry(tb, entry, extack); +} + +/* Returns the number of entries in case of success */ +static int parse_sched_single_entry(struct nlattr *n, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb_entry[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + struct nlattr *tb_list[TCA_TAPRIO_SCHED_MAX + 1] = { }; + struct sched_entry *entry; + bool found = false; + u32 index; + int err; + + err = nla_parse_nested(tb_list, TCA_TAPRIO_SCHED_MAX, + n, entry_list_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_list[TCA_TAPRIO_SCHED_ENTRY]) { + NL_SET_ERR_MSG(extack, "Single-entry must include an entry"); + return -EINVAL; + } + + err = nla_parse_nested(tb_entry, TCA_TAPRIO_SCHED_ENTRY_MAX, + tb_list[TCA_TAPRIO_SCHED_ENTRY], + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]) { + NL_SET_ERR_MSG(extack, "Entry must specify an index\n"); + return -EINVAL; + } + + index = nla_get_u32(tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]); + if (index >= q->num_entries) { + NL_SET_ERR_MSG(extack, "Index for single entry exceeds number of entries in schedule"); + return -EINVAL; + } + + list_for_each_entry(entry, &q->entries, list) { + if (entry->index == index) { + found = true; + break; + } + } + + if (!found) { + NL_SET_ERR_MSG(extack, "Could not find entry"); + return -ENOENT; + } + + err = fill_sched_entry(tb_entry, entry, extack); + if (err < 0) + return err; + + return q->num_entries; +} + +static int parse_sched_list(struct nlattr *list, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list) + return -EINVAL; + + nla_for_each_nested(n, list, rem) { + struct sched_entry *entry; + + if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + err = parse_sched_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + return err; + } + + list_add_tail(&entry->list, &q->entries); + i++; + } + + q->num_entries = i; + + return i; +} + +/* Returns the number of entries in case of success */ +static int parse_taprio_opt(struct nlattr **tb, struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + int err = 0; + int clockid; + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] && + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] && q->num_entries == 0) + return -EINVAL; + + if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) + q->base_time = nla_get_s64( + tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid)) + return -EINVAL; + + q->clockid = clockid; + } + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) + err = parse_sched_list( + tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], q, extack); + else if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + err = parse_sched_single_entry( + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY], q, extack); + + /* parse_sched_* return the number of entries in the schedule, + * a schedule with zero entries is an error. + */ + if (err == 0) { + NL_SET_ERR_MSG(extack, "The schedule should contain at least one entry"); + return -EINVAL; + } + + return err; +} + +static int taprio_parse_mqprio_opt(struct net_device *dev, + struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + int i, j; + + if (!qopt) { + NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); + return -EINVAL; + } + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* taprio imposes that traffic classes map 1:n to tx queues */ + if (qopt->num_tc > dev->num_tx_queues) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); + return -EINVAL; + } + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) { + NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); + return -EINVAL; + } + } + } + + return 0; +} + +static ktime_t taprio_get_start_time(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *entry; + ktime_t now, base, cycle; + s64 n; + + base = ns_to_ktime(q->base_time); + cycle = 0; + + /* Calculate the cycle_time, by summing all the intervals. + */ + list_for_each_entry(entry, &q->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + + if (!cycle) + return base; + + now = q->get_time(); + + if (ktime_after(base, now)) + return base; + + /* Schedule the start time for the beginning of the next + * cycle. + */ + n = div64_s64(ktime_sub_ns(now, base), cycle); + + return ktime_add_ns(base, (n + 1) * cycle); +} + +static void taprio_start_sched(struct Qdisc *sch, ktime_t start) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *first; + unsigned long flags; + + spin_lock_irqsave(&q->current_entry_lock, flags); + + first = list_first_entry(&q->entries, struct sched_entry, + list); + + first->close_time = ktime_add_ns(start, first->interval); + atomic_set(&first->budget, + (first->interval * 1000) / q->picos_per_byte); + rcu_assign_pointer(q->current_entry, NULL); + + spin_unlock_irqrestore(&q->current_entry_lock, flags); + + hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); +} + +static int taprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt *mqprio = NULL; + struct ethtool_link_ksettings ecmd; + int i, err, size; + s64 link_speed; + ktime_t start; + + err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt, + taprio_policy, extack); + if (err < 0) + return err; + + err = -EINVAL; + if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) + mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); + + err = taprio_parse_mqprio_opt(dev, mqprio, extack); + if (err < 0) + return err; + + /* A schedule with less than one entry is an error */ + size = parse_taprio_opt(tb, q, extack); + if (size < 0) + return size; + + hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); + q->advance_timer.function = advance_sched; + + switch (q->clockid) { + case CLOCK_REALTIME: + q->get_time = ktime_get_real; + break; + case CLOCK_MONOTONIC: + q->get_time = ktime_get; + break; + case CLOCK_BOOTTIME: + q->get_time = ktime_get_boottime; + break; + case CLOCK_TAI: + q->get_time = ktime_get_clocktai; + break; + default: + return -ENOTSUPP; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, + &pfifo_qdisc_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)), + extack); + if (!qdisc) + return -ENOMEM; + + if (i < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + + q->qdiscs[i] = qdisc; + } + + if (mqprio) { + netdev_set_num_tc(dev, mqprio->num_tc); + for (i = 0; i < mqprio->num_tc; i++) + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); + } + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + link_speed * 1000 * 1000); + + start = taprio_get_start_time(sch); + if (!start) + return 0; + + taprio_start_sched(sch, start); + + return 0; +} + +static void taprio_destroy(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry, *n; + unsigned int i; + + hrtimer_cancel(&q->advance_timer); + + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) + qdisc_put(q->qdiscs[i]); + + kfree(q->qdiscs); + } + q->qdiscs = NULL; + + netdev_set_num_tc(dev, 0); + + list_for_each_entry_safe(entry, n, &q->entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int taprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + INIT_LIST_HEAD(&q->entries); + spin_lock_init(&q->current_entry_lock); + + /* We may overwrite the configuration later */ + hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); + + q->root = sch; + + /* We only support static clockids. Use an invalid value as default + * and get the valid one on taprio_change(). + */ + q->clockid = -1; + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + /* pre-allocate qdisc, attachment can't fail */ + q->qdiscs = kcalloc(dev->num_tx_queues, + sizeof(q->qdiscs[0]), + GFP_KERNEL); + + if (!q->qdiscs) + return -ENOMEM; + + if (!opt) + return -EINVAL; + + return taprio_change(sch, opt, extack); +} + +static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + + return netdev_get_tx_queue(dev, ntx); +} + +static int taprio_graft(struct Qdisc *sch, unsigned long cl, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = q->qdiscs[cl - 1]; + q->qdiscs[cl - 1] = new; + + if (new) + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int dump_entry(struct sk_buff *msg, + const struct sched_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start(msg, TCA_TAPRIO_SCHED_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, + entry->gate_mask)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, + entry->interval)) + goto nla_put_failure; + + return nla_nest_end(msg, item); + +nla_put_failure: + nla_nest_cancel(msg, item); + return -1; +} + +static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt opt = { 0 }; + struct nlattr *nest, *entry_list; + struct sched_entry *entry; + unsigned int i; + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + return -ENOSPC; + + if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) + goto options_error; + + if (nla_put_s64(skb, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, + q->base_time, TCA_TAPRIO_PAD)) + goto options_error; + + if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + goto options_error; + + entry_list = nla_nest_start(skb, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); + if (!entry_list) + goto options_error; + + list_for_each_entry(entry, &q->entries, list) { + if (dump_entry(skb, entry) < 0) + goto options_error; + } + + nla_nest_end(skb, entry_list); + + return nla_nest_end(skb, nest); + +options_error: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long taprio_find(struct Qdisc *sch, u32 classid) +{ + unsigned int ntx = TC_H_MIN(classid); + + if (!taprio_queue_get(sch, ntx)) + return 0; + return ntx; +} + +static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle |= TC_H_MIN(cl); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + + return 0; +} + +static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + return -1; + return 0; +} + +static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + arg->count = arg->skip; + for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + +static const struct Qdisc_class_ops taprio_class_ops = { + .graft = taprio_graft, + .leaf = taprio_leaf, + .find = taprio_find, + .walk = taprio_walk, + .dump = taprio_dump_class, + .dump_stats = taprio_dump_class_stats, + .select_queue = taprio_select_queue, +}; + +static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { + .cl_ops = &taprio_class_ops, + .id = "taprio", + .priv_size = sizeof(struct taprio_sched), + .init = taprio_init, + .destroy = taprio_destroy, + .peek = taprio_peek, + .dequeue = taprio_dequeue, + .enqueue = taprio_enqueue, + .dump = taprio_dump, + .owner = THIS_MODULE, +}; + +static int __init taprio_module_init(void) +{ + return register_qdisc(&taprio_qdisc_ops); +} + +static void __exit taprio_module_exit(void) +{ + unregister_qdisc(&taprio_qdisc_ops); +} + +module_init(taprio_module_init); +module_exit(taprio_module_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d74d00b29942..42191ed9902b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1048,7 +1048,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, if (!ctx->packet || !ctx->packet->has_cookie_echo) return; - /* fallthru */ + /* fall through */ case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: diff --git a/net/socket.c b/net/socket.c index 01f3f8f32d6f..713dc4833d40 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1475,7 +1475,7 @@ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = move_addr_to_kernel(umyaddr, addrlen, &address); - if (err >= 0) { + if (!err) { err = security_socket_bind(sock, (struct sockaddr *)&address, addrlen); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 91891041e5e1..e65c3a8551e4 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -609,16 +609,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, switch (evt) { case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) + if (netif_carrier_ok(dev) && netif_oper_up(dev)) { + test_and_set_bit_lock(0, &b->up); break; - /* else: fall through */ - case NETDEV_UP: - test_and_set_bit_lock(0, &b->up); - break; + } + /* fall through */ case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; + case NETDEV_UP: + test_and_set_bit_lock(0, &b->up); + break; case NETDEV_CHANGEMTU: if (tipc_mtu_bad(dev, 0)) { bearer_disable(net, b); diff --git a/net/tipc/link.c b/net/tipc/link.c index b1f0bee54eac..fb886b525d95 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -410,6 +410,11 @@ char *tipc_link_name(struct tipc_link *l) return l->name; } +u32 tipc_link_state(struct tipc_link *l) +{ + return l->state; +} + /** * tipc_link_create - create a new link * @n: pointer to associated node @@ -841,9 +846,14 @@ void tipc_link_reset(struct tipc_link *l) l->in_session = false; l->session++; l->mtu = l->advertised_mtu; + spin_lock_bh(&l->wakeupq.lock); + spin_lock_bh(&l->inputq->lock); + skb_queue_splice_init(&l->wakeupq, l->inputq); + spin_unlock_bh(&l->inputq->lock); + spin_unlock_bh(&l->wakeupq.lock); + __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); - skb_queue_splice_init(&l->wakeupq, l->inputq); __skb_queue_purge(&l->backlogq); l->backlog[TIPC_LOW_IMPORTANCE].len = 0; l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; @@ -1380,6 +1390,36 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, __skb_queue_tail(xmitq, skb); } +void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + u32 onode = tipc_own_addr(l->net); + struct tipc_msg *hdr, *ihdr; + struct sk_buff_head tnlq; + struct sk_buff *skb; + u32 dnode = l->addr; + + skb_queue_head_init(&tnlq); + skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, + INT_H_SIZE, BASIC_H_SIZE, + dnode, onode, 0, 0, 0); + if (!skb) { + pr_warn("%sunable to create tunnel packet\n", link_co_err); + return; + } + + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, 1); + msg_set_bearer_id(hdr, l->peer_bearer_id); + + ihdr = (struct tipc_msg *)msg_data(hdr); + tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, + BASIC_H_SIZE, dnode); + msg_set_errcode(ihdr, TIPC_ERR_NO_PORT); + __skb_queue_tail(&tnlq, skb); + tipc_link_xmit(l, &tnlq, xmitq); +} + /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets * with contents of the link's transmit and backlog queues. */ @@ -1476,6 +1516,9 @@ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) return false; if (session != curr_session) return false; + /* Extra sanity check */ + if (!link_is_up(l) && msg_ack(hdr)) + return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; /* Accept only STATE with new sequence number */ diff --git a/net/tipc/link.h b/net/tipc/link.h index 7bc494a33fdf..90488c538a4e 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -88,6 +88,8 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, struct tipc_link **link); void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); +void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl, + struct sk_buff_head *xmitq); void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); int tipc_link_fsm_evt(struct tipc_link *l, int evt); bool tipc_link_is_up(struct tipc_link *l); @@ -107,6 +109,7 @@ u16 tipc_link_rcv_nxt(struct tipc_link *l); u16 tipc_link_acked(struct tipc_link *l); u32 tipc_link_id(struct tipc_link *l); char *tipc_link_name(struct tipc_link *l); +u32 tipc_link_state(struct tipc_link *l); char tipc_link_plane(struct tipc_link *l); int tipc_link_prio(struct tipc_link *l); int tipc_link_window(struct tipc_link *l); diff --git a/net/tipc/node.c b/net/tipc/node.c index 68014f1b6976..2afc4f8c37a7 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -111,6 +111,7 @@ struct tipc_node { int action_flags; struct list_head list; int state; + bool failover_sent; u16 sync_point; int link_cnt; u16 working_links; @@ -680,6 +681,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, *slot0 = bearer_id; *slot1 = bearer_id; tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT); + n->failover_sent = false; n->action_flags |= TIPC_NOTIFY_NODE_UP; tipc_link_set_active(nl, true); tipc_bcast_add_peer(n->net, nl, xmitq); @@ -911,6 +913,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool reset = true; char *if_name; unsigned long intv; + u16 session; *dupl_addr = false; *respond = false; @@ -997,9 +1000,10 @@ void tipc_node_check_dest(struct net *net, u32 addr, goto exit; if_name = strchr(b->name, ':') + 1; + get_random_bytes(&session, sizeof(u16)); if (!tipc_link_create(net, if_name, b->identity, b->tolerance, b->net_plane, b->mtu, b->priority, - b->window, mod(tipc_net(net)->random), + b->window, session, tipc_own_addr(net), addr, peer_id, n->capabilities, tipc_bc_sndlink(n->net), n->bc_entry.link, @@ -1615,6 +1619,14 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl), tipc_link_inputq(l)); } + /* If parallel link was already down, and this happened before + * the tunnel link came up, FAILOVER was never sent. Ensure that + * FAILOVER is sent to get peer out of NODE_FAILINGOVER state. + */ + if (n->state != NODE_FAILINGOVER && !n->failover_sent) { + tipc_link_create_dummy_tnl_msg(l, xmitq); + n->failover_sent = true; + } /* If pkts arrive out of order, use lowest calculated syncpt */ if (less(syncpt, n->sync_point)) n->sync_point = syncpt; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 595c5001b28d..db148c4a916a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1424,8 +1424,10 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) /* Handle implicit connection setup */ if (unlikely(dest)) { rc = __tipc_sendmsg(sock, m, dlen); - if (dlen && (dlen == rc)) + if (dlen && dlen == rc) { + tsk->peer_caps = tipc_node_get_capabilities(net, dnode); tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr)); + } return rc; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d5f9b5235cdd..a02bbdd1b192 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3756,6 +3756,7 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband, return false; /* check availability */ + ridx = array_index_nospec(ridx, IEEE80211_HT_MCS_MASK_LEN); if (sband->ht_cap.mcs.rx_mask[ridx] & rbit) mcs[ridx] |= rbit; else @@ -10234,7 +10235,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; u32 hyst; - int i, n; + int i, n, low_index; int err; /* RSSI reporting disabled? */ @@ -10271,10 +10272,19 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, if (last < wdev->cqm_config->rssi_thresholds[i]) break; - low = i > 0 ? - (wdev->cqm_config->rssi_thresholds[i - 1] - hyst) : S32_MIN; - high = i < n ? - (wdev->cqm_config->rssi_thresholds[i] + hyst - 1) : S32_MAX; + low_index = i - 1; + if (low_index >= 0) { + low_index = array_index_nospec(low_index, n); + low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + } else { + low = S32_MIN; + } + if (i < n) { + i = array_index_nospec(i, n); + high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + } else { + high = S32_MAX; + } return