diff options
639 files changed, 11187 insertions, 5943 deletions
@@ -32,6 +32,7 @@ Alex Shi <[email protected]> <[email protected]> Alex Shi <[email protected]> <[email protected]> Al Viro <[email protected]> Al Viro <[email protected]> +Andi Kleen <[email protected]> <[email protected]> Andi Shyti <[email protected]> <[email protected]> Andreas Herrmann <[email protected]> Andrew Morton <[email protected]> @@ -132,6 +133,7 @@ Jan Glauber <[email protected]> <[email protected]> Jan Glauber <[email protected]> <[email protected]> Jan Glauber <[email protected]> <[email protected]> Jason Gunthorpe <[email protected]> <[email protected]> +Jason Gunthorpe <[email protected]> <[email protected]> Jason Gunthorpe <[email protected]> <[email protected]> Javi Merino <[email protected]> <[email protected]> @@ -178,6 +180,7 @@ Leonardo Bras <[email protected]> <[email protected]> Leonid I Ananiev <[email protected]> Leon Romanovsky <[email protected]> <[email protected]> Leon Romanovsky <[email protected]> <[email protected]> +Leon Romanovsky <[email protected]> <[email protected]> Linas Vepstas <[email protected]> Linus Lüssing <[email protected]> <[email protected]> Linus Lüssing <[email protected]> <[email protected]> diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 index f7e32f218f73..e82fc37be802 100644 --- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 @@ -43,7 +43,7 @@ Description: read only This sysfs interface exposes the number of cores per chip present in the system. -What: /sys/devices/hv_24x7/interface/cpumask +What: /sys/devices/hv_24x7/cpumask Date: July 2020 Contact: Linux on PowerPC Developer List <[email protected]> Description: read only diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index a683976fad6d..d2795ca6821e 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -489,6 +489,9 @@ Files in /sys/fs/ext4/<devname>: multiple of this tuning parameter if the stripe size is not set in the ext4 superblock + mb_max_inode_prealloc + The maximum length of per-inode ext4_prealloc_space list. + mb_max_to_scan The maximum number of extents the multiblock allocator will search to find the best extent. @@ -529,21 +532,21 @@ Files in /sys/fs/ext4/<devname>: Ioctls ====== -There is some Ext4 specific functionality which can be accessed by applications -through the system call interfaces. The list of all Ext4 specific ioctls are -shown in the table below. +Ext4 implements various ioctls which can be used by applications to access +ext4-specific functionality. An incomplete list of these ioctls is shown in the +table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as +well as ioctls that may have been ext4-specific originally but are now supported +by some other filesystem(s) too (``FS_IOC_*``). -Table of Ext4 specific ioctls +Table of Ext4 ioctls - EXT4_IOC_GETFLAGS + FS_IOC_GETFLAGS Get additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_GETFLAGS. + an integer bitfield, with bit values described in ext4.h. - EXT4_IOC_SETFLAGS + FS_IOC_SETFLAGS Set additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_SETFLAGS. + an integer bitfield, with bit values described in ext4.h. EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD Get the inode i_generation number stored for each inode. The diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bdc1f33fd3d1..8af893ef0d46 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1233,8 +1233,7 @@ efi= [EFI] Format: { "debug", "disable_early_pci_dma", "nochunk", "noruntime", "nosoftreserve", - "novamap", "no_disable_early_pci_dma", - "old_map" } + "novamap", "no_disable_early_pci_dma" } debug: enable misc debug output. disable_early_pci_dma: disable the busmaster bit on all PCI bridges while in the EFI boot stub. @@ -1251,8 +1250,6 @@ novamap: do not call SetVirtualAddressMap(). no_disable_early_pci_dma: Leave the busmaster bit set on all PCI bridges while in the EFI boot stub - old_map [X86-64]: switch to the old ioremap-based EFI - runtime services mapping. [Needs CONFIG_X86_UV=y] efi_no_storage_paranoia [EFI; X86] Using this parameter you can use more than 50% of @@ -1341,6 +1338,11 @@ Format: <interval>,<probability>,<space>,<times> See also Documentation/fault-injection/. + fb_tunnels= [NET] + Format: { initns | none } + See Documentation/admin-guide/sysctl/net.rst for + fb_tunnels_only_for_init_ns + floppy= [HW] See Documentation/admin-guide/blockdev/floppy.rst. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 42cd04bca548..57fd6ce68fe0 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -300,7 +300,6 @@ Note: 0: 0 1 2 3 4 5 6 7 RSS hash key: 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89 - netdev_tstamp_prequeue ---------------------- @@ -321,11 +320,20 @@ fb_tunnels_only_for_init_net ---------------------------- Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0, -sit0, ip6tnl0, ip6gre0) are automatically created when a new -network namespace is created, if corresponding tunnel is present -in initial network namespace. -If set to 1, these devices are not automatically created, and -user space is responsible for creating them if needed. +sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities +(a) value = 0; respective fallback tunnels are created when module is +loaded in every net namespaces (backward compatible behavior). +(b) value = 1; [kcmd value: initns] respective fallback tunnels are +created only in init net namespace and every other net namespace will +not have them. +(c) value = 2; [kcmd value: none] fallback tunnels are not created +when a module is loaded in any of the net namespace. Setting value to +"2" is pointless after boot if these modules are built-in, so there is +a kernel command-line option that can change this default. Please refer to +Documentation/admin-guide/kernel-parameters.txt for additional details. + +Not creating fallback tunnels gives control to userspace to create +whatever is needed only and avoid creating devices which are redundant. Default : 0 (for compatibility reasons) diff --git a/Documentation/devicetree/bindings/clock/imx23-clock.yaml b/Documentation/devicetree/bindings/clock/imx23-clock.yaml index 66cb238a1040..ad21899981af 100644 --- a/Documentation/devicetree/bindings/clock/imx23-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx23-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX23 maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/clock/imx28-clock.yaml b/Documentation/devicetree/bindings/clock/imx28-clock.yaml index 72328d5ca09a..f1af1108129e 100644 --- a/Documentation/devicetree/bindings/clock/imx28-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx28-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX28 maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml index ccf5b50e798b..dfa1133f8c5e 100644 --- a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml +++ b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS GPIO controller maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> - Anson Huang <[email protected]> description: | diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml index d3134ed775fa..21ae7bce038e 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS Inter IC (I2C) Controller maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> properties: compatible: diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml index 75dc1168d717..10b45966f1b8 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Enhanced Secure Digital Host Controller (eSDHC) for i.MX maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> allOf: - $ref: "mmc-controller.yaml" diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml index 1cccc0478d49..bec8f8c71ff2 100644 --- a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml +++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS MMC controller maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> description: | The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 1c4474036d46..fa2baca8c726 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -54,7 +54,8 @@ properties: phy-connection-type: description: - Operation mode of the PHY interface + Specifies interface type between the Ethernet device and a physical + layer (PHY) device. enum: # There is not a standard bus between the MAC and the PHY, # something proprietary is being used to embed the PHY in the diff --git a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml new file mode 100644 index 000000000000..fa3ebba4e635 --- /dev/null +++ b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml @@ -0,0 +1,130 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/intel,dwmac-plat.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Intel DWMAC glue layer Device Tree Bindings + +maintainers: + - Vineetha G. Jaya Kumaran <[email protected]> + +select: + properties: + compatible: + contains: + enum: + - intel,keembay-dwmac + required: + - compatible + +allOf: + - $ref: "snps,dwmac.yaml#" + +properties: + compatible: + oneOf: + - items: + - enum: + - intel,keembay-dwmac + - const: snps,dwmac-4.10a + + clocks: + items: + - description: GMAC main clock + - description: PTP reference clock + - description: Tx clock + + clock-names: + items: + - const: stmmaceth + - const: ptp_ref + - const: tx_clk + +required: + - compatible + - clocks + - clock-names + +examples: +# FIXME: Remove defines and include the correct header file +# once it is available in mainline. + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + #define MOVISOC_KMB_PSS_GBE + #define MOVISOC_KMB_PSS_AUX_GBE_PTP + #define MOVISOC_KMB_PSS_AUX_GBE_TX + + stmmac_axi_setup: stmmac-axi-config { + snps,lpi_en; + snps,wr_osr_lmt = <0x0>; + snps,rd_osr_lmt = <0x2>; + snps,blen = <0 0 0 0 16 8 4>; + }; + + mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <2>; + snps,rx-sched-sp; + queue0 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x0>; + snps,priority = <0x0>; + }; + + queue1 { + snps,dcb-algorithm; + snps,map-to-dma-channel = <0x1>; + snps,priority = <0x1>; + }; + }; + + mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <2>; + snps,tx-sched-wrr; + queue0 { + snps,weight = <0x10>; + snps,dcb-algorithm; + snps,priority = <0x0>; + }; + + queue1 { + snps,weight = <0x10>; + snps,dcb-algorithm; + snps,priority = <0x1>; + }; + }; + + gmac0: ethernet@3a000000 { + compatible = "intel,keembay-dwmac", "snps,dwmac-4.10a"; + interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + reg = <0x3a000000 0x8000>; + snps,perfect-filter-entries = <128>; + phy-handle = <ð_phy0>; + phy-mode = "rgmii"; + rx-fifo-depth = <4096>; + tx-fifo-depth = <4096>; + clock-names = "stmmaceth", "ptp_ref", "tx_clk"; + clocks = <&scmi_clk MOVISOC_KMB_PSS_GBE>, + <&scmi_clk MOVISOC_KMB_PSS_AUX_GBE_PTP>, + <&scmi_clk MOVISOC_KMB_PSS_AUX_GBE_TX>; + snps,pbl = <0x4>; + snps,axi-config = <&stmmac_axi_setup>; + snps,mtl-rx-config = <&mtl_rx_setup>; + snps,mtl-tx-config = <&mtl_tx_setup>; + snps,tso; + status = "okay"; + + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + ethernet-phy@0 { + reg = <0>; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 08678af5ed93..8ce5ed8a58dd 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -59,9 +59,15 @@ properties: clocks: maxItems: 1 - pinctrl-0: true + power-domains: + maxItems: 1 + + resets: + maxItems: 1 - pinctrl-names: true + phy-mode: true + + phy-handle: true renesas,no-ether-link: type: boolean @@ -74,6 +80,11 @@ properties: specify when the Ether LINK signal is active-low instead of normal active-high +patternProperties: + "^ethernet-phy@[0-9a-f]$": + type: object + $ref: ethernet-phy.yaml# + required: - compatible - reg @@ -83,7 +94,8 @@ required: - '#address-cells' - '#size-cells' - clocks - - pinctrl-0 + +additionalProperties: false examples: # Lager board @@ -99,8 +111,6 @@ examples: clocks = <&mstp8_clks R8A7790_CLK_ETHER>; phy-mode = "rmii"; phy-handle = <&phy1>; - pinctrl-0 = <ðer_pins>; - pinctrl-names = "default"; renesas,ether-link-active-low; #address-cells = <1>; #size-cells = <0>; @@ -109,7 +119,5 @@ examples: reg = <1>; interrupt-parent = <&irqc0>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; - pinctrl-0 = <&phy1_pins>; - pinctrl-names = "default"; }; }; diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml new file mode 100644 index 000000000000..55913534cbc2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -0,0 +1,80 @@ +# SPDX-License-Identifier: (GPL-2.0+ OR BSD-2-Clause) +# Copyright (C) 2020 Texas Instruments Incorporated +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/net/ti,dp83822.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: TI DP83822 ethernet PHY + +maintainers: + - Dan Murphy <[email protected]> + +description: | + The DP83822 is a low-power, single-port, 10/100 Mbps Ethernet PHY. It + provides all of the physical layer functions needed to transmit and receive + data over standard, twisted-pair cables or to connect to an external, + fiber-optic transceiver. Additionally, the DP83822 provides flexibility to + connect to a MAC through a standard MII, RMII, or RGMII interface + + Specifications about the Ethernet PHY can be found at: + http://www.ti.com/lit/ds/symlink/dp83822i.pdf + +allOf: + - $ref: "ethernet-phy.yaml#" + +properties: + reg: + maxItems: 1 + + ti,link-loss-low: + type: boolean + description: | + DP83822 PHY in Fiber mode only. + Sets the DP83822 to detect a link drop condition when the signal goes + high. If not set then link drop will occur when the signal goes low. + This property is only applicable if the fiber mode support is strapped + to on. + + ti,fiber-mode: + type: boolean + description: | + DP83822 PHY only. + If present the DP83822 PHY is configured to operate in fiber mode + Fiber mode support can also be strapped. If the strap pin is not set + correctly or not set at all then this boolean can be used to enable it. + If the fiber mode is not strapped then signal detection for the PHY + is disabled. + In fiber mode, auto-negotiation is disabled and the PHY can only work in + 100base-fx (full and half duplex) modes. + + rx-internal-delay-ps: + description: | + DP83822 PHY only. + Setting this property to a non-zero number sets the RX internal delay + for the PHY. The internal delay for the PHY is fixed to 3.5ns relative + to receive data. + + tx-internal-delay-ps: + description: | + DP83822 PHY only. + Setting this property to a non-zero number sets the TX internal delay + for the PHY. The internal delay for the PHY is fixed to 3.5ns relative + to transmit data. + +required: + - reg + +examples: + - | + mdio0 { + #address-cells = <1>; + #size-cells = <0>; + ethphy0: ethernet-phy@0 { + reg = <0>; + rx-internal-delay-ps = <1>; + tx-internal-delay-ps = <1>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml index 64b2c64ca806..a1e2be737eec 100644 --- a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml @@ -9,6 +9,14 @@ title: PCIe RC controller on Intel Gateway SoCs maintainers: - Dilip Kota <[email protected]> +select: + properties: + compatible: + contains: + const: intel,lgm-pcie + required: + - compatible + properties: compatible: items: diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml index da68f4a25dd9..8740e076061e 100644 --- a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS PWM controller maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> - Anson Huang <[email protected]> properties: diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml index 1b50cedbfb3e..50df1a40bbe3 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale (Enhanced) Configurable Serial Peripheral Interface (CSPI/eCSPI) for i.MX maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> allOf: - $ref: "/schemas/spi/spi-controller.yaml#" diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml index 22882e769e26..312d8fee9dbb 100644 --- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml +++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml @@ -39,6 +39,7 @@ properties: spi common code does not support use of CS signals discontinuously. i.MX8DXL-EVK board only uses CS1 without using CS0. Therefore, add this property to re-config the chipselect value in the LPSPI driver. + type: boolean required: - compatible diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml index aedac1669998..16b57f57d103 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP i.MX Thermal Binding maintainers: - - Shawn Guo <[email protected]> + - Shawn Guo <[email protected]> - Anson Huang <[email protected]> properties: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml new file mode 100644 index 000000000000..2a0e9cd9fbcf --- /dev/null +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/sifive,clint.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SiFive Core Local Interruptor + +maintainers: + - Palmer Dabbelt <[email protected]> + - Anup Patel <[email protected]> + +description: + SiFive (and other RISC-V) SOCs include an implementation of the SiFive + Core Local Interruptor (CLINT) for M-mode timer and M-mode inter-processor + interrupts. It directly connects to the timer and inter-processor interrupt + lines of various HARTs (or CPUs) so RISC-V per-HART (or per-CPU) local + interrupt controller is the parent interrupt controller for CLINT device. + The clock frequency of CLINT is specified via "timebase-frequency" DT + property of "/cpus" DT node. The "timebase-frequency" DT property is + described in Documentation/devicetree/bindings/riscv/cpus.yaml + +properties: + compatible: + items: + - const: sifive,fu540-c000-clint + - const: sifive,clint0 + + description: + Should be "sifive,<chip>-clint" and "sifive,clint<version>". + Supported compatible strings are - + "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated + onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive + CLINT v0 IP block with no chip integration tweaks. + Please refer to sifive-blocks-ip-versioning.txt for details + + reg: + maxItems: 1 + + interrupts-extended: + minItems: 1 + +additionalProperties: false + +required: + - compatible + - reg + - interrupts-extended + +examples: + - | + timer@2000000 { + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; + interrupts-extended = <&cpu1intc 3 &cpu1intc 7 + &cpu2intc 3 &cpu2intc 7 + &cpu3intc 3 &cpu3intc 7 + &cpu4intc 3 &cpu4intc 7>; + reg = <0x2000000 0x10000>; + }; +... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 2baee2c817c1..63996ab03521 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -993,7 +993,7 @@ patternProperties: "^sst,.*": description: Silicon Storage Technology, Inc. "^sstar,.*": - description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. + description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. (formerly part of MStar Semiconductor, Inc.) "^st,.*": description: STMicroelectronics diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst index 8c74a99f95e2..16f21e182ff6 100644 --- a/Documentation/devicetree/writing-schema.rst +++ b/Documentation/devicetree/writing-schema.rst @@ -5,7 +5,7 @@ Writing DeviceTree Bindings in json-schema Devicetree bindings are written using json-schema vocabulary. Schema files are written in a JSON compatible subset of YAML. YAML is used instead of JSON as it -considered more human readable and has some advantages such as allowing +is considered more human readable and has some advantages such as allowing comments (Prefixed with '#'). Schema Contents @@ -19,7 +19,7 @@ $id A json-schema unique identifier string. The string must be a valid URI typically containing the binding's filename and path. For DT schema, it must begin with "http://devicetree.org/schemas/". The URL is used in constructing - references to other files specified in schema "$ref" properties. A $ref values + references to other files specified in schema "$ref" properties. A $ref value with a leading '/' will have the hostname prepended. A $ref value a relative path or filename only will be prepended with the hostname and path components of the current schema file's '$id' value. A URL is used even for local files, diff --git a/Documentation/filesystems/ext4/about.rst b/Documentation/filesystems/ext4/about.rst index 0aadba052264..cc76b577d2f4 100644 --- a/Documentation/filesystems/ext4/about.rst +++ b/Documentation/filesystems/ext4/about.rst @@ -39,6 +39,6 @@ entry. Other References ---------------- -Also see http://www.nongnu.org/ext2-doc/ for quite a collection of +Also see https://www.nongnu.org/ext2-doc/ for quite a collection of information about ext2/3. Here's another old reference: http://wiki.osdev.org/Ext2 diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst index a48238a2ec09..498b382d25a0 100644 --- a/Documentation/networking/l2tp.rst +++ b/Documentation/networking/l2tp.rst @@ -4,124 +4,364 @@ L2TP ==== -This document describes how to use the kernel's L2TP drivers to -provide L2TP functionality. L2TP is a protocol that tunnels one or -more sessions over an IP tunnel. It is commonly used for VPNs -(L2TP/IPSec) and by ISPs to tunnel subscriber PPP sessions over an IP -network infrastructure. With L2TPv3, it is also useful as a Layer-2 -tunneling infrastructure. - -Features +Layer 2 Tunneling Protocol (L2TP) allows L2 frames to be tunneled over +an IP network. + +This document covers the kernel's L2TP subsystem. It documents kernel +APIs for application developers who want to use the L2TP subsystem and +it provides some technical details about the internal implementation +which may be useful to kernel developers and maintainers. + +Overview ======== -L2TPv2 (PPP over L2TP (UDP tunnels)). -L2TPv3 ethernet pseudowires. -L2TPv3 PPP pseudowires. -L2TPv3 IP encapsulation. -Netlink sockets for L2TPv3 configuration management. - -History -======= - -The original pppol2tp driver was introduced in 2.6.23 and provided -L2TPv2 functionality (rfc2661). L2TPv2 is used to tunnel one or more PPP -sessions over a UDP tunnel. - -L2TPv3 (rfc3931) changes the protocol to allow different frame types -to be passed over an L2TP tunnel by moving the PPP-specific parts of -the protocol out of the core L2TP packet headers. Each frame type is -known as a pseudowire type. Ethernet, PPP, HDLC, Frame Relay and ATM -pseudowires for L2TP are defined in separate RFC standards. Another -change for L2TPv3 is that it can be carried directly over IP with no -UDP header (UDP is optional). It is also possible to create static -unmanaged L2TPv3 tunnels manually without a control protocol -(userspace daemon) to manage them. - -To support L2TPv3, the original pppol2tp driver was split up to -separate the L2TP and PPP functionality. Existing L2TPv2 userspace -apps should be unaffected as the original pppol2tp sockets API is -retained. L2TPv3, however, uses netlink to manage L2TPv3 tunnels and -sessions. - -Design -====== - -The L2TP protocol separates control and data frames. The L2TP kernel -drivers handle only L2TP data frames; control frames are always -handled by userspace. L2TP control frames carry messages between L2TP -clients/servers and are used to setup / teardown tunnels and -sessions. An L2TP client or server is implemented in userspace. - -Each L2TP tunnel is implemented using a UDP or L2TPIP socket; L2TPIP -provides L2TPv3 IP encapsulation (no UDP) and is implemented using a -new l2tpip socket family. The tunnel socket is typically created by -userspace, though for unmanaged L2TPv3 tunnels, the socket can also be -created by the kernel. Each L2TP session (pseudowire) gets a network -interface instance. In the case of PPP, these interfaces are created -indirectly by pppd using a pppol2tp socket. In the case of ethernet, -the netdevice is created upon a netlink request to create an L2TPv3 -ethernet pseudowire. - -For PPP, the PPPoL2TP driver, net/l2tp/l2tp_ppp.c, provides a -mechanism by which PPP frames carried through an L2TP session are -passed through the kernel's PPP subsystem. The standard PPP daemon, -pppd, handles all PPP interaction with the peer. PPP network -interfaces are created for each local PPP endpoint. The kernel's PPP -subsystem arranges for PPP control frames to be delivered to pppd, -while data frames are forwarded as usual. - -For ethernet, the L2TPETH driver, net/l2tp/l2tp_eth.c, implements a -netdevice driver, managing virtual ethernet devices, one per -pseudowire. These interfaces can be managed using standard Linux tools -such as "ip" and "ifconfig". If only IP frames are passed over the -tunnel, the interface can be given an IP addresses of itself and its -peer. If non-IP frames are to be passed over the tunnel, the interface -can be added to a bridge using brctl. All L2TP datapath protocol -functions are handled by the L2TP core driver. - -Each tunnel and session within a tunnel is assigned a unique tunnel_id -and session_id. These ids are carried in the L2TP header of every -control and data packet. (Actually, in L2TPv3, the tunnel_id isn't -present in data frames - it is inferred from the IP connection on -which the packet was received.) The L2TP driver uses the ids to lookup -internal tunnel and/or session contexts to determine how to handle the -packet. Zero tunnel / session ids are treated specially - zero ids are -never assigned to tunnels or sessions in the network. In the driver, -the tunnel context keeps a reference to the tunnel UDP or L2TPIP -socket. The session context holds data that lets the driver interface -to the kernel's network frame type subsystems, i.e. PPP, ethernet. - -Userspace Programming -===================== - -For L2TPv2, there are a number of requirements on the userspace L2TP -daemon in order to use the pppol2tp driver. - -1. Use a UDP socket per tunnel. - -2. Create a single PPPoL2TP socket per tunnel bound to a special null - session id. This is used only for communicating with the driver but - must remain open while the tunnel is active. Opening this tunnel - management socket causes the driver to mark the tunnel socket as an - L2TP UDP encapsulation socket and flags it for use by the - referenced tunnel id. This hooks up the UDP receive path via - udp_encap_rcv() in net/ipv4/udp.c. PPP data frames are never passed - in this special PPPoX socket. - -3. Create a PPPoL2TP socket per L2TP session. This is typically done - by starting pppd with the pppol2tp plugin and appropriate - arguments. A PPPoL2TP tunnel management socket (Step 2) must be - created before the first PPPoL2TP session socket is created. +The kernel's L2TP subsystem implements the datapath for L2TPv2 and +L2TPv3. L2TPv2 is carried over UDP. L2TPv3 is carried over UDP or +directly over IP (protocol 115). + +The L2TP RFCs define two basic kinds of L2TP packets: control packets +(the "control plane"), and data packets (the "data plane"). The kernel +deals only with data packets. The more complex control packets are +handled by user space. + +An L2TP tunnel carries one or more L2TP sessions. Each tunnel is +associated with a socket. Each session is associated with a virtual +netdevice, e.g. ``pppN``, ``l2tpethN``, through which data frames pass +to/from L2TP. Fields in the L2TP header identify the tunnel or session +and whether it is a control or data packet. When tunnels and sessions +are set up using the Linux kernel API, we're just setting up the L2TP +data path. All aspects of the control protocol are to be handled by +user space. + +This split in responsibilities leads to a natural sequence of +operations when establishing tunnels and sessions. The procedure looks +like this: + + 1) Create a tunnel socket. Exchange L2TP control protocol messages + with the peer over that socket in order to establish a tunnel. + + 2) Create a tunnel context in the kernel, using information + obtained from the peer using the control protocol messages. + + 3) Exchange L2TP control protocol messages with the peer over the + tunnel socket in order to establish a session. + + 4) Create a session context in the kernel using information + obtained from the peer using the control protocol messages. + +L2TP APIs +========= + +This section documents each userspace API of the L2TP subsystem. + +Tunnel Sockets +-------------- + +L2TPv2 always uses UDP. L2TPv3 may use UDP or IP encapsulation. + +To create a tunnel socket for use by L2TP, the standard POSIX +socket API is used. + +For example, for a tunnel using IPv4 addresses and UDP encapsulation:: + + int sockfd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); + +Or for a tunnel using IPv6 addresses and IP encapsulation:: + + int sockfd = socket(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP); + +UDP socket programming doesn't need to be covered here. + +IPPROTO_L2TP is an IP protocol type implemented by the kernel's L2TP +subsystem. The L2TPIP socket address is defined in struct +sockaddr_l2tpip and struct sockaddr_l2tpip6 at +`include/uapi/linux/l2tp.h`_. The address includes the L2TP tunnel +(connection) id. To use L2TP IP encapsulation, an L2TPv3 application +should bind the L2TPIP socket using the locally assigned +tunnel id. When the peer's tunnel id and IP address is known, a +connect must be done. + +If the L2TP application needs to handle L2TPv3 tunnel setup requests +from peers using L2TPIP, it must open a dedicated L2TPIP +socket to listen for those requests and bind the socket using tunnel +id 0 since tunnel setup requests are addressed to tunnel id 0. + +An L2TP tunnel and all of its sessions are automatically closed when +its tunnel socket is closed. + +Netlink API +----------- + +L2TP applications use netlink to manage L2TP tunnel and session +instances in the kernel. The L2TP netlink API is defined in +`include/uapi/linux/l2tp.h`_. + +L2TP uses `Generic Netlink`_ (GENL). Several commands are defined: +Create, Delete, Modify and Get for tunnel and session +instances, e.g. ``L2TP_CMD_TUNNEL_CREATE``. The API header lists the +netlink attribute types that can be used with each command. + +Tunnel and session instances are identified by a locally unique +32-bit id. L2TP tunnel ids are given by ``L2TP_ATTR_CONN_ID`` and +``L2TP_ATTR_PEER_CONN_ID`` attributes and L2TP session ids are given +by ``L2TP_ATTR_SESSION_ID`` and ``L2TP_ATTR_PEER_SESSION_ID`` +attributes. If netlink is used to manage L2TPv2 tunnel and session +instances, the L2TPv2 16-bit tunnel/session id is cast to a 32-bit +value in these attributes. + +In the ``L2TP_CMD_TUNNEL_CREATE`` command, ``L2TP_ATTR_FD`` tells the +kernel the tunnel socket fd being used. If not specified, the kernel +creates a kernel socket for the tunnel, using IP parameters set in +``L2TP_ATTR_IP[6]_SADDR``, ``L2TP_ATTR_IP[6]_DADDR``, +``L2TP_ATTR_UDP_SPORT``, ``L2TP_ATTR_UDP_DPORT`` attributes. Kernel +sockets are used to implement unmanaged L2TPv3 tunnels (iproute2's "ip +l2tp" commands). If ``L2TP_ATTR_FD`` is given, it must be a socket fd +that is already bound and connected. There is more information about +unmanaged tunnels later in this document. + +``L2TP_CMD_TUNNEL_CREATE`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Sets the tunnel (connection) id. +PEER_CONN_ID Y Sets the peer tunnel (connection) id. +PROTO_VERSION Y Protocol version. 2 or 3. +ENCAP_TYPE Y Encapsulation type: UDP or IP. +FD N Tunnel socket file descriptor. +UDP_CSUM N Enable IPv4 UDP checksums. Used only if FD is + not set. +UDP_ZERO_CSUM6_TX N Zero IPv6 UDP checksum on transmit. Used only + if FD is not set. +UDP_ZERO_CSUM6_RX N Zero IPv6 UDP checksum on receive. Used only if + FD is not set. +IP_SADDR N IPv4 source address. Used only if FD is not + set. +IP_DADDR N IPv4 destination address. Used only if FD is + not set. +UDP_SPORT N UDP source port. Used only if FD is not set. +UDP_DPORT N UDP destination port. Used only if FD is not + set. +IP6_SADDR N IPv6 source address. Used only if FD is not + set. +IP6_DADDR N IPv6 destination address. Used only if FD is + not set. +DEBUG N Debug flags. +================== ======== === + +``L2TP_CMD_TUNNEL_DESTROY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the tunnel id to be destroyed. +================== ======== === + +``L2TP_CMD_TUNNEL_MODIFY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the tunnel id to be modified. +DEBUG N Debug flags. +================== ======== === + +``L2TP_CMD_TUNNEL_GET`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID N Identifies the tunnel id to be queried. + Ignored in DUMP requests. +================== ======== === + +``L2TP_CMD_SESSION_CREATE`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y The parent tunnel id. +SESSION_ID Y Sets the session id. +PEER_SESSION_ID Y Sets the parent session id. +PW_TYPE Y Sets the pseudowire type. +DEBUG N Debug flags. +RECV_SEQ N Enable rx data sequence numbers. +SEND_SEQ N Enable tx data sequence numbers. +LNS_MODE N Enable LNS mode (auto-enable data sequence + numbers). +RECV_TIMEOUT N Timeout to wait when reordering received + packets. +L2SPEC_TYPE N Sets layer2-specific-sublayer type (L2TPv3 + only). +COOKIE N Sets optional cookie (L2TPv3 only). +PEER_COOKIE N Sets optional peer cookie (L2TPv3 only). +IFNAME N Sets interface name (L2TPv3 only). +================== ======== === + +For Ethernet session types, this will create an l2tpeth virtual +interface which can then be configured as required. For PPP session +types, a PPPoL2TP socket must also be opened and connected, mapping it +onto the new session. This is covered in "PPPoL2TP Sockets" later. + +``L2TP_CMD_SESSION_DESTROY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the parent tunnel id of the session + to be destroyed. +SESSION_ID Y Identifies the session id to be destroyed. +IFNAME N Identifies the session by interface name. If + set, this overrides any CONN_ID and SESSION_ID + attributes. Currently supported for L2TPv3 + Ethernet sessions only. +================== ======== === + +``L2TP_CMD_SESSION_MODIFY`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID Y Identifies the parent tunnel id of the session + to be modified. +SESSION_ID Y Identifies the session id to be modified. +IFNAME N Identifies the session by interface name. If + set, this overrides any CONN_ID and SESSION_ID + attributes. Currently supported for L2TPv3 + Ethernet sessions only. +DEBUG N Debug flags. +RECV_SEQ N Enable rx data sequence numbers. +SEND_SEQ N Enable tx data sequence numbers. +LNS_MODE N Enable LNS mode (auto-enable data sequence + numbers). +RECV_TIMEOUT N Timeout to wait when reordering received + packets. +================== ======== === + +``L2TP_CMD_SESSION_GET`` attributes:- + +================== ======== === +Attribute Required Use +================== ======== === +CONN_ID N Identifies the tunnel id to be queried. + Ignored for DUMP requests. +SESSION_ID N Identifies the session id to be queried. + Ignored for DUMP requests. +IFNAME N Identifies the session by interface name. + If set, this overrides any CONN_ID and + SESSION_ID attributes. Ignored for DUMP + requests. Currently supported for L2TPv3 + Ethernet sessions only. +================== ======== === + +Application developers should refer to `include/uapi/linux/l2tp.h`_ for +netlink command and attribute definitions. + +Sample userspace code using libmnl_: + + - Open L2TP netlink socket:: + + struct nl_sock *nl_sock; + int l2tp_nl_family_id; + + nl_sock = nl_socket_alloc(); + genl_connect(nl_sock); + genl_id = genl_ctrl_resolve(nl_sock, L2TP_GENL_NAME); + + - Create a tunnel:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_TUNNEL_CREATE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_FD, tunl_sock_fd); + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_CONN_ID, peer_tid); + mnl_attr_put_u8(nlh, L2TP_ATTR_PROTO_VERSION, protocol_version); + mnl_attr_put_u16(nlh, L2TP_ATTR_ENCAP_TYPE, encap); + + - Create a session:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_SESSION_CREATE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_CONN_ID, peer_tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_SESSION_ID, sid); + mnl_attr_put_u32(nlh, L2TP_ATTR_PEER_SESSION_ID, peer_sid); + mnl_attr_put_u16(nlh, L2TP_ATTR_PW_TYPE, pwtype); + /* there are other session options which can be set using netlink + * attributes during session creation -- see l2tp.h + */ + + - Delete a session:: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_SESSION_DELETE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + mnl_attr_put_u32(nlh, L2TP_ATTR_SESSION_ID, sid); + + - Delete a tunnel and all of its sessions (if any):: + + struct nlmsghdr *nlh; + struct genlmsghdr *gnlh; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = genl_id; /* assigned to genl socket */ + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + nlh->nlmsg_seq = seq; + + gnlh = mnl_nlmsg_put_extra_header(nlh, sizeof(*gnlh)); + gnlh->cmd = L2TP_CMD_TUNNEL_DELETE; + gnlh->version = L2TP_GENL_VERSION; + gnlh->reserved = 0; + + mnl_attr_put_u32(nlh, L2TP_ATTR_CONN_ID, tid); + +PPPoL2TP Session Socket API +--------------------------- + +For PPP session types, a PPPoL2TP socket must be opened and connected +to the L2TP session. When creating PPPoL2TP sockets, the application provides information -to the driver about the socket in a socket connect() call. Source and -destination tunnel and session ids are provided, as well as the file -descriptor of a UDP socket. See struct pppol2tp_addr in -include/linux/if_pppol2tp.h. Note that zero tunnel / session ids are -treated specially. When creating the per-tunnel PPPoL2TP management -socket in Step 2 above, zero source and destination session ids are -specified, which tells the driver to prepare the supplied UDP file -descriptor for use as an L2TP tunnel socket. +to the kernel about the tunnel and session in a socket connect() +call. Source and destination tunnel and session ids are provided, as +well as the file descriptor of a UDP or L2TPIP socket. See struct +pppol2tp_addr in `include/linux/if_pppol2tp.h`_. For historical reasons, +there are unfortunately slightly different address structures for +L2TPv2/L2TPv3 IPv4/IPv6 tunnels and userspace must use the appropriate +structure that matches the tunnel socket type. Userspace may control behavior of the tunnel or session using setsockopt and ioctl on the PPPoX socket. The following socket @@ -130,229 +370,308 @@ options are supported:- ========= =========================================================== DEBUG bitmask of debug message categories. See below. SENDSEQ - 0 => don't send packets with sequence numbers - - 1 => send packets with sequence numbers + - 1 => send packets with sequence numbers RECVSEQ - 0 => receive packet sequence numbers are optional - - 1 => drop receive packets without sequence numbers + - 1 => drop receive packets without sequence numbers LNSMODE - 0 => act as LAC. - - 1 => act as LNS. + - 1 => act as LNS. REORDERTO reorder timeout (in millisecs). If 0, don't try to reorder. ========= =========================================================== -Only the DEBUG option is supported by the special tunnel management -PPPoX socket. - In addition to the standard PPP ioctls, a PPPIOCGL2TPSTATS is provided to retrieve tunnel and session statistics from the kernel using the PPPoX socket of the appropriate tunnel or session. -For L2TPv3, userspace must use the netlink API defined in -include/linux/l2tp.h to manage tunnel and session contexts. The -general procedure to create a new L2TP tunnel with one session is:- - -1. Open a GENL socket using L2TP_GENL_NAME for configuring the kernel - using netlink. - -2. Create a UDP or L2TPIP socket for the tunnel. - -3. Create a new L2TP tunnel using a L2TP_CMD_TUNNEL_CREATE - request. Set attributes according to desired tunnel parameters, - referencing the UDP or L2TPIP socket created in the previous step. - -4. Create a new L2TP session in the tunnel using a - L2TP_CMD_SESSION_CREATE request. - -The tunnel and all of its sessions are closed when the tunnel socket -is closed. The netlink API may also be used to delete sessions and -tunnels. Configuration and status info may be set or read using netlink. - -The L2TP driver also supports static (unmanaged) L2TPv3 tunnels. These -are where there is no L2TP control message exchange with the peer to -setup the tunnel; the tunnel is configured manually at each end of the -tunnel. There is no need for an L2TP userspace application in this -case -- the tunnel socket is created by the kernel and configured -using parameters sent in the L2TP_CMD_TUNNEL_CREATE netlink -request. The "ip" utility of iproute2 has commands for managing static -L2TPv3 tunnels; do "ip l2tp help" for more information. +Sample userspace code: + + - Create session PPPoX data socket:: + + struct sockaddr_pppol2tp sax; + int fd; + + /* Note, the tunnel socket must be bound already, else