rdev_set_cqm_rssi_range_config(rdev, dev, low, high); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 56be68a27bb9..148c229fe84f 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2667,11 +2667,12 @@ static void reg_process_hint(struct regulatory_request *reg_request) { struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; + enum nl80211_reg_initiator initiator = reg_request->initiator; if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); - switch (reg_request->initiator) { + switch (initiator) { case NL80211_REGDOM_SET_BY_CORE: treatment = reg_process_hint_core(reg_request); break; @@ -2689,7 +2690,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: - WARN(1, "invalid initiator %d\n", reg_request->initiator); + WARN(1, "invalid initiator %d\n", initiator); goto out_free; } @@ -2704,7 +2705,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - wiphy_update_regulatory(wiphy, reg_request->initiator); + wiphy_update_regulatory(wiphy, initiator); wiphy_all_share_dfs_chan_state(wiphy); reg_check_channels(); } @@ -2873,6 +2874,7 @@ static int regulatory_hint_core(const char *alpha2) request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_CORE; + request->wiphy_idx = WIPHY_IDX_INVALID; queue_regulatory_request(request); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d36c3eb7b931..d0e7472dd9fd 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1058,13 +1058,23 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, return NULL; } +/* + * Update RX channel information based on the available frame payload + * information. This is mainly for the 2.4 GHz band where frames can be received + * from neighboring channels and the Beacon frames use the DSSS Parameter Set + * element to indicate the current (transmitting) channel, but this might also + * be needed on other bands if RX frequency does not match with the actual + * operating channel of a BSS. + */ static struct ieee80211_channel * cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, - struct ieee80211_channel *channel) + struct ieee80211_channel *channel, + enum nl80211_bss_scan_width scan_width) { const u8 *tmp; u32 freq; int channel_number = -1; + struct ieee80211_channel *alt_channel; tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); if (tmp && tmp[1] == 1) { @@ -1078,16 +1088,45 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } } - if (channel_number < 0) + if (channel_number < 0) { + /* No channel information in frame payload */ return channel; + } freq = ieee80211_channel_to_frequency(channel_number, channel->band); - channel = ieee80211_get_channel(wiphy, freq); - if (!channel) - return NULL; - if (channel->flags & IEEE80211_CHAN_DISABLED) + alt_channel = ieee80211_get_channel(wiphy, freq); + if (!alt_channel) { + if (channel->band == NL80211_BAND_2GHZ) { + /* + * Better not allow unexpected channels when that could + * be going beyond the 1-11 range (e.g., discovering + * BSS on channel 12 when radio is configured for + * channel 11. + */ + return NULL; + } + + /* No match for the payload channel number - ignore it */ + return channel; + } + + if (scan_width == NL80211_BSS_CHAN_WIDTH_10 || + scan_width == NL80211_BSS_CHAN_WIDTH_5) { + /* + * Ignore channel number in 5 and 10 MHz channels where there + * may not be an n:1 or 1:n mapping between frequencies and + * channel numbers. + */ + return channel; + } + + /* + * Use the channel determined through the payload channel number + * instead of the RX channel reported by the driver. + */ + if (alt_channel->flags & IEEE80211_CHAN_DISABLED) return NULL; - return channel; + return alt_channel; } /* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -1112,7 +1151,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, (data->signal < 0 || data->signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan, + data->scan_width); if (!channel) return NULL; @@ -1210,7 +1250,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, data->chan); + ielen, data->chan, data->scan_width); if (!channel) return NULL; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 167f7025ac98..06943d9c9835 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1278,12 +1278,16 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; - if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) - return -EOPNOTSUPP; + if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { + err = -EOPNOTSUPP; + goto free; + } rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); - return 0; +free: + cfg80211_sinfo_release_content(&sinfo); + return err; } /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ @@ -1293,7 +1297,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); /* we are under RTNL - globally locked - so can use static structs */ static struct iw_statistics wstats; - static struct station_info sinfo; + static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) @@ -1352,6 +1356,8 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; + cfg80211_sinfo_release_content(&sinfo); + return &wstats; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b89c9c7f8c5c..be3520e429c9 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -458,6 +458,7 @@ resume: XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } + crypto_done = false; } while (!err); err = xfrm_rcv_cb(skb, family, x->type->proto, 0); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 2d42cb0c94b8..4ae87c5ce2e3 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -100,6 +100,10 @@ static int xfrm_output_one(struct sk_buff *skb, int err) spin_unlock_bh(&x->lock); skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + goto error_nolock; + } if (xfrm_offload(skb)) { x->type_offload->encap(x, skb); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3110c3fbee20..f094d4b3520d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2491,6 +2491,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) } skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); + return 0; + } dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4791aa8b8185..df7ca2dabc48 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -151,10 +151,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; switch (p->family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + goto