it + * will not be ready + */ + sax.sa_family = AF_PPPOX; + sax.sa_protocol = PX_PROTO_OL2TP; + sax.pppol2tp.fd = tunnel_fd; + sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr; + sax.pppol2tp.addr.sin_port = addr->sin_port; + sax.pppol2tp.addr.sin_family = AF_INET; + sax.pppol2tp.s_tunnel = tunnel_id; + sax.pppol2tp.s_session = session_id; + sax.pppol2tp.d_tunnel = peer_tunnel_id; + sax.pppol2tp.d_session = peer_session_id; + + /* session_fd is the fd of the session's PPPoL2TP socket. + * tunnel_fd is the fd of the tunnel UDP / L2TPIP socket. + */ + fd = connect(session_fd, (struct sockaddr *)&sax, sizeof(sax)); + if (fd < 0 ) { + return -errno; + } + return 0; + +Old L2TPv2-only API +------------------- + +When L2TP was first added to the Linux kernel in 2.6.23, it +implemented only L2TPv2 and did not include a netlink API. Instead, +tunnel and session instances in the kernel were managed directly using +only PPPoL2TP sockets. The PPPoL2TP socket is used as described in +section "PPPoL2TP Session Socket API" but tunnel and session instances +are automatically created on a connect() of the socket instead of +being created by a separate netlink request: + + - Tunnels are managed using a tunnel management socket which is a + dedicated PPPoL2TP socket, connected to (invalid) session + id 0. The L2TP tunnel instance is created when the PPPoL2TP + tunnel management socket is connected and is destroyed when the + socket is closed. + + - Session instances are created in the kernel when a PPPoL2TP + socket is connected to a non-zero session id. Session parameters + are set using setsockopt. The L2TP session instance is destroyed + when the socket is closed. + +This API is still supported but its use is discouraged. Instead, new +L2TPv2 applications should use netlink to first create the tunnel and +session, then create a PPPoL2TP socket for the session. + +Unmanaged L2TPv3 tunnels +------------------------ + +The kernel L2TP subsystem also supports static (unmanaged) L2TPv3 +tunnels. Unmanaged tunnels have no userspace tunnel socket, and +exchange no control messages with the peer to set up the tunnel; the +tunnel is configured manually at each end of the tunnel. All +configuration is done using netlink. There is no need for an L2TP +userspace application in this case -- the tunnel socket is created by +the kernel and configured using parameters sent in the +``L2TP_CMD_TUNNEL_CREATE`` netlink request. The ``ip`` utility of +``iproute2`` has commands for managing static L2TPv3 tunnels; do ``ip +l2tp help`` for more information. Debugging -========= - -The driver supports a flexible debug scheme where kernel trace -messages may be optionally enabled per tunnel and per session. Care is -needed when debugging a live system since the messages are not -rate-limited and a busy system could be swamped. Userspace uses -setsockopt on the PPPoX socket to set a debug mask. +--------- -The following debug mask bits are available: +The L2TP subsystem offers a range of debugging interfaces through the +debugfs filesystem. -================ ============================== -L2TP_MSG_DEBUG verbose debug (if compiled in) -L2TP_MSG_CONTROL userspace - kernel interface -L2TP_MSG_SEQ sequence numbers handling -L2TP_MSG_DATA data packets -================ ============================== +To access these interfaces, the debugfs filesystem must first be mounted:: -If enabled, files under a l2tp debugfs directory can be used to dump -kernel state about L2TP tunnels and sessions. To access it, the -debugfs filesystem must first be mounted:: + # mount -t debugfs debugfs /debug - # mount -t debugfs debugfs /debug +Files under the l2tp directory can then be accessed, providing a summary +of the current population of tunnel and session contexts existing in the +kernel:: -Files under the l2tp directory can then be accessed:: - - # cat /debug/l2tp/tunnels + # cat /debug/l2tp/tunnels The debugfs files should not be used by applications to obtain L2TP state information because the file format is subject to change. It is implemented to provide extra debug information to help diagnose -problems.) Users should use the netlink API. +problems. Applications should instead use the netlink API. -/proc/net/pppol2tp is also provided for backwards compatibility with -the original pppol2tp driver. It lists information about L2TPv2 -tunnels and sessions only. Its use is discouraged. +In addition the L2TP subsystem implements tracepoints using the standard +kernel event tracing API. The available L2TP events can be reviewed as +follows:: -Unmanaged L2TPv3 Tunnels -======================== - -Some commercial L2TP products support unmanaged L2TPv3 ethernet -tunnels, where there is no L2TP control protocol; tunnels are -configured at each side manually. New commands are available in -iproute2's ip utility to support this. - -To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 -and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the -tunnel endpoints:: - - # ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ - udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 - # ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 - # ip -s -d show dev l2tpeth0 - # ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 - # ip li set dev l2tpeth0 up - -Choose IP addresses to be the address of a local IP interface and that -of the remote system. The IP addresses of the l2tpeth0 interface can be -anything suitable. - -Repeat the above at the peer, with ports, tunnel/session ids and IP -addresses reversed. The tunnel and session IDs can be any non-zero -32-bit number, but the values must be reversed at the peer. - -======================== =================== -Host 1 Host2 -======================== =================== -udp_sport=5000 udp_sport=5001 -udp_dport=5001 udp_dport=5000 -tunnel_id=42 tunnel_id=45 -peer_tunnel_id=45 peer_tunnel_id=42 -session_id=128 session_id=5196755 -peer_session_id=5196755 peer_session_id=128 -======================== =================== - -When done at both ends of the tunnel, it should be possible to send -data over the network. e.g.:: - - # ping 10.5.1.1 - - -Sample Userspace Code -===================== - -1. Create tunnel management PPPoX socket:: - - kernel_fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP); - if (kernel_fd >= 0) { - struct sockaddr_pppol2tp sax; - struct sockaddr_in const *peer_addr; - - peer_addr = l2tp_tunnel_get_peer_addr(tunnel); - memset(&sax, 0, sizeof(sax)); - sax.sa_family = AF_PPPOX; - sax.sa_protocol = PX_PROTO_OL2TP; - sax.pppol2tp.fd = udp_fd; /* fd of tunnel UDP socket */ - sax.pppol2tp.addr.sin_addr.s_addr = peer_addr->sin_addr.s_addr; - sax.pppol2tp.addr.sin_port = peer_addr->sin_port; - sax.pppol2tp.addr.sin_family = AF_INET; - sax.pppol2tp.s_tunnel = tunnel_id; - sax.pppol2tp.s_session = 0; /* special case: mgmt socket */ - sax.pppol2tp.d_tunnel = 0; - sax.pppol2tp.d_session = 0; /* special case: mgmt socket */ - - if(connect(kernel_fd, (struct sockaddr *)&sax, sizeof(sax) ) < 0 ) { - perror("connect failed"); - result = -errno; - goto err; - } - } - -2. Create session PPPoX data socket:: - - struct sockaddr_pppol2tp sax; - int fd; - - /* Note, the target socket must be bound already, else it will not be ready */ - sax.sa_family = AF_PPPOX; - sax.sa_protocol = PX_PROTO_OL2TP; - sax.pppol2tp.fd = tunnel_fd; - sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr; - sax.pppol2tp.addr.sin_port = addr->sin_port; - sax.pppol2tp.addr.sin_family = AF_INET; - sax.pppol2tp.s_tunnel = tunnel_id; - sax.pppol2tp.s_session = session_id; - sax.pppol2tp.d_tunnel = peer_tunnel_id; - sax.pppol2tp.d_session = peer_session_id; - - /* session_fd is the fd of the session's PPPoL2TP socket. - * tunnel_fd is the fd of the tunnel UDP socket. - */ - fd = connect(session_fd, (struct sockaddr *)&sax, sizeof(sax)); - if (fd < 0 ) { - return -errno; - } - return 0; + # find /debug/tracing/events/l2tp + +Finally, /proc/net/pppol2tp is also provided for backwards compatibility +with the original pppol2tp code. It lists information about L2TPv2 +tunnels and sessions only. Its use is discouraged. Internal Implementation ======================= -The driver keeps a struct l2tp_tunnel context per L2TP tunnel and a -struct l2tp_session context for each session. The l2tp_tunnel is -always associated with a UDP or L2TP/IP socket and keeps a list of -sessions in the tunnel. The l2tp_session context keeps kernel state -about the session. It has private data which is used for data specific -to the session type. With L2TPv2, the session always carried PPP -traffic. With L2TPv3, the session can also carry ethernet frames -(ethernet pseudowire) or other data types such as ATM, HDLC or Frame -Relay. - -When a tunnel is first opened, the reference count on the socket is -increased using sock_hold(). This ensures that the kernel socket -cannot be removed while L2TP's data structures reference it. - -Some L2TP sessions also have a socket (PPP pseudowires) while others -do not (ethernet pseudowires). We can't use the socket reference count -as the reference count for session contexts. The L2TP implementation -therefore has its own internal reference counts on the session -contexts. - -To Do -===== - -Add L2TP tunnel switching support. This would route tunneled traffic -from one L2TP tunnel into another. Specified in -http://tools.ietf.org/html/draft-ietf-l2tpext-tunnel-switching-08 - -Add L2TPv3 VLAN pseudowire support. - -Add L2TPv3 IP pseudowire support. - -Add L2TPv3 ATM pseudowire support. +This section is for kernel developers and maintainers. + +Sockets +------- + +UDP sockets are implemented by the networking core. When an L2TP +tunnel is created using a UDP socket, the socket is set up as an +encapsulated UDP socket by setting encap_rcv and encap_destroy +callbacks on the UDP socket. l2tp_udp_encap_recv is called when +packets are received on the socket. l2tp_udp_encap_destroy is called +when userspace closes the socket. + +L2TPIP sockets are implemented in `net/l2tp/l2tp_ip.c`_ and +`net/l2tp/l2tp_ip6.c`_. + +Tunnels +------- + +The kernel keeps a struct l2tp_tunnel context per L2TP tunnel. The +l2tp_tunnel is always associated with a UDP or L2TP/IP socket and +keeps a list of sessions in the tunnel. When a tunnel is first +registered with L2TP core, the reference count on the socket is +increased. This ensures that the socket cannot be removed while L2TP's +data structures reference it. + +Tunnels are identified by a unique tunnel id. The id is 16-bit for +L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit +value. + +Tunnels are kept in a per-net list, indexed by tunnel id. The tunnel +id namespace is shared by L2TPv2 and L2TPv3. The tunnel context can be +derived from the socket's sk_user_data. + +Handling tunnel socket close is perhaps the most tricky part of the +L2TP implementation. If userspace closes a tunnel socket, the L2TP +tunnel and all of its sessions must be closed and destroyed. Since the +tunnel context holds a ref on the tunnel socket, the socket's +sk_destruct won't be called until the tunnel sock_put's its +socket. For UDP sockets, when userspace closes the tunnel socket, the +socket's encap_destroy handler is invoked, which L2TP uses to initiate +its tunnel close actions. For L2TPIP sockets, the socket's close +handler initiates the same tunnel close actions. All sessions are +first closed. Each session drops its tunnel ref. When the tunnel ref +reaches zero, the tunnel puts its socket ref. When the socket is +eventually destroyed, it's sk_destruct finally frees the L2TP tunnel +context. + +Sessions +-------- + +The kernel keeps a struct l2tp_session context for each session. Each +session has private data which is used for data specific to the +session type. With L2TPv2, the session always carries PPP +traffic. With L2TPv3, the session can carry Ethernet frames (Ethernet +pseudowire) or other data types such as PPP, ATM, HDLC or Frame +Relay. Linux currently implements only Ethernet and PPP session types. + +Some L2TP session types also have a socket (PPP pseudowires) while +others do not (Ethernet pseudowires). We can't therefore use the +socket reference count as the reference count for session +contexts. The L2TP implementation therefore has its own internal +reference counts on the session contexts. + +Like tunnels, L2TP sessions are identified by a unique +session id. Just as with tunnel ids, the session id is 16-bit for +L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit +value. + +Sessions hold a ref on their parent tunnel to ensure that the tunnel +stays extant while one or more sessions references it. + +Sessions are kept in a per-tunnel list, indexed by session id. L2TPv3 +sessions are also kept in a per-net list indexed by session id, +because L2TPv3 session ids are unique across all tunnels and L2TPv3 +data packets do not contain a tunnel id in the header. This list is +therefore needed to find the session context associated with a +received data packet when the tunnel context cannot be derived from +the tunnel socket. + +Although the L2TPv3 RFC specifies that L2TPv3 session ids are not +scoped by the tunnel, the kernel does not police this for L2TPv3 UDP +tunnels and does not add sessions of L2TPv3 UDP tunnels into the +per-net session list. In the UDP receive code, we must trust that the +tunnel can be identified using the tunnel socket's sk_user_data and +lookup the session in the tunnel's session list instead of the per-net +session list. + +PPP +--- + +`net/l2tp/l2tp_ppp.c`_ implements the PPPoL2TP socket family. Each PPP +session has a PPPoL2TP socket. + +The PPPoL2TP socket's sk_user_data references the l2tp_session. + +Userspace sends and receives PPP packets over L2TP using a PPPoL2TP +socket. Only PPP control frames pass over this socket: PPP data +packets are handled entirely by the kernel, passing between the L2TP +session and its associated ``pppN`` netdev through the PPP channel +interface of the kernel PPP subsystem. + +The L2TP PPP implementation handles the closing of a PPPoL2TP socket +by closing its corresponding L2TP session. This is complicated because +it must consider racing with netlink session create/destroy requests +and pppol2tp_connect trying to reconnect with a session that is in the +process of being closed. Unlike tunnels, PPP sessions do not hold a +ref on their associated socket, so code must be careful to sock_hold +the socket where necessary. For all the details, see commit +3d609342cc04129ff7568e19316ce3d7451a27e8. + +Ethernet +-------- + +`net/l2tp/l2tp_eth.c`_ implements L2TPv3 Ethernet pseudowires. It +manages a netdev for each session. + +L2TP Ethernet sessions are created and destroyed by netlink request, +or are destroyed when the tunnel is destroyed. Unlike PPP sessions, +Ethernet sessions do not have an associated socket. Miscellaneous ============= -The L2TP drivers were developed as part of the OpenL2TP project by -Katalix Systems Ltd. OpenL2TP is a full-featured L2TP client / server, -designed from the ground up to have the L2TP datapath in the -kernel. The project also implemented the pppol2tp plugin for pppd -which allows pppd to use the kernel driver. Details can be found at -http://www.openl2tp.org. +RFCs +---- + +The kernel code implements the datapath features specified in the +following RFCs: + +======= =============== =================================== +RFC2661 L2TPv2 https://tools.ietf.org/html/rfc2661 +RFC3931 L2TPv3 https://tools.ietf.org/html/rfc3931 +RFC4719 L2TPv3 Ethernet https://tools.ietf.org/html/rfc4719 +======= =============== =================================== + +Implementations +--------------- + +A number of open source applications use the L2TP kernel subsystem: + +============ ============================================== +iproute2 https://github.com/shemminger/iproute2 +go-l2tp https://github.com/katalix/go-l2tp +tunneldigger https://github.com/wlanslovenija/tunneldigger +xl2tpd https://github.com/xelerance/xl2tpd +============ ============================================== + +Limitations +----------- + +The current implementation has a number of limitations: + + 1) Multiple UDP sockets with the same 5-tuple address cannot be + used. The kernel's tunnel context is identified using private + data associated with the socket so it is important that each + socket is uniquely identified by its address. + + 2) Interfacing with openvswitch is not yet implemented. It may be + useful to map OVS Ethernet and VLAN ports into L2TPv3 tunnels. + + 3) VLAN pseudowires are implemented using an ``l2tpethN`` interface + configured with a VLAN sub-interface. Since L2TPv3 VLAN + pseudowires carry one and only one VLAN, it may be better to use + a single netdevice rather than an ``l2tpethN`` and ``l2tpethN``:M + pair per VLAN session. The netlink attribute + ``L2TP_ATTR_VLAN_ID`` was added for this, but it was never + implemented. + +Testing +------- + +Unmanaged L2TPv3 Ethernet features are tested by the kernel's built-in +selftests. See `tools/testing/selftests/net/l2tp.sh`_. + +Another test suite, l2tp-ktest_, covers all +of the L2TP APIs and tunnel/session types. This may be integrated into +the kernel's built-in L2TP selftests in the future. + +.. Links +.. _Generic Netlink: generic_netlink.html +.. _libmnl: https://www.netfilter.org/projects/libmnl +.. _include/uapi/linux/l2tp.h: ../../../include/uapi/linux/l2tp.h +.. _include/linux/if_pppol2tp.h: ../../../include/linux/if_pppol2tp.h +.. _net/l2tp/l2tp_ip.c: ../../../net/l2tp/l2tp_ip.c +.. _net/l2tp/l2tp_ip6.c: ../../../net/l2tp/l2tp_ip6.c +.. _net/l2tp/l2tp_ppp.c: ../../../net/l2tp/l2tp_ppp.c +.. _net/l2tp/l2tp_eth.c: ../../../net/l2tp/l2tp_eth.c +.. _tools/testing/selftests/net/l2tp.sh: ../../../tools/testing/selftests/net/l2tp.sh +.. _l2tp-ktest: https://github.com/katalix/l2tp-ktest diff --git a/MAINTAINERS b/MAINTAINERS index deaafb617361..a1c15b6714a0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1286,7 +1286,7 @@ S: Supported F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt F: drivers/net/ethernet/apm/xgene/ -F: drivers/net/phy/mdio-xgene.c +F: drivers/net/mdio/mdio-xgene.c APPLIED MICRO (APM) X-GENE SOC PMU M: Khuong Dinh <[email protected]> @@ -4692,6 +4692,15 @@ S: Supported W: http://www.chelsio.com F: drivers/crypto/chelsio +CXGB4 INLINE CRYPTO DRIVER +M: Ayush Sawal <[email protected]> +M: Vinay Kumar Yadav <[email protected]> +M: Rohit Maheshwari <[email protected]> +S: Supported +W: http://www.chelsio.com +F: drivers/net/ethernet/chelsio/inline_crypto/ + CXGB4 ETHERNET DRIVER (CXGB4) M: Vishal Kulkarni <[email protected]> @@ -5050,7 +5059,7 @@ F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h DEVLINK -M: Jiri Pirko <[email protected]> +M: Jiri Pirko <[email protected]> S: Supported F: Documentation/networking/devlink @@ -6081,7 +6090,7 @@ F: include/linux/dynamic_debug.h F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION -M: Tal Gilboa <[email protected]> +M: Tal Gilboa <[email protected]> S: Maintained F: Documentation/networking/net_dim.rst F: include/linux/dim.h @@ -6161,7 +6170,7 @@ F: Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt F: drivers/edac/aspeed_edac.c EDAC-BLUEFIELD -M: Shravan Kumar Ramani <[email protected]> +M: Shravan Kumar Ramani <[email protected]> S: Supported F: drivers/edac/bluefield_edac.c @@ -6483,8 +6492,8 @@ S: Odd Fixes F: drivers/net/ethernet/agere/ ETHERNET BRIDGE -M: Roopa Prabhu <[email protected]> -M: Nikolay Aleksandrov <[email protected]> +M: Roopa Prabhu <[email protected]> +M: Nikolay Aleksandrov <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained @@ -6504,11 +6513,14 @@ F: Documentation/devicetree/bindings/net/ethernet-phy.yaml F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst +F: drivers/net/mdio/ +F: drivers/net/pcs/ F: drivers/net/phy/ F: drivers/of/of_mdio.c F: drivers/of/of_net.c F: include/dt-bindings/net/qca-ar803x.h F: include/linux/*mdio*.h +F: include/linux/mdio/*.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h @@ -6599,7 +6611,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <[email protected]> -M: Ofer Levi <[email protected]> +M: Ofer Levi <[email protected]> S: Supported F: arch/arc/boot/dts/eznps.dts F: arch/arc/plat-eznps @@ -8563,7 +8575,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Doug Ledford <[email protected]> -M: Jason Gunthorpe <[email protected]> +M: Jason Gunthorpe <[email protected]> S: Supported W: https://github.com/linux-rdma/rdma-core @@ -9226,7 +9238,7 @@ F: drivers/firmware/iscsi_ibft* ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR M: Sagi Grimberg <[email protected]> -M: Max Gurtovoy <[email protected]> +M: Max Gurtovoy <[email protected]> S: Supported W: http://www.openfabrics.org @@ -10281,6 +10293,13 @@ S: Maintained W: http://linux-test-project.github.io/ T: git git://github.com/linux-test-project/ltp.git +LYNX PCS MODULE +M: Ioana Ciornei <[email protected]> +S: Supported +F: drivers/net/phy/pcs-lynx.c +F: include/linux/pcs-lynx.h + M68K ARCHITECTURE M: Geert Uytterhoeven <[email protected]> @@ -10488,7 +10507,7 @@ M: Tobias Waldekranz <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/marvell,mvusb.yaml -F: drivers/net/phy/mdio-mvusb.c +F: drivers/net/mdio/mdio-mvusb.c MARVELL XENON MMC/SD/SDIO HOST CONTROLLER DRIVER M: Hu Ziji <[email protected]> @@ -11072,7 +11091,7 @@ F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt F: drivers/input/touchscreen/melfas_mip4.c MELLANOX ETHERNET DRIVER (mlx4_en) -M: Tariq Toukan <[email protected]> +M: Tariq Toukan <[email protected]> S: Supported W: http://www.mellanox.com @@ -11080,7 +11099,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) -M: Saeed Mahameed <[email protected]> +M: Saeed Mahameed <[email protected]> S: Supported W: http://www.mellanox.com @@ -11088,7 +11107,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS -R: Boris Pismenny <[email protected]> +R: Boris Pismenny <[email protected]> S: Supported W: http://www.mellanox.com @@ -11099,8 +11118,8 @@ F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h MELLANOX ETHERNET SWITCH DRIVERS -M: Jiri Pirko <[email protected]> -M: Ido Schimmel <[email protected]> +M: Jiri Pirko <[email protected]> +M: Ido Schimmel <[email protected]> S: Supported W: http://www.mellanox.com @@ -11109,7 +11128,7 @@ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) S: Supported W: http://www.mellanox.com @@ -11119,7 +11138,7 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Andy Shevchenko <[email protected]> M: Darren Hart <[email protected]> -M: Vadim Pasternak <[email protected]> +M: Vadim Pasternak <[email protected]> S: Supported F: Documentation/ABI/testing/sysfs-platform-mellanox-bootctl @@ -11127,7 +11146,7 @@ F: drivers/platform/mellanox/ F: include/linux/platform_data/mlxreg.h MELLANOX MLX4 core VPI driver -M: Tariq Toukan <[email protected]> +M: Tariq Toukan <[email protected]> S: Supported @@ -11137,7 +11156,7 @@ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ MELLANOX MLX4 IB driver -M: Yishai Hadas <[email protected]> +M: Yishai Hadas <[email protected]> S: Supported W: http://www.mellanox.com @@ -11147,8 +11166,8 @@ F: include/linux/mlx4/ F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX5 core VPI driver -M: Saeed Mahameed <[email protected]> -M: Leon Romanovsky <[email protected]> +M: Saeed Mahameed <[email protected]> +M: Leon Romanovsky <[email protected]> S: Supported @@ -11159,7 +11178,7 @@ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ MELLANOX MLX5 IB driver -M: Leon Romanovsky <[email protected]> +M: Leon Romanovsky <[email protected]> S: Supported W: http://www.mellanox.com @@ -11169,8 +11188,8 @@ F: include/linux/mlx5/ F: include/uapi/rdma/mlx5-abi.h MELLANOX MLXCPLD I2C AND MUX DRIVER -M: Vadim Pasternak <[email protected]> -M: Michael Shych <[email protected]> +M: Vadim Pasternak <[email protected]> +M: Michael Shych <[email protected]> S: Supported F: Documentation/i2c/busses/i2c-mlxcpld.rst @@ -11178,7 +11197,7 @@ F: drivers/i2c/busses/i2c-mlxcpld.c F: drivers/i2c/muxes/i2c-mux-mlxcpld.c MELLANOX MLXCPLD LED DRIVER -M: Vadim Pasternak <[email protected]> +M: Vadim Pasternak <[email protected]> S: Supported F: Documentation/leds/leds-mlxcpld.rst @@ -11186,7 +11205,7 @@ F: drivers/leds/leds-mlxcpld.c F: drivers/leds/leds-mlxreg.c MELLANOX PLATFORM DRIVER -M: Vadim Pasternak <[email protected]> +M: Vadim Pasternak <[email protected]> S: Supported F: drivers/platform/x86/mlx-platform.c @@ -12167,8 +12186,8 @@ F: net/ipv6/syncookies.c F: net/ipv6/tcp*.c NETWORKING [TLS] -M: Boris Pismenny <[email protected]> -M: Aviad Yehezkel <[email protected]> +M: Boris Pismenny <[email protected]> +M: Aviad Yehezkel <[email protected]> M: John Fastabend <[email protected]> M: Daniel Borkmann <[email protected]> M: Jakub Kicinski <[email protected]> @@ -12468,7 +12487,7 @@ S: Supported F: drivers/nfc/nxp-nci OBJAGG -M: Jiri Pirko <[email protected]> +M: Jiri Pirko <[email protected]> S: Supported F: include/linux/objagg.h @@ -13110,7 +13129,7 @@ F: drivers/video/logo/logo_parisc* F: include/linux/hp_sdc.h PARMAN -M: Jiri Pirko <[email protected]> +M: Jiri Pirko <[email protected]> S: Supported F: include/linux/parman.h @@ -15637,6 +15656,7 @@ L: [email protected] S: Maintained F: drivers/net/phy/phylink.c F: drivers/net/phy/sfp* +F: include/linux/mdio/mdio-i2c.h F: include/linux/phylink.h F: include/linux/sfp.h K: phylink\.h|struct\s+phylink|\.phylink|>phylink_|phylink_(autoneg|clear|connect|create|destroy|disconnect|ethtool|helper|mac|mii|of|set|start|stop|test|validate) @@ -16034,7 +16054,7 @@ F: drivers/infiniband/sw/siw/ F: include/uapi/rdma/siw-abi.h SOFT-ROCE DRIVER (rxe) -M: Zhu Yanjun <[email protected]> +M: Zhu Yanjun <[email protected]> S: Supported F: drivers/infiniband/sw/rxe/ @@ -16721,8 +16741,8 @@ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER M: Jose Abreu <[email protected]> S: Supported -F: drivers/net/phy/mdio-xpcs.c -F: include/linux/mdio-xpcs.h +F: drivers/net/pcs/pcs-xpcs.c +F: include/linux/pcs/pcs-xpcs.h SYNOPSYS DESIGNWARE I2C DRIVER M: Jarkko Nikula <[email protected]> @@ -265,8 +265,7 @@ no-dot-config-targets := $(clean-targets) \ $(version_h) headers headers_% archheaders archscripts \ %asm-generic kernelversion %src-pkg dt_binding_check \ outputmakefile -no-sync-config-targets := $(no-dot-config-targets) install %install \ - kernelrelease +no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ config-build := @@ -292,7 +291,7 @@ ifneq ($(KBUILD_EXTMOD),) endif ifeq ($(KBUILD_EXTMOD),) - ifneq ($(filter config %config,$(MAKECMDGOALS)),) + ifneq ($(filter %config,$(MAKECMDGOALS)),) config-build := 1 ifneq ($(words $(MAKECMDGOALS)),1) mixed-build := 1 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 55bc8546d9c7..b45f0124cc16 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -165,6 +165,7 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@ # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 65568b23868a..e52c927aade5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -473,7 +473,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6bd1d3ad037a..c332d49780dc 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), + .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2646178c8329..55af8b504b65 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -170,19 +170,6 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 - .if \regsize == 32 - /* - * If we're returning from a 32-bit task on a system affected by - * 1418040 then re-enable userspace access to the virtual counter. - */ -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 @@ -294,14 +281,6 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 84ec630b8ab5..b63ce4c54cfe 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -516,6 +516,39 @@ static void entry_task_switch(struct task_struct *next) } /* + * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. + * Assuming the virtual counter is enabled at the beginning of times: + * + * - disable access when switching from a 64bit task to a 32bit task + * - enable access when switching from a 32bit task to a 64bit task + */ +static void erratum_1418040_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + bool prev32, next32; + u64 val; + + if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + return; + + prev32 = is_compat_thread(task_thread_info(prev)); + next32 = is_compat_thread(task_thread_info(next)); + + if (prev32 == next32) + return; + + val = read_sysreg(cntkctl_el1); + + if (!next32) + val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + else + val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + + write_sysreg(val, cntkctl_el1); +} + +/* * Thread switching. */ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, @@ -530,6 +563,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); + erratum_1418040_thread_switch(prev, next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 5139a5f19256..d6adb4677c25 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ # Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ +quiet_cmd_vdso_install = INSTALL32 $@ cmd_vdso_install = cp $(obj)/[email protected] $(MODLIB)/vdso/vdso32.so vdso.so: $(obj)/vdso.so.dbg diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 691d21e4c717..46dc3d75cf13 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1640,6 +1640,10 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)) + kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ + "Only trusted guests should be used on this system.\n"); + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0121ef2c7c8d..ba00bcc0c884 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -343,7 +343,8 @@ static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, + bool may_block) { struct kvm *kvm = mmu->kvm; pgd_t *pgd; @@ -369,11 +370,16 @@ static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. */ - if (next != end) + if (may_block && next != end) cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } +static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +{ + __unmap_stage2_range(mmu, start, size, true); +} + static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -2208,18 +2214,21 @@ static int handle_hva_to_gpa(struct kvm *kvm, static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(&kvm->arch.mmu, gpa, size); + unsigned flags = *(unsigned *)data; + bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE; + + __unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block); return 0; } int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, unsigned flags) { if (!kvm->arch.mmu.pgd) return 0; trace_kvm_unmap_hva_range(start, end); - handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags); return 0; } diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 10850897a91c..779b6972aa84 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -366,6 +366,15 @@ pgd_index (unsigned long address) } #define pgd_index pgd_index +/* + * In the kernel's mapped region we know everything is in region number 5, so + * as an optimisation its PGD already points to the area for that region. + * However, this also means that we cannot use pgd_index() and we must + * never add the region here. + */ +#define pgd_offset_k(addr) \ + (init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))) + /* Look up a pgd entry in the gate area. On IA-64, the gate-area resides in the kernel-mapped segment, hence we use pgd_offset_k() here. */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index d35eaed1668f..825d337a505a 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -969,7 +969,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 87fa8d8a1031..28c366d307e7 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -486,7 +486,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fdddb822d564..e005b4581023 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,6 +9,11 @@ #ifndef __ASSEMBLY__ +/* + * Added to include __machine_check_early_realmode_* functions + */ +#include <asm/mce.h> + /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 925cf89cbf4b..6bfc87915d5d 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index d635b96c7ea6..7355ed05e65e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -15,11 +15,18 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e020d269416d..10ded83414de 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index adf2cda67f9a..89aa8248a57d 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,6 +210,9 @@ struct mce_error_info { #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 1e8b2e1ec1db..daec64d41b44 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; } /* To support perf_regs sier update */ extern bool is_sier_available(void); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 86c9eb064b22..f6acabb6c9be 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -62,6 +62,11 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; }; /* diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..bdf5f10f8b9f 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,24 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + /* Max regs without the extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */ +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK) +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */ +#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK) + +#define PERF_REG_MAX_ISA_300 (PERF_REG_POWERPC_MMCR2 + 1) +#define PERF_REG_MAX_ISA_31 (PERF_REG_POWERPC_SIER3 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3d406a9626e8..2aa89c6b2896 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power10(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power10", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 6f8c0c6b937a..8dc46f38680b 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -64,10 +64,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -extern long __machine_check_early_realmode_p10(struct pt_regs *regs); - static int hv_mode; static struct { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b198b0ff25bc..808ec9fab605 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) min = pvr & 0xFF; break; case 0x004e: /* POWER9 bits 12-15 give chip type */ + case 0x0080: /* POWER10 bit 12 gives SMT8/4 */ maj = (pvr >> 8) & 0x0F; min = pvr & 0xFF; break; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 41fedec69ac3..49db50d1db04 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index d6c1069e9954..ed0c9c43d0cf 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index c0162911f6cb..d426eaf76bb0 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr) { if (!IS_ENABLED(CONFIG_MODULES)) return false; +#ifdef MODULES_VADDR + if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M)) + return false; + if (addr > ALIGN(MODULES_END, SZ_256M) - 1) + return false; +#else if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) return false; - if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1) return false; +#endif return true; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 1da9dbba9217..890a71c5293e 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1115,8 +1115,10 @@ void hash__early_init_mmu_secondary(void) && cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); - if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY)) +#ifdef CONFIG_PPC_MEM_KEYS + if (mmu_has_feature(MMU_FTR_PKEY)) mtspr(SPRN_UAMOR, default_uamor); +#endif } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 78fe34986594..93d20e1ed845 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2141,6 +2141,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } @@ -2323,6 +2327,7 @@ int register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV /* diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cdb7bfbd157e..6e7e820508df 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, @@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, - &dev_attr_cpumask.attr, NULL, }; @@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = { &event_desc_group, &event_long_desc_group, &if_group, + &cpumask_attr_group, NULL, }; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index a213a0aa5d25..8e53f2fc3fe0 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -13,9 +13,11 @@ #include <asm/ptrace.h> #include <asm/perf_regs.h> +u64 PERF_REG_EXTENDED_MASK; + #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) -#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1)) +#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK)) static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]), @@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; +/* Function to return the extended register values */ +static u64 get_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_POWERPC_MMCR0: + return mfspr(SPRN_MMCR0); + case PERF_REG_POWERPC_MMCR1: + return mfspr(SPRN_MMCR1); + case PERF_REG_POWERPC_MMCR2: + return mfspr(SPRN_MMCR2); +#ifdef CONFIG_PPC64 + case PERF_REG_POWERPC_MMCR3: + return mfspr(SPRN_MMCR3); + case PERF_REG_POWERPC_SIER2: + return mfspr(SPRN_SIER2); + case PERF_REG_POWERPC_SIER3: + return mfspr(SPRN_SIER3); +#endif + default: return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) - return 0; + u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + perf_reg_extended_max = PERF_REG_MAX_ISA_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + perf_reg_extended_max = PERF_REG_MAX_ISA_300; if (idx == PERF_REG_POWERPC_SIER && (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || @@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) IS_ENABLED(CONFIG_PPC32))) return 0; + if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max) + return get_ext_regs_value(idx); + + /* + * If the idx is referring to value beyond the + * supported registers, return 0 with a warning + */ + if (WARN_ON_ONCE(idx >= perf_reg_extended_max)) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f7cff7f36a1c..83148656b524 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -87,6 +87,8 @@ #define POWER10_MMCRA_IFM3 0x00000000C0000000UL #define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { { PM_RUN_CYC_ALT, PM_RUN_CYC }, @@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = { .cache_events = &power10_cache_events, .attr_groups = power10_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power10_pmu(void) @@ -408,6 +411,9 @@ int init_power10_pmu(void) strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) return -ENODEV; + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + rc = register_power_pmu(&power10_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 05dae38b969a..2a57e93a79dc 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -90,6 +90,8 @@ enum { #define POWER9_MMCRA_IFM3 0x00000000C0000000UL #define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = { .cache_events = &power9_cache_events, .attr_groups = power9_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power9_pmu(void) @@ -457,6 +460,9 @@ int init_power9_pmu(void) } } + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300; + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c9c25fb0783c..023a4f987bb2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (pe->dma_setup_done) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index c6e0d8abf75e..7a974ed6b240 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -107,22 +107,28 @@ static int pseries_cpu_disable(void) */ static void pseries_cpu_die(unsigned int cpu) { - int tries; int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); + unsigned long timeout = jiffies + msecs_to_jiffies(120000); - for (tries = 0; tries < 25; tries++) { + while (true) { cpu_status = smp_query_cpu_stopped(pcpu); if (cpu_status == QCSS_STOPPED || cpu_status == QCSS_HARDWARE_ERROR) break; - cpu_relax(); + if (time_after(jiffies, timeout)) { + pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n", + cpu, pcpu); + timeout = jiffies + msecs_to_jiffies(120000); + } + + cond_resched(); } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); + if (cpu_status == QCSS_HARDWARE_ERROR) { + pr_warn("CPU %i (hwid %i) reported error while dying\n", + cpu, pcpu); } /* Isolation and deallocation are definitely done by diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f3736fcd98fc..13c86a292c6d 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7b5905529146..df18372861d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -81,7 +81,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_INTC - select RISCV_TIMER + select RISCV_TIMER if RISCV_SBI select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6c88148f1b9b..8a55f6156661 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -12,6 +12,7 @@ config SOC_SIFIVE config SOC_VIRT bool "QEMU Virt Machine" + select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -24,6 +25,7 @@ config SOC_VIRT config SOC_KENDRYTE bool "Kendryte K210 SoC" depends on !MMU + select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index f27596e9663e..e046a0babde4 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -26,6 +26,7 @@ CONFIG_EXPERT=y CONFIG_SLOB=y # CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set +CONFIG_SOC_VIRT=y CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" @@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set -# CONFIG_DEVMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y @@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1 CONFIG_SERIAL_8250_RUNTIME_UARTS=1 CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_SIFIVE_PLIC=y -# CONFIG_VALIDATE_FS_PARSER is not set CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 3a55f0e00d6c..2c2cda6cc1c5 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y @@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y @@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h deleted file mode 100644 index a279b17a6aad..000000000000 --- a/arch/riscv/include/asm/clint.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_RISCV_CLINT_H -#define _ASM_RISCV_CLINT_H 1 - -#include <linux/io.h> -#include <linux/smp.h> - -#ifdef CONFIG_RISCV_M_MODE -extern u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void); - -static inline void clint_send_ipi_single(unsigned long hartid) -{ - writel(1, clint_ipi_base + hartid); -} - -static inline void clint_send_ipi_mask(const struct cpumask *mask) -{ - int cpu; - - for_each_cpu(cpu, mask) - clint_send_ipi_single(cpuid_to_hartid_map(cpu)); -} - -static inline void clint_clear_ipi(unsigned long hartid) -{ - writel(0, clint_ipi_base + hartid); -} -#else /* CONFIG_RISCV_M_MODE */ -#define clint_init_boot_cpu() do { } while (0) - -/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */ -void clint_send_ipi_single(unsigned long hartid); -void clint_send_ipi_mask(const struct cpumask *hartid_mask); -void clint_clear_ipi(unsigned long hartid); -#endif /* CONFIG_RISCV_M_MODE */ - -#endif /* _ASM_RISCV_CLINT_H */ diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 6dfd2a1446d5..df1f7c4cd433 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -15,6 +15,11 @@ struct seq_file; extern unsigned long boot_cpu_hartid; +struct riscv_ipi_ops { + void (*ipi_inject)(const struct cpumask *target); + void (*ipi_clear)(void); +}; + #ifdef CONFIG_SMP /* * Mapping between linux logical cpu index and hartid. @@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu); int riscv_hartid_to_cpuid(int hartid); void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out); +/* Set custom IPI operations */ +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops); + +/* Clear IPI for current CPU */ +void riscv_clear_ipi(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); @@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in, cpumask_set_cpu(boot_cpu_hartid, out); } +static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ +} + +static inline void riscv_clear_ipi(void) +{ +} + #endif /* CONFIG_SMP */ #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index bad2a7c2cda5..a3fb85d505d4 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -7,41 +7,27 @@ #define _ASM_RISCV_TIMEX_H #include <asm/csr.h> -#include <asm/mmio.h> typedef unsigned long cycles_t; -extern u64 __iomem *riscv_time_val; -extern u64 __iomem *riscv_time_cmp; - -#ifdef CONFIG_64BIT -#define mmio_get_cycles() readq_relaxed(riscv_time_val) -#else -#define mmio_get_cycles() readl_relaxed(riscv_time_val) -#define mmio_get_cycles_hi() readl_relaxed(((u32 *)riscv_time_val) + 1) -#endif - static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIME); - return mmio_get_cycles(); + return csr_read(CSR_TIME); } #define get_cycles get_cycles +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { return get_cycles(); } #else /* CONFIG_64BIT */ -static inline u32 get_cycles_hi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIMEH); - return mmio_get_cycles_hi(); -} - static inline u64 get_cycles64(void) { u32 hi, lo; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a5287ab9f7f2..dc93710f0b2f 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,7 @@ obj-y += cacheinfo.o obj-y += patch.o obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o traps_misaligned.o +obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f383ef5672b2..226ccce0f9e0 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } +static void sbi_send_cpumask_ipi(const struct cpumask *target) +{ + struct cpumask hartid_mask; + + riscv_cpuid_to_hartid_mask(target, &hartid_mask); + + sbi_send_ipi(cpumask_bits(&hartid_mask)); +} + +static struct riscv_ipi_ops sbi_ipi_ops = { + .ipi_inject = sbi_send_cpumask_ipi +}; int __init sbi_init(void) { @@ -587,5 +599,7 @@ int __init sbi_init(void) __sbi_rfence = __sbi_rfence_v01; } + riscv_set_ipi_ops(&sbi_ipi_ops); + return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f04373be54a6..2c6dd329312b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -18,7 +18,6 @@ #include <linux/swiotlb.h> #include <linux/smp.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/setup.h> #include <asm/sections.h> @@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - clint_init_boot_cpu(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 554b0fb47060..ea028d9e0d24 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -18,7 +18,6 @@ #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/clint.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> @@ -86,9 +85,25 @@ static void ipi_stop(void) wait_for_interrupt(); } +static struct riscv_ipi_ops *ipi_ops; + +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ + ipi_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_ipi_ops); + +void riscv_clear_ipi(void) +{ + if (ipi_ops && ipi_ops->ipi_clear) + ipi_ops->ipi_clear(); + + csr_clear(CSR_IP, IE_SIE); +} +EXPORT_SYMBOL_GPL(riscv_clear_ipi); + static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - struct cpumask hartid_mask; int cpu; smp_mb__before_atomic(); @@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(mask); else - clint_send_ipi_mask(mask); + pr_warn("SMP: IPI inject method not available\n"); } static void send_ipi_single(int cpu, enum ipi_message_type op) { - int hartid = cpuid_to_hartid_map(cpu); - smp_mb__before_atomic(); set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); -} - -static inline void clear_ipi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(cpumask_of(cpu)); else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + pr_warn("SMP: IPI inject method not available\n"); } #ifdef CONFIG_IRQ_WORK @@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs) irq_enter(); - clear_ipi(); + riscv_clear_ipi(); while (true) { unsigned long ops; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 356825a57551..96167d55ed98 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/irq.h> #include <asm/mmu_context.h> @@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void) struct mm_struct *mm = &init_mm; unsigned int curr_cpuid = smp_processor_id(); - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + riscv_clear_ipi(); /* All kernel threads share the same mm context. */ mmgrab(mm); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 11d2f7d05f91..a76dd27fb2e8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3902c9f6f2d6..4b62d6b55024 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); +void zpci_remove_device(struct zpci_dev *zdev) +{ + struct zpci_bus *zbus = zdev->zbus; + struct pci_dev *pdev; + + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (pdev) { + if (pdev->is_virtfn) + return zpci_remove_virtfn(pdev, zdev->vfn); + pci_stop_and_remove_bus_device_locked(pdev); + } +} + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - if (zdev->zbus->bus) { - struct pci_dev *pdev; - - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); - } + if (zdev->zbus->bus) + zpci_remove_device(zdev); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 642a99384688..5967f3014156 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev, { int rc; - virtfn->physfn = pci_dev_get(pdev); rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) { - pci_dev_put(pdev); - virtfn->physfn = NULL; + if (rc) return rc; - } + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + return 0; } @@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ int rc = 0; - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - WARN_ON(vfid < 0); + if (!zbus->multifunction) + return 0; + /* If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what @@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, zdev = zbus->function[i]; if (zdev && zdev->is_physfn) { pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); if (cand_devfn == virtfn->devfn) { rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); break; } + /* balance pci_get_slot() */ + pci_dev_put(pdev); } } return rc; @@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) { - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; return 0; } #endif +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + /* + * With pdev->no_vf_scan the common PCI probing code does not + * perform PF/VF linking. + */ + if (zdev->vfn) + zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + +} + static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { struct pci_bus *bus; @@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) } pdev = pci_scan_single_device(bus, zdev->devfn); - if (pdev) { - if (!zdev->is_physfn) { - rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn); - if (rc) - goto failed_with_pdev; - } + if (pdev) pci_bus_add_device(pdev); - } - return 0; -failed_with_pdev: - pci_stop_and_remove_bus_device(pdev); - pci_dev_put(pdev); - return rc; + return 0; } static void zpci_bus_add_devices(struct zpci_bus *zbus) diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 89be3c354b7b..4972433df458 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } + +#ifdef CONFIG_PCI_IOV +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} +#else /* CONFIG_PCI_IOV */ +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} +#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index fdebd286f402..9a3a291cad43 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1); break; } + /* the configuration request may be stale */ + if (zdev->state != ZPCI_FN_STATE_STANDBY) + break; zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; ret = zpci_enable_device(zdev); @@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) break; if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); ret = zpci_disable_device(zdev); if (ret) @@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* Give the driver a hint that the function is * already unusable. */ pdev->error_state = pci_channel_io_perm_failure; - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); } zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ab3af7275d8..5303dbc5c9bc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void); _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e03841f053d..a5d0207e7189 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 599d73206299..33945283fe07 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,7 +975,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -10751,9 +10751,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct x86_exception fault; + u32 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) { + vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 3576ad7bd380..68b087bff59c 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -653,9 +653,8 @@ config ATCPIT100_TIMER This option enables support for the Andestech ATCPIT100 timers. config RISCV_TIMER - bool "Timer for the RISC-V platform" + bool "Timer for the RISC-V platform" if COMPILE_TEST depends on GENERIC_SCHED_CLOCK && RISCV - default y select TIMER_PROBE select TIMER_OF help @@ -663,6 +662,15 @@ config RISCV_TIMER is accessed via both the SBI and the rdcycle instruction. This is required for all RISC-V systems. +config CLINT_TIMER + bool "CLINT Timer for the RISC-V platform" if COMPILE_TEST + depends on GENERIC_SCHED_CLOCK && RISCV + select TIMER_PROBE + select TIMER_OF + help + This option enables the CLINT timer for RISC-V systems. The CLINT + driver is usually used for NoMMU RISC-V systems. + config CSKY_MP_TIMER bool "SMP Timer for the C-SKY platform" if COMPILE_TEST depends on CSKY diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index eaedb7240ae7..1c444cc3bb44 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -89,6 +89,7 @@ obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += timer-riscv.o +obj-$(CONFIG_CLINT_TIMER) += timer-clint.o obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c new file mode 100644 index 000000000000..8eeafa82c03d --- /dev/null +++ b/drivers/clocksource/timer-clint.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * + * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a + * CLINT MMIO timer device. + */ + +#define pr_fmt(fmt) "clint: " fmt +#include <linux/bitops.h> +#include <linux/clocksource.h> +#include <linux/clockchips.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/sched_clock.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> +#include <linux/smp.h> + +#define CLINT_IPI_OFF 0 +#define CLINT_TIMER_CMP_OFF 0x4000 +#define CLINT_TIMER_VAL_OFF 0xbff8 + +/* CLINT manages IPI and Timer for RISC-V M-mode */ +static u32 __iomem *clint_ipi_base; +static u64 __iomem *clint_timer_cmp; +static u64 __iomem *clint_timer_val; +static unsigned long clint_timer_freq; +static unsigned int clint_timer_irq; + +static void clint_send_ipi(const struct cpumask *target) +{ + unsigned int cpu; + + for_each_cpu(cpu, target) + writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu)); +} + +static void clint_clear_ipi(void) +{ + writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id())); +} + +static struct riscv_ipi_ops clint_ipi_ops = { + .ipi_inject = clint_send_ipi, + .ipi_clear = clint_clear_ipi, +}; + +#ifdef CONFIG_64BIT +#define clint_get_cycles() readq_relaxed(clint_timer_val) +#else +#define clint_get_cycles() readl_relaxed(clint_timer_val) +#define clint_get_cycles_hi() readl_relaxed(((u32 *)clint_timer_val) + 1) +#endif + +#ifdef CONFIG_64BIT +static u64 notrace clint_get_cycles64(void) +{ + return clint_get_cycles(); +} +#else /* CONFIG_64BIT */ +static u64 notrace clint_get_cycles64(void) +{ + u32 hi, lo; + + do { + hi = clint_get_cycles_hi(); + lo = clint_get_cycles(); + } while (hi != clint_get_cycles_hi()); + + return ((u64)hi << 32) | lo; +} +#endif /* CONFIG_64BIT */ + +static u64 clint_rdtime(struct clocksource *cs) +{ + return clint_get_cycles64(); +} + +static struct clocksource clint_clocksource = { + .name = "clint_clocksource", + .rating = 300, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clint_rdtime, +}; + +static int clint_clock_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + void __iomem *r = clint_timer_cmp + + cpuid_to_hartid_map(smp_processor_id()); + + csr_set(CSR_IE, IE_TIE); + writeq_relaxed(clint_get_cycles64() + delta, r); + return 0; +} + +static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = { + .name = "clint_clockevent", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 100, + .set_next_event = clint_clock_next_event, +}; + +static int clint_timer_starting_cpu(unsigned int cpu) +{ + struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu); + + ce->cpumask = cpumask_of(cpu); + clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff); + + enable_percpu_irq(clint_timer_irq, + irq_get_trigger_type(clint_timer_irq)); + return 0; +} + +static int clint_timer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(clint_timer_irq); + return 0; +} + +static irqreturn_t clint_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event); + + csr_clear(CSR_IE, IE_TIE); + evdev->event_handler(evdev); + + return IRQ_HANDLED; +} + +static int __init clint_timer_init_dt(struct device_node *np) +{ + int rc; + u32 i, nr_irqs; + void __iomem *base; + struct of_phandle_args oirq; + + /* + * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or + * RV_IRQ_SOFT. If it's anything else then we ignore the device. + */ + nr_irqs = of_irq_count(np); + for (i = 0; i < nr_irqs; i++) { + if (of_irq_parse_one(np, i, &oirq)) { + pr_err("%pOFP: failed to parse irq %d.\n", np, i); + continue; + } + + if ((oirq.args_count != 1) || + (oirq.args[0] != RV_IRQ_TIMER && + oirq.args[0] != RV_IRQ_SOFT)) { + pr_err("%pOFP: invalid irq %d (hwirq %d)\n", + np, i, oirq.args[0]); + return -ENODEV; + } + + /* Find parent irq domain and map timer irq */ + if (!clint_timer_irq && + oirq.args[0] == RV_IRQ_TIMER && + irq_find_host(oirq.np)) + clint_timer_irq = irq_of_parse_and_map(np, i); + } + + /* If CLINT timer irq not found then fail */ + if (!clint_timer_irq) { + pr_err("%pOFP: timer irq not found\n", np); + return -ENODEV; + } + + base = of_iomap(np, 0); + if (!base) { + pr_err("%pOFP: could not map registers\n", np); + return -ENODEV; + } + + clint_ipi_base = base + CLINT_IPI_OFF; + clint_timer_cmp = base + CLINT_TIMER_CMP_OFF; + clint_timer_val = base + CLINT_TIMER_VAL_OFF; + clint_timer_freq = riscv_timebase; + + pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq); + + rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq); + if (rc) { + pr_err("%pOFP: clocksource register failed [%d]\n", np, rc); + goto fail_iounmap; + } + + sched_clock_register(clint_get_cycles64, 64, clint_timer_freq); + + rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt, + "clint-timer", &clint_clock_event); + if (rc) { + pr_err("registering percpu irq failed [%d]\n", rc); + goto fail_iounmap; + } + + rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING, + "clockevents/clint/timer:starting", + clint_timer_starting_cpu, + clint_timer_dying_cpu); + if (rc) { + pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc); + goto fail_free_irq; + } + + riscv_set_ipi_ops(&clint_ipi_ops); + clint_clear_ipi(); + + return 0; + +fail_free_irq: + free_irq(clint_timer_irq, &clint_clock_event); +fail_iounmap: + iounmap(base); + return rc; +} + +TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt); +TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 9de1dabfb126..c51c5ed15aa7 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -19,26 +19,13 @@ #include <linux/of_irq.h> #include <asm/smp.h> #include <asm/sbi.h> - -u64 __iomem *riscv_time_cmp; -u64 __iomem *riscv_time_val; - -static inline void mmio_set_timer(u64 val) -{ - void __iomem *r; - - r = riscv_time_cmp + cpuid_to_hartid_map(smp_processor_id()); - writeq_relaxed(val, r); -} +#include <asm/timex.h> static int riscv_clock_next_event(unsigned long delta, struct clock_event_device *ce) { csr_set(CSR_IE, IE_TIE); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_set_timer(get_cycles64() + delta); - else - mmio_set_timer(get_cycles64() + delta); + sbi_set_timer(get_cycles64() + delta); return 0; } diff --git a/drivers/crypto/chelsio/Kconfig b/drivers/crypto/chelsio/Kconfig index 2984fdf51e85..af161dab49bd 100644 --- a/drivers/crypto/chelsio/Kconfig +++ b/drivers/crypto/chelsio/Kconfig @@ -22,27 +22,6 @@ config CRYPTO_DEV_CHELSIO To compile this driver as a module, choose M here: the module will be called chcr. -config CHELSIO_IPSEC_INLINE - bool "Chelsio IPSec XFRM Tx crypto offload" - depends on CHELSIO_T4 - depends on CRYPTO_DEV_CHELSIO - depends on XFRM_OFFLOAD - depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD - default n - help - Enable support for IPSec Tx Inline. - -config CRYPTO_DEV_CHELSIO_TLS - tristate "Chelsio Crypto Inline TLS Driver" - depends on CHELSIO_T4 - depends on TLS_TOE - select CRYPTO_DEV_CHELSIO - help - Support Chelsio Inline TLS with Chelsio crypto accelerator. - - To compile this driver as a module, choose M here: the module - will be called chtls. - config CHELSIO_TLS_DEVICE bool "Chelsio Inline KTLS Offload" depends on CHELSIO_T4 diff --git a/drivers/crypto/chelsio/Makefile b/drivers/crypto/chelsio/Makefile index 0e9d035927e9..f2e8e2fb4e60 100644 --- a/drivers/crypto/chelsio/Makefile +++ b/drivers/crypto/chelsio/Makefile @@ -6,5 +6,3 @@ chcr-objs := chcr_core.o chcr_algo.o #ifdef CONFIG_CHELSIO_TLS_DEVICE chcr-objs += chcr_ktls.o #endif -chcr-$(CONFIG_CHELSIO_IPSEC_INLINE) += chcr_ipsec.o -obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ diff --git a/drivers/crypto/chelsio/chcr_algo.h b/drivers/crypto/chelsio/chcr_algo.h index d4f6e010dc79..507aafe93f21 100644 --- a/drivers/crypto/chelsio/chcr_algo.h +++ b/drivers/crypto/chelsio/chcr_algo.h @@ -86,39 +86,6 @@ KEY_CONTEXT_OPAD_PRESENT_M) #define KEY_CONTEXT_OPAD_PRESENT_F KEY_CONTEXT_OPAD_PRESENT_V(1U) -#define TLS_KEYCTX_RXFLIT_CNT_S 24 -#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) - -#define TLS_KEYCTX_RXPROT_VER_S 20 -#define TLS_KEYCTX_RXPROT_VER_M 0xf -#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) - -#define TLS_KEYCTX_RXCIPH_MODE_S 16 -#define TLS_KEYCTX_RXCIPH_MODE_M 0xf -#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) - -#define TLS_KEYCTX_RXAUTH_MODE_S 12 -#define TLS_KEYCTX_RXAUTH_MODE_M 0xf -#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) - -#define TLS_KEYCTX_RXCIAU_CTRL_S 11 -#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) - -#define TLS_KEYCTX_RX_SEQCTR_S 9 -#define TLS_KEYCTX_RX_SEQCTR_M 0x3 -#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) - -#define TLS_KEYCTX_RX_VALID_S 8 -#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) - -#define TLS_KEYCTX_RXCK_SIZE_S 3 -#define TLS_KEYCTX_RXCK_SIZE_M 0x7 -#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) - -#define TLS_KEYCTX_RXMK_SIZE_S 0 -#define TLS_KEYCTX_RXMK_SIZE_M 0x7 -#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) - #define CHCR_HASH_MAX_DIGEST_SIZE 64 #define CHCR_MAX_SHA_DIGEST_SIZE 64 diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c index bd8dac806e7a..b3570b41a737 100644 --- a/drivers/crypto/chelsio/chcr_core.c +++ b/drivers/crypto/chelsio/chcr_core.c @@ -40,10 +40,6 @@ static const struct tlsdev_ops chcr_ktls_ops = { }; #endif -#ifdef CONFIG_CHELSIO_IPSEC_INLINE -static void update_netdev_features(void); -#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - static chcr_handler_func work_handlers[NUM_CPL_CMDS] = { [CPL_FW6_PLD] = cpl_fw6_pld_handler, #ifdef CONFIG_CHELSIO_TLS_DEVICE @@ -60,10 +56,8 @@ static struct cxgb4_uld_info chcr_uld_info = { .add = chcr_uld_add, .state_change = chcr_uld_state_change, .rx_handler = chcr_uld_rx_handler, -#if defined(CONFIG_CHELSIO_IPSEC_INLINE) || defined(CONFIG_CHELSIO_TLS_DEVICE) - .tx_handler = chcr_uld_tx_handler, -#endif /* CONFIG_CHELSIO_IPSEC_INLINE || CONFIG_CHELSIO_TLS_DEVICE */ #if defined(CONFIG_CHELSIO_TLS_DEVICE) + .tx_handler = chcr_uld_tx_handler, .tlsdev_ops = &chcr_ktls_ops, #endif }; @@ -241,19 +235,11 @@ int chcr_uld_rx_handler(void *handle, const __be64 *rsp, return 0; } -#if defined(CONFIG_CHELSIO_IPSEC_INLINE) || defined(CONFIG_CHELSIO_TLS_DEVICE) +#if defined(CONFIG_CHELSIO_TLS_DEVICE) int chcr_uld_tx_handler(struct sk_buff *skb, struct net_device *dev) { - /* In case if skb's decrypted bit is set, it's nic tls packet, else it's - * ipsec packet. - */ -#ifdef CONFIG_CHELSIO_TLS_DEVICE if (skb->decrypted) return chcr_ktls_xmit(skb, dev); -#endif -#ifdef CONFIG_CHELSIO_IPSEC_INLINE - return chcr_ipsec_xmit(skb, dev); -#endif return 0; } #endif /* CONFIG_CHELSIO_IPSEC_INLINE || CONFIG_CHELSIO_TLS_DEVICE */ @@ -305,24 +291,6 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state) return ret; } -#ifdef CONFIG_CHELSIO_IPSEC_INLINE -static void update_netdev_features(void) -{ - struct uld_ctx *u_ctx, *tmp; - - mutex_lock(&drv_data.drv_mutex); - list_for_each_entry_safe(u_ctx, tmp, &drv_data.inact_dev, entry) { - if (u_ctx->lldi.crypto & ULP_CRYPTO_IPSEC_INLINE) - chcr_add_xfrmops(&u_ctx->lldi); - } - list_for_each_entry_safe(u_ctx, tmp, &drv_data.act_dev, entry) { - if (u_ctx->lldi.crypto & ULP_CRYPTO_IPSEC_INLINE) - chcr_add_xfrmops(&u_ctx->lldi); - } - mutex_unlock(&drv_data.drv_mutex); -} -#endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - static int __init chcr_crypto_init(void) { INIT_LIST_HEAD(&drv_data.act_dev); @@ -332,12 +300,6 @@ static int __init chcr_crypto_init(void) drv_data.last_dev = NULL; cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info); - #ifdef CONFIG_CHELSIO_IPSEC_INLINE - rtnl_lock(); - update_netdev_features(); - rtnl_unlock(); - #endif /* CONFIG_CHELSIO_IPSEC_INLINE */ - return 0; } diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h index 67d77abd6775..81f6e61401e5 100644 --- a/drivers/crypto/chelsio/chcr_core.h +++ b/drivers/crypto/chelsio/chcr_core.h @@ -72,54 +72,6 @@ struct _key_ctx { unsigned char key[]; }; -#define KEYCTX_TX_WR_IV_S 55 -#define KEYCTX_TX_WR_IV_M 0x1ffULL -#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) -#define KEYCTX_TX_WR_IV_G(x) \ - (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) - -#define KEYCTX_TX_WR_AAD_S 47 -#define KEYCTX_TX_WR_AAD_M 0xffULL -#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) -#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ - KEYCTX_TX_WR_AAD_M) - -#define KEYCTX_TX_WR_AADST_S 39 -#define KEYCTX_TX_WR_AADST_M 0xffULL -#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) -#define KEYCTX_TX_WR_AADST_G(x) \ - (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) - -#define KEYCTX_TX_WR_CIPHER_S 30 -#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL -#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) -#define KEYCTX_TX_WR_CIPHER_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) - -#define KEYCTX_TX_WR_CIPHERST_S 23 -#define KEYCTX_TX_WR_CIPHERST_M 0x7f -#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) -#define KEYCTX_TX_WR_CIPHERST_G(x) \ - (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) - -#define KEYCTX_TX_WR_AUTH_S 14 -#define KEYCTX_TX_WR_AUTH_M 0x1ff -#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) -#define KEYCTX_TX_WR_AUTH_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) - -#define KEYCTX_TX_WR_AUTHST_S 7 -#define KEYCTX_TX_WR_AUTHST_M 0x7f -#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) -#define KEYCTX_TX_WR_AUTHST_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) - -#define KEYCTX_TX_WR_AUTHIN_S 0 -#define KEYCTX_TX_WR_AUTHIN_M 0x7f -#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) -#define KEYCTX_TX_WR_AUTHIN_G(x) \ - (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) - #define WQ_RETRY 5 struct chcr_driver_data { struct list_head act_dev; @@ -157,42 +109,6 @@ struct uld_ctx { struct chcr_dev dev; }; -struct sge_opaque_hdr { - void *dev; - dma_addr_t addr[MAX_SKB_FRAGS + 1]; -}; - -struct chcr_ipsec_req { - struct ulp_txpkt ulptx; - struct ulptx_idata sc_imm; - struct cpl_tx_sec_pdu sec_cpl; - struct _key_ctx key_ctx; -}; - -struct chcr_ipsec_wr { - struct fw_ulptx_wr wreq; - struct chcr_ipsec_req req; -}; - -#define ESN_IV_INSERT_OFFSET 12 -struct chcr_ipsec_aadiv { - __be32 spi; - u8 seq_no[8]; - u8 iv[8]; -}; - -struct ipsec_sa_entry { - int hmac_ctrl; - u16 esn; - u16 resv; - unsigned int enckey_len; - unsigned int kctx_len; - unsigned int authsize; - __be32 key_ctx_hdr; - char salt[MAX_SALT]; - char key[2 * AES_MAX_KEY_SIZE]; -}; - /* * sgl_len - calculates the size of an SGL of the given capacity * @n: the number of SGL entries diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 5860ca41185c..2acd9f9284a2 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1710,9 +1710,9 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) - tp_event = HW_EVENT_ERR_FATAL; - else tp_event = HW_EVENT_ERR_UNCORRECTED; + else + tp_event = HW_EVENT_ERR_FATAL; } else { tp_event = HW_EVENT_ERR_CORRECTED; } diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index fd363746f5b0..b8fc4b84fd86 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -1155,7 +1155,7 @@ static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m, u32 optypenum = GET_BITFIELD(m->status, 4, 6); int rc; - tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) : + tp_event = uc_err ? (ripv ? HW_EVENT_ERR_UNCORRECTED : HW_EVENT_ERR_FATAL) : HW_EVENT_ERR_CORRECTED; /* diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index d414698ca324..c5ab634cb6a4 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2982,9 +2982,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 6d8d6dc626bf..2b4ce8e5ac2f 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -493,9 +493,9 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index fdd1db025dbf..3aa07c3b5136 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -381,6 +381,7 @@ static int __init efisubsys_init(void) efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { pr_err("efi: Firmware registration failed.\n"); + destroy_workqueue(efi_rts_wq); return -ENOMEM; } @@ -424,6 +425,7 @@ err_unregister: generic_ops_unregister(); err_put: kobject_put(efi_kobj); + destroy_workqueue(efi_rts_wq); return error; } diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 6bca70bbb43d..f735db55adc0 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -187,20 +187,28 @@ int efi_printk(const char *fmt, ...) */ efi_status_t efi_parse_options(char const *cmdline) { - size_t len = strlen(cmdline) + 1; + size_t len; efi_status_t status; char *str, *buf; + if (!cmdline) + return EFI_SUCCESS; + + len = strnlen(cmdline, COMMAND_LINE_SIZE - 1) + 1; status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, len, (void **)&buf); if (status != EFI_SUCCESS) return status; - str = skip_spaces(memcpy(buf, cmdline, len)); + memcpy(buf, cmdline, len - 1); + buf[len - 1] = '\0'; + str = skip_spaces(buf); while (*str) { char *param, *val; str = next_arg(str, ¶m, &val); + if (!val && !strcmp(param, "--")) + break; if (!strcmp(param, "nokaslr")) { efi_nokaslr = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index c7fd0c47b254..1102de76d876 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -195,19 +195,32 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, unsigned int engine_id, unsigned int queue_id) { - uint32_t sdma_engine_reg_base[2] = { - SOC15_REG_OFFSET(SDMA0, 0, - mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL, - SOC15_REG_OFFSET(SDMA1, 0, - mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL - }; - uint32_t retval = sdma_engine_reg_base[engine_id] + uint32_t sdma_engine_reg_base = 0; + uint32_t sdma_rlc_reg_offset; + + switch (engine_id) { + default: + dev_warn(adev->dev, + "Invalid sdma engine id (%d), using engine id 0\n", + engine_id); + fallthrough; + case 0: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, + mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + case 1: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0, + mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + } + + sdma_rlc_reg_offset = sdma_engine_reg_base + queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL); pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id, - queue_id, retval); + queue_id, sdma_rlc_reg_offset); - return retval; + return sdma_rlc_reg_offset; } static inline struct v9_mqd *get_mqd(void *mqd) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index bcce4c0be462..1bedb416eebd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1243,7 +1243,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, if (!obj || !obj->ent) return; - debugfs_remove(obj->ent); obj->ent = NULL; put_obj(obj); } @@ -1257,7 +1256,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) amdgpu_ras_debugfs_remove(adev, &obj->head); } - debugfs_remove_recursive(con->dir); con->dir = NULL; } /* debugfs end */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 134cc36e30c5..0739e259bf91 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -462,7 +462,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, unsigned int pages; int i, r; - *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); + *sgt = kmalloc(sizeof(**sgt), GFP_KERNEL); if (!*sgt) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index cb9d60a4e05e..b95f22262a90 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -691,6 +691,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_UTCL1_CNTL1, 0x30000000, 0x30000000) }; static const struct soc15_reg_rlcg rlcg_access_gc_9_0[] = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index fa0bca3e1f73..5d2505956f84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -135,6 +135,12 @@ static void gfxhub_v2_1_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -190,6 +196,12 @@ static void gfxhub_v2_1_enable_system_domain(struct amdgpu_device *adev) static void gfxhub_v2_1_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_HI32, @@ -326,6 +338,13 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 757fa8e83f5b..c79fc54bc3c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -134,6 +134,12 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -189,6 +195,12 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev) static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); @@ -318,6 +330,13 @@ void mmhub_v2_0_gart_disable(struct amdgpu_device *adev) void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index d488d250805d..e16874f30d5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -179,12 +179,11 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) } break; case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: err = psp_init_ta_microcode(&adev->psp, chip_name); if (err) return err; break; - case CHIP_NAVY_FLOUNDER: - break; default: BUG(); } 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 e4b33c67b634..df9338257ae0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2196,6 +2196,7 @@ void amdgpu_dm_update_connector_after_detect( drm_connector_update_edid_property(connector, aconnector->edid); + drm_add_edid_modes(connector, aconnector->edid); if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 078b7e344185..2d5c7daaee23 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1108,6 +1108,18 @@ static enum bp_result bios_parser_enable_disp_power_gating( action); } +static enum bp_result bios_parser_enable_lvtma_control( + struct dc_bios *dcb, + uint8_t uc_pwr_on) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + + if (!bp->cmd_tbl.enable_lvtma_control) + return BP_RESULT_FAILURE; + + return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on); +} + static bool bios_parser_is_accelerated_mode( struct dc_bios *dcb) { @@ -2208,7 +2220,9 @@ static const struct dc_vbios_funcs vbios_funcs = { .get_board_layout_info = bios_get_board_layout_info, .pack_data_tables = bios_parser_pack_data_tables, - .get_atom_dc_golden_table = bios_get_atom_dc_golden_table + .get_atom_dc_golden_table = bios_get_atom_dc_golden_table, + + .enable_lvtma_control = bios_parser_enable_lvtma_control }; static bool bios_parser2_construct( diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index bed91572f82a..eb3ae5c3677c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -904,6 +904,33 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id) return 0; } +/****************************************************************************** + ****************************************************************************** + ** + ** LVTMA CONTROL + ** + ****************************************************************************** + *****************************************************************************/ + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on); + +static void init_enable_lvtma_control(struct bios_parser *bp) +{ + /* TODO add switch for table vrsion */ + bp->cmd_tbl.enable_lvtma_control = enable_lvtma_control; + +} + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on) +{ + enum bp_result result = BP_RESULT_FAILURE; + return result; +} + void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) { init_dig_encoder_control(bp); @@ -919,4 +946,5 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) init_set_dce_clock(bp); init_get_smu_clock_info(bp); + init_enable_lvtma_control(bp); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h index 7a2af24dfe60..7bdce013cde5 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h @@ -94,7 +94,8 @@ struct cmd_tbl { struct bp_set_dce_clock_parameters *bp_params); unsigned int (*get_smu_clock_info)( struct bios_parser *bp, uint8_t id); - + enum bp_result (*enable_lvtma_control)(struct bios_parser *bp, + uint8_t uc_pwr_on); }; void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp); 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 4bd6e03a7ef3..117d8aaf2a9b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3286,12 +3286,11 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx) core_link_set_avmute(pipe_ctx, true); } + dc->hwss.blank_stream(pipe_ctx); #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, true); #endif - dc->hwss.blank_stream(pipe_ctx); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index d06d07042a12..0811f941f430 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -136,6 +136,10 @@ struct dc_vbios_funcs { enum bp_result (*get_atom_dc_golden_table)( struct dc_bios *dcb); + + enum bp_result (*enable_lvtma_control)( + struct dc_bios *bios, + uint8_t uc_pwr_on); }; struct bios_registers { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h index 70ec691e14d2..99c68ca9c7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h @@ -49,7 +49,7 @@ #define DCN_PANEL_CNTL_REG_LIST()\ DCN_PANEL_CNTL_SR(PWRSEQ_CNTL, LVTMA), \ DCN_PANEL_CNTL_SR(PWRSEQ_STATE, LVTMA), \ - DCE_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ + DCN_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ SR(BL_PWM_CNTL), \ SR(BL_PWM_CNTL2), \ SR(BL_PWM_PERIOD_CNTL), \ 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 49380ed3aeae..45c9e9027886 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 @@ -842,6 +842,17 @@ void dce110_edp_power_control( cntl.coherent = false; cntl.lanes_number = LANE_COUNT_FOUR; cntl.hpd_sel = link->link_enc->hpd_source; + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_POWER_ON) + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_ON); + else + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_OFF); + } + bp_result = link_transmitter_control(ctx->dc_bios, &cntl); if (!power_up) @@ -919,8 +930,21 @@ void dce110_edp_backlight_control( /*edp 1.2*/ if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) edp_receiver_ready_T7(link); + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLON); + else + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLOFF); + } + link_transmitter_control(ctx->dc_bios, &cntl); + + if (enable && link->dpcd_sink_ext_caps.bits.oled) msleep(OLED_POST_T7_DELAY); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index 07b2f9399671..842abb4c475b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -121,35 +121,35 @@ void enc1_update_generic_info_packet( switch (packet_index) { case 0: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC0_FRAME_UPDATE, 1); + AFMT_GENERIC0_IMMEDIATE_UPDATE, 1); break; case 1: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC1_FRAME_UPDATE, 1); + AFMT_GENERIC1_IMMEDIATE_UPDATE, 1); break; case 2: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC2_FRAME_UPDATE, 1); + AFMT_GENERIC2_IMMEDIATE_UPDATE, 1); break; case 3: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC3_FRAME_UPDATE, 1); + AFMT_GENERIC3_IMMEDIATE_UPDATE, 1); break; case 4: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC4_FRAME_UPDATE, 1); + AFMT_GENERIC4_IMMEDIATE_UPDATE, 1); break; case 5: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC5_FRAME_UPDATE, 1); + AFMT_GENERIC5_IMMEDIATE_UPDATE, 1); break; case 6: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC6_FRAME_UPDATE, 1); + AFMT_GENERIC6_IMMEDIATE_UPDATE, 1); break; case 7: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC7_FRAME_UPDATE, 1); + AFMT_GENERIC7_IMMEDIATE_UPDATE, 1); break; default: break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index ed385b1477be..30eae7459d50 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -281,7 +281,14 @@ struct dcn10_stream_enc_registers { SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\ @@ -345,7 +352,14 @@ struct dcn10_stream_enc_registers { type AFMT_GENERIC2_FRAME_UPDATE;\ type AFMT_GENERIC3_FRAME_UPDATE;\ type AFMT_GENERIC4_FRAME_UPDATE;\ + type AFMT_GENERIC0_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC1_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC2_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC3_IMMEDIATE_UPDATE;\ type