out; + break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + goto out; + break; #else err = -EAFNOSUPPORT; @@ -1396,10 +1402,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) switch (p->sel.family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + return -EINVAL; + break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + return -EINVAL; + break; #else return -EAFNOSUPPORT; @@ -1480,6 +1492,9 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) (ut[i].family != prev_family)) return -EINVAL; + if (ut[i].mode >= XFRM_MODE_MAX) + return -EINVAL; + prev_family = ut[i].family; switch (ut[i].family) { diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index b5282cbbe489..617ff1aa818f 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -145,9 +145,11 @@ int snd_hdac_i915_init(struct hdac_bus *bus) if (!acomp->ops) { request_module("i915"); /* 10s timeout */ - wait_for_completion_timeout(&bind_complete, 10 * 1000); + wait_for_completion_timeout(&bind_complete, + msecs_to_jiffies(10 * 1000)); } if (!acomp->ops) { + dev_info(bus->dev, "couldn't bind with audio component\n"); snd_hdac_acomp_exit(bus); return -ENODEV; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1d117f00d04d..3ac7ba9b342d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6409,6 +6409,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 439b8a27488d..195ba486640f 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1325,7 +1325,7 @@ class Tui(object): msg = '' while True: self.screen.erase() - self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' % + self.screen.addstr(0, 0, 'Set update interval (defaults to %.1fs).' % DELAY_DEFAULT, curses.A_BOLD) self.screen.addstr(4, 0, msg) self.screen.addstr(2, 0, 'Change delay from %.1fs to ' % diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 0f45633bd634..802b4af18729 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,11 +9,11 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric" +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no -IP="ip -netns testns" +IP="ip -netns ns1" log_test() { @@ -47,8 +47,10 @@ log_test() setup() { set -e - ip netns add testns + ip netns add ns1 $IP link set dev lo up + ip netns exec ns1 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns1 sysctl -qw net.ipv6.conf.all.forwarding=1 $IP link add dummy0 type dummy $IP link set dev dummy0 up @@ -61,7 +63,8 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del testns + ip netns del ns1 + ip netns del ns2 &> /dev/null } get_linklocal() @@ -639,11 +642,14 @@ add_initial_route6() check_route6() { - local pfx="2001:db8:104::/64" + local pfx local expected="$1" local out local rc=0 + set -- $expected + pfx=$1 + out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') [ "${out}" = "${expected}" ] && return 0 @@ -690,28 +696,33 @@ route_setup() [ "${VERBOSE}" = "1" ] && set -x set -e - $IP li add red up type vrf table 101 + ip netns add ns2 + ip -netns ns2 link set dev lo up + ip netns exec ns2 sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ns2 sysctl -qw net.ipv6.conf.all.forwarding=1 + $IP li add veth1 type veth peer name veth2 $IP li add veth3 type veth peer name veth4 $IP li set veth1 up $IP li set veth3 up - $IP li set veth2 vrf red up - $IP li set veth4 vrf red up - $IP li add dummy1 type dummy - $IP li set dummy1 vrf red up - - $IP -6 addr add 2001:db8:101::1/64 dev veth1 - $IP -6 addr add 2001:db8:101::2/64 dev veth2 - $IP -6 addr add 2001:db8:103::1/64 dev veth3 - $IP -6 addr add 2001:db8:103::2/64 dev veth4 - $IP -6 addr add 2001:db8:104::1/64 dev dummy1 + $IP li set veth2 netns ns2 up + $IP li set veth4 netns ns2 up + ip -netns ns2 li add dummy1 type dummy + ip -netns ns2 li set dummy1 up + $IP -6 addr add 2001:db8:101::1/64 dev veth1 nodad + $IP -6 addr add 2001:db8:103::1/64 dev veth3 nodad $IP addr add 172.16.101.1/24 dev veth1 - $IP addr add 172.16.101.2/24 dev veth2 $IP addr add 172.16.103.1/24 dev veth3 - $IP addr add 172.16.103.2/24 dev veth4 - $IP addr add 172.16.104.1/24 dev dummy1 + + ip -netns ns2 -6 addr add 2001:db8:101::2/64 dev veth2 nodad + ip -netns ns2 -6 addr add 2001:db8:103::2/64 dev veth4 nodad + ip -netns ns2 -6 addr add 2001:db8:104::1/64 dev dummy1 nodad + + ip -netns ns2 addr add 172.16.101.2/24 dev veth2 + ip -netns ns2 addr add 172.16.103.2/24 dev veth4 + ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 set +ex } @@ -944,7 +955,7 @@ ipv6_addr_metric_test() log_test $rc 0 "Modify metric of address" # verify prefix route removed on down - run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" + run_cmd "ip netns exec ns1 sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1" run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then @@ -967,6 +978,77 @@ ipv6_addr_metric_test() cleanup } +ipv6_route_metrics_test() +{ + local rc + + echo + echo "IPv6 routes with metrics" + + route_setup + + # + # single path with metrics + # + run_cmd "$IP -6 ro add 2001:db8:111::/64 via 2001:db8:101::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:111::/64 via 2001:db8:101::2 dev veth1 metric 1024 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + # + # multipath via separate routes with metrics + # + run_cmd "$IP -6 ro add 2001:db8:112::/64 via 2001:db8:101::2 mtu 1400" + run_cmd "$IP -6 ro append 2001:db8:112::/64 via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:112::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on first" + + # second route is coalesced to first to make a multipath route. + # MTU of the second path is hidden from display! + run_cmd "$IP -6 ro add 2001:db8:113::/64 via 2001:db8:101::2" + run_cmd "$IP -6 ro append 2001:db8:113::/64 via 2001:db8:103::2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:113::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route via 2 single routes with mtu metric on 2nd" + + run_cmd "$IP -6 ro del 2001:db8:113::/64 via 2001:db8:101::2" + if [ $? -eq 0 ]; then + check_route6 "2001:db8:113::/64 via 2001:db8:103::2 dev veth3 metric 1024 mtu 1400" + log_test $? 