AFMT_GENERIC4_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC5_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC6_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC7_IMMEDIATE_UPDATE;\ type AFMT_GENERIC5_FRAME_UPDATE;\ type AFMT_GENERIC6_FRAME_UPDATE;\ type AFMT_GENERIC7_FRAME_UPDATE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 66180b4332f1..c8cfd3ba1c15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1457,8 +1457,8 @@ static void dcn20_update_dchubp_dpp( /* Any updates are handled in dc interface, just need to apply existing for plane enable */ if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || - pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport) - && pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + pipe_ctx->update_flags.bits.scaler || viewport_changed == true) && + pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { dc->hwss.set_cursor_position(pipe_ctx); dc->hwss.set_cursor_attribute(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h index bf0044f7417e..dcbf28dd72d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h @@ -167,7 +167,9 @@ LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\ - LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh) + LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\ LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 790baf552695..9140b3fc767a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3141,7 +3141,7 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); BW_VAL_TRACE_COUNT(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h index 8e9fd59ccde8..2fbf879cd327 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h @@ -61,7 +61,10 @@ DPCS_DCN2_MASK_SH_LIST(mask_sh),\ LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT_18_BIT, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\ - LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh) + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) + void dcn30_link_encoder_construct( struct dcn20_link_encoder *enc20, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 653a571e366d..ebe0cc5b833b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -491,6 +491,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = { [id] = {\ LE_DCN3_REG_LIST(id), \ UNIPHY_DCN2_REG_LIST(phyid), \ + SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \ } static const struct dce110_aux_registers_shift aux_shift = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index b54814f11b74..2beb284f89b0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -63,6 +63,7 @@ typedef struct { #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN30_MAX_DSC_IMAGE_WIDTH 5184 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib); static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation( @@ -3984,6 +3985,9 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } else if (v->PlaneRequiredDISPCLKWithoutODMCombine > v->MaxDispclkRoundedDownToDFSGranularity) { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; + } else if (v->DSCEnabled[k] && (v->HActive[k] > DCN30_MAX_DSC_IMAGE_WIDTH)) { + v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; + v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; } else { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithoutODMCombine; diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index c30437ae8395..21011edea337 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -101,6 +101,13 @@ enum bp_pipe_control_action { ASIC_PIPE_INIT }; +enum bp_lvtma_control_action { + LVTMA_CONTROL_LCD_BLOFF = 2, + LVTMA_CONTROL_LCD_BLON = 3, + LVTMA_CONTROL_POWER_ON = 12, + LVTMA_CONTROL_POWER_OFF = 13 +}; + struct bp_encoder_control { enum bp_encoder_control_action action; enum engine_id engine_id; diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h index 89ef9f6860e5..16df2a485dd0 100644 --- a/drivers/gpu/drm/amd/display/include/fixed31_32.h +++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h @@ -431,6 +431,9 @@ struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg); */ static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2) { + if (arg1.value == 0) + return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero; + return dc_fixpt_exp( dc_fixpt_mul( dc_fixpt_log(arg1), diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 81820f3d6b3b..d988533d4af5 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -324,22 +324,44 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Choose number of frames to insert based on how close it * can get to the mid point of the variable range. + * - Delta for CEIL: delta_from_mid_point_in_us_1 + * - Delta for FLOOR: delta_from_mid_point_in_us_2 */ - if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us && - (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 || - mid_point_frames_floor < 2)) { + if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) { + /* Check for out of range. + * If using CEIL produces a value that is out of range, + * then we are forced to use FLOOR. + */ + frames_to_insert = mid_point_frames_floor; + } else if (mid_point_frames_floor < 2) { + /* Check if FLOOR would result in non-LFC. In this case + * choose to use CEIL + */ + frames_to_insert = mid_point_frames_ceil; + } else if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + /* If choosing CEIL results in a frame duration that is + * closer to the mid point of the range. + * Choose CEIL + */ frames_to_insert = mid_point_frames_ceil; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - - delta_from_mid_point_in_us_1; } else { + /* If choosing FLOOR results in a frame duration that is + * closer to the mid point of the range. + * Choose FLOOR + */ frames_to_insert = mid_point_frames_floor; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - - delta_from_mid_point_in_us_2; } /* Prefer current frame multiplier when BTR is enabled unless it drifts * too far from the midpoint */ + if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - + delta_from_mid_point_in_us_1; + } else { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - + delta_from_mid_point_in_us_2; + } if (in_out_vrr->btr.frames_to_insert != 0 && delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) { if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) < diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index 6c991de8f371..fb962b9ceffb 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -2204,14 +2204,17 @@ static const struct throttling_logging_label { }; static void arcturus_log_thermal_throttling_event(struct smu_context *smu) { + int ret; int throttler_idx, throtting_events = 0, buf_idx = 0; struct amdgpu_device *adev = smu->adev; uint32_t throttler_status; char log_buf[256]; - arcturus_get_smu_metrics_data(smu, - METRICS_THROTTLER_STATUS, - &throttler_status); + ret = arcturus_get_smu_metrics_data(smu, + METRICS_THROTTLER_STATUS, + &throttler_status); + if (ret) + return; memset(log_buf, 0, sizeof(log_buf)); for (throttler_idx = 0; throttler_idx < ARRAY_SIZE(logging_label); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 3b8839641770..ea70d736f6a8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -979,10 +979,7 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint64_t features_enabled; - int i; - bool enabled; - int ret = 0; + int i, ret = 0; PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisableAllSmuFeatures, @@ -990,17 +987,8 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) "[DisableAllSMUFeatures] Failed to disable all smu features!", return ret); - ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); - PP_ASSERT_WITH_CODE(!ret, - "[DisableAllSMUFeatures] Failed to get enabled smc features!", - return ret); - - for (i = 0; i < GNLD_FEATURES_MAX; i++) { - enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? - true : false; - data->smu_features[i].enabled = enabled; - data->smu_features[i].supported = enabled; - } + for (i = 0; i < GNLD_FEATURES_MAX; i++) + data->smu_features[i].enabled = 0; return 0; } @@ -1652,12 +1640,6 @@ static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr) data->uvd_power_gated = true; data->vce_power_gated = true; - - if (data->smu_features[GNLD_DPM_UVD].enabled) - data->uvd_power_gated = false; - - if (data->smu_features[GNLD_DPM_VCE].enabled) - data->vce_power_gated = false; } static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) @@ -3230,10 +3212,11 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks) { - uint64_t features_enabled; - uint64_t features_to_enable; - uint64_t features_to_disable; - int ret = 0; + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + uint64_t features_enabled, features_to_enable, features_to_disable; + int i, ret = 0; + bool enabled; if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX)) return -EINVAL; @@ -3262,6 +3245,17 @@ static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return ret; } + /* Update the cached feature enablement state */ + ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); + if (ret) + return ret; + + for (i = 0; i < GNLD_FEATURES_MAX; i++) { + enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? + true : false; + data->smu_features[i].enabled = enabled; + } + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 729ec6e0d43a..b2ec3a5141cc 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -14930,7 +14930,7 @@ static int intel_atomic_check(struct drm_device *dev, if (any_ms && !check_digital_port_conflicts(state)) { drm_dbg_kms(&dev_priv->drm, "rejecting conflicting digital port configuration\n"); - ret = EINVAL; + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 3644752cc5ec..5a5cfe25085b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -2044,9 +2044,12 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); static int i915_lpsp_capability_show(struct seq_file *m, void *data) { struct drm_connector *connector = m->private; - struct intel_encoder *encoder = - intel_attached_encoder(to_intel_connector(connector)); struct drm_i915_private *i915 = to_i915(connector->dev); + struct intel_encoder *encoder; + + encoder = intel_attached_encoder(to_intel_connector(connector)); + if (!encoder) + return -ENODEV; if (connector->status != connector_status_connected) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 0c713e83274d..e0fcb89c736b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4147,6 +4147,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = { }, }, { + .name = "TC cold off", + .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, + .ops = &tgl_tc_cold_off_ops, + .id = DISP_PW_ID_NONE, + }, + { .name = "AUX A", .domains = TGL_AUX_A_IO_POWER_DOMAINS, .ops = &icl_aux_power_well_ops, @@ -4332,12 +4338,6 @@ static const struct i915_power_well_desc tgl_power_wells[] = { .hsw.irq_pipe_mask = BIT(PIPE_D), }, }, - { - .name = "TC cold off", - .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, - .ops = &tgl_tc_cold_off_ops, - .id = DISP_PW_ID_NONE, - }, }; static const struct i915_power_well_desc rkl_power_wells[] = { @@ -5240,10 +5240,10 @@ struct buddy_page_mask { }; static const struct buddy_page_mask tgl_buddy_page_masks[] = { - { .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE }, { .num_channels = 1, .type = INTEL_DRAM_DDR4, .page_mask = 0xF }, { .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C }, { .num_channels = 2, .type = INTEL_DRAM_DDR4, .page_mask = 0x1F }, + { .num_channels = 4, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x38 }, {} }; diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 072725a448db..ad86c5eb5bba 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -70,6 +70,7 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, { u8 *cfg_base = vgpu_cfg_space(vgpu); u8 mask, new, old; + pci_power_t pwr; int i = 0; for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) { @@ -91,6 +92,15 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, /* For other configuration space directly copy as it is. */ if (i < bytes) memcpy(cfg_base + off + i, src + i, bytes - i); + + if (off == vgpu->cfg_space.pmcsr_off && vgpu->cfg_space.pmcsr_off) { + pwr = (pci_power_t __force)(*(u16*)(&vgpu_cfg_space(vgpu)[off]) + & PCI_PM_CTRL_STATE_MASK); + if (pwr == PCI_D3hot) + vgpu->d3_entered = true; + gvt_dbg_core("vgpu-%d power status changed to %d\n", + vgpu->id, pwr); + } } /** @@ -366,6 +376,7 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; const struct intel_gvt_device_info *info = &gvt->device_info; u16 *gmch_ctl; + u8 next; memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, info->cfg_space_size); @@ -401,6 +412,19 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, pci_resource_len(gvt->gt->i915->drm.pdev, 2); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); + + /* PM Support */ + vgpu->cfg_space.pmcsr_off = 0; + if (vgpu_cfg_space(vgpu)[PCI_STATUS] & PCI_STATUS_CAP_LIST) { + next = vgpu_cfg_space(vgpu)[PCI_CAPABILITY_LIST]; + do { + if (vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_ID] == PCI_CAP_ID_PM) { + vgpu->cfg_space.pmcsr_off = next + PCI_PM_CTRL; + break; + } + next = vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_NEXT]; + } while (next); + } } /** diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 210016192ce7..a3a4305eda01 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2501,7 +2501,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return create_scratch_page_tree(vgpu); } -static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) { struct list_head *pos, *n; struct intel_vgpu_mm *mm; diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 320b8d6ad92f..52d0d88abd86 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -279,4 +279,6 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes); +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu); + #endif /* _GVT_GTT_H_ */ diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index a4a6db6b7f90..ff7f2515a6fe 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -106,6 +106,7 @@ struct intel_vgpu_pci_bar { struct intel_vgpu_cfg_space { unsigned char virtual_cfg_space[PCI_CFG_SPACE_EXP_SIZE]; struct intel_vgpu_pci_bar bar[INTEL_GVT_MAX_BAR_NUM]; + u32 pmcsr_off; }; #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space) @@ -198,6 +199,8 @@ struct intel_vgpu { struct intel_vgpu_submission submission; struct radix_tree_root page_track_tree; u32 hws_pga[I915_NUM_ENGINES]; + /* Set on PCI_D3, reset on DMLR, not reflecting the actual PM state */ + bool d3_entered; struct dentry *debugfs; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 7d361623ff67..8fa9b31a2484 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -257,6 +257,7 @@ void intel_gvt_release_vgpu(struct intel_vgpu *vgpu) intel_gvt_deactivate_vgpu(vgpu); mutex_lock(&vgpu->vgpu_lock); + vgpu->d3_entered = false; intel_vgpu_clean_workloads(vgpu, ALL_ENGINES); intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); @@ -393,6 +394,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init(&vgpu->object_idr); intel_vgpu_init_cfg_space(vgpu, param->primary); + vgpu->d3_entered = false; ret = intel_vgpu_init_mmio(vgpu); if (ret) @@ -557,10 +559,15 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); - intel_vgpu_invalidate_ppgtt(vgpu); + if (engine_mask == ALL_ENGINES) + intel_vgpu_invalidate_ppgtt(vgpu); /*fence will not be reset during virtual reset */ if (dmlr) { - intel_vgpu_reset_gtt(vgpu); + if(!vgpu->d3_entered) { + intel_vgpu_invalidate_ppgtt(vgpu); + intel_vgpu_destroy_all_ppgtt_mm(vgpu); + } + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_reset_resource(vgpu); } @@ -572,7 +579,14 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; - vgpu->pv_notified = false; + /* + * PCI_D0 is set before dmlr, so reset d3_entered here + * after done using. + */ + if(vgpu->d3_entered) + vgpu->d3_entered = false; + else + vgpu->pv_notified = false; } } diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 28bc5f13ae52..056994224c6b 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -445,8 +445,6 @@ static void i915_pmu_event_destroy(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); drm_WARN_ON(&i915->drm, event->parent); - - module_put(THIS_MODULE); } static int @@ -538,10 +536,8 @@ static int i915_pmu_event_init(struct perf_event *event) if (ret) return ret; - if (!event->parent) { - __module_get(THIS_MODULE); + if (!event->parent) event->destroy = i915_pmu_event_destroy; - } return 0; } @@ -1130,6 +1126,7 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->base.attr_groups) goto err_attr; + pmu->base.module = THIS_MODULE; pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c index 939a6caebb03..632b912b0bc9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_buddy.c +++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c @@ -8,8 +8,6 @@ #include "../i915_selftest.h" #include "i915_random.h" -#define SZ_8G (1ULL << 33) - static void __igt_dump_block(struct i915_buddy_mm *mm, struct i915_buddy_block *block, bool buddy) @@ -281,18 +279,22 @@ static int igt_check_mm(struct i915_buddy_mm *mm) static void igt_mm_config(u64 *size, u64 *chunk_size) { I915_RND_STATE(prng); - u64 s, ms; + u32 s, ms; /* Nothing fancy, just try to get an interesting bit pattern */ prandom_seed_state(&prng, i915_selftest.random_seed); - s = i915_prandom_u64_state(&prng) & (SZ_8G - 1); - ms = BIT_ULL(12 + (prandom_u32_state(&prng) % ilog2(s >> 12))); - s = max(s & -ms, ms); + /* Let size be a random number of pages up to 8 GB (2M pages) */ + s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); + /* Let the chunk size be a random power of 2 less than size */ + ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); + /* Round size down to the chunk size */ + s &= -ms; - *chunk_size = ms; - *size = s; + /* Convert from pages to bytes */ + *chunk_size = (u64)ms << 12; + *size = (u64)s << 12; } static int igt_buddy_alloc_smoke(void *arg) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index b9810bf156c3..f127e633f7ca 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -78,6 +78,7 @@ static void mock_device_release(struct drm_device *dev) drm_mode_config_cleanup(&i915->drm); out: + i915_params_free(&i915->params); put_device(&i915->drm.pdev->dev); i915->drm.pdev = NULL; } @@ -165,6 +166,8 @@ struct drm_i915_private *mock_gem_device(void) i915->drm.pdev = pdev; drmm_add_final_kfree(&i915->drm, i915); + i915_params_copy(&i915->params, &i915_modparams); + intel_runtime_pm_init_early(&i915->runtime_pm); /* Using the global GTT may ask questions about KMS users, so prepare */ diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 7a2430e34e00..c8da7adc6b30 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -179,6 +179,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, vfpriv->ctx_id, buflist, out_fence); + dma_fence_put(&out_fence->f); virtio_gpu_notify(vgdev); return 0; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 2cdd3cd9ce75..e83651b7747d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -79,6 +79,7 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo) } sg_free_table(shmem->pages); + kfree(shmem->pages); shmem->pages = NULL; drm_gem_shmem_unpin(&bo->base.base); } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ef0cd2998671..c36b4d2b61e0 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2751,7 +2751,7 @@ static int __init ib_core_init(void) ret = addr_init(); if (ret) { - pr_warn("Could't init IB address resolution\n"); + pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index dad0df8a2467..17ac8b7c5710 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -821,7 +821,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct ib_event event; unsigned int flags; - if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR && + rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); bnxt_re_unlock_cqs(qp, flags); diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 9af82ff933d7..73d197e21730 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe) case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_RDMA_WRITE: + case IB_WR_RDMA_WRITE_WITH_IMM: switch (prev->wr.opcode) { case IB_WR_TID_RDMA_WRITE: req = wqe_to_tid_req(prev); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index da9888deff8c..6edcbdcd8f43 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -65,8 +65,6 @@ #define HNS_ROCE_CQE_WCMD_EMPTY_BIT 0x2 #define HNS_ROCE_MIN_CQE_CNT 16 -#define HNS_ROCE_RESERVED_SGE 1 - #define HNS_ROCE_MAX_IRQ_NUM 128 #define HNS_ROCE_SGE_IN_WQE 2 diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 07b4c85d341d..aeb3a6fa7d47 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -535,7 +535,7 @@ static void hns_roce_set_sdb_ext(struct hns_roce_dev *hr_dev, u32 ext_sdb_alept, roce_write(hr_dev, ROCEE_EXT_DB_SQ_H_REG, val); dev_dbg(dev, "ext SDB depth: 0x%x\n", db->ext_db->esdb_dep); - dev_dbg(dev, "ext SDB threshold: epmty: 0x%x, ful: 0x%x\n", + dev_dbg(dev, "ext SDB threshold: empty: 0x%x, ful: 0x%x\n", ext_sdb_alept, ext_sdb_alful); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index d2968594664b..4cda95ed1fbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -633,7 +633,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1); - if (unlikely(wr->num_sge >= hr_qp->rq.max_gs)) { + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { ibdev_err(ibdev, "rq:num_sge=%d >= qp->sq.max_gs=%d\n", wr->num_sge, hr_qp->rq.max_gs); ret = -EINVAL; @@ -653,7 +653,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, if (wr->num_sge < hr_qp->rq.max_gs) { dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); dseg->addr = 0; - dseg->len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); } /* rq support inline data */ @@ -787,8 +786,8 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, } if (wr->num_sge < srq->max_gs) { - dseg[i].len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); - dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); + dseg[i].len = 0; + dseg[i].lkey = cpu_to_le32(0x100); dseg[i].addr = 0; } @@ -5070,7 +5069,7 @@ static int hns_roce_v2_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr) attr->srq_limit = limit_wl; attr->max_wr = srq->wqe_cnt - 1; - attr->max_sge = srq->max_gs - HNS_ROCE_RESERVED_SGE; + attr->max_sge = srq->max_gs; out: hns_roce_free_cmd_mailbox(hr_dev, mailbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1fb1c583d0f8..ac29be43b6bd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -92,9 +92,7 @@ #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 -#define HNS_ROCE_INVALID_LKEY 0x0 -#define HNS_ROCE_INVALID_SGE_LENGTH 0x80000000 - +#define HNS_ROCE_INVALID_LKEY 0x100 #define HNS_ROCE_CMQ_TX_TIMEOUT 30000 #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2 #define HNS_ROCE_V2_RSV_QPS 8 diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index e94ca130ff5e..c063c450c715 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -386,8 +386,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, return -EINVAL; } - hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) + - HNS_ROCE_RESERVED_SGE); + hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge)); if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE) hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); @@ -402,7 +401,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, hr_qp->rq_inl_buf.wqe_cnt = 0; cap->max_recv_wr = cnt; - cap->max_recv_sge = hr_qp->rq.max_gs - HNS_ROCE_RESERVED_SGE; + cap->max_recv_sge = hr_qp->rq.max_gs; return 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index f40a000e94ee..b9e2dbd372b6 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -297,7 +297,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, spin_lock_init(&srq->lock); srq->wqe_cnt = roundup_pow_of_two(init_attr->attr.max_wr + 1); - srq->max_gs = init_attr->attr.max_sge + HNS_ROCE_RESERVED_SGE; + srq->max_gs = init_attr->attr.max_sge; if (udata) { ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c9abe1c01e4e..662e7fc7f628 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -120,7 +120,7 @@ static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev) IB_QPS_ERR, NULL); if (status) { - usnic_err("Failed to transistion qp grp %u from %s to %s\n", + usnic_err("Failed to transition qp grp %u from %s to %s\n", qp_grp->grp_id, usnic_ib_qp_grp_state_to_string (cur_state), diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 4959f5df21bd..5141d49a046b 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !gfpflags_allow_blocking(gfp) && !coherent) - cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, - gfp); + page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr, + gfp, NULL); else cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs); if (!cpu_addr) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 1368d1d6a114..c3dbe64e628e 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -473,6 +473,10 @@ config NET_SB1000 source "drivers/net/phy/Kconfig" +source "drivers/net/mdio/Kconfig" + +source "drivers/net/pcs/Kconfig" + source "drivers/net/plip/Kconfig" source "drivers/net/ppp/Kconfig" diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 94b60800887a..72e18d505d1a 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -21,6 +21,8 @@ obj-$(CONFIG_MDIO) += mdio.o obj-$(CONFIG_NET) += Space.o loopback.o obj-$(CONFIG_NETCONSOLE) += netconsole.o obj-y += phy/ +obj-y += mdio/ +obj-y += pcs/ obj-$(CONFIG_RIONET) += rionet.o obj-$(CONFIG_NET_TEAM) += team/ obj-$(CONFIG_TUN) += tun.o diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 415a37e44cae..c5d3032dd1a2 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2948,6 +2948,9 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; + } else if (slave->link == BOND_LINK_BACK) { + bond_propose_link_state(slave, BOND_LINK_FAIL); + commit++; } continue; } @@ -3056,6 +3059,19 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + bond_set_slave_link_state(slave, BOND_LINK_FAIL, + BOND_SLAVE_NOTIFY_NOW); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + + /* A slave has just been enslaved and has become + * the current active slave. + */ + if (rtnl_dereference(bond->curr_active_slave)) + RCU_INIT_POINTER(bond->current_arp_slave, NULL); + continue; + default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", @@ -3106,8 +3122,6 @@ static bool bond_ab_arp_probe(struct bonding *bond) return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6500179c2ca2..0837ae0e0c5e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1554,6 +1554,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, return ret; switch (ret) { + case -ETIMEDOUT: + return ret; case -ENOSPC: dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n", addr, vid); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index eb600b3dbf26..b588614d1e5e 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -28,6 +28,53 @@ static struct dsa_loop_mib_entry dsa_loop_mibs[] = { static struct phy_device *phydevs[PHY_MAX_ADDR]; +enum dsa_loop_devlink_resource_id { + DSA_LOOP_DEVLINK_PARAM_ID_VTU, +}; + +static u64 dsa_loop_devlink_vtu_get(void *priv) +{ + struct dsa_loop_priv *ps = priv; + unsigned int i, count = 0; + struct dsa_loop_vlan *vl; + + for (i = 0; i < ARRAY_SIZE(ps->vlans); i++) { + vl = &ps->vlans[i]; + if (vl->members) + count++; + } + + return count; +} + +static int dsa_loop_setup_devlink_resources(struct dsa_switch *ds) +{ + struct devlink_resource_size_params size_params; + struct dsa_loop_priv *ps = ds->priv; + int err; + + devlink_resource_size_params_init(&size_params, ARRAY_SIZE(ps->vlans), + ARRAY_SIZE(ps->vlans), + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + err = dsa_devlink_resource_register(ds, "VTU", ARRAY_SIZE(ps->vlans), + DSA_LOOP_DEVLINK_PARAM_ID_VTU, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &size_params); + if (err) + goto out; + + dsa_devlink_resource_occ_get_register(ds, + DSA_LOOP_DEVLINK_PARAM_ID_VTU, + dsa_loop_devlink_vtu_get, ps); + + return 0; + +out: + dsa_devlink_resources_unregister(ds); + return err; +} + static enum dsa_tag_protocol dsa_loop_get_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -48,7 +95,12 @@ static int dsa_loop_setup(struct dsa_switch *ds) dev_dbg(ds->dev, "%s\n", __func__); - return 0; + return dsa_loop_setup_devlink_resources(ds); +} + +static void dsa_loop_teardown(struct dsa_switch *ds) +{ + dsa_devlink_resources_unregister(ds); } static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port, int sset) @@ -243,6 +295,7 @@ static int dsa_loop_port_max_mtu(struct dsa_switch *ds, int port) static const struct dsa_switch_ops dsa_loop_driver = { .get_tag_protocol = dsa_loop_get_protocol, .setup = dsa_loop_setup, + .teardown = dsa_loop_teardown, .get_strings = dsa_loop_get_strings, .get_ethtool_stats = dsa_loop_get_ethtool_stats, .get_sset_count = dsa_loop_get_sset_count, @@ -290,6 +343,7 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) ds->dev = &mdiodev->dev; ds->ops = &dsa_loop_driver; ds->priv = ps; + ds->configure_vlan_while_not_filtering = true; ps->bus = mdiodev->bus; dev_set_drvdata(&mdiodev->dev, ds); diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c index a4c488b12e8f..094d17a1d037 100644 --- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -211,49 +211,20 @@ int mv88e6xxx_port_hwtstamp_get(struct dsa_switch *ds, int port, -EFAULT : 0; } -/* Get the start of the PTP header in this skb */ -static u8 *parse_ptp_header(struct sk_buff *skb, unsigned int type) -{ - u8 *data = skb_mac_header(skb); - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return NULL; - } - - /* Ensure that the entire header is present in this packet. */ - if (skb->len + ETH_HLEN < offset + 34) - return NULL; - - return data + offset; -} - /* Returns a pointer to the PTP header if the caller should time stamp, * or NULL if the caller should not. */ -static u8 *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, int port, - struct sk_buff *skb, unsigned int type) +static struct ptp_header *mv88e6xxx_should_tstamp(struct mv88e6xxx_chip *chip, + int port, struct sk_buff *skb, + unsigned int type) { struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; - u8 *hdr; + struct ptp_header *hdr; if (!chip->info->ptp_support) return NULL; - hdr = parse_ptp_header(skb, type); + hdr = ptp_parse_header(skb, type); if (!hdr) return NULL; @@ -275,12 +246,11 @@ static int mv88e6xxx_ts_valid(u16 status) static int seq_match(struct sk_buff *skb, u16 ts_seqid) { unsigned int type = SKB_PTP_TYPE(skb); - u8 *hdr = parse_ptp_header(skb, type); - __be16 *seqid; + struct ptp_header *hdr; - seqid = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); + hdr = ptp_parse_header(skb, type); - return ts_seqid == ntohs(*seqid); + return ts_seqid == ntohs(hdr->sequence_id); } static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip, @@ -357,9 +327,9 @@ static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip, &ps->rx_queue2); } -static int is_pdelay_resp(u8 *msgtype) +static int is_pdelay_resp(const struct ptp_header *hdr) { - return (*msgtype & 0xf) == 3; + return (hdr->tsmt & 0xf) == 3; } bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, @@ -367,7 +337,7 @@ bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port, { struct mv88e6xxx_port_hwtstamp *ps; struct mv88e6xxx_chip *chip; - u8 *hdr; + struct ptp_header *hdr; chip = ds->priv; ps = &chip->port_hwtstamp[port]; @@ -503,8 +473,7 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, { struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port]; - __be16 *seq_ptr; - u8 *hdr; + struct ptp_header *hdr; if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP)) return false; @@ -513,15 +482,13 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port, if (!hdr) return false; - seq_ptr = (__be16 *)(hdr + OFF_PTP_SEQUENCE_ID); - if (test_and_set_bit_lock(MV88E6XXX_HWTSTAMP_TX_IN_PROGRESS, &ps->state)) return false; ps->tx_skb = clone; ps->tx_tstamp_start = jiffies; - ps->tx_seq_id = be16_to_cpup(seq_ptr); + ps->tx_seq_id = be16_to_cpu(hdr->sequence_id); ptp_schedule_worker(chip->ptp_clock, 0); return true; diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index f121619d81fe..e19718d4a7d4 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -8,8 +8,9 @@ config NET_DSA_MSCC_FELIX select MSCC_OCELOT_SWITCH_LIB select NET_DSA_TAG_OCELOT select FSL_ENETC_MDIO + select PCS_LYNX help - This driver supports network switches from the the Vitesse / + This driver supports network switches from the Vitesse / Microsemi / Microchip Ocelot family of switching cores that are connected to their host CPU via Ethernet. The following switches are supported: diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index c69d9592a2b7..ccc0427faf02 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -19,6 +19,7 @@ #include <linux/of_net.h> #include <linux/pci.h> #include <linux/of.h> +#include <linux/pcs-lynx.h> #include <net/pkt_sched.h> #include <net/dsa.h> #include "felix.h" @@ -196,27 +197,16 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port, felix->info->phylink_validate(ocelot, port, supported, state); } -static int felix_phylink_mac_pcs_get_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state) -{ - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); - - if (felix->info->pcs_link_state) - felix->info->pcs_link_state(ocelot, port, state); - - return 0; -} - static void felix_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int link_an_mode, const struct phylink_link_state *state) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + struct dsa_port *dp = dsa_to_port(ds, port); - if (felix->info->pcs_config) - felix->info->pcs_config(ocelot, port, link_an_mode, state); + if (felix->pcs[port]) + phylink_set_pcs(dp->pl, &felix->pcs[port]->pcs); } static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, @@ -306,10 +296,6 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); - if (felix->info->pcs_link_up) - felix->info->pcs_link_up(ocelot, port, link_an_mode, interface, - speed, duplex); - if (felix->info->port_sched_speed_set) felix->info->port_sched_speed_set(ocelot, port, speed); } @@ -626,11 +612,6 @@ static int felix_setup(struct dsa_switch *ds) ds->mtu_enforcement_ingress = true; ds->configure_vlan_while_not_filtering = true; - /* It looks like the MAC/PCS interrupt register - PM0_IEVENT (0x8040) - * isn't instantiated for the Felix PF. - * In-band AN may take a few ms to complete, so we need to poll. - */ - ds->pcs_poll = true; return 0; } @@ -786,7 +767,6 @@ const struct dsa_switch_ops felix_switch_ops = { .get_sset_count = felix_get_sset_count, .get_ts_info = felix_get_ts_info, .phylink_validate = felix_phylink_validate, - .phylink_mac_link_state = felix_phylink_mac_pcs_get_state, .phylink_mac_config = felix_phylink_mac_config, .phylink_mac_link_down = felix_phylink_mac_link_down, .phylink_mac_link_up = felix_phylink_mac_link_up, diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 98f14621ac23..9bceb994b7db 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -28,15 +28,6 @@ struct felix_info { int imdio_pci_bar; int (*mdio_bus_alloc)(struct ocelot *ocelot); void (*mdio_bus_free)(struct ocelot *ocelot); - void (*pcs_config)(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state); - void (*pcs_link_up)(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex); - void (*pcs_link_state)(struct ocelot *ocelot, int port, - struct phylink_link_state *state); void (*phylink_validate)(struct ocelot *ocelot, int port, unsigned long *supported, struct phylink_link_state *state); @@ -59,20 +50,11 @@ struct felix { const struct felix_info *info; struct ocelot ocelot; struct mii_bus *imdio; - struct phy_device **pcs; + struct lynx_pcs **pcs; resource_size_t switch_base; resource_size_t imdio_base; }; -void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, - struct phylink_link_state *state); -void vsc9959_pcs_config(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state); -void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex); void vsc9959_mdio_bus_free(struct ocelot *ocelot); #endif diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9b720c8ddfc3..126a53a811f7 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -9,6 +9,7 @@ #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot.h> #include <linux/packing.h> +#include <linux/pcs-lynx.h> #include <net/pkt_sched.h> #include <linux/iopoll.h> #include <linux/mdio.h> @@ -766,347 +767,6 @@ static int vsc9959_reset(struct ocelot *ocelot) return 0; } -/* We enable SGMII AN only when the PHY has managed = "in-band-status" in the - * device tree. If we are in MLO_AN_PHY mode, we program directly state->speed - * into the PCS, which is retrieved out-of-band over MDIO. This also has the - * benefit of working with SGMII fixed-links, like downstream switches, where - * both link partners attempt to operate as AN slaves and therefore AN never - * completes. But it also has the disadvantage that some PHY chips don't pass - * traffic if SGMII AN is enabled but not completed (acknowledged by us), so - * setting MLO_AN_INBAND is actually required for those. - */ -static void vsc9959_pcs_config_sgmii(struct phy_device *pcs, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - int bmsr, bmcr; - - /* Some PHYs like VSC8234 don't like it when AN restarts on - * their system side and they restart line side AN too, going - * into an endless link up/down loop. Don't restart PCS AN if - * link is up already. - * We do check that AN is enabled just in case this is the 1st - * call, PCS detects a carrier but AN is disabled from power on - * or by boot loader. - */ - bmcr = phy_read(pcs, MII_BMCR); - if (bmcr < 0) - return; - - bmsr = phy_read(pcs, MII_BMSR); - if (bmsr < 0) - return; - - if ((bmcr & BMCR_ANENABLE) && (bmsr & BMSR_LSTATUS)) - return; - - /* SGMII spec requires tx_config_Reg[15:0] to be exactly 0x4001 - * for the MAC PCS in order to acknowledge the AN. - */ - phy_write(pcs, MII_ADVERTISE, ADVERTISE_SGMII | - ADVERTISE_LPACK); - - phy_write(pcs, ENETC_PCS_IF_MODE, - ENETC_PCS_IF_MODE_SGMII_EN | - ENETC_PCS_IF_MODE_USE_SGMII_AN); - - /* Adjust link timer for SGMII */ - phy_write(pcs, ENETC_PCS_LINK_TIMER1, - ENETC_PCS_LINK_TIMER1_VAL); - phy_write(pcs, ENETC_PCS_LINK_TIMER2, - ENETC_PCS_LINK_TIMER2_VAL); - - phy_set_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -static void vsc9959_pcs_config_usxgmii(struct phy_device *pcs, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - /* Configure device ability for the USXGMII Replicator */ - phy_write_mmd(pcs, MDIO_MMD_VEND2, MII_ADVERTISE, - MDIO_USXGMII_2500FULL | - MDIO_USXGMII_LINK | - ADVERTISE_SGMII | - ADVERTISE_LPACK); -} - -void vsc9959_pcs_config(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - const struct phylink_link_state *state) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - /* The PCS does not implement the BMSR register fully, so capability - * detection via genphy_read_abilities does not work. Since we can get - * the PHY config word from the LPA register though, there is still - * value in using the generic phy_resolve_aneg_linkmode function. So - * populate the supported and advertising link modes manually here. - */ - linkmode_set_bit_array(phy_basic_ports_array, - ARRAY_SIZE(phy_basic_ports_array), - pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, pcs->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, pcs->supported); - if (pcs->interface == PHY_INTERFACE_MODE_2500BASEX || - pcs->interface == PHY_INTERFACE_MODE_USXGMII) - linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, - pcs->supported); - if (pcs->interface != PHY_INTERFACE_MODE_2500BASEX) - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - pcs->supported); - phy_advertise_supported(pcs); - - if (!phylink_autoneg_inband(link_an_mode)) - return; - - switch (pcs->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_config_sgmii(pcs, link_an_mode, state); - break; - case PHY_INTERFACE_MODE_2500BASEX: - phydev_err(pcs, "AN not supported on 3.125GHz SerDes lane\n"); - break; - case PHY_INTERFACE_MODE_USXGMII: - vsc9959_pcs_config_usxgmii(pcs, link_an_mode, state); - break; - default: - dev_err(ocelot->dev, "Unsupported link mode %s\n", - phy_modes(pcs->interface)); - } -} - -static void vsc9959_pcs_link_up_sgmii(struct phy_device *pcs, - unsigned int link_an_mode, - int speed, int duplex) -{ - u16 if_mode = ENETC_PCS_IF_MODE_SGMII_EN; - - switch (speed) { - case SPEED_1000: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_1000); - break; - case SPEED_100: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_100); - break; - case SPEED_10: - if_mode |= ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_10); - break; - default: - phydev_err(pcs, "Invalid PCS speed %d\n", speed); - return; - } - - if (duplex == DUPLEX_HALF) - if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF; - - phy_write(pcs, ENETC_PCS_IF_MODE, if_mode); - phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane - * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have - * auto-negotiation of any link parameters. Electrically it is compatible with - * a single lane of XAUI. - * The hardware reference manual wants to call this mode SGMII, but it isn't - * really, since the fundamental features of SGMII: - * - Downgrading the link speed by duplicating symbols - * - Auto-negotiation - * are not there. - * The speed is configured at 1000 in the IF_MODE and BMCR MDIO registers - * because the clock frequency is actually given by a PLL configured in the - * Reset Configuration Word (RCW). - * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o - * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a - * lower link speed on line side, the system-side interface remains fixed at - * 2500 Mbps and we do rate adaptation through pause frames. - */ -static void vsc9959_pcs_link_up_2500basex(struct phy_device *pcs, - unsigned int link_an_mode, - int speed, int duplex) -{ - u16 if_mode = ENETC_PCS_IF_MODE_SGMII_SPEED(ENETC_PCS_SPEED_2500) | - ENETC_PCS_IF_MODE_SGMII_EN; - - if (duplex == DUPLEX_HALF) - if_mode |= ENETC_PCS_IF_MODE_DUPLEX_HALF; - - phy_write(pcs, ENETC_PCS_IF_MODE, if_mode); - phy_clear_bits(pcs, MII_BMCR, BMCR_ANENABLE); -} - -void vsc9959_pcs_link_up(struct ocelot *ocelot, int port, - unsigned int link_an_mode, - phy_interface_t interface, - int speed, int duplex) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - if (phylink_autoneg_inband(link_an_mode)) - return; - - switch (interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_link_up_sgmii(pcs, link_an_mode, speed, duplex); - break; - case PHY_INTERFACE_MODE_2500BASEX: - vsc9959_pcs_link_up_2500basex(pcs, link_an_mode, speed, - duplex); - break; - case PHY_INTERFACE_MODE_USXGMII: - phydev_err(pcs, "USXGMII only supports in-band AN for now\n"); - break; - default: - dev_err(ocelot->dev, "Unsupported link mode %s\n", - phy_modes(pcs->interface)); - } -} - -static void vsc9959_pcs_link_state_resolve(struct phy_device *pcs, - struct phylink_link_state *state) -{ - state->an_complete = pcs->autoneg_complete; - state->an_enabled = pcs->autoneg; - state->link = pcs->link; - state->duplex = pcs->duplex; - state->speed = pcs->speed; - /* SGMII AN does not negotiate flow control, but that's ok, - * since phylink already knows that, and does: - * link_state.pause |= pl->phy_state.pause; - */ - state->pause = MLO_PAUSE_NONE; - - phydev_dbg(pcs, - "mode=%s/%s/%s adv=%*pb lpa=%*pb link=%u an_enabled=%u an_complete=%u\n", - phy_modes(pcs->interface), - phy_speed_to_str(pcs->speed), - phy_duplex_to_str(pcs->duplex), - __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS, pcs->lp_advertising, - pcs->link, pcs->autoneg, pcs->autoneg_complete); -} - -static void vsc9959_pcs_link_state_sgmii(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int err; - - err = genphy_update_link(pcs); - if (err < 0) - return; - - if (pcs->autoneg_complete) { - u16 lpa = phy_read(pcs, MII_LPA); - - mii_lpa_to_linkmode_lpa_sgmii(pcs->lp_advertising, lpa); - - phy_resolve_aneg_linkmode(pcs); - } -} - -static void vsc9959_pcs_link_state_2500basex(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int err; - - err = genphy_update_link(pcs); - if (err < 0) - return; - - pcs->speed = SPEED_2500; - pcs->asym_pause = true; - pcs->pause = true; -} - -static void vsc9959_pcs_link_state_usxgmii(struct phy_device *pcs, - struct phylink_link_state *state) -{ - int status, lpa; - - status = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_BMSR); - if (status < 0) - return; - - pcs->autoneg = true; - pcs->autoneg_complete = !!(status & BMSR_ANEGCOMPLETE); - pcs->link = !!(status & BMSR_LSTATUS); - - if (!pcs->link || !pcs->autoneg_complete) - return; - - lpa = phy_read_mmd(pcs, MDIO_MMD_VEND2, MII_LPA); - if (lpa < 0) - return; - - switch (lpa & MDIO_USXGMII_SPD_MASK) { - case MDIO_USXGMII_10: - pcs->speed = SPEED_10; - break; - case MDIO_USXGMII_100: - pcs->speed = SPEED_100; - break; - case MDIO_USXGMII_1000: - pcs->speed = SPEED_1000; - break; - case MDIO_USXGMII_2500: - pcs->speed = SPEED_2500; - break; - default: - break; - } - - if (lpa & MDIO_USXGMII_FULL_DUPLEX) - pcs->duplex = DUPLEX_FULL; - else - pcs->duplex = DUPLEX_HALF; -} - -void vsc9959_pcs_link_state(struct ocelot *ocelot, int port, - struct phylink_link_state *state) -{ - struct felix *felix = ocelot_to_felix(ocelot); - struct phy_device *pcs = felix->pcs[port]; - - if (!pcs) - return; - - pcs->speed = SPEED_UNKNOWN; - pcs->duplex = DUPLEX_UNKNOWN; - pcs->pause = 0; - pcs->asym_pause = 0; - - switch (pcs->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - vsc9959_pcs_link_state_sgmii(pcs, state); - break; - case PHY_INTERFACE_MODE_2500BASEX: - vsc9959_pcs_link_state_2500basex(pcs, state); - break; - case PHY_INTERFACE_MODE_USXGMII: - vsc9959_pcs_link_state_usxgmii(pcs, state); - break; - default: - return; - } - - vsc9959_pcs_link_state_resolve(pcs, state); -} - static void vsc9959_phylink_validate(struct ocelot *ocelot, int port, unsigned long *supported, struct phylink_link_state *state) @@ -1195,7 +855,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) int rc; felix->pcs = devm_kcalloc(dev, felix->info->num_ports, - sizeof(struct phy_device *), + sizeof(struct lynx_pcs *), GFP_KERNEL); if (!felix->pcs) { dev_err(dev, "failed to allocate array for PCS PHYs\n"); @@ -1246,18 +906,26 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct phy_device *pcs; - bool is_c45 = false; + struct mdio_device *pcs; + struct lynx_pcs *lynx; + + if (dsa_is_unused_port(felix->ds, port)) + continue; - if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_USXGMII) - is_c45 = true; + if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) + continue; - pcs = get_phy_device(felix->imdio, port, is_c45); + pcs = mdio_device_create(felix->imdio, port); if (IS_ERR(pcs)) continue; - pcs->interface = ocelot_port->phy_mode; - felix->pcs[port] = pcs; + lynx = lynx_pcs_create(pcs); + if (!lynx) { + mdio_device_free(pcs); + continue; + } + + felix->pcs[port] = lynx; dev_info(dev, "Found PCS at internal MDIO address %d\n", port); } @@ -1271,12 +939,13 @@ void vsc9959_mdio_bus_free(struct ocelot *ocelot) int port; for (port = 0; port < ocelot->num_phys_ports; port++) { - struct phy_device *pcs = felix->pcs[port]; + struct lynx_pcs *pcs = felix->pcs[port]; if (!pcs) continue; - put_device(&pcs->mdio.dev); + mdio_device_free(pcs->mdio); + lynx_pcs_destroy(pcs); } mdiobus_unregister(felix->imdio); } @@ -1499,9 +1168,6 @@ static const struct felix_info felix_info_vsc9959 = { .imdio_pci_bar = 0, .mdio_bus_alloc = vsc9959_mdio_bus_alloc, .mdio_bus_free = vsc9959_mdio_bus_free, - .pcs_config = vsc9959_pcs_config, - .pcs_link_up = vsc9959_pcs_link_up, - .pcs_link_state = vsc9959_pcs_link_state, .phylink_validate = vsc9959_phylink_validate, .prevalidate_phy_mode = vsc9959_prevalidate_phy_mode, .port_setup_tc = vsc9959_port_setup_tc, diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 625b1891d955..2d6a5f5758f8 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -7,6 +7,7 @@ #include <soc/mscc/ocelot_sys.h> #include <soc/mscc/ocelot.h> #include <linux/of_platform.h> +#include <linux/pcs-lynx.h> #include <linux/packing.h> #include <linux/iopoll.h> #include "felix.h" @@ -960,18 +961,27 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - struct phy_device *pcs; int addr = port + 4; + struct mdio_device *pcs; + struct lynx_pcs *lynx; + + if (dsa_is_unused_port(felix->ds, port)) + continue; if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) continue; - pcs = get_phy_device(felix->imdio, addr, false); + pcs = mdio_device_create(felix->imdio, addr); if (IS_ERR(pcs)) continue; - pcs->interface = ocelot_port->phy_mode; - felix->pcs[port] = pcs; + lynx = lynx_pcs_create(pcs); + if (!lynx) { + mdio_device_free(pcs); + continue; + } + + felix->pcs[port] = lynx; dev_info(dev, "Found PCS at internal MDIO address %d\n", addr); } @@ -1013,9 +1023,6 @@ static const struct felix_info seville_info_vsc9953 = { .num_ports = 10, .mdio_bus_alloc = vsc9953_mdio_bus_alloc, .mdio_bus_free = vsc9959_mdio_bus_free, - .pcs_config = vsc9959_pcs_config, - .pcs_link_up = vsc9959_pcs_link_up, - .pcs_link_state = vsc9959_pcs_link_state, .phylink_validate = vsc9953_phylink_validate, .prevalidate_phy_mode = vsc9953_prevalidate_phy_mode, .xmit_template_populate = vsc9953_xmit_template_populate, diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index d3b30bacc94e..f11474cac59f 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -789,8 +789,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) * it with zeros to ETH_ZLEN for us. */ if (skb_shinfo(skb)->nr_frags == 0) { - skb_dma = pci_map_single(tp->tx_pdev, skb->data, skb->len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, skb->data, + skb->len, DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(skb->len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -800,8 +800,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) int i, len; len = skb_headlen(skb); - skb_dma = pci_map_single(tp->tx_pdev, skb->data, len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, skb->data, len, + DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -818,8 +818,8 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev) len = skb_frag_size(frag); frag_addr = skb_frag_address(frag); - skb_dma = pci_map_single(tp->tx_pdev, frag_addr, len, - PCI_DMA_TODEVICE); + skb_dma = dma_map_single(&tp->tx_pdev->dev, frag_addr, + len, DMA_TO_DEVICE); txd->flags = TYPHOON_FRAG_DESC | TYPHOON_DESC_VALID; txd->len = cpu_to_le16(len); txd->frag.addr = cpu_to_le32(skb_dma); @@ -1349,12 +1349,12 @@ typhoon_download_firmware(struct typhoon *tp) image_data = typhoon_fw->data; fHdr = (struct typhoon_file_header *) image_data; - /* Cannot just map the firmware image using pci_map_single() as + /* Cannot just map the firmware image using dma_map_single() as * the firmware is vmalloc()'d and may not be physically contiguous, - * so we allocate some consistent memory to copy the sections into. + * so we allocate some coherent memory to copy the sections into. */ err = -ENOMEM; - dpage = pci_alloc_consistent(pdev, PAGE_SIZE, &dpage_dma); + dpage = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, &dpage_dma, GFP_ATOMIC); if (!dpage) { netdev_err(tp->dev, "no DMA mem for firmware\n"); goto err_out; @@ -1460,7 +1460,7 @@ err_out_irq: iowrite32(irqMasked, ioaddr + TYPHOON_REG_INTR_MASK); iowrite32(irqEnabled, ioaddr + TYPHOON_REG_INTR_ENABLE); - pci_free_consistent(pdev, PAGE_SIZE, dpage, dpage_dma); + dma_free_coherent(&pdev->dev, PAGE_SIZE, dpage, dpage_dma); err_out: return err; @@ -1527,8 +1527,8 @@ typhoon_clean_tx(struct typhoon *tp, struct transmit_ring *txRing, */ skb_dma = (dma_addr_t) le32_to_cpu(tx->frag.addr); dma_len = le16_to_cpu(tx->len); - pci_unmap_single(tp->pdev, skb_dma, dma_len, - PCI_DMA_TODEVICE); + dma_unmap_single(&tp->pdev->dev, skb_dma, dma_len, + DMA_TO_DEVICE); } tx->flags = 0; @@ -1609,8 +1609,8 @@ typhoon_alloc_rx_skb(struct typhoon *tp, u32 idx) skb_reserve(skb, 2); #endif - dma_addr = pci_map_single(tp->pdev, skb->data, - PKT_BUF_SZ, PCI_DMA_FROMDEVICE); + dma_addr = dma_map_single(&tp->pdev->dev, skb->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); /* Since no card does 64 bit DAC, the high bits will never * change from zero. @@ -1665,20 +1665,19 @@ typhoon_rx(struct typhoon *tp, struct basic_ring *rxRing, volatile __le32 * read if (pkt_len < rx_copybreak && (new_skb = netdev_alloc_skb(tp->dev, pkt_len + 2)) != NULL) { skb_reserve(new_skb, 2); - pci_dma_sync_single_for_cpu(tp->pdev, dma_addr, - PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&tp->pdev->dev, dma_addr, + PKT_BUF_SZ, DMA_FROM_DEVICE); skb_copy_to_linear_data(new_skb, skb->data, pkt_len); - pci_dma_sync_single_for_device(tp->pdev, dma_addr, - PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&tp->pdev->dev, dma_addr, + PKT_BUF_SZ, + DMA_FROM_DEVICE); skb_put(new_skb, pkt_len); typhoon_recycle_rx_skb(tp, idx); } else { new_skb = skb; skb_put(new_skb, pkt_len); - pci_unmap_single(tp->pdev, dma_addr, PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&tp->pdev->dev, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); typhoon_alloc_rx_skb(tp, idx); } new_skb->protocol = eth_type_trans(new_skb, tp->dev); @@ -1792,8 +1791,8 @@ typhoon_free_rx_rings(struct typhoon *tp) for (i = 0; i < RXENT_ENTRIES; i++) { struct rxbuff_ent *rxb = &tp->rxbuffers[i]; if (rxb->skb) { - pci_unmap_single(tp->pdev, rxb->dma_addr, PKT_BUF_SZ, - PCI_DMA_FROMDEVICE); + dma_unmap_single(&tp->pdev->dev, rxb->dma_addr, + PKT_BUF_SZ, DMA_FROM_DEVICE); dev_kfree_skb(rxb->skb); rxb->skb = NULL; } @@ -2306,7 +2305,7 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto error_out_disable; } - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err < 0) { err_msg = "No usable DMA configuration"; goto error_out_mwi; @@ -2355,8 +2354,8 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* allocate pci dma space for rx and tx descriptor rings */ - shared = pci_alloc_consistent(pdev, sizeof(struct typhoon_shared), - &shared_dma); + shared = dma_alloc_coherent(&pdev->dev, sizeof(struct typhoon_shared), + &shared_dma, GFP_KERNEL); if (!shared) { err_msg = "could not allocate DMA memory"; err = -ENOMEM; @@ -2509,8 +2508,8 @@ error_out_reset: typhoon_reset(ioaddr, NoWait); error_out_dma: - pci_free_consistent(pdev, sizeof(struct typhoon_shared), - shared, shared_dma); + dma_free_coherent(&pdev->dev, sizeof(struct typhoon_shared), shared, + shared_dma); error_out_remap: pci_iounmap(pdev, ioaddr); error_out_regions: @@ -2537,8 +2536,8 @@ typhoon_remove_one(struct pci_dev *pdev) pci_restore_state(pdev); typhoon_reset(tp->ioaddr, NoWait); pci_iounmap(pdev, tp->ioaddr); - pci_free_consistent(pdev, sizeof(struct typhoon_shared), - tp->shared, tp->shared_dma); + dma_free_coherent(&pdev->dev, sizeof(struct typhoon_shared), + tp->shared, tp->shared_dma); pci_release_regions(pdev); pci_clear_mwi(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 08db4c9da2fa..a001bc902359 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -657,8 +657,10 @@ static void block_input(struct net_device *dev, int count, outb_p(E8390_RREAD+E8390_START, nic_base + AXNET_CMD); insw(nic_base + AXNET_DATAPORT,buf,count>>1); - if (count & 0x01) - buf[count-1] = inb(nic_base + AXNET_DATAPORT), xfer_count++; + if (count & 0x01) { + buf[count-1] = inb(nic_base + AXNET_DATAPORT); + xfer_count++; + } } @@ -1270,10 +1272,12 @@ static void ei_tx_intr(struct net_device *dev) ei_local->txing = 1; NS8390_trigger_send(dev, ei_local->tx2, ei_local->tx_start_page + 6); netif_trans_update(dev); - ei_local->tx2 = -1, + ei_local->tx2 = -1; ei_local->lasttx = 2; + } else { + ei_local->lasttx = 20; + ei_local->txing = 0; } - else ei_local->lasttx = 20, ei_local->txing = 0; } else if (ei_local->tx2 < 0) { @@ -1289,9 +1293,10 @@ static void ei_tx_intr(struct net_device *dev) netif_trans_update(dev); ei_local->tx1 = -1; ei_local->lasttx = 1; + } else { + ei_local->lasttx = 10; + ei_local->txing = 0; } - else - ei_local->lasttx = 10, ei_local->txing = 0; } // else // netdev_warn(dev, "unexpected TX-done interrupt, lasttx=%d\n", diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c index babc92e2692e..1f48d7f6365c 100644 --- a/drivers/net/ethernet/8390/lib8390.c +++ b/drivers/net/ethernet/8390/lib8390.c @@ -597,10 +597,12 @@ static void ei_tx_intr(struct net_device *dev) ei_local->txing = 1; NS8390_trigger_send(dev, ei_local->tx2, ei_local->tx_start_page + 6); netif_trans_update(dev); - ei_local->tx2 = -1, + ei_local->tx2 = -1; ei_local->lasttx = 2; - } else - ei_local->lasttx = 20, ei_local->txing = 0; + } else { + ei_local->lasttx = 20; + ei_local->txing = 0; + } } else if (ei_local->tx2 < 0) { if (ei_local->lasttx != 2 && ei_local->lasttx != -2) pr_err("%s: bogus last_tx_buffer %d, tx2=%d\n", @@ -612,8 +614,10 @@ static void ei_tx_intr(struct net_device *dev) netif_trans_update(dev); ei_local->tx1 = -1; ei_local->lasttx = 1; - } else - ei_local->lasttx = 10, ei_local->txing = 0; + } else { + ei_local->lasttx = 10; + ei_local->txing = 0; + } } /* else netdev_warn(dev, "unexpected TX-done interrupt, lasttx=%d\n", ei_local->lasttx); diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 645efac6310d..c383f16889f4 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -1178,8 +1178,10 @@ static void dma_block_input(struct net_device *dev, int count, outb_p(E8390_RREAD+E8390_START, nic_base + PCNET_CMD); insw(nic_base + PCNET_DATAPORT,buf,count>>1); - if (count & 0x01) - buf[count-1] = inb(nic_base + PCNET_DATAPORT), xfer_count++; + if (count & 0x01) { + buf[count-1] = inb(nic_base + PCNET_DATAPORT); + xfer_count++; + } /* This was for the ALPHA version only, but enough people have been encountering problems that it is still here. */ diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index ba0055bb1614..555299737b51 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -886,7 +886,9 @@ static int netdev_open(struct net_device *dev) tx_ring_size = ((sizeof(starfire_tx_desc) * TX_RING_SIZE + QUEUE_ALIGN - 1) / QUEUE_ALIGN) * QUEUE_ALIGN; rx_ring_size = sizeof(struct starfire_rx_desc) * RX_RING_SIZE; np->queue_mem_size = tx_done_q_size + rx_done_q_size + tx_ring_size + rx_ring_size; - np->queue_mem = pci_alloc_consistent(np->pci_dev, np->queue_mem_size, &np->queue_mem_dma); + np->queue_mem = dma_alloc_coherent(&np->pci_dev->dev, + np->queue_mem_size, + &np->queue_mem_dma, GFP_ATOMIC); if (np->queue_mem == NULL) { free_irq(irq, dev); return -ENOMEM; @@ -1136,9 +1138,11 @@ static void init_ring(struct net_device *dev) np->rx_info[i].skb = skb; if (skb == NULL) break; - np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(np->pci_dev, - np->rx_info[i].mapping)) { + np->rx_info[i].mapping = dma_map_single(&np->pci_dev->dev, + skb->data, + np->rx_buf_sz, + DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, np->rx_info[i].mapping)) { dev_kfree_skb(skb); np->rx_info[i].skb = NULL; break; @@ -1217,18 +1221,19 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) status |= skb_first_frag_len(skb) | (skb_num_frags(skb) << 16); np->tx_info[entry].mapping = - pci_map_single(np->pci_dev, skb->data, skb_first_frag_len(skb), PCI_DMA_TODEVICE); + dma_map_single(&np->pci_dev->dev, skb->data, + skb_first_frag_len(skb), + DMA_TO_DEVICE); } else { const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[i - 1]; status |= skb_frag_size(this_frag); np->tx_info[entry].mapping = - pci_map_single(np->pci_dev, + dma_map_single(&np->pci_dev->dev, skb_frag_address(this_frag), skb_frag_size(this_frag), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } - if (pci_dma_mapping_error(np->pci_dev, - np->tx_info[entry].mapping)) { + if (dma_mapping_error(&np->pci_dev->dev, np->tx_info[entry].mapping)) { dev->stats.tx_dropped++; goto err_out; } @@ -1271,18 +1276,16 @@ err_out: entry = prev_tx % TX_RING_SIZE; np->tx_info[entry].skb = NULL; if (i > 0) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, - skb_first_frag_len(skb), - PCI_DMA_TODEVICE); + skb_first_frag_len(skb), DMA_TO_DEVICE); np->tx_info[entry].mapping = 0; entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE; for (j = 1; j < i; j++) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, - skb_frag_size( - &skb_shinfo(skb)->frags[j-1]), - PCI_DMA_TODEVICE); + skb_frag_size(&skb_shinfo(skb)->frags[j - 1]), + DMA_TO_DEVICE); entry++; } } @@ -1356,20 +1359,20 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) u16 entry = (tx_status & 0x7fff) / sizeof(starfire_tx_desc); struct sk_buff *skb = np->tx_info[entry].skb; np->tx_info[entry].skb = NULL; - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, skb_first_frag_len(skb), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); np->tx_info[entry].mapping = 0; np->dirty_tx += np->tx_info[entry].used_slots; entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE; { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - pci_unmap_single(np->pci_dev, + dma_unmap_single(&np->pci_dev->dev, np->tx_info[entry].mapping, skb_frag_size(&skb_shinfo(skb)->frags[i]), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); np->dirty_tx++; entry++; } @@ -1461,16 +1464,18 @@ static int __netdev_rx(struct net_device *dev, int *quota) if (pkt_len < rx_copybreak && (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ - pci_dma_sync_single_for_cpu(np->pci_dev, - np->rx_info[entry].mapping, - pkt_len, PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&np->pci_dev->dev, + np->rx_info[entry].mapping, + pkt_len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, np->rx_info[entry].skb->data, pkt_len); - pci_dma_sync_single_for_device(np->pci_dev, - np->rx_info[entry].mapping, - pkt_len, PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&np->pci_dev->dev, + np->rx_info[entry].mapping, + pkt_len, DMA_FROM_DEVICE); skb_put(skb, pkt_len); } else { - pci_unmap_single(np->pci_dev, np->rx_info[entry].mapping, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&np->pci_dev->dev, + np->rx_info[entry].mapping, + np->rx_buf_sz, DMA_FROM_DEVICE); skb = np->rx_info[entry].skb; skb_put(skb, pkt_len); np->rx_info[entry].skb = NULL; @@ -1588,9 +1593,9 @@ static void refill_rx_ring(struct net_device *dev) if (skb == NULL) break; /* Better luck next round. */ np->rx_info[entry].mapping = - pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(np->pci_dev, - np->rx_info[entry].mapping)) { + dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, np->rx_info[entry].mapping)) { dev_kfree_skb(skb); np->rx_info[entry].skb = NULL; break; @@ -1963,7 +1968,9 @@ static int netdev_close(struct net_device *dev) for (i = 0; i < RX_RING_SIZE; i++) { np->rx_ring[i].rxaddr = cpu_to_dma(0xBADF00D0); /* An invalid address. */ if (np->rx_info[i].skb != NULL) { - pci_unmap_single(np->pci_dev, np->rx_info[i].mapping, np->rx_buf_sz, PCI_DMA_FROMDEVICE); + dma_unmap_single(&np->pci_dev->dev, + np->rx_info[i].mapping, + np->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(np->rx_info[i].skb); } np->rx_info[i].skb = NULL; @@ -1973,9 +1980,8 @@ static int netdev_close(struct net_device *dev) struct sk_buff *skb = np->tx_info[i].skb; if (skb == NULL) continue; - pci_unmap_single(np->pci_dev, - np->tx_info[i].mapping, - skb_first_frag_len(skb), PCI_DMA_TODEVICE); + dma_unmap_single(&np->pci_dev->dev, np->tx_info[i].mapping, + skb_first_frag_len(skb), DMA_TO_DEVICE); np->tx_info[i].mapping = 0; dev_kfree_skb(skb); np->tx_info[i].skb = NULL; @@ -2018,7 +2024,8 @@ static void starfire_remove_one(struct pci_dev *pdev) unregister_netdev(dev); if (np->queue_mem) - pci_free_consistent(pdev, np->queue_mem_size, np->queue_mem, np->queue_mem_dma); + dma_free_coherent(&pdev->dev, np->queue_mem_size, + np->queue_mem, np->queue_mem_dma); /* XXX: add wakeup code -- requires firmware for MagicPacket */ diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 2a6c9725e092..a3a8edf9a734 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2180,13 +2180,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter, int i; for (i = first_index; i < first_index + count; i++) { - /* Check if napi was initialized before */ - if (!ENA_IS_XDP_INDEX(adapter, i) || - adapter->ena_napi[i].xdp_ring) - netif_napi_del(&adapter->ena_napi[i].napi); - else - WARN_ON(ENA_IS_XDP_INDEX(adapter, i) && - adapter->ena_napi[i].xdp_ring); + netif_napi_del(&adapter->ena_napi[i].napi); + + WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) && + adapter->ena_napi[i].xdp_ring); } } @@ -3601,16 +3598,14 @@ static void ena_fw_reset_device(struct work_struct *work) { struct ena_adapter *adapter = container_of(work, struct ena_adapter, reset_task); - struct pci_dev *pdev = adapter->pdev; - if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { - dev_err(&pdev->dev, - "device reset schedule while reset bit is off\n"); - return; - } rtnl_lock(); - ena_destroy_device(adapter, false); - ena_restore_device(adapter); + + if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + ena_destroy_device(adapter, false); + ena_restore_device(adapter); + } + rtnl_unlock(); } @@ -3692,7 +3687,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, } u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.missed_tx = missed_tx; + tx_ring->tx_stats.missed_tx += missed_tx; u64_stats_update_end(&tx_ring->syncp); return rc; @@ -4389,8 +4384,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - del_timer_sync(&adapter->timer_service); + /* Make sure timer and reset routine won't be called after + * freeing device resources. + */ + del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); rtnl_lock(); /* lock released inside the below if-else block */ @@ -4558,6 +4556,9 @@ static void ena_keep_alive_wd(void *adapter_data, tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low; u64_stats_update_begin(&adapter->syncp); + /* These stats are accumulated by the device, so the counters indicate + * all drops since last reset. + */ adapter->dev_stats.rx_drops = rx_drops; adapter->dev_stats.tx_drops = tx_drops; u64_stats_update_end(&adapter->syncp); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index d35a338120cf..643f5e646740 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -18,6 +18,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/of_mdio.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <net/ip.h> #include <linux/prefetch.h> @@ -26,7 +27,6 @@ #include "xgene_enet_hw.h" #include "xgene_enet_cle.h" #include "xgene_enet_ring2.h" -#include "../../../phy/mdio-xgene.h" #define ETHER_MIN_PACKET 64 #define ETHER_STD_PACKET 1518 diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 16a944707ba9..8941ac4df9e3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -1631,8 +1631,8 @@ static int hw_atl_b0_get_mac_temp(struct aq_hw_s *self, u32 *temp) hw_atl_ts_reset_set(self, 0); } - err = readx_poll_timeout_atomic(hw_atl_b0_ts_ready_and_latch_high_get, - self, val, val == 1, 10000U, 500000U); + err = readx_poll_timeout(hw_atl_b0_ts_ready_and_latch_high_get, self, + val, val == 1, 10000U, 500000U); if (err) return err; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index decab9a8e4a8..c7288e1fa3a2 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -826,16 +826,16 @@ static inline void atl1c_clean_buffer(struct pci_dev *pdev, return; if (buffer_info->dma) { if (buffer_info->flags & ATL1C_PCIMAP_FROMDEVICE) - pci_driection = PCI_DMA_FROMDEVICE; + pci_driection = DMA_FROM_DEVICE; else - pci_driection = PCI_DMA_TODEVICE; + pci_driection = DMA_TO_DEVICE; if (buffer_info->flags & ATL1C_PCIMAP_SINGLE) - pci_unmap_single(pdev, buffer_info->dma, - buffer_info->length, pci_driection); + dma_unmap_single(&pdev->dev, buffer_info->dma, + buffer_info->length, pci_driection); else if (buffer_info->flags & ATL1C_PCIMAP_PAGE) - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, pci_driection); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, pci_driection); } if (buffer_info->skb) dev_consume_skb_any(buffer_info->skb); @@ -933,9 +933,8 @@ static void atl1c_free_ring_resources(struct atl1c_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; - pci_free_consistent(pdev, adapter->ring_header.size, - adapter->ring_header.desc, - adapter->ring_header.dma); + dma_free_coherent(&pdev->dev, adapter->ring_header.size, + adapter->ring_header.desc, adapter->ring_header.dma); adapter->ring_header.desc = NULL; /* Note: just free tdp_ring.buffer_info, @@ -1717,10 +1716,9 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter) ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); buffer_info->skb = skb; buffer_info->length = adapter->rx_buffer_len; - mapping = pci_map_single(pdev, vir_addr, - buffer_info->length, - PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(pdev, mapping))) { + mapping = dma_map_single(&pdev->dev, vir_addr, + buffer_info->length, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(&pdev->dev, mapping))) { dev_kfree_skb(skb); buffer_info->skb = NULL; buffer_info->length = 0; @@ -1831,8 +1829,8 @@ rrs_checked: rfd_index = (rrs->word0 >> RRS_RX_RFD_INDEX_SHIFT) & RRS_RX_RFD_INDEX_MASK; buffer_info = &rfd_ring->buffer_info[rfd_index]; - pci_unmap_single(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); skb = buffer_info->skb; } else { /* TODO */ @@ -2106,10 +2104,10 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); buffer_info->length = map_len; - buffer_info->dma = pci_map_single(adapter->pdev, - skb->data, hdr_len, PCI_DMA_TODEVICE); - if (unlikely(pci_dma_mapping_error(adapter->pdev, - buffer_info->dma))) + buffer_info->dma = dma_map_single(&adapter->pdev->dev, + skb->data, hdr_len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))) goto err_dma; ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE, @@ -2131,10 +2129,10 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); buffer_info->length = buf_len - mapped_len; buffer_info->dma = - pci_map_single(adapter->pdev, skb->data + mapped_len, - buffer_info->length, PCI_DMA_TODEVICE); - if (unlikely(pci_dma_mapping_error(adapter->pdev, - buffer_info->dma))) + dma_map_single(&adapter->pdev->dev, + skb->data + mapped_len, + buffer_info->length, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))) goto err_dma; ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); @@ -2542,8 +2540,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) { + if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || + (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 223ef846123e..fb78f6c31708 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -654,11 +654,13 @@ static void atl1e_clean_tx_ring(struct atl1e_adapter *adapter) tx_buffer = &tx_ring->tx_buffer[index]; if (tx_buffer->dma) { if (tx_buffer->flags & ATL1E_TX_PCIMAP_SINGLE) - pci_unmap_single(pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&pdev->dev, tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); else if (tx_buffer->flags & ATL1E_TX_PCIMAP_PAGE) - pci_unmap_page(pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); tx_buffer->dma = 0; } } @@ -774,8 +776,8 @@ static void atl1e_free_ring_resources(struct atl1e_adapter *adapter) atl1e_clean_rx_ring(adapter); if (adapter->ring_vir_addr) { - pci_free_consistent(pdev, adapter->ring_size, - adapter->ring_vir_addr, adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); adapter->ring_vir_addr = NULL; } @@ -810,11 +812,12 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) /* real ring DMA buffer */ size = adapter->ring_size; - adapter->ring_vir_addr = pci_zalloc_consistent(pdev, adapter->ring_size, - &adapter->ring_dma); + adapter->ring_vir_addr = dma_alloc_coherent(&pdev->dev, + adapter->ring_size, + &adapter->ring_dma, GFP_KERNEL); if (adapter->ring_vir_addr == NULL) { netdev_err(adapter->netdev, - "pci_alloc_consistent failed, size = D%d\n", size); + "dma_alloc_coherent failed, size = D%d\n", size); return -ENOMEM; } @@ -870,8 +873,8 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) return 0; failed: if (adapter->ring_vir_addr != NULL) { - pci_free_consistent(pdev, adapter->ring_size, - adapter->ring_vir_addr, adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); adapter->ring_vir_addr = NULL; } return err; @@ -1233,11 +1236,15 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter) tx_buffer = &tx_ring->tx_buffer[next_to_clean]; if (tx_buffer->dma) { if (tx_buffer->flags & ATL1E_TX_PCIMAP_SINGLE) - pci_unmap_single(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); else if (tx_buffer->flags & ATL1E_TX_PCIMAP_PAGE) - pci_unmap_page(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_page(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); tx_buffer->dma = 0; } @@ -1710,8 +1717,9 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, tx_buffer = atl1e_get_tx_buffer(adapter, use_tpd); tx_buffer->length = map_len; - tx_buffer->dma = pci_map_single(adapter->pdev, - skb->data, hdr_len, PCI_DMA_TODEVICE); + tx_buffer->dma = dma_map_single(&adapter->pdev->dev, + skb->data, hdr_len, + DMA_TO_DEVICE); if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) return -ENOSPC; @@ -1739,8 +1747,9 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, ((buf_len - mapped_len) >= MAX_TX_BUF_LEN) ? MAX_TX_BUF_LEN : (buf_len - mapped_len); tx_buffer->dma = - pci_map_single(adapter->pdev, skb->data + mapped_len, - map_len, PCI_DMA_TODEVICE); + dma_map_single(&adapter->pdev->dev, + skb->data + mapped_len, map_len, + DMA_TO_DEVICE); if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) { /* We need to unwind the mappings we've done */ @@ -1749,8 +1758,10 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, while (adapter->tx_ring.next_to_use != ring_end) { tpd = atl1e_get_tpd(adapter); tx_buffer = atl1e_get_tx_buffer(adapter, tpd); - pci_unmap_single(adapter->pdev, tx_buffer->dma, - tx_buffer->length, PCI_DMA_TODEVICE); + dma_unmap_single(&adapter->pdev->dev, + tx_buffer->dma, + tx_buffer->length, + DMA_TO_DEVICE); } /* Reset the tx rings next pointer */ adapter->tx_ring.next_to_use = ring_start; @@ -2300,8 +2311,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) || - (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)) != 0)) { + if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) || + (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) { dev_err(&pdev->dev, "No usable DMA configuration,aborting\n"); goto err_dma; } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b35fcfcd692d..60f8aa79deb2 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1050,11 +1050,11 @@ static s32 atl1_setup_ring_resources(struct atl1_adapter *adapter) + sizeof(struct stats_msg_block) + 40; - ring_header->desc = pci_alloc_consistent(pdev, ring_header->size, - &ring_header->dma); + ring_header->desc = dma_alloc_coherent(&pdev->dev, ring_header->size, + &ring_header->dma, GFP_KERNEL); if (unlikely(!ring_header->desc)) { if (netif_msg_drv(adapter)) - dev_err(&pdev->dev, "pci_alloc_consistent failed\n"); + dev_err(&pdev->dev, "dma_alloc_coherent failed\n"); goto err_nomem; } @@ -1136,8 +1136,8 @@ static void atl1_clean_rx_ring(struct atl1_adapter *adapter) for (i = 0; i < rfd_ring->count; i++) { buffer_info = &rfd_ring->buffer_info[i]; if (buffer_info->dma) { - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); buffer_info->dma = 0; } if (buffer_info->skb) { @@ -1175,8 +1175,8 @@ static void atl1_clean_tx_ring(struct atl1_adapter *adapter) for (i = 0; i < tpd_ring->count; i++) { buffer_info = &tpd_ring->buffer_info[i]; if (buffer_info->dma) { - pci_unmap_page(pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_TODEVICE); + dma_unmap_page(&pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); buffer_info->dma = 0; } } @@ -1217,8 +1217,8 @@ static void atl1_free_ring_resources(struct atl1_adapter *adapter) atl1_clean_rx_ring(adapter); kfree(tpd_ring->buffer_info); - pci_free_consistent(pdev, ring_header->size, ring_header->desc, - ring_header->dma); + dma_free_coherent(&pdev->dev, ring_header->size, ring_header->desc, + ring_header->dma); tpd_ring->buffer_info = NULL; tpd_ring->desc = NULL; @@ -1866,9 +1866,9 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter) buffer_info->length = (u16) adapter->rx_buffer_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(pdev, page, offset, + buffer_info->dma = dma_map_page(&pdev->dev, page, offset, adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma); rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len); rfd_desc->coalese = 0; @@ -1992,8 +1992,8 @@ rrd_ok: } /* Good Receive */ - pci_unmap_page(adapter->pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_FROMDEVICE); + dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_FROM_DEVICE); buffer_info->dma = 0; skb = buffer_info->skb; length = le16_to_cpu(rrd->xsz.xsum_sz.pkt_size); @@ -2062,8 +2062,8 @@ static int atl1_intr_tx(struct atl1_adapter *adapter) while (cmb_tpd_next_to_clean != sw_tpd_next_to_clean) { buffer_info = &tpd_ring->buffer_info[sw_tpd_next_to_clean]; if (buffer_info->dma) { - pci_unmap_page(adapter->pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_TODEVICE); + dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); buffer_info->dma = 0; } @@ -2210,9 +2210,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->length = hdr_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(adapter->pdev, page, + buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, offset, hdr_len, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; @@ -2235,9 +2235,10 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, (hdr_len + i * ATL1_MAX_TX_BUF_LEN)); offset = offset_in_page(skb->data + (hdr_len + i * ATL1_MAX_TX_BUF_LEN)); - buffer_info->dma = pci_map_page(adapter->pdev, - page, offset, buffer_info->length, - PCI_DMA_TODEVICE); + buffer_info->dma = dma_map_page(&adapter->pdev->dev, + page, offset, + buffer_info->length, + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2247,8 +2248,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, buffer_info->length = buf_len; page = virt_to_page(skb->data); offset = offset_in_page(skb->data); - buffer_info->dma = pci_map_page(adapter->pdev, page, - offset, buf_len, PCI_DMA_TODEVICE); + buffer_info->dma = dma_map_page(&adapter->pdev->dev, page, + offset, buf_len, + DMA_TO_DEVICE); if (++next_to_use == tpd_ring->count) next_to_use = 0; } @@ -2922,7 +2924,7 @@ static int atl1_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * various kernel subsystems to support the mechanics required by a * fixed-high-32-bit system. */ - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "no usable DMA configuration\n"); goto err_dma; diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index c915852b8892..e2526c0fb7cf 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -281,8 +281,8 @@ static s32 atl2_setup_ring_resources(struct atl2_adapter *adapter) adapter->txs_ring_size * 4 + 7 + /* dword align */ adapter->rxd_ring_size * 1536 + 127; /* 128bytes align */ - adapter->ring_vir_addr = pci_alloc_consistent(pdev, size, - &adapter->ring_dma); + adapter->ring_vir_addr = dma_alloc_coherent(&pdev->dev, size, + &adapter->ring_dma, GFP_KERNEL); if (!adapter->ring_vir_addr) return -ENOMEM; @@ -663,8 +663,8 @@ static int atl2_request_irq(struct atl2_adapter *adapter) static void atl2_free_ring_resources(struct atl2_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; - pci_free_consistent(pdev, adapter->ring_size, adapter->ring_vir_addr, - adapter->ring_dma); + dma_free_coherent(&pdev->dev, adapter->ring_size, + adapter->ring_vir_addr, adapter->ring_dma); } /** @@ -1328,8 +1328,8 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * until the kernel has the proper infrastructure to support 64-bit DMA * on these devices. */ - if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) && - pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) { + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) && + dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32))) { printk(KERN_ERR "atl2: No usable DMA configuration, aborting\n"); err = -EIO; goto err_dma; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 017169023cca..cf4fe5b17f8a 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -280,13 +280,10 @@ int octeon_init_droq(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no, droq->max_count); - droq->recv_buf_list = (struct octeon_recv_buffer *) - vzalloc_node(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE), - numa_node); + droq->recv_buf_list = vzalloc_node(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE), + numa_node); if (!droq->recv_buf_list) - droq->recv_buf_list = (struct octeon_recv_buffer *) - vzalloc(array_size(droq->max_count, - OCT_DROQ_RECVBUF_SIZE)); + droq->recv_buf_list = vzalloc(array_size(droq->max_count, OCT_DROQ_RECVBUF_SIZE)); if (!droq->recv_buf_list) { dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n"); goto init_droq_fail; diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index f6f3ef9a93cf..87cc0ef68b31 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -134,4 +134,6 @@ config CHELSIO_LIB help Common library for Chelsio drivers. +source "drivers/net/ethernet/chelsio/inline_crypto/Kconfig" + endif # NET_VENDOR_CHELSIO diff --git a/drivers/net/ethernet/chelsio/Makefile b/drivers/net/ethernet/chelsio/Makefile index c0f978d2e8a7..1a6fd8b2bb7d 100644 --- a/drivers/net/ethernet/chelsio/Makefile +++ b/drivers/net/ethernet/chelsio/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_CHELSIO_T3) += cxgb3/ obj-$(CONFIG_CHELSIO_T4) += cxgb4/ obj-$(CONFIG_CHELSIO_T4VF) += cxgb4vf/ obj-$(CONFIG_CHELSIO_LIB) += libcxgb/ +obj-$(CONFIG_CHELSIO_INLINE_CRYPTO) += inline_crypto/ diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 99736796e1a0..0e4a0f413960 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -997,17 +997,17 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_disable_pdev; } - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; - if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { - pr_err("%s: unable to obtain 64-bit DMA for " - "consistent allocations\n", pci_name(pdev)); + if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + pr_err("%s: unable to obtain 64-bit DMA for coherent allocations\n", + pci_name(pdev)); err = -ENODEV; goto out_disable_pdev; } - } else if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) != 0) { + } else if ((err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) != 0) { pr_err("%s: no usable DMA configuration\n", pci_name(pdev)); goto out_disable_pdev; } diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 47b5c8e2104b..21016de20b2d 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -509,9 +509,8 @@ static void free_freelQ_buffers(struct pci_dev *pdev, struct freelQ *q) while (q->credits--) { struct freelQ_ce *ce = &q->centries[cidx]; - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); dev_kfree_skb(ce->skb); ce->skb = NULL; if (++cidx == q->size) @@ -529,8 +528,8 @@ static void free_rx_resources(struct sge *sge) if (sge->respQ.entries) { size = sizeof(struct respQ_e) * sge->respQ.size; - pci_free_consistent(pdev, size, sge->respQ.entries, - sge->respQ.dma_addr); + dma_free_coherent(&pdev->dev, size, sge->respQ.entries, + sge->respQ.dma_addr); } for (i = 0; i < SGE_FREELQ_N; i++) { @@ -542,8 +541,8 @@ static void free_rx_resources(struct sge *sge) } if (q->entries) { size = sizeof(struct freelQ_e) * q->size; - pci_free_consistent(pdev, size, q->entries, - q->dma_addr); + dma_free_coherent(&pdev->dev, size, q->entries, + q->dma_addr); } } } @@ -564,7 +563,8 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p) q->size = p->freelQ_size[i]; q->dma_offset = sge->rx_pkt_pad ? 