0 " MTU of second leg" + fi + + # + # multipath with metrics + # + run_cmd "$IP -6 ro add 2001:db8:115::/64 mtu 1400 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + rc=$? + if [ $rc -eq 0 ]; then + check_route6 "2001:db8:115::/64 metric 1024 mtu 1400 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300 + run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP -6 ro add 2001:db8:114::/64 via 2001:db8:101::2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -1005,11 +1087,15 @@ add_initial_route() check_route() { - local pfx="172.16.104.0/24" + local pfx local expected="$1" local out local rc=0 + set -- $expected + pfx=$1 + [ "${pfx}" = "unreachable" ] && pfx=$2 + out=$($IP ro ls match ${pfx}) [ "${out}" = "${expected}" ] && return 0 @@ -1319,6 +1405,43 @@ ipv4_addr_metric_test() cleanup } +ipv4_route_metrics_test() +{ + local rc + + echo + echo "IPv4 route add / append tests" + + route_setup + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 mtu 1400" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.111.0/24 via 172.16.101.2 dev veth1 mtu 1400" + rc=$? + fi + log_test $rc 0 "Single path route with mtu metric" + + + run_cmd "$IP ro add 172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 nexthop via 172.16.103.2" + rc=$? + if [ $rc -eq 0 ]; then + check_route "172.16.112.0/24 mtu 1400 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1" + rc=$? + fi + log_test $rc 0 "Multipath route with mtu metric" + + $IP ro add 172.16.104.0/24 via 172.16.101.2 mtu 1300 + run_cmd "ip netns exec ns1 ping -w1 -c1 -s 1500 172.16.104.1" + log_test $? 0 "Using route with mtu metric" + + run_cmd "$IP ro add 172.16.111.0/24 via 172.16.101.2 congctl lock foo" + log_test $? 2 "Invalid metric (fails metric_convert)" + + route_cleanup +} + + ################################################################################ # usage @@ -1385,6 +1508,8 @@ do ipv4_route_test|ipv4_rt) ipv4_route_test;; ipv6_addr_metric) ipv6_addr_metric_test;; ipv4_addr_metric) ipv4_addr_metric_test;; + ipv6_route_metrics) ipv6_route_metrics_test;; + ipv4_route_metrics) ipv4_route_metrics_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c index 2366dc6bce71..61ae2782388e 100644 --- a/tools/testing/selftests/net/ip_defrag.c +++ b/tools/testing/selftests/net/ip_defrag.c @@ -203,7 +203,6 @@ static void send_udp_frags(int fd_raw, struct sockaddr *addr, { struct ip *iphdr = (struct ip *)ip_frame; struct ip6_hdr *ip6hdr = (struct ip6_hdr *)ip_frame; - struct udphdr udphdr; int res; int offset; int frag_len; diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile index 93baacab7693..d056486f49de 100644 --- a/tools/testing/selftests/powerpc/alignment/Makefile +++ b/tools/testing/selftests/powerpc/alignment/Makefile @@ -1,5 +1,6 @@ TEST_GEN_PROGS := copy_first_unaligned alignment_handler +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index b4d7432a0ecd..d40300a65b42 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -4,6 +4,7 @@ TEST_GEN_FILES := exec_target CFLAGS += -O2 +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile index 1be547434a49..ede4d3dae750 100644 --- a/tools/testing/selftests/powerpc/cache_shape/Makefile +++ b/tools/testing/selftests/powerpc/cache_shape/Makefile @@ -5,6 +5,7 @@ all: $(TEST_PROGS) $(TEST_PROGS): ../harness.c ../utils.c +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 1cf89a34d97c..44574f3818b3 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -17,6 +17,7 @@ TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \ EXTRA_SOURCES := validate.c ../harness.c stubs.S +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/copyuser_64_t%: copyuser_64.S $(EXTRA_SOURCES) diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index 55d7db7a616b..5df476364b4d 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -3,6 +3,7 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \ dscr_sysfs_thread_test +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/dscr_default_test: LDLIBS += -lpthread diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile index 0dd3a01fdab9..11a10d7a2bbd 100644 --- a/tools/testing/selftests/powerpc/math/Makefile +++ b/tools/testing/selftests/powerpc/math/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 8ebbe96d80a8..33ced6e0ad25 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -5,6 +5,7 @@ noarg: TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors TEST_GEN_FILES := tempfile +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 6e1629bf5b09..19046db995fe 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -5,6 +5,7 @@ noarg: TEST_GEN_PROGS := count_instructions l3_bank_test per_event_excludes EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c +top_srcdir = ../../../../.. include ../../lib.mk all: $(TEST_GEN_PROGS) ebb diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index c4e64bc2e265..bd5dfa509272 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -17,6 +17,7 @@ TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test \ lost_exception_test no_handler_test \ cycles_with_mmcr2_test +top_srcdir = ../../../../../.. include ../../../lib.mk $(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \ diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile index 175366db7be8..ea2b7bd09e36 100644 --- a/tools/testing/selftests/powerpc/primitives/Makefile +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -2,6 +2,7 @@ CFLAGS += -I$(CURDIR) TEST_GEN_PROGS := load_unaligned_zeropad +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 28f5b781a553..923d531265f8 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -4,6 +4,7 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \ perf-hwbreak +top_srcdir = ../../../../.. include ../../lib.mk all: $(TEST_PROGS) diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile index a7cbd5082e27..1fca25c6ace0 100644 --- a/tools/testing/selftests/powerpc/signal/Makefile +++ b/tools/testing/selftests/powerpc/signal/Makefile @@ -8,6 +8,7 @@ $(TEST_PROGS): ../harness.c ../utils.c signal.S CFLAGS += -maltivec signal_tm: CFLAGS += -mhtm +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile index 10b35c87a4f4..7fc0623d85c3 100644 --- a/tools/testing/selftests/powerpc/stringloops/Makefile +++ b/tools/testing/selftests/powerpc/stringloops/Makefile @@ -29,6 +29,7 @@ endif ASFLAGS = $(CFLAGS) +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): $(EXTRA_SOURCES) diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile index 30b8ff8fb82e..fcd2dcb8972b 100644 --- a/tools/testing/selftests/powerpc/switch_endian/Makefile +++ b/tools/testing/selftests/powerpc/switch_endian/Makefile @@ -5,6 +5,7 @@ ASFLAGS += -O2 -Wall -g -nostdlib -m64 EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile index da22ca7c38c1..161b8846336f 100644 --- a/tools/testing/selftests/powerpc/syscalls/Makefile +++ b/tools/testing/selftests/powerpc/syscalls/Makefile @@ -2,6 +2,7 @@ TEST_GEN_PROGS := ipc_unmuxed CFLAGS += -I../../../../../usr/include +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index c0e45d2dde25..9fc2cf6fbc92 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -6,6 +6,7 @@ TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \ $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile index f8ced26748f8..fb82068c9fda 100644 --- a/tools/testing/selftests/powerpc/vphn/Makefile +++ b/tools/testing/selftests/powerpc/vphn/Makefile @@ -2,6 +2,7 @@ TEST_GEN_PROGS := test-vphn CFLAGS += -m64 +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 642d4e12abea..eec2663261f2 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -56,15 +56,13 @@ unsigned int yield_mod_cnt, nr_abort; printf(fmt, ## __VA_ARGS__); \ } while (0) -#if defined(__x86_64__) || defined(__i386__) +#ifdef __i386__ #define INJECT_ASM_REG "eax" #define RSEQ_INJECT_CLOBBER \ , INJECT_ASM_REG -#ifdef __i386__ - #define RSEQ_INJECT_ASM(n) \ "mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \ "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ @@ -76,9 +74,16 @@ unsigned int yield_mod_cnt, nr_abort; #elif defined(__x86_64__) +#define INJECT_ASM_REG_P "rax" +#define INJECT_ASM_REG "eax" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG_P \ + , INJECT_ASM_REG + #define RSEQ_INJECT_ASM(n) \ - "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG "\n\t" \ - "mov (%%" INJECT_ASM_REG "), %%" INJECT_ASM_REG "\n\t" \ + "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \ + "mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \ "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ "jz 333f\n\t" \ "222:\n\t" \ @@ -86,10 +91,6 @@ unsigned int yield_mod_cnt, nr_abort; "jnz 222b\n\t" \ "333:\n\t" -#else -#error "Unsupported architecture" -#endif - #elif defined(__s390__) #define RSEQ_INJECT_INPUT \ diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index 49a6f8c3fdae..f9281e8aa313 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -232,6 +232,8 @@ directory: and the other is a test whether the command leaked memory or not. (This one is a preliminary version, it may not work quite right yet, but the overall template is there and it should only need tweaks.) + - buildebpfPlugin.py: + builds all programs in $EBPFDIR. ACKNOWLEDGEMENTS diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile new file mode 100644 index 000000000000..dc92eb271d9a --- /dev/null +++ b/tools/testing/selftests/tc-testing/bpf/Makefile @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0 + +APIDIR := ../../../../include/uapi +TEST_GEN_FILES = action.o + +top_srcdir = ../../../../.. +include ../../lib.mk + +CLANG ?= clang +LLC ?= llc +PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) + +ifeq ($(PROBE),) + CPU ?= probe +else + CPU ?= generic +endif + +CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') + +CLANG_FLAGS = -I. -I$(APIDIR) \ + $(CLANG_SYS_INCLUDES) \ + -Wno-compare-distinct-pointer-types + +$(OUTPUT)/%.o: %.c + $(CLANG) $(CLANG_FLAGS) \ + -O2 -target bpf -emit-llvm -c $< -o - | \ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/bpf/action.c new file mode 100644 index 000000000000..c32b99b80e19 --- /dev/null +++ b/tools/testing/selftests/tc-testing/bpf/action.c @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Davide Caratti, Red Hat inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include <linux/bpf.h> +#include <linux/pkt_cls.h> + +__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s) +{ + return TC_ACT_OK; +} + +__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s) +{ + s->data = 0x0; + return TC_ACT_OK; +} + +char _license[] __attribute__((section("license"),used)) = "GPL"; diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py new file mode 100644 index 000000000000..9f0ba10c44b4 --- /dev/null +++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py @@ -0,0 +1,66 @@ +''' +build ebpf program +''' + +import os +import signal +from string import Template +import subprocess +import time +from TdcPlugin import TdcPlugin +from tdc_config import * + +class SubPlugin(TdcPlugin): + def __init__(self): + self.sub_class = 'buildebpf/SubPlugin' + self.tap = '' + super().__init__() + + def pre_suite(self, testcount, testidlist): + super().pre_suite(testcount, testidlist) + + if self.args.buildebpf: + self._ebpf_makeall() + + def post_suite(self, index): + super().post_suite(index) + + self._ebpf_makeclean() + + def add_args(self, parser): + super().add_args(parser) + + self.argparser_group = self.argparser.add_argument_group( + 'buildebpf', + 'options for buildebpfPlugin') + self.argparser_group.add_argument( + '-B', '--buildebpf', action='store_true', + help='build eBPF programs') + + return self.argparser + + def _ebpf_makeall(self): + if self.args.buildebpf: + self._make('all') + + def _ebpf_makeclean(self): + if self.args.buildebpf: + self._make('clean') + + def _make(self, target): + command = 'make -C {} {}'.format(self.args.NAMES['EBPFDIR'], target) + proc = subprocess.Popen(command, + shell=True, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + env=ENVIR) + (rawout, serr) = proc.communicate() + + if proc.returncode != 0 and len(serr) > 0: + foutput = serr.decode("utf-8") + else: + foutput = rawout.decode("utf-8") + + proc.stdout.close() + proc.stderr.close() + return proc, foutput diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 6f289a49e5ec..5970cee6d05f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -55,7 +55,6 @@ "bpf" ], "setup": [ - "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { return 2; }' | clang -O2 -x c -c - -target bpf -o _b.o", [ "$TC action flush action bpf", 0, @@ -63,14 +62,13 @@ 255 ] ], - "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667", + "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ - "$TC action flush action bpf", - "rm -f _b.o" + "$TC action flush action bpf" ] }, { @@ -81,7 +79,6 @@ "bpf" ], "setup": [ - "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { s->data = 0x0; return 2; }' | clang -O2 -x c -c - -target bpf -o _c.o", [ "$TC action flush action bpf", 0, @@ -89,10 +86,10 @@ 255 ] ], - "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667", + "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667", "expExitCode": "255", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref", "matchCount": "0", "teardown": [ [ @@ -100,8 +97,7 @@ 0, 1, 255 - ], - "rm -f _c.o" + ] ] }, { diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index a023d0d62b25..d651bc1501bd 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -16,7 +16,9 @@ NAMES = { 'DEV2': '', 'BATCH_FILE': './batch.txt', # Name of the namespace to use - 'NS': 'tcut' + 'NS': 'tcut', + # Directory containing eBPF test programs + 'EBPFDIR': './bpf' } diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c index 235259011704..35edd61d1663 100644 --- a/tools/testing/selftests/x86/test_vdso.c +++ b/tools/testing/selftests/x86/test_vdso.c @@ -17,6 +17,7 @@ #include <errno.h> #include <sched.h> #include <stdbool.h> +#include <limits.h> #ifndef SYS_getcpu # ifdef __x86_64__ @@ -31,6 +32,14 @@ int nerrs = 0; +typedef int (*vgettime_t)(clockid_t, struct timespec *); + +vgettime_t vdso_clock_gettime; + +typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz); + +vgtod_t vdso_gettimeofday; + typedef long (*getcpu_t)(unsigned *, unsigned *, void *); getcpu_t vgetcpu; @@ -95,6 +104,15 @@ static void fill_function_pointers() printf("Warning: failed to find getcpu in vDSO\n"); vgetcpu = (getcpu_t) vsyscall_getcpu(); + + vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_clock_gettime) + printf("Warning: failed to find clock_gettime in vDSO\n"); + + vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gettimeofday) + printf("Warning: failed to find gettimeofday in vDSO\n"); + } static long sys_getcpu(unsigned * cpu, unsigned * node, @@ -103,6 +121,16 @@ static long sys_getcpu(unsigned * cpu, unsigned * node, return syscall(__NR_getcpu, cpu, node, cache); } +static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(__NR_clock_gettime, id, ts); +} + +static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz) +{ + return syscall(__NR_gettimeofday, tv, tz); +} + static void test_getcpu(void) { printf("[RUN]\tTesting getcpu...\n"); @@ -155,10 +183,154 @@ static void test_getcpu(void) } } +static bool ts_leq(const struct timespec *a, const struct timespec *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_nsec <= b->tv_nsec; +} + +static bool tv_leq(const struct timeval *a, const struct timeval *b) +{ + if (a->tv_sec != b->tv_sec) + return a->tv_sec < b->tv_sec; + else + return a->tv_usec <= b->tv_usec; +} + +static char const * const clocknames[] = { + [0] = "CLOCK_REALTIME", + [1] = "CLOCK_MONOTONIC", + [2] = "CLOCK_PROCESS_CPUTIME_ID", + [3] = "CLOCK_THREAD_CPUTIME_ID", + [4] = "CLOCK_MONOTONIC_RAW", + [5] = "CLOCK_REALTIME_COARSE", + [6] = "CLOCK_MONOTONIC_COARSE", + [7] = "CLOCK_BOOTTIME", + [8] = "CLOCK_REALTIME_ALARM", + [9] = "CLOCK_BOOTTIME_ALARM", + [10] = "CLOCK_SGI_CYCLE", + [11] = "CLOCK_TAI", +}; + +static void test_one_clock_gettime(int clock, const char *name) +{ + struct timespec start, vdso, end; + int vdso_ret, end_ret; + + printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock); + + if (sys_clock_gettime(clock, &start) < 0) { + if (errno == EINVAL) { + vdso_ret = vdso_clock_gettime(clock, &vdso); + if (vdso_ret == -EINVAL) { + printf("[OK]\tNo such clock.\n"); + } else { + printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret); + nerrs++; + } + } else { + printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno); + } + return; + } + + vdso_ret = vdso_clock_gettime(clock, &vdso); + end_ret = sys_clock_gettime(clock, &end); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n", + (unsigned long long)start.tv_sec, start.tv_nsec, + (unsigned long long)vdso.tv_sec, vdso.tv_nsec, + (unsigned long long)end.tv_sec, end.tv_nsec); + + if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } +} + +static void test_clock_gettime(void) +{ + for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); + clock++) { + test_one_clock_gettime(clock, clocknames[clock]); + } + + /* Also test some invalid clock ids */ + test_one_clock_gettime(-1, "invalid"); + test_one_clock_gettime(INT_MIN, "invalid"); + test_one_clock_gettime(INT_MAX, "invalid"); +} + +static void test_gettimeofday(void) +{ + struct timeval start, vdso, end; + struct timezone sys_tz, vdso_tz; + int vdso_ret, end_ret; + + if (!vdso_gettimeofday) + return; + + printf("[RUN]\tTesting gettimeofday...\n"); + + if (sys_gettimeofday(&start, &sys_tz) < 0) { + printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno); + nerrs++; + return; + } + + vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz); + end_ret = sys_gettimeofday(&end, NULL); + + if (vdso_ret != 0 || end_ret != 0) { + printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n", + vdso_ret, errno); + nerrs++; + return; + } + + printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n", + (unsigned long long)start.tv_sec, start.tv_usec, + (unsigned long long)vdso.tv_sec, vdso.tv_usec, + (unsigned long long)end.tv_sec, end.tv_usec); + + if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) { + printf("[FAIL]\tTimes are out of sequence\n"); + nerrs++; + } + + if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest && + sys_tz.tz_dsttime == vdso_tz.tz_dsttime) { + printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n", + sys_tz.tz_minuteswest, sys_tz.tz_dsttime); + } else { + printf("[FAIL]\ttimezones do not match\n"); + nerrs++; + } + + /* And make sure that passing NULL for tz doesn't crash. */ + vdso_gettimeofday(&vdso, NULL); +} + int main(int argc, char **argv) { fill_function_pointers(); + test_clock_gettime(); + test_gettimeofday(); + + /* + * Test getcpu() last so that, if something goes wrong setting affinity, + * we still run the other tests. + */ test_getcpu(); return nerrs ? 1 : 0; |