0 : NET_IP_ALIGN; size = sizeof(struct freelQ_e) * q->size; - q->entries = pci_alloc_consistent(pdev, size, &q->dma_addr); + q->entries = dma_alloc_coherent(&pdev->dev, size, + &q->dma_addr, GFP_KERNEL); if (!q->entries) goto err_no_mem; @@ -601,7 +601,8 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p) sge->respQ.credits = 0; size = sizeof(struct respQ_e) * sge->respQ.size; sge->respQ.entries = - pci_alloc_consistent(pdev, size, &sge->respQ.dma_addr); + dma_alloc_coherent(&pdev->dev, size, &sge->respQ.dma_addr, + GFP_KERNEL); if (!sge->respQ.entries) goto err_no_mem; return 0; @@ -624,9 +625,10 @@ static void free_cmdQ_buffers(struct sge *sge, struct cmdQ *q, unsigned int n) ce = &q->centries[cidx]; while (n--) { if (likely(dma_unmap_len(ce, dma_len))) { - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), + dma_unmap_single(&pdev->dev, + dma_unmap_addr(ce, dma_addr), dma_unmap_len(ce, dma_len), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); if (q->sop) q->sop = 0; } @@ -663,8 +665,8 @@ static void free_tx_resources(struct sge *sge) } if (q->entries) { size = sizeof(struct cmdQ_e) * q->size; - pci_free_consistent(pdev, size, q->entries, - q->dma_addr); + dma_free_coherent(&pdev->dev, size, q->entries, + q->dma_addr); } } } @@ -689,7 +691,8 @@ static int alloc_tx_resources(struct sge *sge, struct sge_params *p) q->stop_thres = 0; spin_lock_init(&q->lock); size = sizeof(struct cmdQ_e) * q->size; - q->entries = pci_alloc_consistent(pdev, size, &q->dma_addr); + q->entries = dma_alloc_coherent(&pdev->dev, size, + &q->dma_addr, GFP_KERNEL); if (!q->entries) goto err_no_mem; @@ -837,8 +840,8 @@ static void refill_free_list(struct sge *sge, struct freelQ *q) break; skb_reserve(skb, q->dma_offset); - mapping = pci_map_single(pdev, skb->data, dma_len, - PCI_DMA_FROMDEVICE); + mapping = dma_map_single(&pdev->dev, skb->data, dma_len, + DMA_FROM_DEVICE); skb_reserve(skb, sge->rx_pkt_pad); ce->skb = skb; @@ -1049,15 +1052,15 @@ static inline struct sk_buff *get_packet(struct adapter *adapter, goto use_orig_buf; skb_put(skb, len); - pci_dma_sync_single_for_cpu(pdev, - dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), + DMA_FROM_DEVICE); skb_copy_from_linear_data(ce->skb, skb->data, len); - pci_dma_sync_single_for_device(pdev, - dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), - PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), + DMA_FROM_DEVICE); recycle_fl_buf(fl, fl->cidx); return skb; } @@ -1068,8 +1071,8 @@ use_orig_buf: return NULL; } - pci_unmap_single(pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), PCI_DMA_FROMDEVICE); + dma_unmap_single(&pdev->dev, dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); skb = ce->skb; prefetch(skb->data); @@ -1091,8 +1094,9 @@ static void unexpected_offload(struct adapter *adapter, struct freelQ *fl) struct freelQ_ce *ce = &fl->centries[fl->cidx]; struct sk_buff *skb = ce->skb; - pci_dma_sync_single_for_cpu(adapter->pdev, dma_unmap_addr(ce, dma_addr), - dma_unmap_len(ce, dma_len), PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&adapter->pdev->dev, + dma_unmap_addr(ce, dma_addr), + dma_unmap_len(ce, dma_len), DMA_FROM_DEVICE); pr_err("%s: unexpected offload packet, cmd %u\n", adapter->name, *skb->data); recycle_fl_buf(fl, fl->cidx); @@ -1209,8 +1213,8 @@ static inline void write_tx_descs(struct adapter *adapter, struct sk_buff *skb, e = e1 = &q->entries[pidx]; ce = &q->centries[pidx]; - mapping = pci_map_single(adapter->pdev, skb->data, - skb_headlen(skb), PCI_DMA_TODEVICE); + mapping = dma_map_single(&adapter->pdev->dev, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); desc_mapping = mapping; desc_len = skb_headlen(skb); diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 6dabbf1502c7..ee6188dea705 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2372,10 +2372,7 @@ no_mem: if (fl->use_pages) { void *addr = fl->sdesc[fl->cidx].pg_chunk.va; - prefetch(addr); -#if L1_CACHE_BYTES < 128 - prefetch(addr + L1_CACHE_BYTES); -#endif + net_prefetch(addr); __refill_fl(adap, fl); if (lro > 0) { lro_add_page(adap, qs, fl, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 9cb8b229c1b3..e5d5c0fb7f47 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1196,6 +1196,9 @@ struct adapter { struct cxgb4_tc_u32_table *tc_u32; struct chcr_ktls chcr_ktls; struct chcr_stats_debug chcr_stats; +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + struct ch_ipsec_stats_debug ch_ipsec_stats; +#endif /* TC flower offload */ bool tc_flower_initialized; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 05f33b7e3677..42112e8ad687 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3542,14 +3542,17 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic_read(&adap->chcr_stats.error)); seq_printf(seq, "Fallback: %10u \n", atomic_read(&adap->chcr_stats.fallback)); - seq_printf(seq, "IPSec PDU: %10u\n", - atomic_read(&adap->chcr_stats.ipsec_cnt)); seq_printf(seq, "TLS PDU Tx: %10u\n", atomic_read(&adap->chcr_stats.tls_pdu_tx)); seq_printf(seq, "TLS PDU Rx: %10u\n", atomic_read(&adap->chcr_stats.tls_pdu_rx)); seq_printf(seq, "TLS Keys (DDR) Count: %10u\n", atomic_read(&adap->chcr_stats.tls_key)); +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) + seq_puts(seq, "\nChelsio Inline IPsec Crypto Accelerator Stats\n"); + seq_printf(seq, "IPSec PDU: %10u\n", + atomic_read(&adap->ch_ipsec_stats.ipsec_cnt)); +#endif #ifdef CONFIG_CHELSIO_TLS_DEVICE seq_puts(seq, "\nChelsio KTLS Crypto Accelerator Stats\n"); seq_printf(seq, "Tx TLS offload refcount: %20u\n", diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 650db92cb11c..f6c1ec140e09 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -604,17 +604,14 @@ int cxgb4_get_free_ftid(struct net_device *dev, u8 family, bool hash_en, /* If the new rule wants to get inserted into * HPFILTER region, but its prio is greater * than the rule with the highest prio in HASH - * region, then reject the rule. - */ - if (t->tc_hash_tids_max_prio && - tc_prio > t->tc_hash_tids_max_prio) - break; - - /* If there's not enough slots available - * in HPFILTER region, then move on to - * normal FILTER region immediately. + * region, or if there's not enough slots + * available in HPFILTER region, then skip + * trying to insert this rule into HPFILTER + * region and directly go to the next region. */ - if (ftid + n > t->nhpftids) { + if ((t->tc_hash_tids_max_prio && + tc_prio > t->tc_hash_tids_max_prio) || + (ftid + n) > t->nhpftids) { ftid = t->nhpftids; continue; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index a963fd0b4540..83c8189e4088 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -302,6 +302,7 @@ enum cxgb4_uld { CXGB4_ULD_ISCSI, CXGB4_ULD_ISCSIT, CXGB4_ULD_CRYPTO, + CXGB4_ULD_IPSEC, CXGB4_ULD_TLS, CXGB4_ULD_MAX }; @@ -368,7 +369,6 @@ struct chcr_stats_debug { atomic_t complete; atomic_t error; atomic_t fallback; - atomic_t ipsec_cnt; atomic_t tls_pdu_tx; atomic_t tls_pdu_rx; atomic_t tls_key; @@ -394,6 +394,12 @@ struct chcr_stats_debug { #endif }; +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) +struct ch_ipsec_stats_debug { + atomic_t ipsec_cnt; +}; +#endif + #define OCQ_WIN_OFFSET(pdev, vres) \ (pci_resource_len((pdev), 2) - roundup_pow_of_two((vres)->ocq.size)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index d2b587d1670a..fddd70ee6436 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1416,9 +1416,9 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) pi = netdev_priv(dev); adap = pi->adapter; ssi = skb_shinfo(skb); -#ifdef CONFIG_CHELSIO_IPSEC_INLINE +#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE) if (xfrm_offload(skb) && !ssi->gso_size) - return adap->uld[CXGB4_ULD_CRYPTO].tx_handler(skb, dev); + return adap->uld[CXGB4_ULD_IPSEC].tx_handler(skb, dev); #endif /* CHELSIO_IPSEC_INLINE */ #ifdef CONFIG_CHELSIO_TLS_DEVICE @@ -2553,19 +2553,22 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) pkt_len = ETH_HLEN + sizeof(CXGB4_SELFTEST_LB_STR); - flits = DIV_ROUND_UP(pkt_len + sizeof(struct cpl_tx_pkt) + - sizeof(*wr), sizeof(__be64)); + flits = DIV_ROUND_UP(pkt_len + sizeof(*cpl) + sizeof(*wr), + sizeof(__be64)); ndesc = flits_to_desc(flits); lb = &pi->ethtool_lb; lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; + __netif_tx_lock(q->txq, smp_processor_id()); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; - if (unlikely(credits < 0)) + if (unlikely(credits < 0)) { + __netif_tx_unlock(q->txq); return -ENOMEM; + } wr = (void *)&q->q.desc[q->q.pidx]; memset(wr, 0, sizeof(struct tx_desc)); @@ -2598,6 +2601,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); + __netif_tx_unlock(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 8a56491bb034..e49370f9d59b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -4745,9 +4745,11 @@ static void le_intr_handler(struct adapter *adap) static struct intr_info t6_le_intr_info[] = { { T6_LIPMISS_F, "LE LIP miss", -1, 0 }, { T6_LIP0_F, "LE 0 LIP error", -1, 0 }, + { CMDTIDERR_F, "LE cmd tid error", -1, 1 }, { TCAMINTPERR_F, "LE parity error", -1, 1 }, { T6_UNKNOWNCMD_F, "LE unknown command", -1, 1 }, { SSRAMINTPERR_F, "LE request queue parity error", -1, 1 }, + { HASHTBLMEMCRCERR_F, "LE hash table mem crc error", -1, 0 }, { 0 } }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index 065c01c654ff..b11a172b5174 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -3017,6 +3017,14 @@ #define REV_V(x) ((x) << REV_S) #define REV_G(x) (((x) >> REV_S) & REV_M) +#define HASHTBLMEMCRCERR_S 27 +#define HASHTBLMEMCRCERR_V(x) ((x) << HASHTBLMEMCRCERR_S) +#define HASHTBLMEMCRCERR_F HASHTBLMEMCRCERR_V(1U) + +#define CMDTIDERR_S 22 +#define CMDTIDERR_V(x) ((x) << CMDTIDERR_S) +#define CMDTIDERR_F CMDTIDERR_V(1U) + #define T6_UNKNOWNCMD_S 3 #define T6_UNKNOWNCMD_V(x) ((x) << T6_UNKNOWNCMD_S) #define T6_UNKNOWNCMD_F T6_UNKNOWNCMD_V(1U) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Kconfig b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig new file mode 100644 index 000000000000..a3ef057031e4 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/Kconfig @@ -0,0 +1,38 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Chelsio inline crypto configuration +# + +config CHELSIO_INLINE_CRYPTO + bool "Chelsio Inline Crypto support" + default y + help + Enable support for inline crypto. + Allows enable/disable from list of inline crypto drivers. + +if CHELSIO_INLINE_CRYPTO + +config CRYPTO_DEV_CHELSIO_TLS + tristate "Chelsio Crypto Inline TLS Driver" + depends on CHELSIO_T4 + depends on TLS_TOE + help + Support Chelsio Inline TLS with Chelsio crypto accelerator. + Enable inline TLS support for Tx and Rx. + + To compile this driver as a module, choose M here: the module + will be called chtls. + +config CHELSIO_IPSEC_INLINE + tristate "Chelsio IPSec XFRM Tx crypto offload" + depends on CHELSIO_T4 + depends on XFRM_OFFLOAD + depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD + help + Support Chelsio Inline IPsec with Chelsio crypto accelerator. + Enable inline IPsec support for Tx. + + To compile this driver as a module, choose M here: the module + will be called ch_ipsec. + +endif # CHELSIO_INLINE_CRYPTO diff --git a/drivers/net/ethernet/chelsio/inline_crypto/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/Makefile new file mode 100644 index 000000000000..9a86ee8f1f38 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_CRYPTO_DEV_CHELSIO_TLS) += chtls/ +obj-$(CONFIG_CHELSIO_IPSEC_INLINE) += ch_ipsec/ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile new file mode 100644 index 000000000000..efdcaaebc455 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +ccflags-y := -I $(srctree)/drivers/net/ethernet/chelsio/cxgb4 \ + -I $(srctree)/drivers/crypto/chelsio + +obj-$(CONFIG_CHELSIO_IPSEC_INLINE) += ch_ipsec.o +ch_ipsec-objs := chcr_ipsec.o + + diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c index 967babd67a51..276f8841becc 100644 --- a/drivers/crypto/chelsio/chcr_ipsec.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c @@ -60,9 +60,7 @@ #include <crypto/scatterwalk.h> #include <crypto/internal/hash.h> -#include "chcr_core.h" -#include "chcr_algo.h" -#include "chcr_crypto.h" +#include "chcr_ipsec.h" /* * Max Tx descriptor space we allow for an Ethernet packet to be inlined @@ -71,11 +69,17 @@ #define MAX_IMM_TX_PKT_LEN 256 #define GCM_ESP_IV_SIZE 8 +static LIST_HEAD(uld_ctx_list); +static DEFINE_MUTEX(dev_mutex); + static int chcr_xfrm_add_state(struct xfrm_state *x); static void chcr_xfrm_del_state(struct xfrm_state *x); static void chcr_xfrm_free_state(struct xfrm_state *x); static bool chcr_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static void chcr_advance_esn_state(struct xfrm_state *x); +static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state); +static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop); +static void update_netdev_features(void); static const struct xfrmdev_ops chcr_xfrmdev_ops = { .xdo_dev_state_add = chcr_xfrm_add_state, @@ -102,6 +106,57 @@ void chcr_add_xfrmops(const struct cxgb4_lld_info *lld) } } +static struct cxgb4_uld_info ch_ipsec_uld_info = { + .name = CHIPSEC_DRV_MODULE_NAME, + .nrxq = MAX_ULD_QSETS, + /* Max ntxq will be derived from fw config file*/ + .rxq_size = 1024, + .add = ch_ipsec_uld_add, + .state_change = ch_ipsec_uld_state_change, + .tx_handler = chcr_ipsec_xmit, +}; + +static void *ch_ipsec_uld_add(const struct cxgb4_lld_info *infop) +{ + struct ipsec_uld_ctx *u_ctx; + + pr_info_once("%s - version %s\n", CHIPSEC_DRV_DESC, + CHIPSEC_DRV_VERSION); + u_ctx = kzalloc(sizeof(*u_ctx), GFP_KERNEL); + if (!u_ctx) { + u_ctx = ERR_PTR(-ENOMEM); + goto out; + } + u_ctx->lldi = *infop; +out: + return u_ctx; +} + +static int ch_ipsec_uld_state_change(void *handle, enum cxgb4_state new_state) +{ + struct ipsec_uld_ctx *u_ctx = handle; + + pr_info("new_state %u\n", new_state); + switch (new_state) { + case CXGB4_STATE_UP: + pr_info("%s: Up\n", pci_name(u_ctx->lldi.pdev)); + mutex_lock(&dev_mutex); + list_add_tail(&u_ctx->entry, &uld_ctx_list); + mutex_unlock(&dev_mutex); + break; + case CXGB4_STATE_START_RECOVERY: + case CXGB4_STATE_DOWN: + case CXGB4_STATE_DETACH: + pr_info("%s: Down\n", pci_name(u_ctx->lldi.pdev)); + list_del(&u_ctx->entry); + break; + default: + break; + } + + return 0; +} + static inline int chcr_ipsec_setauthsize(struct xfrm_state *x, struct ipsec_sa_entry *sa_entry) { @@ -538,7 +593,7 @@ inline void *chcr_crypto_wreq(struct sk_buff *skb, unsigned int kctx_len = sa_entry->kctx_len; int qid = q->q.cntxt_id; - atomic_inc(&adap->chcr_stats.ipsec_cnt); + atomic_inc(&adap->ch_ipsec_stats.ipsec_cnt); flits = calc_tx_sec_flits(skb, sa_entry, &immediate); ndesc = DIV_ROUND_UP(flits, 2); @@ -752,3 +807,51 @@ out_free: dev_kfree_skb_any(skb); cxgb4_ring_tx_db(adap, &q->q, ndesc); return NETDEV_TX_OK; } + +static void update_netdev_features(void) +{ + struct ipsec_uld_ctx *u_ctx, *tmp; + + mutex_lock(&dev_mutex); + list_for_each_entry_safe(u_ctx, tmp, &uld_ctx_list, entry) { + if (u_ctx->lldi.crypto & ULP_CRYPTO_IPSEC_INLINE) + chcr_add_xfrmops(&u_ctx->lldi); + } + mutex_unlock(&dev_mutex); +} + +static int __init chcr_ipsec_init(void) +{ + cxgb4_register_uld(CXGB4_ULD_IPSEC, &ch_ipsec_uld_info); + + rtnl_lock(); + update_netdev_features(); + rtnl_unlock(); + + return 0; +} + +static void __exit chcr_ipsec_exit(void) +{ + struct ipsec_uld_ctx *u_ctx, *tmp; + struct adapter *adap; + + mutex_lock(&dev_mutex); + list_for_each_entry_safe(u_ctx, tmp, &uld_ctx_list, entry) { + adap = pci_get_drvdata(u_ctx->lldi.pdev); + atomic_set(&adap->ch_ipsec_stats.ipsec_cnt, 0); + list_del(&u_ctx->entry); + kfree(u_ctx); + } + mutex_unlock(&dev_mutex); + cxgb4_unregister_uld(CXGB4_ULD_IPSEC); +} + +module_init(chcr_ipsec_init); +module_exit(chcr_ipsec_exit); + +MODULE_DESCRIPTION("Crypto IPSEC for Chelsio Terminator cards."); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Chelsio Communications"); +MODULE_VERSION(CHIPSEC_DRV_VERSION); + diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h new file mode 100644 index 000000000000..1d110d2edd64 --- /dev/null +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2018 Chelsio Communications, Inc. */ + +#ifndef __CHCR_IPSEC_H__ +#define __CHCR_IPSEC_H__ + +#include <crypto/algapi.h> +#include "t4_hw.h" +#include "cxgb4.h" +#include "t4_msg.h" +#include "cxgb4_uld.h" + +#include "chcr_core.h" +#include "chcr_algo.h" +#include "chcr_crypto.h" + +#define CHIPSEC_DRV_MODULE_NAME "ch_ipsec" +#define CHIPSEC_DRV_VERSION "1.0.0.0-ko" +#define CHIPSEC_DRV_DESC "Chelsio T6 Crypto Ipsec offload Driver" + +struct ipsec_uld_ctx { + struct list_head entry; + struct cxgb4_lld_info lldi; +}; + +struct chcr_ipsec_req { + struct ulp_txpkt ulptx; + struct ulptx_idata sc_imm; + struct cpl_tx_sec_pdu sec_cpl; + struct _key_ctx key_ctx; +}; + +struct chcr_ipsec_wr { + struct fw_ulptx_wr wreq; + struct chcr_ipsec_req req; +}; + +#define ESN_IV_INSERT_OFFSET 12 +struct chcr_ipsec_aadiv { + __be32 spi; + u8 seq_no[8]; + u8 iv[8]; +}; + +struct ipsec_sa_entry { + int hmac_ctrl; + u16 esn; + u16 resv; + unsigned int enckey_len; + unsigned int kctx_len; + unsigned int authsize; + __be32 key_ctx_hdr; + char salt[MAX_SALT]; + char key[2 * AES_MAX_KEY_SIZE]; +}; + +#endif /* __CHCR_IPSEC_H__ */ + diff --git a/drivers/crypto/chelsio/chtls/Makefile b/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile index bc11495acdb3..bc11495acdb3 100644 --- a/drivers/crypto/chelsio/chtls/Makefile +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/Makefile diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index 459442704eb1..2d3dfdd2a716 100644 --- a/drivers/crypto/chelsio/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -32,6 +32,94 @@ #include "chcr_core.h" #include "chcr_crypto.h" +#define CHTLS_DRV_VERSION "1.0.0.0-ko" + +#define TLS_KEYCTX_RXFLIT_CNT_S 24 +#define TLS_KEYCTX_RXFLIT_CNT_V(x) ((x) << TLS_KEYCTX_RXFLIT_CNT_S) + +#define TLS_KEYCTX_RXPROT_VER_S 20 +#define TLS_KEYCTX_RXPROT_VER_M 0xf +#define TLS_KEYCTX_RXPROT_VER_V(x) ((x) << TLS_KEYCTX_RXPROT_VER_S) + +#define TLS_KEYCTX_RXCIPH_MODE_S 16 +#define TLS_KEYCTX_RXCIPH_MODE_M 0xf +#define TLS_KEYCTX_RXCIPH_MODE_V(x) ((x) << TLS_KEYCTX_RXCIPH_MODE_S) + +#define TLS_KEYCTX_RXAUTH_MODE_S 12 +#define TLS_KEYCTX_RXAUTH_MODE_M 0xf +#define TLS_KEYCTX_RXAUTH_MODE_V(x) ((x) << TLS_KEYCTX_RXAUTH_MODE_S) + +#define TLS_KEYCTX_RXCIAU_CTRL_S 11 +#define TLS_KEYCTX_RXCIAU_CTRL_V(x) ((x) << TLS_KEYCTX_RXCIAU_CTRL_S) + +#define TLS_KEYCTX_RX_SEQCTR_S 9 +#define TLS_KEYCTX_RX_SEQCTR_M 0x3 +#define TLS_KEYCTX_RX_SEQCTR_V(x) ((x) << TLS_KEYCTX_RX_SEQCTR_S) + +#define TLS_KEYCTX_RX_VALID_S 8 +#define TLS_KEYCTX_RX_VALID_V(x) ((x) << TLS_KEYCTX_RX_VALID_S) + +#define TLS_KEYCTX_RXCK_SIZE_S 3 +#define TLS_KEYCTX_RXCK_SIZE_M 0x7 +#define TLS_KEYCTX_RXCK_SIZE_V(x) ((x) << TLS_KEYCTX_RXCK_SIZE_S) + +#define TLS_KEYCTX_RXMK_SIZE_S 0 +#define TLS_KEYCTX_RXMK_SIZE_M 0x7 +#define TLS_KEYCTX_RXMK_SIZE_V(x) ((x) << TLS_KEYCTX_RXMK_SIZE_S) + +#define KEYCTX_TX_WR_IV_S 55 +#define KEYCTX_TX_WR_IV_M 0x1ffULL +#define KEYCTX_TX_WR_IV_V(x) ((x) << KEYCTX_TX_WR_IV_S) +#define KEYCTX_TX_WR_IV_G(x) \ + (((x) >> KEYCTX_TX_WR_IV_S) & KEYCTX_TX_WR_IV_M) + +#define KEYCTX_TX_WR_AAD_S 47 +#define KEYCTX_TX_WR_AAD_M 0xffULL +#define KEYCTX_TX_WR_AAD_V(x) ((x) << KEYCTX_TX_WR_AAD_S) +#define KEYCTX_TX_WR_AAD_G(x) (((x) >> KEYCTX_TX_WR_AAD_S) & \ + KEYCTX_TX_WR_AAD_M) + +#define KEYCTX_TX_WR_AADST_S 39 +#define KEYCTX_TX_WR_AADST_M 0xffULL +#define KEYCTX_TX_WR_AADST_V(x) ((x) << KEYCTX_TX_WR_AADST_S) +#define KEYCTX_TX_WR_AADST_G(x) \ + (((x) >> KEYCTX_TX_WR_AADST_S) & KEYCTX_TX_WR_AADST_M) + +#define KEYCTX_TX_WR_CIPHER_S 30 +#define KEYCTX_TX_WR_CIPHER_M 0x1ffULL +#define KEYCTX_TX_WR_CIPHER_V(x) ((x) << KEYCTX_TX_WR_CIPHER_S) +#define KEYCTX_TX_WR_CIPHER_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHER_S) & KEYCTX_TX_WR_CIPHER_M) + +#define KEYCTX_TX_WR_CIPHERST_S 23 +#define KEYCTX_TX_WR_CIPHERST_M 0x7f +#define KEYCTX_TX_WR_CIPHERST_V(x) ((x) << KEYCTX_TX_WR_CIPHERST_S) +#define KEYCTX_TX_WR_CIPHERST_G(x) \ + (((x) >> KEYCTX_TX_WR_CIPHERST_S) & KEYCTX_TX_WR_CIPHERST_M) + +#define KEYCTX_TX_WR_AUTH_S 14 +#define KEYCTX_TX_WR_AUTH_M 0x1ff +#define KEYCTX_TX_WR_AUTH_V(x) ((x) << KEYCTX_TX_WR_AUTH_S) +#define KEYCTX_TX_WR_AUTH_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTH_S) & KEYCTX_TX_WR_AUTH_M) + +#define KEYCTX_TX_WR_AUTHST_S 7 +#define KEYCTX_TX_WR_AUTHST_M 0x7f +#define KEYCTX_TX_WR_AUTHST_V(x) ((x) << KEYCTX_TX_WR_AUTHST_S) +#define KEYCTX_TX_WR_AUTHST_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHST_S) & KEYCTX_TX_WR_AUTHST_M) + +#define KEYCTX_TX_WR_AUTHIN_S 0 +#define KEYCTX_TX_WR_AUTHIN_M 0x7f +#define KEYCTX_TX_WR_AUTHIN_V(x) ((x) << KEYCTX_TX_WR_AUTHIN_S) +#define KEYCTX_TX_WR_AUTHIN_G(x) \ + (((x) >> KEYCTX_TX_WR_AUTHIN_S) & KEYCTX_TX_WR_AUTHIN_M) + +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + #define MAX_IVS_PAGE 256 #define TLS_KEY_CONTEXT_SZ 64 #define CIPHER_BLOCK_SIZE 16 diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 05520dccd906..05520dccd906 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h index 47ba81e42f5d..47ba81e42f5d 100644 --- a/drivers/crypto/chelsio/chtls/chtls_cm.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c index f1820aca0d33..f1820aca0d33 100644 --- a/drivers/crypto/chelsio/chtls/chtls_hw.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 2e9acae1cba3..2e9acae1cba3 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 66d247efd561..9098b3eed4da 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -638,4 +638,4 @@ module_exit(chtls_unregister); MODULE_DESCRIPTION("Chelsio TLS Inline driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Chelsio Communications"); -MODULE_VERSION(DRV_VERSION); +MODULE_VERSION(CHTLS_DRV_VERSION); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 66e67b24a887..62e271aea4a5 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2389,7 +2389,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) dev_info(dev, "probe %s ID %d\n", dev_name(dev), id); - netdev = alloc_etherdev_mq(sizeof(*port), TX_QUEUE_NUM); + netdev = devm_alloc_etherdev_mqs(dev, sizeof(*port), TX_QUEUE_NUM, TX_QUEUE_NUM); if (!netdev) { dev_err(dev, "Can't allocate ethernet device #%d\n", id); return -ENOMEM; @@ -2521,7 +2521,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) } port->netdev = NULL; - free_netdev(netdev); return ret; } @@ -2530,7 +2529,6 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev) struct gemini_ethernet_port *port = platform_get_drvdata(pdev); gemini_port_remove(port); - free_netdev(port->netdev); return 0; } diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index be6d8a9ada27..e8e563d6e86b 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -7,7 +7,6 @@ */ -#define DRV_NAME "DL2000/TC902x-based linux driver" #include "dl2k.h" #include <linux/dma-mapping.h> diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index bf846b42bc74..78e008b81374 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -562,10 +562,13 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) BD_ENET_TX_TC); CBDS_SC(bdp, BD_ENET_TX_READY); - if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) - bdp++, curidx++; - else - bdp = fep->tx_bd_base, curidx = 0; + if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0) { + bdp++; + curidx++; + } else { + bdp = fep->tx_bd_base; + curidx = 0; + } len = skb_frag_size(frag); CBDW_BUFADDR(bdp, skb_frag_dma_map(fep->dev, frag, 0, len, diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index b513b8c5c3b5..41dd3d0f3452 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -750,8 +750,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) continue; err = gfar_parse_group(child, priv, model); - if (err) + if (err) { + of_node_put(child); goto err_grp_init; + } } } else { /* SQ_SG_MODE */ err = gfar_parse_group(np, priv, model); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index b43dec0560a8..b98244f75ab9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -13,8 +13,6 @@ #include "hns_dsaf_ppe.h" #include "hns_dsaf_rcb.h" -#define AE_NAME_PORT_ID_IDX 6 - static struct hns_mac_cb *hns_get_mac_cb(struct hnae_handle *handle) { struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 23f278e46975..3af33ade7b60 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -557,10 +557,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); skb = *out_skb = napi_alloc_skb(&ring_data->napi, HNS_RX_HEAD_SIZE); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 87776ce3539b..1a1ba6a41bfe 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3091,10 +3091,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring) * lines. In such a case, single fetch would suffice to cache in the * relevant part of the header. */ - prefetch(ring->va); -#if L1_CACHE_BYTES < 128 - prefetch(ring->va + L1_CACHE_BYTES); -#endif + net_prefetch(ring->va); if (!skb) { ret = hns3_alloc_skb(ring, length, ring->va); diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile index 67b59d0ba769..2f89119c9b69 100644 --- a/drivers/net/ethernet/huawei/hinic/Makefile +++ b/drivers/net/ethernet/huawei/hinic/Makefile @@ -4,4 +4,5 @@ obj-$(CONFIG_HINIC) += hinic.o hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \ hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \ hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \ - hinic_common.o hinic_ethtool.o hinic_devlink.o hinic_hw_mbox.o hinic_sriov.o + hinic_common.o hinic_ethtool.o hinic_devlink.o hinic_hw_mbox.o \ + hinic_sriov.o hinic_debugfs.o diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c new file mode 100644 index 000000000000..19eb839177ec --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#include <linux/debugfs.h> +#include <linux/device.h> + +#include "hinic_debugfs.h" + +static struct dentry *hinic_dbgfs_root; + +enum sq_dbg_info { + GLB_SQ_ID, + SQ_PI, + SQ_CI, + SQ_FI, + SQ_MSIX_ENTRY, +}; + +static char *sq_fields[] = {"glb_sq_id", "sq_pi", "sq_ci", "sq_fi", "sq_msix_entry"}; + +static u64 hinic_dbg_get_sq_info(struct hinic_dev *nic_dev, struct hinic_sq *sq, int idx) +{ + struct hinic_wq *wq = sq->wq; + + switch (idx) { + case GLB_SQ_ID: + return nic_dev->hwdev->func_to_io.global_qpn + sq->qid; + case SQ_PI: + return atomic_read(&wq->prod_idx) & wq->mask; + case SQ_CI: + return atomic_read(&wq->cons_idx) & wq->mask; + case SQ_FI: + return be16_to_cpu(*(__be16 *)(sq->hw_ci_addr)) & wq->mask; + case SQ_MSIX_ENTRY: + return sq->msix_entry; + } + + return 0; +} + +enum rq_dbg_info { + GLB_RQ_ID, + RQ_HW_PI, + RQ_SW_CI, + RQ_SW_PI, + RQ_MSIX_ENTRY, +}; + +static char *rq_fields[] = {"glb_rq_id", "rq_hw_pi", "rq_sw_ci", "rq_sw_pi", "rq_msix_entry"}; + +static u64 hinic_dbg_get_rq_info(struct hinic_dev *nic_dev, struct hinic_rq *rq, int idx) +{ + struct hinic_wq *wq = rq->wq; + + switch (idx) { + case GLB_RQ_ID: + return nic_dev->hwdev->func_to_io.global_qpn + rq->qid; + case RQ_HW_PI: + return be16_to_cpu(*(__be16 *)(rq->pi_virt_addr)) & wq->mask; + case RQ_SW_CI: + return atomic_read(&wq->cons_idx) & wq->mask; + case RQ_SW_PI: + return atomic_read(&wq->prod_idx) & wq->mask; + case RQ_MSIX_ENTRY: + return rq->msix_entry; + } + + return 0; +} + +enum func_tbl_info { + VALID, + RX_MODE, + MTU, + RQ_DEPTH, + QUEUE_NUM, +}; + +static char *func_table_fields[] = {"valid", "rx_mode", "mtu", "rq_depth", "cfg_q_num"}; + +static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx) +{ + struct tag_sml_funcfg_tbl *funcfg_table_elem; + struct hinic_cmd_lt_rd *read_data; + u16 out_size = sizeof(*read_data); + int err; + + read_data = kzalloc(sizeof(*read_data), GFP_KERNEL); + if (!read_data) + return ~0; + + read_data->node = TBL_ID_FUNC_CFG_SM_NODE; + read_data->inst = TBL_ID_FUNC_CFG_SM_INST; + read_data->entry_size = HINIC_FUNCTION_CONFIGURE_TABLE_SIZE; + read_data->lt_index = HINIC_HWIF_FUNC_IDX(nic_dev->hwdev->hwif); + read_data->len = HINIC_FUNCTION_CONFIGURE_TABLE_SIZE; + + err = hinic_port_msg_cmd(nic_dev->hwdev, HINIC_PORT_CMD_RD_LINE_TBL, read_data, + sizeof(*read_data), read_data, &out_size); + if (err || out_size != sizeof(*read_data) || read_data->status) { + netif_err(nic_dev, drv, nic_dev->netdev, + "Failed to get func table, err: %d, status: 0x%x, out size: 0x%x\n", + err, read_data->status, out_size); + kfree(read_data); + return ~0; + } + + funcfg_table_elem = (struct tag_sml_funcfg_tbl *)read_data->data; + + switch (idx) { + case VALID: + return funcfg_table_elem->dw0.bs.valid; + case RX_MODE: + return funcfg_table_elem->dw0.bs.nic_rx_mode; + case MTU: + return funcfg_table_elem->dw1.bs.mtu; + case RQ_DEPTH: + return funcfg_table_elem->dw13.bs.cfg_rq_depth; + case QUEUE_NUM: + return funcfg_table_elem->dw13.bs.cfg_q_num; + } + + kfree(read_data); + + return ~0; +} + +static ssize_t hinic_dbg_cmd_read(struct file *filp, char __user *buffer, size_t count, + loff_t *ppos) +{ + struct hinic_debug_priv *dbg; + char ret_buf[20]; + int *desc; + u64 out; + int ret; + + desc = filp->private_data; + dbg = container_of(desc, struct hinic_debug_priv, field_id[*desc]); + + switch (dbg->type) { + case HINIC_DBG_SQ_INFO: + out = hinic_dbg_get_sq_info(dbg->dev, dbg->object, *desc); + break; + + case HINIC_DBG_RQ_INFO: + out = hinic_dbg_get_rq_info(dbg->dev, dbg->object, *desc); + break; + + case HINIC_DBG_FUNC_TABLE: + out = hinic_dbg_get_func_table(dbg->dev, *desc); + break; + + default: + netif_warn(dbg->dev, drv, dbg->dev->netdev, "Invalid hinic debug cmd: %d\n", + dbg->type); + return -EINVAL; + } + + ret = snprintf(ret_buf, sizeof(ret_buf), "0x%llx\n", out); + + return simple_read_from_buffer(buffer, count, ppos, ret_buf, ret); +} + +static const struct file_operations hinic_dbg_cmd_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = hinic_dbg_cmd_read, +}; + +static int create_dbg_files(struct hinic_dev *dev, enum hinic_dbg_type type, void *data, + struct dentry *root, struct hinic_debug_priv **dbg, char **field, + int nfile) +{ + struct hinic_debug_priv *tmp; + int i; + + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + tmp->dev = dev; + tmp->object = data; + tmp->type = type; + tmp->root = root; + + for (i = 0; i < nfile; i++) { + tmp->field_id[i] = i; + debugfs_create_file(field[i], 0400, root, &tmp->field_id[i], &hinic_dbg_cmd_fops); + } + + *dbg = tmp; + + return 0; +} + +static void rem_dbg_files(struct hinic_debug_priv *dbg) +{ + if (dbg->type != HINIC_DBG_FUNC_TABLE) + debugfs_remove_recursive(dbg->root); + + kfree(dbg); +} + +int hinic_sq_debug_add(struct hinic_dev *dev, u16 sq_id) +{ + struct hinic_sq *sq; + struct dentry *root; + char sub_dir[16]; + + sq = dev->txqs[sq_id].sq; + + sprintf(sub_dir, "0x%x", sq_id); + + root = debugfs_create_dir(sub_dir, dev->sq_dbgfs); + + return create_dbg_files(dev, HINIC_DBG_SQ_INFO, sq, root, &sq->dbg, sq_fields, + ARRAY_SIZE(sq_fields)); +} + +void hinic_sq_debug_rem(struct hinic_sq *sq) +{ + if (sq->dbg) + rem_dbg_files(sq->dbg); +} + +int hinic_rq_debug_add(struct hinic_dev *dev, u16 rq_id) +{ + struct hinic_rq *rq; + struct dentry *root; + char sub_dir[16]; + + rq = dev->rxqs[rq_id].rq; + + sprintf(sub_dir, "0x%x", rq_id); + + root = debugfs_create_dir(sub_dir, dev->rq_dbgfs); + + return create_dbg_files(dev, HINIC_DBG_RQ_INFO, rq, root, &rq->dbg, rq_fields, + ARRAY_SIZE(rq_fields)); +} + +void hinic_rq_debug_rem(struct hinic_rq *rq) +{ + if (rq->dbg) + rem_dbg_files(rq->dbg); +} + +int hinic_func_table_debug_add(struct hinic_dev *dev) +{ + if (HINIC_IS_VF(dev->hwdev->hwif)) + return 0; + + return create_dbg_files(dev, HINIC_DBG_FUNC_TABLE, dev, dev->func_tbl_dbgfs, &dev->dbg, + func_table_fields, ARRAY_SIZE(func_table_fields)); +} + +void hinic_func_table_debug_rem(struct hinic_dev *dev) +{ + if (!HINIC_IS_VF(dev->hwdev->hwif) && dev->dbg) + rem_dbg_files(dev->dbg); +} + +void hinic_sq_dbgfs_init(struct hinic_dev *nic_dev) +{ + nic_dev->sq_dbgfs = debugfs_create_dir("SQs", nic_dev->dbgfs_root); +} + +void hinic_sq_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->sq_dbgfs); +} + +void hinic_rq_dbgfs_init(struct hinic_dev *nic_dev) +{ + nic_dev->rq_dbgfs = debugfs_create_dir("RQs", nic_dev->dbgfs_root); +} + +void hinic_rq_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->rq_dbgfs); +} + +void hinic_func_tbl_dbgfs_init(struct hinic_dev *nic_dev) +{ + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + nic_dev->func_tbl_dbgfs = debugfs_create_dir("func_table", nic_dev->dbgfs_root); +} + +void hinic_func_tbl_dbgfs_uninit(struct hinic_dev *nic_dev) +{ + if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) + debugfs_remove_recursive(nic_dev->func_tbl_dbgfs); +} + +void hinic_dbg_init(struct hinic_dev *nic_dev) +{ + nic_dev->dbgfs_root = debugfs_create_dir(pci_name(nic_dev->hwdev->hwif->pdev), + hinic_dbgfs_root); +} + +void hinic_dbg_uninit(struct hinic_dev *nic_dev) +{ + debugfs_remove_recursive(nic_dev->dbgfs_root); + nic_dev->dbgfs_root = NULL; +} + +void hinic_dbg_register_debugfs(const char *debugfs_dir_name) +{ + hinic_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL); +} + +void hinic_dbg_unregister_debugfs(void) +{ + debugfs_remove_recursive(hinic_dbgfs_root); + hinic_dbgfs_root = NULL; +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h new file mode 100644 index 000000000000..e9e00cfa1329 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + */ + +#ifndef HINIC_DEBUGFS_H +#define HINIC_DEBUGFS_H + +#include "hinic_dev.h" + +#define TBL_ID_FUNC_CFG_SM_NODE 11 +#define TBL_ID_FUNC_CFG_SM_INST 1 + +#define HINIC_FUNCTION_CONFIGURE_TABLE_SIZE 64 +#define HINIC_FUNCTION_CONFIGURE_TABLE 1 + +struct hinic_cmd_lt_rd { + u8 status; + u8 version; + u8 rsvd0[6]; + + unsigned char node; + unsigned char inst; + unsigned char entry_size; + unsigned char rsvd; + unsigned int lt_index; + unsigned int offset; + unsigned int len; + unsigned char data[100]; +}; + +struct tag_sml_funcfg_tbl { + union { + struct { + u32 rsvd0 :8; + u32 nic_rx_mode :5; + u32 rsvd1 :18; + u32 valid :1; + } bs; + + u32 value; + } dw0; + + union { + struct { + u32 vlan_id :12; + u32 vlan_mode :3; + u32 fast_recycled_mode :1; + u32 mtu :16; + } bs; + + u32 value; + } dw1; + + u32 dw2; + u32 dw3; + u32 dw4; + u32 dw5; + u32 dw6; + u32 dw7; + u32 dw8; + u32 dw9; + u32 dw10; + u32 dw11; + u32 dw12; + + union { + struct { + u32 rsvd2 :15; + u32 cfg_q_num :9; + u32 cfg_rq_depth :6; + u32 vhd_type :2; + } bs; + + u32 value; + } dw13; + + u32 dw14; + u32 dw15; +}; + +int hinic_sq_debug_add(struct hinic_dev *dev, u16 sq_id); + +void hinic_sq_debug_rem(struct hinic_sq *sq); + +int hinic_rq_debug_add(struct hinic_dev *dev, u16 rq_id); + +void hinic_rq_debug_rem(struct hinic_rq *rq); + +int hinic_func_table_debug_add(struct hinic_dev *dev); + +void hinic_func_table_debug_rem(struct hinic_dev *dev); + +void hinic_sq_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_sq_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_rq_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_rq_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_func_tbl_dbgfs_init(struct hinic_dev *nic_dev); + +void hinic_func_tbl_dbgfs_uninit(struct hinic_dev *nic_dev); + +void hinic_dbg_init(struct hinic_dev *nic_dev); + +void hinic_dbg_uninit(struct hinic_dev *nic_dev); + +void hinic_dbg_register_debugfs(const char *debugfs_dir_name); + +void hinic_dbg_unregister_debugfs(void); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h index 0a1e20edf7cf..fb3e89141a0d 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -58,6 +58,20 @@ struct hinic_intr_coal_info { u8 resend_timer_cfg; }; +enum hinic_dbg_type { + HINIC_DBG_SQ_INFO, + HINIC_DBG_RQ_INFO, + HINIC_DBG_FUNC_TABLE, +}; + +struct hinic_debug_priv { + struct hinic_dev *dev; + void *object; + enum hinic_dbg_type type; + struct dentry *root; + int field_id[64]; +}; + struct hinic_dev { struct net_device *netdev; struct hinic_hwdev *hwdev; @@ -97,6 +111,12 @@ struct hinic_dev { int lb_test_rx_idx; int lb_pkt_len; u8 *lb_test_rx_buf; + + struct dentry *dbgfs_root; + struct dentry *sq_dbgfs; + struct dentry *rq_dbgfs; + struct dentry *func_tbl_dbgfs; + struct hinic_debug_priv *dbg; struct devlink *devlink; bool cable_unplugged; bool module_unrecognized; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 0c737765d113..239685152f6e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -465,6 +465,7 @@ int hinic_hwdev_ifup(struct hinic_hwdev *hwdev, u16 sq_depth, u16 rq_depth) func_to_io->hwdev = hwdev; func_to_io->sq_depth = sq_depth; func_to_io->rq_depth = rq_depth; + func_to_io->global_qpn = base_qpn; err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs, ceq_msix_entries); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index 701eb81e09a7..416492e48274 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -96,6 +96,8 @@ enum hinic_port_cmd { HINIC_PORT_CMD_RSS_TEMP_MGR = 49, + HINIC_PORT_CMD_RD_LINE_TBL = 57, + HINIC_PORT_CMD_RSS_CFG = 66, HINIC_PORT_CMD_FWCTXT_INIT = 69, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c index 3e3fa742e476..6772d8978722 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -305,6 +305,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io, func_to_io->sq_db[q_id] = db_base; + qp->sq.qid = q_id; err = hinic_init_sq(&qp->sq, hwif, &func_to_io->sq_wq[q_id], sq_msix_entry, CI_ADDR(func_to_io->ci_addr_base, q_id), @@ -314,6 +315,7 @@ static int init_qp(struct hinic_func_to_io *func_to_io, goto err_sq_init; } + qp->rq.qid = q_id; err = hinic_init_rq(&qp->rq, hwif, &func_to_io->rq_wq[q_id], rq_msix_entry); if (err) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h index ee6d60762d84..52159a90278a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h @@ -59,6 +59,7 @@ struct hinic_nic_cfg { struct hinic_func_to_io { struct hinic_hwif *hwif; struct hinic_hwdev *hwdev; + u16 global_qpn; struct hinic_ceqs ceqs; struct hinic_wqs wqs; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index ca3e2d060284..0dfa51ad5855 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -81,6 +81,8 @@ struct hinic_sq { struct hinic_wq *wq; + u16 qid; + u32 irq; u16 msix_entry; @@ -90,6 +92,7 @@ struct hinic_sq { void __iomem *db_base; struct sk_buff **saved_skb; + struct hinic_debug_priv *dbg; }; struct hinic_rq { @@ -97,6 +100,8 @@ struct hinic_rq { struct hinic_wq *wq; + u16 qid; + struct cpumask affinity_mask; u32 irq; u16 msix_entry; @@ -110,6 +115,7 @@ struct hinic_rq { u16 *pi_virt_addr; dma_addr_t pi_dma_addr; + struct hinic_debug_priv *dbg; }; struct hinic_qp { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 501056fd32ee..797c55a1d9c6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -24,6 +24,7 @@ #include <linux/delay.h> #include <linux/err.h> +#include "hinic_debugfs.h" #include "hinic_hw_qp.h" #include "hinic_hw_dev.h" #include "hinic_devlink.h" @@ -153,6 +154,8 @@ static int create_txqs(struct hinic_dev *nic_dev) if (!nic_dev->txqs) return -ENOMEM; + hinic_sq_dbgfs_init(nic_dev); + for (i = 0; i < num_txqs; i++) { struct hinic_sq *sq = hinic_hwdev_get_sq(nic_dev->hwdev, i); @@ -162,13 +165,27 @@ static int create_txqs(struct hinic_dev *nic_dev) "Failed to init Txq\n"); goto err_init_txq; } + + err = hinic_sq_debug_add(nic_dev, i); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to add SQ%d debug\n", i); + goto err_add_sq_dbg; + } + } return 0; +err_add_sq_dbg: + hinic_clean_txq(&nic_dev->txqs[i]); err_init_txq: - for (j = 0; j < i; j++) + for (j = 0; j < i; j++) { + hinic_sq_debug_rem(nic_dev->txqs[j].sq); hinic_clean_txq(&nic_dev->txqs[j]); + } + + hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); return err; @@ -186,8 +203,12 @@ static void free_txqs(struct hinic_dev *nic_dev) if (!nic_dev->txqs) return; - for (i = 0; i < num_txqs; i++) + for (i = 0; i < num_txqs; i++) { + hinic_sq_debug_rem(nic_dev->txqs[i].sq); hinic_clean_txq(&nic_dev->txqs[i]); + } + + hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); nic_dev->txqs = NULL; @@ -213,6 +234,8 @@ static int create_rxqs(struct hinic_dev *nic_dev) if (!nic_dev->rxqs) return -ENOMEM; + hinic_rq_dbgfs_init(nic_dev); + for (i = 0; i < num_rxqs; i++) { struct hinic_rq *rq = hinic_hwdev_get_rq(nic_dev->hwdev, i); @@ -222,13 +245,26 @@ static int create_rxqs(struct hinic_dev *nic_dev) "Failed to init rxq\n"); goto err_init_rxq; } + + err = hinic_rq_debug_add(nic_dev, i); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to add RQ%d debug\n", i); + goto err_add_rq_dbg; + } } return 0; +err_add_rq_dbg: + hinic_clean_rxq(&nic_dev->rxqs[i]); err_init_rxq: - for (j = 0; j < i; j++) + for (j = 0; j < i; j++) { + hinic_rq_debug_rem(nic_dev->rxqs[j].rq); hinic_clean_rxq(&nic_dev->rxqs[j]); + } + + hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); return err; @@ -246,8 +282,12 @@ static void free_rxqs(struct hinic_dev *nic_dev) if (!nic_dev->rxqs) return; - for (i = 0; i < num_rxqs; i++) + for (i = 0; i < num_rxqs; i++) { + hinic_rq_debug_rem(nic_dev->rxqs[i].rq); hinic_clean_rxq(&nic_dev->rxqs[i]); + } + + hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); nic_dev->rxqs = NULL; @@ -1260,6 +1300,16 @@ static int nic_dev_init(struct pci_dev *pdev) goto err_init_intr; } + hinic_dbg_init(nic_dev); + + hinic_func_tbl_dbgfs_init(nic_dev); + + err = hinic_func_table_debug_add(nic_dev); + if (err) { + dev_err(&pdev->dev, "Failed to add func_table debug\n"); + goto err_add_func_table_dbg; + } + err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); @@ -1269,6 +1319,10 @@ static int nic_dev_init(struct pci_dev *pdev) return 0; err_reg_netdev: + hinic_func_table_debug_rem(nic_dev); +err_add_func_table_dbg: + hinic_func_tbl_dbgfs_uninit(nic_dev); + hinic_dbg_uninit(nic_dev); hinic_free_intr_coalesce(nic_dev); err_init_intr: err_set_pfc: @@ -1391,6 +1445,12 @@ static void hinic_remove(struct pci_dev *pdev) unregister_netdev(netdev); + hinic_func_table_debug_rem(nic_dev); + + hinic_func_tbl_dbgfs_uninit(nic_dev); + + hinic_dbg_uninit(nic_dev); + hinic_free_intr_coalesce(nic_dev); hinic_port_del_mac(nic_dev, netdev->dev_addr, 0); @@ -1445,4 +1505,17 @@ static struct pci_driver hinic_driver = { .sriov_configure = hinic_pci_sriov_configure, }; -module_pci_driver(hinic_driver); +static int __init hinic_module_init(void) +{ + hinic_dbg_register_debugfs(HINIC_DRV_NAME); + return pci_register_driver(&hinic_driver); +} + +static void __exit hinic_module_exit(void) +{ + pci_unregister_driver(&hinic_driver); + hinic_dbg_unregister_debugfs(); +} + +module_init(hinic_module_init); +module_exit(hinic_module_exit); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5afb3c9c52d2..86a83e53dce5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -104,8 +104,7 @@ static int send_login(struct ibmvnic_adapter *adapter); static void send_cap_queries(struct ibmvnic_adapter *adapter); static int init_sub_crqs(struct ibmvnic_adapter *); static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter); -static int ibmvnic_init(struct ibmvnic_adapter *); -static int ibmvnic_reset_init(struct ibmvnic_adapter *); +static int ibmvnic_reset_init(struct ibmvnic_adapter *, bool reset); static void release_crq_queue(struct ibmvnic_adapter *); static int __ibmvnic_set_mac(struct net_device *, u8 *); static int init_crq_queue(struct ibmvnic_adapter *adapter); @@ -297,8 +296,7 @@ static void deactivate_rx_pools(struct ibmvnic_adapter *adapter) { int i; - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) + for (i = 0; i < adapter->num_active_rx_pools; i++) adapter->rx_pool[i].active = 0; } @@ -306,6 +304,7 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, struct ibmvnic_rx_pool *pool) { int count = pool->size - atomic_read(&pool->available); + u64 handle = adapter->rx_scrq[pool->index]->handle; struct device *dev = &adapter->vdev->dev; int buffers_added = 0; unsigned long lpar_rc; @@ -314,7 +313,6 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, unsigned int offset; dma_addr_t dma_addr; unsigned char *dst; - u64 *handle_array; int shift = 0; int index; int i; @@ -322,10 +320,6 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, if (!pool->active) return; - handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf-> - off_rxadd_subcrqs)); - for (i = 0; i < count; ++i) { skb = alloc_skb(pool->buff_size, GFP_ATOMIC); if (!skb) { @@ -369,8 +363,7 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, #endif sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift); - lpar_rc = send_subcrq(adapter, handle_array[pool->index], - &sub_crq); + lpar_rc = send_subcrq(adapter, handle, &sub_crq); if (lpar_rc != H_SUCCESS) goto failure; @@ -407,8 +400,7 @@ static void replenish_pools(struct ibmvnic_adapter *adapter) int i; adapter->replenish_task_cycles++; - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) { + for (i = 0; i < adapter->num_active_rx_pools; i++) { if (adapter->rx_pool[i].active) replenish_rx_pool(adapter, &adapter->rx_pool[i]); } @@ -475,22 +467,20 @@ static int init_stats_token(struct ibmvnic_adapter *adapter) static int reset_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; + u64 buff_size; int rx_scrqs; int i, j, rc; - u64 *size_array; - size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); - - rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + buff_size = adapter->cur_rx_buf_sz; + rx_scrqs = adapter->num_active_rx_pools; for (i = 0; i < rx_scrqs; i++) { rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); - if (rx_pool->buff_size != be64_to_cpu(size_array[i])) { + if (rx_pool->buff_size != buff_size) { free_long_term_buff(adapter, &rx_pool->long_term_buff); - rx_pool->buff_size = be64_to_cpu(size_array[i]); + rx_pool->buff_size = buff_size; rc = alloc_long_term_buff(adapter, &rx_pool->long_term_buff, rx_pool->size * @@ -558,13 +548,11 @@ static int init_rx_pools(struct net_device *netdev) struct device *dev = &adapter->vdev->dev; struct ibmvnic_rx_pool *rx_pool; int rxadd_subcrqs; - u64 *size_array; + u64 buff_size; int i, j; - rxadd_subcrqs = - be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); + rxadd_subcrqs = adapter->num_active_rx_scrqs; + buff_size = adapter->cur_rx_buf_sz; adapter->rx_pool = kcalloc(rxadd_subcrqs, sizeof(struct ibmvnic_rx_pool), @@ -582,11 +570,11 @@ static int init_rx_pools(struct net_device *netdev) netdev_dbg(adapter->netdev, "Initializing rx_pool[%d], %lld buffs, %lld bytes each\n", i, adapter->req_rx_add_entries_per_subcrq, - be64_to_cpu(size_array[i])); + buff_size); rx_pool->size = adapter->req_rx_add_entries_per_subcrq; rx_pool->index = i; - rx_pool->buff_size = be64_to_cpu(size_array[i]); + rx_pool->buff_size = buff_size; rx_pool->active = 1; rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int), @@ -649,7 +637,7 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) int tx_scrqs; int i, rc; - tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + tx_scrqs = adapter->num_active_tx_pools; for (i = 0; i < tx_scrqs; i++) { rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); if (rc) @@ -738,7 +726,7 @@ static int init_tx_pools(struct net_device *netdev) int tx_subcrqs; int i, rc; - tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + tx_subcrqs = adapter->num_active_tx_scrqs; adapter->tx_pool = kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); if (!adapter->tx_pool) @@ -974,7 +962,7 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) return -1; } - if (adapter->init_done_rc == 1) { + if (adapter->init_done_rc == PARTIALSUCCESS) { /* Partuial success, delay and re-send */ mdelay(1000); resend = true; @@ -1524,9 +1512,9 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned int offset; int num_entries = 1; unsigned char *dst; - u64 *handle_array; int index = 0; u8 proto = 0; + u64 handle; netdev_tx_t ret = NETDEV_TX_OK; if (test_bit(0, &adapter->resetting)) { @@ -1553,8 +1541,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_scrq = adapter->tx_scrq[queue_num]; txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb)); - handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + - be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs)); + handle = tx_scrq->handle; index = tx_pool->free_map[tx_pool->consumer_index]; @@ -1666,14 +1653,14 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) ret = NETDEV_TX_OK; goto tx_err_out; } - lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num], + lpar_rc = send_subcrq_indirect(adapter, handle, (u64)tx_buff->indir_dma, (u64)num_entries); dma_unmap_single(dev, tx_buff->indir_dma, sizeof(tx_buff->indir_arr), DMA_TO_DEVICE); } else { tx_buff->num_entries = num_entries; - lpar_rc = send_subcrq(adapter, handle_array[queue_num], + lpar_rc = send_subcrq(adapter, handle, &tx_crq); } if (lpar_rc != H_SUCCESS) { @@ -1868,7 +1855,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter, return rc; } - rc = ibmvnic_reset_init(adapter); + rc = ibmvnic_reset_init(adapter, true); if (rc) return IBMVNIC_INIT_FAILED; @@ -1986,7 +1973,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, goto out; } - rc = ibmvnic_reset_init(adapter); + rc = ibmvnic_reset_init(adapter, true); if (rc) { rc = IBMVNIC_INIT_FAILED; goto out; @@ -2093,7 +2080,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, return rc; } - rc = ibmvnic_init(adapter); + rc = ibmvnic_reset_init(adapter, false); if (rc) return rc; @@ -3568,8 +3555,7 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, if (rc) { if (rc == H_CLOSED) { dev_warn(dev, "CRQ Queue closed\n"); - if (test_bit(0, &adapter->resetting)) - ibmvnic_reset(adapter, VNIC_RESET_FATAL); + /* do not reset, report the fail, wait for passive init from server */ } dev_warn(dev, "Send error (rc=%d)\n", rc); @@ -4292,6 +4278,11 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, struct net_device *netdev = adapter->netdev; struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf; struct ibmvnic_login_buffer *login = adapter->login_buf; + u64 *tx_handle_array; + u64 *rx_handle_array; + int num_tx_pools; + int num_rx_pools; + u64 *size_array; int i; dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, @@ -4326,6 +4317,30 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_remove(adapter->vdev); return -EIO; } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); + /* variable buffer sizes are not supported, so just read the + * first entry. + */ + adapter->cur_rx_buf_sz = be64_to_cpu(size_array[0]); + + num_tx_pools = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + num_rx_pools = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + + tx_handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_txsubm_subcrqs)); + rx_handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_subcrqs)); + + for (i = 0; i < num_tx_pools; i++) + adapter->tx_scrq[i]->handle = tx_handle_array[i]; + + for (i = 0; i < num_rx_pools; i++) + adapter->rx_scrq[i]->handle = rx_handle_array[i]; + + adapter->num_active_tx_scrqs = num_tx_pools; + adapter->num_active_rx_scrqs = num_rx_pools; + release_login_rsp_buffer(adapter); release_login_buffer(adapter); complete(&adapter->init_done); @@ -4971,7 +4986,7 @@ map_failed: return retrc; } -static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) +static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) { struct device *dev = &adapter->vdev->dev; unsigned long timeout = msecs_to_jiffies(30000); @@ -4980,12 +4995,19 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) adapter->from_passive_init = false; - old_num_rx_queues = adapter->req_rx_queues; - old_num_tx_queues = adapter->req_tx_queues; + if (reset) { + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + reinit_completion(&adapter->init_done); + } - reinit_completion(&adapter->init_done); adapter->init_done_rc = 0; - ibmvnic_send_crq_init(adapter); + rc = ibmvnic_send_crq_init(adapter); + if (rc) { + dev_err(dev, "Send crq init failed with error %d\n", rc); + return rc; + } + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Initialization sequence timed out\n"); return -1; @@ -4996,13 +5018,8 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) return adapter->init_done_rc; } - if (adapter->from_passive_init) { - adapter->state = VNIC_OPEN; - adapter->from_passive_init = false; - return -1; - } - - if (test_bit(0, &adapter->resetting) && !adapter->wait_for_reset && + if (reset && + test_bit(0, &adapter->resetting) && !adapter->wait_for_reset && adapter->reset_reason != VNIC_RESET_MOBILITY) { if (adapter->req_rx_queues != old_num_rx_queues || adapter->req_tx_queues != old_num_tx_queues) { @@ -5030,48 +5047,6 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) return rc; } -static int ibmvnic_init(struct ibmvnic_adapter *adapter) -{ - struct device *dev = &adapter->vdev->dev; - unsigned long timeout = msecs_to_jiffies(30000); - int rc; - - adapter->from_passive_init = false; - - adapter->init_done_rc = 0; - ibmvnic_send_crq_init(adapter); - if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - dev_err(dev, "Initialization sequence timed out\n"); - return -1; - } - - if (adapter->init_done_rc) { - release_crq_queue(adapter); - return adapter->init_done_rc; - } - - if (adapter->from_passive_init) { - adapter->state = VNIC_OPEN; - adapter->from_passive_init = false; - return -1; - } - - rc = init_sub_crqs(adapter); - if (rc) { - dev_err(dev, "Initialization of sub crqs failed\n"); - release_crq_queue(adapter); - return rc; - } - - rc = init_sub_crq_irqs(adapter); - if (rc) { - dev_err(dev, "Failed to initialize sub crq irqs\n"); - release_crq_queue(adapter); - } - - return rc; -} - static struct device_attribute dev_attr_failover; static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) @@ -5134,7 +5109,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) goto ibmvnic_init_fail; } - rc = ibmvnic_init(adapter); + rc = ibmvnic_reset_init(adapter, false); if (rc && rc != EAGAIN) goto ibmvnic_init_fail; } while (rc == EAGAIN); @@ -5284,8 +5259,7 @@ static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev) for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++) ret += 4 * PAGE_SIZE; /* the scrq message queue */ - for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - i++) + for (i = 0; i < adapter->num_active_rx_pools; i++) ret += adapter->rx_pool[i].size * IOMMU_PAGE_ALIGN(adapter->rx_pool[i].buff_size, tbl); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index f8416e1d4cf0..8da98794eda9 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -875,6 +875,7 @@ struct ibmvnic_sub_crq_queue { struct ibmvnic_adapter *adapter; atomic_t used; char name[32]; + u64 handle; }; struct ibmvnic_long_term_buff { @@ -1075,6 +1076,7 @@ struct ibmvnic_adapter { u32 num_active_rx_napi; u32 num_active_tx_scrqs; u32 num_active_tx_pools; + u32 cur_rx_buf_sz; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index d88dd41a9442..99b8252eb969 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -310,10 +310,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); -#endif + net_prefetch(page_addr); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f14bfc33844c..91ab824926b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1992,10 +1992,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -2078,10 +2076,8 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); + /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index ca041b39ffda..256fa07d54d5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1309,10 +1309,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, @@ -1376,10 +1373,8 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); + /* build an skb around the page buffer */ skb = build_skb(va - IAVF_SKB_PAD, truesize); if (unlikely(!skb)) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index b061dc10703d..eae75260fe20 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -919,10 +919,7 @@ ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch((void *)(xdp->data + L1_CACHE_BYTES)); -#endif + net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) @@ -964,10 +961,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch((void *)(xdp->data + L1_CACHE_BYTES)); -#endif /* L1_CACHE_BYTES */ + net_prefetch(xdp->data); /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 4f05f6efe6af..698bb6a4b088 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8047,10 +8047,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); @@ -8104,10 +8101,7 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* build an skb around the page buffer */ skb = build_skb(va - IGB_SKB_PAD, truesize); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9593aa4eea36..c6968fdb6caa 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1550,10 +1550,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* build an skb around the page buffer */ skb = build_skb(va - IGC_SKB_PAD, truesize); @@ -1589,10 +1586,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); -#if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); -#endif + net_prefetch(va); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGC_RX_HDR_LEN); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index e67b1a59ecb7..0fcd82036d4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -193,7 +193,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } /* alloc the udl from per cpu ddp pool */ - ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_KERNEL, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index c4d41f8aad4a..0b675c34ce49 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2095,10 +2095,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -2161,10 +2159,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, * likely have a consumer accessing first few bytes of meta * data, and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb to around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index a428113e6d54..50afec43e001 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -866,10 +866,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(xdp->data); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data); + /* Note, we get here by enabling legacy-rx via: * * ethtool --set-priv-flags <dev> legacy-rx on @@ -947,10 +945,7 @@ static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring, * have a consumer accessing first few bytes of meta data, * and then actual data. */ - prefetch(xdp->data_meta); -#if L1_CACHE_BYTES < 128 - prefetch(xdp->data_meta + L1_CACHE_BYTES); -#endif + net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ skb = build_skb(xdp->data_hard_start, truesize); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index 1b25948c662b..0bc2410c8949 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += octeontx2_af.o octeontx2_mbox-y := mbox.o octeontx2_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \ - rvu_reg.o rvu_npc.o rvu_debugfs.o + rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index a4e65da8d95b..8f17e26dca53 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -468,6 +468,35 @@ static void cgx_lmac_pause_frm_config(struct cgx *cgx, int lmac_id, bool enable) } } +void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable) +{ + struct cgx *cgx = cgxd; + u64 cfg; + + if (!cgx) + return; + + if (enable) { + /* Enable inbound PTP timestamping */ + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg |= CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg |= CGX_SMUX_RX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } else { + /* Disable inbound PTP stamping */ + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg &= ~CGX_SMUX_RX_FRM_CTL_PTP_MODE; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } +} + /* CGX Firmware interface low level support */ static int cgx_fwi_cmd_send(u64 req, u64 *resp, struct lmac *lmac) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 394f96591feb..27ca3291682b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -58,8 +58,10 @@ #define CGXX_SMUX_RX_FRM_CTL 0x20020 #define CGX_SMUX_RX_FRM_CTL_CTL_BCK BIT_ULL(3) +#define CGX_SMUX_RX_FRM_CTL_PTP_MODE BIT_ULL(12) #define CGXX_GMP_GMI_RXX_FRM_CTL 0x38028 #define CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK BIT_ULL(3) +#define CGX_GMP_GMI_RXX_FRM_CTL_PTP_MODE BIT_ULL(12) #define CGXX_SMUX_TX_CTL 0x20178 #define CGXX_SMUX_TX_PAUSE_PKT_TIME 0x20110 #define CGXX_SMUX_TX_PAUSE_PKT_INTERVAL 0x20120 @@ -139,4 +141,6 @@ int cgx_lmac_get_pause_frm(void *cgxd, int lmac_id, u8 *tx_pause, u8 *rx_pause); int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause); +void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable); + #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6dfd0f90cd70..4aaef0a2b51c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -127,6 +127,7 @@ M(ATTACH_RESOURCES, 0x002, attach_resources, rsrc_attach, msg_rsp) \ M(DETACH_RESOURCES, 0x003, detach_resources, rsrc_detach, msg_rsp) \ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ +M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ @@ -143,6 +144,8 @@ M(CGX_STOP_LINKEVENTS, 0x208, cgx_stop_linkevents, msg_req, msg_rsp) \ M(CGX_GET_LINKINFO, 0x209, cgx_get_linkinfo, msg_req, cgx_link_info_msg) \ M(CGX_INTLBK_ENABLE, 0x20A, cgx_intlbk_enable, msg_req, msg_rsp) \ M(CGX_INTLBK_DISABLE, 0x20B, cgx_intlbk_disable, msg_req, msg_rsp) \ +M(CGX_PTP_RX_ENABLE, 0x20C, cgx_ptp_rx_enable, msg_req, msg_rsp) \ +M(CGX_PTP_RX_DISABLE, 0x20D, cgx_ptp_rx_disable, msg_req, msg_rsp) \ M(CGX_CFG_PAUSE_FRM, 0x20E, cgx_cfg_pause_frm, cgx_pause_frm_cfg, \ cgx_pause_frm_cfg) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ @@ -213,6 +216,8 @@ M(NIX_LSO_FORMAT_CFG, 0x8011, nix_lso_format_cfg, \ nix_lso_format_cfg, \ nix_lso_format_cfg_rsp) \ M(NIX_RXVLAN_ALLOC, 0x8012, nix_rxvlan_alloc, msg_req, msg_rsp) \ +M(NIX_LF_PTP_TX_ENABLE, 0x8013, nix_lf_ptp_tx_enable, msg_req, msg_rsp) \ +M(NIX_LF_PTP_TX_DISABLE, 0x8014, nix_lf_ptp_tx_disable, msg_req, msg_rsp) \ M(NIX_BP_ENABLE, 0x8016, nix_bp_enable, nix_bp_cfg_req, \ nix_bp_cfg_rsp) \ M(NIX_BP_DISABLE, 0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \ @@ -858,4 +863,20 @@ struct npc_get_kex_cfg_rsp { u8 mkex_pfl_name[MKEX_NAME_LEN]; }; +enum ptp_op { + PTP_OP_ADJFINE = 0, + PTP_OP_GET_CLOCK = 1, +}; + +struct ptp_req { + struct mbox_msghdr hdr; + u8 op; + s64 scaled_ppm; +}; + +struct ptp_rsp { + struct mbox_msghdr hdr; + u64 clk; +}; + #endif /* MBOX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c new file mode 100644 index 000000000000..f69f4f35ae48 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell PTP driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include <linux/bitfield.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include "ptp.h" +#include "mbox.h" +#include "rvu.h" + +#define DRV_NAME "Marvell PTP Driver" + +#define PCI_DEVID_OCTEONTX2_PTP 0xA00C +#define PCI_SUBSYS_DEVID_OCTX2_98xx_PTP 0xB100 +#define PCI_SUBSYS_DEVID_OCTX2_96XX_PTP 0xB200 +#define PCI_SUBSYS_DEVID_OCTX2_95XX_PTP 0xB300 +#define PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP 0xB400 +#define PCI_SUBSYS_DEVID_OCTX2_95MM_PTP 0xB500 +#define PCI_DEVID_OCTEONTX2_RST 0xA085 + +#define PCI_PTP_BAR_NO 0 +#define PCI_RST_BAR_NO 0 + +#define PTP_CLOCK_CFG 0xF00ULL +#define PTP_CLOCK_CFG_PTP_EN BIT_ULL(0) +#define PTP_CLOCK_LO 0xF08ULL +#define PTP_CLOCK_HI 0xF10ULL +#define PTP_CLOCK_COMP 0xF18ULL + +#define RST_BOOT 0x1600ULL +#define RST_MUL_BITS GENMASK_ULL(38, 33) +#define CLOCK_BASE_RATE 50000000ULL + +static u64 get_clock_rate(void) +{ + u64 cfg, ret = CLOCK_BASE_RATE * 16; + struct pci_dev *pdev; + void __iomem *base; + + /* To get the input clock frequency with which PTP co-processor + * block is running the base frequency(50 MHz) needs to be multiplied + * with multiplier bits present in RST_BOOT register of RESET block. + * Hence below code gets the multiplier bits from the RESET PCI + * device present in the system. + */ + pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_RST, NULL); + if (!pdev) + goto error; + + base = pci_ioremap_bar(pdev, PCI_RST_BAR_NO); + if (!base) + goto error_put_pdev; + + cfg = readq(base + RST_BOOT); + ret = CLOCK_BASE_RATE * FIELD_GET(RST_MUL_BITS, cfg); + + iounmap(base); + +error_put_pdev: + pci_dev_put(pdev); + +error: + return ret; +} + +struct ptp *ptp_get(void) +{ + struct pci_dev *pdev; + struct ptp *ptp; + + /* If the PTP pci device is found on the system and ptp + * driver is bound to it then the PTP pci device is returned + * to the caller(rvu driver). + */ + pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_PTP, NULL); + if (!pdev) + return ERR_PTR(-ENODEV); + + ptp = pci_get_drvdata(pdev); + if (!ptp) + ptp = ERR_PTR(-EPROBE_DEFER); + if (IS_ERR(ptp)) + pci_dev_put(pdev); + + return ptp; +} + +void ptp_put(struct ptp *ptp) +{ + if (!ptp) + return; + + pci_dev_put(ptp->pdev); +} + +static int ptp_adjfine(struct ptp *ptp, long scaled_ppm) +{ + bool neg_adj = false; + u64 comp; + u64 adj; + s64 ppb; + + if (scaled_ppm < 0) { + neg_adj = true; + scaled_ppm = -scaled_ppm; + } + + /* The hardware adds the clock compensation value to the PTP clock + * on every coprocessor clock cycle. Typical convention is that it + * represent number of nanosecond betwen each cycle. In this + * convention compensation value is in 64 bit fixed-point + * representation where upper 32 bits are number of nanoseconds + * and lower is fractions of nanosecond. + * The scaled_ppm represent the ratio in "parts per million" by which + * the compensation value should be corrected. + * To calculate new compenstation value we use 64bit fixed point + * arithmetic on following formula + * comp = tbase + tbase * scaled_ppm / (1M * 2^16) + * where tbase is the basic compensation value calculated + * initialy in the probe function. + */ + comp = ((u64)1000000000ull << 32) / ptp->clock_rate; + /* convert scaled_ppm to ppb */ + ppb = 1 + scaled_ppm; + ppb *= 125; + ppb >>= 13; + adj = comp * ppb; + adj = div_u64(adj, 1000000000ull); + comp = neg_adj ? comp - adj : comp + adj; + + writeq(comp, ptp->reg_base + PTP_CLOCK_COMP); + + return 0; +} + +static int ptp_get_clock(struct ptp *ptp, u64 *clk) +{ + /* Return the current PTP clock */ + *clk = readq(ptp->reg_base + PTP_CLOCK_HI); + + return 0; +} + +static int ptp_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct ptp *ptp; + u64 clock_comp; + u64 clock_cfg; + int err; + + ptp = devm_kzalloc(dev, sizeof(*ptp), GFP_KERNEL); + if (!ptp) { + err = -ENOMEM; + goto error; + } + + ptp->pdev = pdev; + + err = pcim_enable_device(pdev); + if (err) + goto error_free; + + err = pcim_iomap_regions(pdev, 1 << PCI_PTP_BAR_NO, pci_name(pdev)); + if (err) + goto error_free; + + ptp->reg_base = pcim_iomap_table(pdev)[PCI_PTP_BAR_NO]; + + ptp->clock_rate = get_clock_rate(); + + /* Enable PTP clock */ + clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); + clock_cfg |= PTP_CLOCK_CFG_PTP_EN; + writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); + + clock_comp = ((u64)1000000000ull << 32) / ptp->clock_rate; + /* Initial compensation value to start the nanosecs counter */ + writeq(clock_comp, ptp->reg_base + PTP_CLOCK_COMP); + + pci_set_drvdata(pdev, ptp); + + return 0; + +error_free: + devm_kfree(dev, ptp); + +error: + /* For `ptp_get()` we need to differentiate between the case + * when the core has not tried to probe this device and the case when + * the probe failed. In the later case we pretend that the + * initialization was successful and keep the error in + * `dev->driver_data`. + */ + pci_set_drvdata(pdev, ERR_PTR(err)); + return 0; +} + +static void ptp_remove(struct pci_dev *pdev) +{ + struct ptp *ptp = pci_get_drvdata(pdev); + u64 clock_cfg; + + if (IS_ERR_OR_NULL(ptp)) + return; + + /* Disable PTP clock */ + clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); + clock_cfg &= ~PTP_CLOCK_CFG_PTP_EN; + writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); +} + +static const struct pci_device_id ptp_id_table[] = { + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_98xx_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_96XX_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_95XX_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_LOKI_PTP) }, + { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_PTP, + PCI_VENDOR_ID_CAVIUM, + PCI_SUBSYS_DEVID_OCTX2_95MM_PTP) }, + { 0, } +}; + +struct pci_driver ptp_driver = { + .name = DRV_NAME, + .id_table = ptp_id_table, + .probe = ptp_probe, + .remove = ptp_remove, +}; + +int rvu_mbox_handler_ptp_op(struct rvu *rvu, struct ptp_req *req, + struct ptp_rsp *rsp) +{ + int err = 0; + + /* This function is the PTP mailbox handler invoked when + * called by AF consumers/netdev drivers via mailbox mechanism. + * It is used by netdev driver to get the PTP clock and to set + * frequency adjustments. Since mailbox can be called without + * notion of whether the driver is bound to ptp device below + * validation is needed as first step. + */ + if (!rvu->ptp) + return -ENODEV; + + switch (req->op) { + case PTP_OP_ADJFINE: + err = ptp_adjfine(rvu->ptp, req->scaled_ppm); + break; + case PTP_OP_GET_CLOCK: + err = ptp_get_clock(rvu->ptp, &rsp->clk); + break; + default: + err = -EINVAL; + break; + } + + return err; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h new file mode 100644 index 000000000000..878bc395d28f --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell PTP driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#ifndef PTP_H +#define PTP_H + +#include <linux/timecounter.h> +#include <linux/time64.h> +#include <linux/spinlock.h> + +struct ptp { + struct pci_dev *pdev; + void __iomem *reg_base; + u32 clock_rate; +}; + +struct ptp *ptp_get(void); +void ptp_put(struct ptp *ptp); + +extern struct pci_driver ptp_driver; + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 557e4292c846..c3ef73ae782c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -18,6 +18,7 @@ #include "cgx.h" #include "rvu.h" #include "rvu_reg.h" +#include "ptp.h" #define DRV_NAME "octeontx2-af" #define DRV_STRING "Marvell OcteonTX2 RVU Admin Function Driver" @@ -2565,13 +2566,21 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); + rvu->ptp = ptp_get(); + if (IS_ERR(rvu->ptp)) { + err = PTR_ERR(rvu->ptp); + if (err == -EPROBE_DEFER) + goto err_release_regions; + rvu->ptp = NULL; + } + /* Map Admin function CSRs */ rvu->afreg_base = pcim_iomap(pdev, PCI_AF_REG_BAR_NUM, 0); rvu->pfreg_base = pcim_iomap(pdev, PCI_PF_REG_BAR_NUM, 0); if (!rvu->afreg_base || !rvu->pfreg_base) { dev_err(dev, "Unable to map admin function CSRs, aborting\n"); err = -ENOMEM; - goto err_release_regions; + goto err_put_ptp; } /* Store module params in rvu structure */ @@ -2586,7 +2595,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = rvu_setup_hw_resources(rvu); if (err) - goto err_release_regions; + goto err_put_ptp; /* Init mailbox btw AF and PFs */ err = rvu_mbox_init(rvu, &rvu->afpf_wq_info, TYPE_AFPF, @@ -2626,6 +2635,8 @@ err_hwsetup: rvu_reset_all_blocks(rvu); rvu_free_hw_resources(rvu); rvu_clear_rvum_blk_revid(rvu); +err_put_ptp: + ptp_put(rvu->ptp); err_release_regions: pci_release_regions(pdev); err_disable_device: @@ -2651,6 +2662,7 @@ static void rvu_remove(struct pci_dev *pdev) rvu_reset_all_blocks(rvu); rvu_free_hw_resources(rvu); rvu_clear_rvum_blk_revid(rvu); + ptp_put(rvu->ptp); pci_release_regions(pdev); pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); @@ -2676,9 +2688,19 @@ static int __init rvu_init_module(void) if (err < 0) return err; + err = pci_register_driver(&ptp_driver); + if (err < 0) + goto ptp_err; + err = pci_register_driver(&rvu_driver); if (err < 0) - pci_unregister_driver(&cgx_driver); + goto rvu_err; + + return 0; +rvu_err: + pci_unregister_driver(&ptp_driver); +ptp_err: + pci_unregister_driver(&cgx_driver); return err; } @@ -2686,6 +2708,7 @@ static int __init rvu_init_module(void) static void __exit rvu_cleanup_module(void) { pci_unregister_driver(&rvu_driver); + pci_unregister_driver(&ptp_driver); pci_unregister_driver(&cgx_driver); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index dcf25a092008..05da7a91944a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -289,6 +289,8 @@ struct rvu_fwdata { u64 reserved[FWDATA_RESERVED_MEM]; }; +struct ptp; + struct rvu { void __iomem *afreg_base; void __iomem *pfreg_base; @@ -337,6 +339,8 @@ struct rvu { /* Firmware data */ struct rvu_fwdata *fwdata; + struct ptp *ptp; + #ifdef CONFIG_DEBUG_FS struct rvu_debugfs rvu_dbg; #endif @@ -469,6 +473,7 @@ int rvu_npc_init(struct rvu *rvu); void rvu_npc_freemem(struct rvu *rvu); int rvu_npc_get_pkind(struct rvu *rvu, u16 pf); void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf); +int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool en); void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, u8 *mac_addr); void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index f3c82e489897..fe3389c144b5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -509,6 +509,45 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, return 0; } +static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + u8 cgx_id, lmac_id; + void *cgxd; + + /* This msg is expected only from PFs that are mapped to CGX LMACs, + * if received from other PF/VF simply ACK, nothing to do. + */ + if ((pcifunc & RVU_PFVF_FUNC_MASK) || + !is_pf_cgxmapped(rvu, pf)) + return -ENODEV; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + + cgx_lmac_ptp_config(cgxd, lmac_id, enable); + /* If PTP is enabled then inform NPC that packets to be + * parsed by this PF will have their data shifted by 8 bytes + * and if PTP is disabled then no shift is required + */ + if (npc_config_ts_kpuaction(rvu, pf, pcifunc, enable)) + return -EINVAL; + + return 0; +} + +int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true); +} + +int rvu_mbox_handler_cgx_ptp_rx_disable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, false); +} + static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en) { int pf = rvu_get_pf(pcifunc); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 36953d4f51c7..bb8c607cdcba 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3319,6 +3319,49 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_ctx_free(rvu, pfvf); } +#define NIX_AF_LFX_TX_CFG_PTP_EN BIT_ULL(32) + +static int rvu_nix_lf_ptp_tx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int blkaddr; + int nixlf; + u64 cfg; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + block = &hw->block[blkaddr]; + nixlf = rvu_get_lf(rvu, block, pcifunc, 0); + if (nixlf < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf)); + + if (enable) + cfg |= NIX_AF_LFX_TX_CFG_PTP_EN; + else + cfg &= ~NIX_AF_LFX_TX_CFG_PTP_EN; + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf), cfg); + + return 0; +} + +int rvu_mbox_handler_nix_lf_ptp_tx_enable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_nix_lf_ptp_tx_cfg(rvu, req->hdr.pcifunc, true); +} + +int rvu_mbox_handler_nix_lf_ptp_tx_disable(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_nix_lf_ptp_tx_cfg(rvu, req->hdr.pcifunc, false); +} + int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu, struct nix_lso_format_cfg *req, struct nix_lso_format_cfg_rsp *rsp) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0a214084406a..e2e585d4de9b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -27,6 +27,7 @@ #define NIXLF_PROMISC_ENTRY 2 #define NPC_PARSE_RESULT_DMAC_OFFSET 8 +#define NPC_HW_TSTAMP_OFFSET 8 static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 pcifunc); @@ -61,6 +62,36 @@ int rvu_npc_get_pkind(struct rvu *rvu, u16 pf) return -1; } +#define NPC_AF_ACTION0_PTR_ADVANCE GENMASK_ULL(27, 20) + +int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool enable) +{ + int pkind, blkaddr; + u64 val; + + pkind = rvu_npc_get_pkind(rvu, pf); + if (pkind < 0) { + dev_err(rvu->dev, "%s: pkind not mapped\n", __func__); + return -EINVAL; + } + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, pcifunc); + if (blkaddr < 0) { + dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__); + return -EINVAL; + } + + val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind)); + val &= ~NPC_AF_ACTION0_PTR_ADVANCE; + /* If timestamp is enabled then configure NPC to shift 8 bytes */ + if (enable) + val |= FIELD_PREP(NPC_AF_ACTION0_PTR_ADVANCE, + NPC_HW_TSTAMP_OFFSET); + rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind), val); + + return 0; +} + static int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 778df331c8ac..b2c6385707c9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_OCTEONTX2_PF) += octeontx2_nicpf.o obj-$(CONFIG_OCTEONTX2_VF) += octeontx2_nicvf.o -octeontx2_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o +octeontx2_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ + otx2_ptp.o octeontx2_nicvf-y := otx2_vf.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 93c4cf7fedbf..f8934234e70a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -671,6 +671,13 @@ static int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (!sq->sg) return -ENOMEM; + if (pfvf->ptp) { + err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt, + sizeof(*sq->timestamps)); + if (err) + return err; + } + sq->head = 0; sq->sqe_per_sqb = (pfvf->hw.sqb_size / sq->sqe_size) - 1; sq->num_sqbs = (qset->sqe_cnt + sq->sqe_per_sqb) / sq->sqe_per_sqb; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 2fa29889522e..689925b680db 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -13,6 +13,9 @@ #include <linux/pci.h> #include <linux/iommu.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> #include <mbox.h> #include "otx2_reg.h" @@ -209,6 +212,17 @@ struct refill_work { struct otx2_nic *pf; }; +struct otx2_ptp { + struct ptp_clock_info ptp_info; + struct ptp_clock *ptp_clock; + struct otx2_nic *nic; + + struct cyclecounter cycle_counter; + struct timecounter time_counter; +}; + +#define OTX2_HW_TIMESTAMP_LEN 8 + struct otx2_nic { void __iomem *reg_base; struct net_device *netdev; @@ -216,6 +230,8 @@ struct otx2_nic { u16 max_frs; u16 rbsize; /* Receive buffer size */ +#define OTX2_FLAG_RX_TSTAMP_ENABLED BIT_ULL(0) +#define OTX2_FLAG_TX_TSTAMP_ENABLED BIT_ULL(1) #define OTX2_FLAG_INTF_DOWN BIT_ULL(2) #define OTX2_FLAG_RX_PAUSE_ENABLED BIT_ULL(9) #define OTX2_FLAG_TX_PAUSE_ENABLED BIT_ULL(10) @@ -251,6 +267,9 @@ struct otx2_nic { /* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */ int nix_blkaddr; + + struct otx2_ptp *ptp; + struct hwtstamp_config tstamp; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index d59f5a9c7273..0341d9694e8b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -13,8 +13,10 @@ #include <linux/stddef.h> #include <linux/etherdevice.h> #include <linux/log2.h> +#include <linux/net_tstamp.h> #include "otx2_common.h" +#include "otx2_ptp.h" #define DRV_NAME "octeontx2-nicpf" #define DRV_VF_NAME "octeontx2-nicvf" @@ -663,6 +665,31 @@ static u32 otx2_get_link(struct net_device *netdev) return pfvf->linfo.link_up; } +static int otx2_get_ts_info(struct net_device *netdev, + struct ethtool_ts_info *info) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + + if (!pfvf->ptp) + return ethtool_op_get_ts_info(netdev, info); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->phc_index = otx2_ptp_clock_index(pfvf); + + info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + + info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_ALL); + + return 0; +} + static const struct ethtool_ops otx2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, @@ -687,6 +714,7 @@ static const struct ethtool_ops otx2_ethtool_ops = { .set_msglevel = otx2_set_msglevel, .get_pauseparam = otx2_get_pauseparam, .set_pauseparam = otx2_set_pauseparam, + .get_ts_info = otx2_get_ts_info, }; void otx2_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 75a8c407e815..f5f874a2b53e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -21,6 +21,7 @@ #include "otx2_common.h" #include "otx2_txrx.h" #include "otx2_struct.h" +#include "otx2_ptp.h" #define DRV_NAME "octeontx2-nicpf" #define DRV_STRING "Marvell OcteonTX2 NIC Physical Function Driver" @@ -41,6 +42,9 @@ enum { TYPE_PFVF, }; +static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable); +static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable); + static int otx2_change_mtu(struct net_device *netdev, int new_mtu) { bool if_up = netif_running(netdev); @@ -1281,7 +1285,8 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; /* Get the size of receive buffers to allocate */ - pf->rbsize = RCV_FRAG_LEN(pf->netdev->mtu + OTX2_ETH_HLEN); + pf->rbsize = RCV_FRAG_LEN(OTX2_HW_TIMESTAMP_LEN + pf->netdev->mtu + + OTX2_ETH_HLEN); mutex_lock(&mbox->lock); /* NPA init */ @@ -1547,6 +1552,16 @@ int otx2_open(struct net_device *netdev) otx2_set_cints_affinity(pf); + /* When reinitializing enable time stamping if it is enabled before */ + if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) { + pf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED; + otx2_config_hw_tx_tstamp(pf, true); + } + if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) { + pf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED; + otx2_config_hw_rx_tstamp(pf, true); + } + pf->flags &= ~OTX2_FLAG_INTF_DOWN; /* 'intf_down' may be checked on any cpu */ smp_wmb(); @@ -1738,6 +1753,143 @@ static void otx2_reset_task(struct work_struct *work) rtnl_unlock(); } +static int otx2_config_hw_rx_tstamp(struct otx2_nic *pfvf, bool enable) +{ + struct msg_req *req; + int err; + + if (pfvf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED && enable) + return 0; + + mutex_lock(&pfvf->mbox.lock); + if (enable) + req = otx2_mbox_alloc_msg_cgx_ptp_rx_enable(&pfvf->mbox); + else + req = otx2_mbox_alloc_msg_cgx_ptp_rx_disable(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + + mutex_unlock(&pfvf->mbox.lock); + if (enable) + pfvf->flags |= OTX2_FLAG_RX_TSTAMP_ENABLED; + else + pfvf->flags &= ~OTX2_FLAG_RX_TSTAMP_ENABLED; + return 0; +} + +static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable) +{ + struct msg_req *req; + int err; + + if (pfvf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED && enable) + return 0; + + mutex_lock(&pfvf->mbox.lock); + if (enable) + req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_enable(&pfvf->mbox); + else + req = otx2_mbox_alloc_msg_nix_lf_ptp_tx_disable(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + + mutex_unlock(&pfvf->mbox.lock); + if (enable) + pfvf->flags |= OTX2_FLAG_TX_TSTAMP_ENABLED; + else + pfvf->flags &= ~OTX2_FLAG_TX_TSTAMP_ENABLED; + return 0; +} + +static int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + struct hwtstamp_config config; + + if (!pfvf->ptp) + return -ENODEV; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + otx2_config_hw_tx_tstamp(pfvf, false); + break; + case HWTSTAMP_TX_ON: + otx2_config_hw_tx_tstamp(pfvf, true); + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + otx2_config_hw_rx_tstamp(pfvf, false); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + otx2_config_hw_rx_tstamp(pfvf, true); + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + memcpy(&pfvf->tstamp, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +static int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + struct hwtstamp_config *cfg = &pfvf->tstamp; + + switch (cmd) { + case SIOCSHWTSTAMP: + return otx2_config_hwtstamp(netdev, req); + case SIOCGHWTSTAMP: + return copy_to_user(req->ifr_data, cfg, + sizeof(*cfg)) ? -EFAULT : 0; + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops otx2_netdev_ops = { .ndo_open = otx2_open, .ndo_stop = otx2_stop, @@ -1748,6 +1900,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_features = otx2_set_features, .ndo_tx_timeout = otx2_tx_timeout, .ndo_get_stats64 = otx2_get_stats64, + .ndo_do_ioctl = otx2_ioctl, }; static int otx2_wq_init(struct otx2_nic *pf) @@ -1920,6 +2073,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Assign default mac address */ otx2_get_mac_from_af(netdev); + /* Don't check for error. Proceed without ptp */ + otx2_ptp_init(pf); + /* NPA's pool is a stack to which SW frees buffer pointers via Aura. * HW allocates buffer pointer from stack and uses it for DMA'ing * ingress packet. In some scenarios HW can free back allocated buffer @@ -1952,7 +2108,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_detach_rsrc; + goto err_ptp_destroy; } err = otx2_wq_init(pf); @@ -1972,6 +2128,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_unreg_netdev: unregister_netdev(netdev); +err_ptp_destroy: + otx2_ptp_destroy(pf); err_detach_rsrc: otx2_detach_resources(&pf->mbox); err_disable_mbox_intr: @@ -2113,6 +2271,11 @@ static void otx2_remove(struct pci_dev *pdev) pf = netdev_priv(netdev); + if (pf->flags & OTX2_FLAG_TX_TSTAMP_ENABLED) + otx2_config_hw_tx_tstamp(pf, false); + if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) + otx2_config_hw_rx_tstamp(pf, false); + cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); @@ -2122,6 +2285,7 @@ static void otx2_remove(struct pci_dev *pdev) if (pf->otx2_wq) destroy_workqueue(pf->otx2_wq); + otx2_ptp_destroy(pf); otx2_detach_resources(&pf->mbox); otx2_disable_mbox_intr(pf); otx2_pfaf_mbox_destroy(pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c new file mode 100644 index 000000000000..7bcf5246350f --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell OcteonTx2 PTP support for ethernet driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include "otx2_common.h" +#include "otx2_ptp.h" + +static int otx2_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct ptp_req *req; + int err; + + if (!ptp->nic) + return -ENODEV; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return -ENOMEM; + + req->op = PTP_OP_ADJFINE; + req->scaled_ppm = scaled_ppm; + + err = otx2_sync_mbox_msg(&ptp->nic->mbox); + if (err) + return err; + + return 0; +} + +static u64 ptp_cc_read(const struct cyclecounter *cc) +{ + struct otx2_ptp *ptp = container_of(cc, struct otx2_ptp, cycle_counter); + struct ptp_req *req; + struct ptp_rsp *rsp; + int err; + + if (!ptp->nic) + return 0; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return 0; + + req->op = PTP_OP_GET_CLOCK; + + err = otx2_sync_mbox_msg(&ptp->nic->mbox); + if (err) + return 0; + + rsp = (struct ptp_rsp *)otx2_mbox_get_rsp(&ptp->nic->mbox.mbox, 0, + &req->hdr); + if (IS_ERR(rsp)) + return 0; + + return rsp->clk; +} + +static int otx2_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + + mutex_lock(&pfvf->mbox.lock); + timecounter_adjtime(&ptp->time_counter, delta); + mutex_unlock(&pfvf->mbox.lock); + + return 0; +} + +static int otx2_ptp_gettime(struct ptp_clock_info *ptp_info, + struct timespec64 *ts) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + u64 nsec; + + mutex_lock(&pfvf->mbox.lock); + nsec = timecounter_read(&ptp->time_counter); + mutex_unlock(&pfvf->mbox.lock); + + *ts = ns_to_timespec64(nsec); + + return 0; +} + +static int otx2_ptp_settime(struct ptp_clock_info *ptp_info, + const struct timespec64 *ts) +{ + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + struct otx2_nic *pfvf = ptp->nic; + u64 nsec; + + nsec = timespec64_to_ns(ts); + + mutex_lock(&pfvf->mbox.lock); + timecounter_init(&ptp->time_counter, &ptp->cycle_counter, nsec); + mutex_unlock(&pfvf->mbox.lock); + + return 0; +} + +static int otx2_ptp_enable(struct ptp_clock_info *ptp_info, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +int otx2_ptp_init(struct otx2_nic *pfvf) +{ + struct otx2_ptp *ptp_ptr; + struct cyclecounter *cc; + struct ptp_req *req; + int err; + + mutex_lock(&pfvf->mbox.lock); + /* check if PTP block is available */ + req = otx2_mbox_alloc_msg_ptp_op(&pfvf->mbox); + if (!req) { + mutex_unlock(&pfvf->mbox.lock); + return -ENOMEM; + } + + req->op = PTP_OP_GET_CLOCK; + + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + mutex_unlock(&pfvf->mbox.lock); + return err; + } + mutex_unlock(&pfvf->mbox.lock); + + ptp_ptr = kzalloc(sizeof(*ptp_ptr), GFP_KERNEL); + if (!ptp_ptr) { + err = -ENOMEM; + goto error; + } + + ptp_ptr->nic = pfvf; + + cc = &ptp_ptr->cycle_counter; + cc->read = ptp_cc_read; + cc->mask = CYCLECOUNTER_MASK(64); + cc->mult = 1; + cc->shift = 0; + + timecounter_init(&ptp_ptr->time_counter, &ptp_ptr->cycle_counter, + ktime_to_ns(ktime_get_real())); + + ptp_ptr->ptp_info = (struct ptp_clock_info) { + .owner = THIS_MODULE, + .name = "OcteonTX2 PTP", + .max_adj = 1000000000ull, + .n_ext_ts = 0, + .n_pins = 0, + .pps = 0, + .adjfine = otx2_ptp_adjfine, + .adjtime = otx2_ptp_adjtime, + .gettime64 = otx2_ptp_gettime, + .settime64 = otx2_ptp_settime, + .enable = otx2_ptp_enable, + }; + + ptp_ptr->ptp_clock = ptp_clock_register(&ptp_ptr->ptp_info, pfvf->dev); + if (IS_ERR_OR_NULL(ptp_ptr->ptp_clock)) { + err = ptp_ptr->ptp_clock ? + PTR_ERR(ptp_ptr->ptp_clock) : -ENODEV; + kfree(ptp_ptr); + goto error; + } + + pfvf->ptp = ptp_ptr; + +error: + return err; +} + +void otx2_ptp_destroy(struct otx2_nic *pfvf) +{ + struct otx2_ptp *ptp = pfvf->ptp; + + if (!ptp) + return; + + ptp_clock_unregister(ptp->ptp_clock); + kfree(ptp); + pfvf->ptp = NULL; +} + +int otx2_ptp_clock_index(struct otx2_nic *pfvf) +{ + if (!pfvf->ptp) + return -ENODEV; + + return ptp_clock_index(pfvf->ptp->ptp_clock); +} + +int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) +{ + if (!pfvf->ptp) + return -ENODEV; + + *tsns = timecounter_cyc2time(&pfvf->ptp->time_counter, tstamp); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h new file mode 100644 index 000000000000..706d63a43ae1 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 PTP support for ethernet driver */ + +#ifndef OTX2_PTP_H +#define OTX2_PTP_H + +int otx2_ptp_init(struct otx2_nic *pfvf); +void otx2_ptp_destroy(struct otx2_nic *pfvf); + +int otx2_ptp_clock_index(struct otx2_nic *pfvf); +int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns); + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 3a5b34a2a7a6..1f90426ce8cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -16,6 +16,7 @@ #include "otx2_common.h" #include "otx2_struct.h" #include "otx2_txrx.h" +#include "otx2_ptp.h" #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx))) @@ -81,8 +82,11 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, int budget, int *tx_pkts, int *tx_bytes) { struct nix_send_comp_s *snd_comp = &cqe->comp; + struct skb_shared_hwtstamps ts; struct sk_buff *skb = NULL; + u64 timestamp, tsns; struct sg_list *sg; + int err; if (unlikely(snd_comp->status) && netif_msg_tx_err(pfvf)) net_err_ratelimited("%s: TX%d: Error in send CQ status:%x\n", @@ -94,6 +98,18 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, if (unlikely(!skb)) return; + if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) { + timestamp = ((u64 *)sq->timestamps->base)[snd_comp->sqe_id]; + if (timestamp != 1) { + err = otx2_ptp_tstamp2time(pfvf, timestamp, &tsns); + if (!err) { + memset(&ts, 0, sizeof(ts)); + ts.hwtstamp = ns_to_ktime(tsns); + skb_tstamp_tx(skb, &ts); + } + } + } + *tx_bytes += skb->len; (*tx_pkts)++; otx2_dma_unmap_skb_frags(pfvf, sg); @@ -101,16 +117,47 @@ static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, sg->skb = (u64)NULL; } +static void otx2_set_rxtstamp(struct otx2_nic *pfvf, + struct sk_buff *skb, void *data) +{ + u64 tsns; + int err; + + if (!(pfvf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED)) + return; + + /* The first 8 bytes is the timestamp */ + err = otx2_ptp_tstamp2time(pfvf, be64_to_cpu(*(__be64 *)data), &tsns); + if (err) + return; + + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(tsns); +} + static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, - u64 iova, int len) + u64 iova, int len, struct nix_rx_parse_s *parse) { struct page *page; + int off = 0; void *va; va = phys_to_virt(otx2_iova_to_phys(pfvf->iommu_domain, iova)); + + if (likely(!skb_shinfo(skb)->nr_frags)) { + /* Check if data starts at some nonzero offset + * from the start of the buffer. For now the + * only possible offset is 8 bytes in the case + * where packet is prepended by a timestamp. + */ + if (parse->laptr) { + otx2_set_rxtstamp(pfvf, skb, va); + off = OTX2_HW_TIMESTAMP_LEN; + } + } + page = virt_to_page(va); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - va - page_address(page), len, pfvf->rbsize); + va - page_address(page) + off, len - off, pfvf->rbsize); otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, pfvf->rbsize, DMA_FROM_DEVICE); @@ -239,7 +286,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, if (unlikely(!skb)) return; - otx2_skb_add_frag(pfvf, skb, cqe->sg.seg_addr, cqe->sg.seg_size); + otx2_skb_add_frag(pfvf, skb, cqe->sg.seg_addr, cqe->sg.seg_size, parse); cq->pool_ptrs++; otx2_set_rxhash(pfvf, cqe, skb); @@ -482,10 +529,27 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, ipv6_hdr(skb)->payload_len = htons(ext->lso_sb - skb_network_offset(skb)); } + } else if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + ext->tstmp = 1; } + *offset += sizeof(*ext); } +static void otx2_sqe_add_mem(struct otx2_snd_queue *sq, int *offset, + int alg, u64 iova) +{ + struct nix_sqe_mem_s *mem; + + mem = (struct nix_sqe_mem_s *)(sq->sqe_base + *offset); + mem->subdc = NIX_SUBDC_MEM; + mem->alg = alg; + mem->wmem = 1; /* wait for the memory operation */ + mem->addr = iova; + + *offset += sizeof(*mem); +} + /* Add SQE header subdescriptor structure */ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, struct nix_sqe_hdr_s *sqe_hdr, @@ -736,6 +800,21 @@ static int otx2_get_sqe_count(struct otx2_nic *pfvf, struct sk_buff *skb) return skb_shinfo(skb)->gso_segs; } +static void otx2_set_txtstamp(struct otx2_nic *pfvf, struct sk_buff *skb, + struct otx2_snd_queue *sq, int *offset) +{ + u64 iova; + + if (!skb_shinfo(skb)->gso_size && + skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + iova = sq->timestamps->iova + (sq->head * sizeof(u64)); + otx2_sqe_add_mem(sq, offset, NIX_SENDMEMALG_E_SETTSTMP, iova); + } else { + skb_tx_timestamp(skb); + } +} + bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, struct sk_buff *skb, u16 qidx) { @@ -789,6 +868,8 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, return false; } + otx2_set_txtstamp(pfvf, skb, sq, &offset); + sqe_hdr->sizem1 = (offset / 16) - 1; netdev_tx_sent_queue(txq, skb->len); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index da97f2d4416f..73af15685657 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -91,6 +91,7 @@ struct otx2_snd_queue { struct qmem *sqe; struct qmem *tso_hdrs; struct sg_list *sg; + struct qmem *timestamps; struct queue_stats stats; u16 sqb_count; u64 *sqb_ptrs; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b50c567ef508..99d7737e8ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -705,7 +705,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud frags = ring->rx_info + (index << priv->log_rx_info); va = page_address(frags[0].page) + frags[0].page_offset; - prefetchw(va); + net_prefetchw(va); /* * make sure we read the CQE after we read the ownership bit */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index d521449186cc..145592788de5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -201,7 +201,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) pi = mlx5e_xdpsq_get_next_pi(sq, MLX5_SEND_WQE_MAX_WQEBBS); session->wqe = MLX5E_TX_FETCH_WQE(sq, pi); - prefetchw(session->wqe->data); + net_prefetchw(session->wqe->data); session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; session->pkt_count = 0; @@ -322,7 +322,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, struct mlx5e_xdpsq_stats *stats = sq->stats; - prefetchw(wqe); + net_prefetchw(wqe); if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) { stats->err++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 902ce77d0178..bb6669d2a916 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -49,7 +49,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt32; xdp_set_data_meta_invalid(xdp); xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); - prefetch(xdp->data); + net_prefetch(xdp->data); rcu_read_lock(); consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); @@ -100,7 +100,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, xdp->data_end = xdp->data + cqe_bcnt; xdp_set_data_meta_invalid(xdp); xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); - prefetch(xdp->data); + net_prefetch(xdp->data); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { rq->stats->wqe_err++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 57034c58b971..7aab69e991a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -30,7 +30,6 @@ * SOFTWARE. */ -#include <linux/prefetch.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> @@ -1141,8 +1140,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, dma_sync_single_range_for_cpu(rq->pdev, di->addr, wi->offset, frag_size, DMA_FROM_DEVICE); - prefetchw(va); /* xdp_frame data area */ - prefetch(data); + net_prefetchw(va); /* xdp_frame data area */ + net_prefetch(data); rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); @@ -1184,7 +1183,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); while (byte_cnt) { u16 frag_consumed_bytes = @@ -1399,7 +1398,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); if (unlikely(frag_offset >= PAGE_SIZE)) { di++; @@ -1452,8 +1451,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset, frag_size, DMA_FROM_DEVICE); - prefetchw(va); /* xdp_frame data area */ - prefetch(data); + net_prefetchw(va); /* xdp_frame data area */ + net_prefetch(data); rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 46790216ce86..ce8ab1f01876 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -30,7 +30,6 @@ * SOFTWARE. */ -#include <linux/prefetch.h> #include <linux/ip.h> #include <linux/udp.h> #include <net/udp.h> @@ -115,7 +114,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv) return NULL; } - prefetchw(skb->data); + net_prefetchw(skb->data); skb_reserve(skb, NET_IP_ALIGN); /* Reserve for ethernet and IP header */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 079b080de7f7..485e3e02eb70 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4174,7 +4174,6 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4); #define MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M BIT(0) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII BIT(1) -#define MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII BIT(2) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R BIT(3) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G BIT(4) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G BIT(5) @@ -4197,7 +4196,6 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 BIT(2) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 BIT(3) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR BIT(4) -#define MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2 BIT(5) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 BIT(6) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 BIT(7) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR BIT(12) @@ -4210,10 +4208,6 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 BIT(20) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22) -#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23) -#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX BIT(24) -#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_T BIT(25) -#define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T BIT(26) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 14c78f73bb65..f08cad5b5657 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -993,22 +993,12 @@ struct mlxsw_sp1_port_link_mode { static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, - .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT, - .speed = SPEED_100, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, .speed = SPEED_1000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T, - .mask_ethtool = ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - .speed = SPEED_10000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, @@ -1023,11 +1013,6 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { .speed = SPEED_10000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2, - .mask_ethtool = ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT, - .speed = SPEED_20000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, .mask_ethtool = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, .speed = SPEED_40000, @@ -1092,11 +1077,6 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { .mask_ethtool = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, .speed = SPEED_100000, }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, - .mask_ethtool = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, - .speed = SPEED_100000, - }, }; #define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode) @@ -1237,14 +1217,6 @@ mlxsw_sp2_mask_ethtool_1000base_x_sgmii[] = { ARRAY_SIZE(mlxsw_sp2_mask_ethtool_1000base_x_sgmii) static const enum ethtool_link_mode_bit_indices -mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii[] = { - ETHTOOL_LINK_MODE_2500baseX_Full_BIT, -}; - -#define MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN \ - ARRAY_SIZE(mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii) - -static const enum ethtool_link_mode_bit_indices mlxsw_sp2_mask_ethtool_5gbase_r[] = { ETHTOOL_LINK_MODE_5000baseT_Full_BIT, }; @@ -1408,16 +1380,6 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .speed = SPEED_1000, }, { - .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII, - .mask_ethtool = mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii, - .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN, - .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | - MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X | - MLXSW_SP_PORT_MASK_WIDTH_8X, - .speed = SPEED_2500, - }, - { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R, .mask_ethtool = mlxsw_sp2_mask_ethtool_5gbase_r, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 9650562fc0ef..ca8090a28dec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -314,11 +314,9 @@ static int mlxsw_sp_ptp_parse(struct sk_buff *skb, u8 *p_message_type, u16 *p_sequence_id) { - unsigned int offset = 0; unsigned int ptp_class; - u8 *data; + struct ptp_header *hdr; - data = skb_mac_header(skb); ptp_class = ptp_classify_raw(skb); switch (ptp_class & PTP_CLASS_VMASK) { @@ -329,30 +327,14 @@ static int mlxsw_sp_ptp_parse(struct sk_buff *skb, return -ERANGE; } - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return -ERANGE; - } - - /* PTP header is 34 bytes. */ - if (skb->len < offset + 34) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return -EINVAL; - *p_message_type = data[offset] & 0x0f; - *p_domain_number = data[offset + 4]; - *p_sequence_id = (u16)(data[offset + 30]) << 8 | data[offset + 31]; + *p_message_type = ptp_get_msgtype(hdr, ptp_class); + *p_domain_number = hdr->domain_number; + *p_sequence_id = be16_to_cpu(hdr->sequence_id); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 2e41c5519c1b..433f14ade464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -291,7 +291,7 @@ static void mlxsw_sp_rx_sample_listener(struct sk_buff *skb, u8 local_port, static const struct mlxsw_sp_trap_policer_item mlxsw_sp_trap_policer_items_arr[] = { { - .policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(1, 10 * 1024, 4096), }, { .policer = MLXSW_SP_TRAP_POLICER(2, 128, 128), @@ -303,25 +303,25 @@ mlxsw_sp_trap_policer_items_arr[] = { .policer = MLXSW_SP_TRAP_POLICER(4, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(5, 16 * 1024, 8192), }, { .policer = MLXSW_SP_TRAP_POLICER(6, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(7, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(7, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(8, 20 * 1024, 1024), + .policer = MLXSW_SP_TRAP_POLICER(8, 20 * 1024, 8192), }, { .policer = MLXSW_SP_TRAP_POLICER(9, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(10, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(10, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(11, 360, 128), + .policer = MLXSW_SP_TRAP_POLICER(11, 256, 128), }, { .policer = MLXSW_SP_TRAP_POLICER(12, 128, 128), @@ -330,19 +330,19 @@ mlxsw_sp_trap_policer_items_arr[] = { .policer = MLXSW_SP_TRAP_POLICER(13, 128, 128), }, { - .policer = MLXSW_SP_TRAP_POLICER(14, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(14, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(15, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(15, 1024, 512), }, { - .policer = MLXSW_SP_TRAP_POLICER(16, 24 * 1024, 4096), + .policer = MLXSW_SP_TRAP_POLICER(16, 24 * 1024, 16384), }, { - .policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 4096), + .policer = MLXSW_SP_TRAP_POLICER(17, 19 * 1024, 8192), }, { - .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), + .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 512), }, { .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 6f9a725662fb..5023d91269f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -551,16 +551,6 @@ struct mlxsw_sx_port_link_mode { static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, - .supported = SUPPORTED_100baseT_Full, - .advertised = ADVERTISED_100baseT_Full, - .speed = 100, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_TX, - .speed = 100, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .supported = SUPPORTED_1000baseKX_Full, @@ -568,12 +558,6 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { .speed = 1000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_T, - .supported = SUPPORTED_10000baseT_Full, - .advertised = ADVERTISED_10000baseT_Full, - .speed = 10000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .supported = SUPPORTED_10000baseKX4_Full, @@ -590,12 +574,6 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { .speed = 10000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2, - .supported = SUPPORTED_20000baseKR2_Full, - .advertised = ADVERTISED_20000baseKR2_Full, - .speed = 20000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, .supported = SUPPORTED_40000baseCR4_Full, .advertised = ADVERTISED_40000baseCR4_Full, @@ -634,8 +612,7 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { { .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 | MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, + MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4, .speed = 100000, }, }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index bf516285510f..a2926b1b3cff 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -24,6 +24,7 @@ #define NFP_FLOWER_LAYER_VXLAN BIT(7) #define NFP_FLOWER_LAYER2_GRE BIT(0) +#define NFP_FLOWER_LAYER2_QINQ BIT(4) #define NFP_FLOWER_LAYER2_GENEVE BIT(5) #define NFP_FLOWER_LAYER2_GENEVE_OP BIT(6) #define NFP_FLOWER_LAYER2_TUN_IPV6 BIT(7) @@ -319,6 +320,22 @@ struct nfp_flower_mac_mpls { __be32 mpls_lse; }; +/* VLAN details (2W/8B) + * 3 2 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | outer_tpid | outer_tci | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | inner_tpid | inner_tci | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct nfp_flower_vlan { + __be16 outer_tpid; + __be16 outer_tci; + __be16 inner_tpid; + __be16 inner_tci; +}; + /* L4 ports (for UDP, TCP, SCTP) (1W/4B) * 3 2 1 * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 3bf9c1afa45e..caf12eec9945 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -30,6 +30,8 @@ struct nfp_app; #define NFP_FLOWER_MASK_ELEMENT_RS 1 #define NFP_FLOWER_MASK_HASH_BITS 10 +#define NFP_FLOWER_KEY_MAX_LW 32 + #define NFP_FL_META_FLAG_MANAGE_MASK BIT(7) #define NFP_FL_MASK_REUSE_TIME_NS 40000 @@ -44,6 +46,7 @@ struct nfp_app; #define NFP_FL_FEATS_FLOW_MOD BIT(5) #define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_IPV6_TUN BIT(7) +#define NFP_FL_FEATS_VLAN_QINQ BIT(8) #define NFP_FL_FEATS_HOST_ACK BIT(31) #define NFP_FL_ENABLE_FLOW_MERGE BIT(0) @@ -57,7 +60,8 @@ struct nfp_app; NFP_FL_FEATS_VF_RLIM | \ NFP_FL_FEATS_FLOW_MOD | \ NFP_FL_FEATS_PRE_TUN_RULES | \ - NFP_FL_FEATS_IPV6_TUN) + NFP_FL_FEATS_IPV6_TUN | \ + NFP_FL_FEATS_VLAN_QINQ) struct nfp_fl_mask_id { struct circ_buf mask_id_free_list; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index f7f01e2e3dce..255a4dff6288 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -10,7 +10,7 @@ static void nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, struct nfp_flower_meta_tci *msk, - struct flow_rule *rule, u8 key_type) + struct flow_rule *rule, u8 key_type, bool qinq_sup) { u16 tmp_tci; @@ -24,7 +24,7 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, msk->nfp_flow_key_layer = key_type; msk->mask_id = ~0; - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + if (!qinq_sup && flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { struct flow_match_vlan match; flow_rule_match_vlan(rule, &match); @@ -231,6 +231,50 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext, } static void +nfp_flower_fill_vlan(struct flow_dissector_key_vlan *key, + struct nfp_flower_vlan *frame, + bool outer_vlan) +{ + u16 tci; + + tci = NFP_FLOWER_MASK_VLAN_PRESENT; + tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + key->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + key->vlan_id); + + if (outer_vlan) { + frame->outer_tci = cpu_to_be16(tci); + frame->outer_tpid = key->vlan_tpid; + } else { + frame->inner_tci = cpu_to_be16(tci); + frame->inner_tpid = key->vlan_tpid; + } +} + +static void +nfp_flower_compile_vlan(struct nfp_flower_vlan *ext, + struct nfp_flower_vlan *msk, + struct flow_rule *rule) +{ + struct flow_match_vlan match; + + memset(ext, 0, sizeof(struct nfp_flower_vlan)); + memset(msk, 0, sizeof(struct nfp_flower_vlan)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + flow_rule_match_vlan(rule, &match); + nfp_flower_fill_vlan(match.key, ext, true); + nfp_flower_fill_vlan(match.mask, msk, true); + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + flow_rule_match_cvlan(rule, &match); + nfp_flower_fill_vlan(match.key, ext, false); + nfp_flower_fill_vlan(match.mask, msk, false); + } +} + +static void nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext, struct nfp_flower_ipv4 *msk, struct flow_rule *rule) { @@ -433,7 +477,10 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(flow); + struct nfp_flower_priv *priv = app->priv; + bool qinq_sup; u32 port_id; + int ext_len; int err; u8 *ext; u8 *msk; @@ -446,9 +493,11 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, ext = nfp_flow->unmasked_data; msk = nfp_flow->mask_data; + qinq_sup = !!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ); + nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext, (struct nfp_flower_meta_tci *)msk, - rule, key_ls->key_layer); + rule, key_ls->key_layer, qinq_sup); ext += sizeof(struct nfp_flower_meta_tci); msk += sizeof(struct nfp_flower_meta_tci); @@ -547,6 +596,14 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, } } + if (NFP_FLOWER_LAYER2_QINQ & key_ls->key_layer_two) { + nfp_flower_compile_vlan((struct nfp_flower_vlan *)ext, + (struct nfp_flower_vlan *)msk, + rule); + ext += sizeof(struct nfp_flower_vlan); + msk += sizeof(struct nfp_flower_vlan); + } + if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN || key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) { if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) { @@ -589,5 +646,15 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, } } + /* Check that the flow key does not exceed the maximum limit. + * All structures in the key is multiples of 4 bytes, so use u32. + */ + ext_len = (u32 *)ext - (u32 *)nfp_flow->unmasked_data; + if (ext_len > NFP_FLOWER_KEY_MAX_LW) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: flow key too long"); + return -EOPNOTSUPP; + } + return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 4651fe417b7f..44cf738636ef 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -31,6 +31,7 @@ BIT(FLOW_DISSECTOR_KEY_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_VLAN) | \ + BIT(FLOW_DISSECTOR_KEY_CVLAN) | \ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ @@ -66,7 +67,8 @@ NFP_FLOWER_LAYER_IPV6) #define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ - (NFP_FLOWER_LAYER_PORT | \ + (NFP_FLOWER_LAYER_EXT_META | \ + NFP_FLOWER_LAYER_PORT | \ NFP_FLOWER_LAYER_MAC | \ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) @@ -285,6 +287,30 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support VLAN PCP offload"); return -EOPNOTSUPP; } + if (priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ && + !(key_layer_two & NFP_FLOWER_LAYER2_QINQ)) { + key_layer |= NFP_FLOWER_LAYER_EXT_META; + key_size += sizeof(struct nfp_flower_ext_meta); + key_size += sizeof(struct nfp_flower_vlan); + key_layer_two |= NFP_FLOWER_LAYER2_QINQ; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan cvlan; + + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support VLAN QinQ offload"); + return -EOPNOTSUPP; + } + + flow_rule_match_vlan(rule, &cvlan); + if (!(key_layer_two & NFP_FLOWER_LAYER2_QINQ)) { + key_layer |= NFP_FLOWER_LAYER_EXT_META; + key_size += sizeof(struct nfp_flower_ext_meta); + key_size += sizeof(struct nfp_flower_vlan); + key_layer_two |= NFP_FLOWER_LAYER2_QINQ; + } } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { @@ -1066,6 +1092,7 @@ err_destroy_merge_flow: * nfp_flower_validate_pre_tun_rule() * @app: Pointer to the APP handle * @flow: Pointer to NFP flow representation of rule + * @key_ls: Pointer to NFP key layers structure * @extack: Netlink extended ACK report * * Verifies the flow as a pre-tunnel rule. @@ -1075,10 +1102,13 @@ err_destroy_merge_flow: static int nfp_flower_validate_pre_tun_rule(struct nfp_app *app, struct nfp_fl_payload *flow, + struct nfp_fl_key_ls *key_ls, struct netlink_ext_ack *extack) { + struct nfp_flower_priv *priv = app->priv; struct nfp_flower_meta_tci *meta_tci; struct nfp_flower_mac_mpls *mac; + u8 *ext = flow->unmasked_data; struct nfp_fl_act_head *act; u8 *mask = flow->mask_data; bool vlan = false; @@ -1086,20 +1116,25 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, u8 key_layer; meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; - if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { - u16 vlan_tci = be16_to_cpu(meta_tci->tci); - - vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; - flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); - vlan = true; - } else { - flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + key_layer = key_ls->key_layer; + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } } - key_layer = meta_tci->nfp_flow_key_layer; if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); return -EOPNOTSUPP; + } else if (key_ls->key_layer_two & ~NFP_FLOWER_LAYER2_QINQ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non-vlan in extended match fields"); + return -EOPNOTSUPP; } if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { @@ -1109,7 +1144,13 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, /* Skip fields known to exist. */ mask += sizeof(struct nfp_flower_meta_tci); + ext += sizeof(struct nfp_flower_meta_tci); + if (key_ls->key_layer_two) { + mask += sizeof(struct nfp_flower_ext_meta); + ext += sizeof(struct nfp_flower_ext_meta); + } mask += sizeof(struct nfp_flower_in_port); + ext += sizeof(struct nfp_flower_in_port); /* Ensure destination MAC address is fully matched. */ mac = (struct nfp_flower_mac_mpls *)mask; @@ -1118,6 +1159,8 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + mask += sizeof(struct nfp_flower_mac_mpls); + ext += sizeof(struct nfp_flower_mac_mpls); if (key_layer & NFP_FLOWER_LAYER_IPV4 || key_layer & NFP_FLOWER_LAYER_IPV6) { /* Flags and proto fields have same offset in IPv4 and IPv6. */ @@ -1130,7 +1173,6 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, sizeof(struct nfp_flower_ipv4) : sizeof(struct nfp_flower_ipv6); - mask += sizeof(struct nfp_flower_mac_mpls); /* Ensure proto and flags are the only IP layer fields. */ for (i = 0; i < size; i++) @@ -1138,6 +1180,25 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); return -EOPNOTSUPP; } + ext += size; + mask += size; + } + + if ((priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ)) { + if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_QINQ) { + struct nfp_flower_vlan *vlan_tags; + u16 vlan_tci; + + vlan_tags = (struct nfp_flower_vlan *)ext; + + vlan_tci = be16_to_cpu(vlan_tags->outer_tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } } /* Action must be a single egress or pop_vlan and egress. */ @@ -1220,7 +1281,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_destroy_flow; if (flow_pay->pre_tun_rule.dev) { - err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, key_layer, extack); if (err) goto err_destroy_flow; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index f5a910c458ba..f699ed19eb4f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -42,13 +42,11 @@ struct ionic { struct ionic_dev_bar bars[IONIC_BARS_MAX]; unsigned int num_bars; struct ionic_identity ident; - struct list_head lifs; - struct ionic_lif *master_lif; + struct ionic_lif *lif; unsigned int nnqs_per_lif; unsigned int neqs_per_lif; unsigned int ntxqs_per_lif; unsigned int nrxqs_per_lif; - DECLARE_BITMAP(lifbits, IONIC_LIFS_MAX); unsigned int nintrs; DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); struct work_struct nb_work; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 85c686c16741..d1d6fb6669e5 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -294,21 +294,21 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_port_reset; } - err = ionic_lifs_size(ionic); + err = ionic_lif_size(ionic); if (err) { - dev_err(dev, "Cannot size LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot size LIF: %d, aborting\n", err); goto err_out_port_reset; } - err = ionic_lifs_alloc(ionic); + err = ionic_lif_alloc(ionic); if (err) { - dev_err(dev, "Cannot allocate LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot allocate LIF: %d, aborting\n", err); goto err_out_free_irqs; } - err = ionic_lifs_init(ionic); + err = ionic_lif_init(ionic->lif); if (err) { - dev_err(dev, "Cannot init LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot init LIF: %d, aborting\n", err); goto err_out_free_lifs; } @@ -321,9 +321,9 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(dev, "Cannot enable existing VFs: %d\n", err); } - err = ionic_lifs_register(ionic); + err = ionic_lif_register(ionic->lif); if (err) { - dev_err(dev, "Cannot register LIFs: %d, aborting\n", err); + dev_err(dev, "Cannot register LIF: %d, aborting\n", err); goto err_out_deinit_lifs; } @@ -336,12 +336,13 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_out_deregister_lifs: - ionic_lifs_unregister(ionic); + ionic_lif_unregister(ionic->lif); err_out_deinit_lifs: ionic_vf_dealloc(ionic); - ionic_lifs_deinit(ionic); + ionic_lif_deinit(ionic->lif); err_out_free_lifs: - ionic_lifs_free(ionic); + ionic_lif_free(ionic->lif); + ionic->lif = NULL; err_out_free_irqs: ionic_bus_free_irq_vectors(ionic); err_out_port_reset: @@ -377,11 +378,12 @@ static void ionic_remove(struct pci_dev *pdev) if (!ionic) return; - if (ionic->master_lif) { + if (ionic->lif) { ionic_devlink_unregister(ionic); - ionic_lifs_unregister(ionic); - ionic_lifs_deinit(ionic); - ionic_lifs_free(ionic); + ionic_lif_unregister(ionic->lif); + ionic_lif_deinit(ionic->lif); + ionic_lif_free(ionic->lif); + ionic->lif = NULL; ionic_bus_free_irq_vectors(ionic); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 11621ccc1faf..683bbbf75115 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -76,7 +76,7 @@ static int q_tail_show(struct seq_file *seq, void *v) { struct ionic_queue *q = seq->private; - seq_printf(seq, "%d\n", q->tail->index); + seq_printf(seq, "%d\n", q->tail_idx); return 0; } @@ -86,7 +86,7 @@ static int q_head_show(struct seq_file *seq, void *v) { struct ionic_queue *q = seq->private; - seq_printf(seq, "%d\n", q->head->index); + seq_printf(seq, "%d\n", q->head_idx); return 0; } @@ -96,7 +96,7 @@ static int cq_tail_show(struct seq_file *seq, void *v) { struct ionic_cq *cq = seq->private; - seq_printf(seq, "%d\n", cq->tail->index); + seq_printf(seq, "%d\n", cq->tail_idx); return 0; } @@ -112,7 +112,8 @@ static const struct debugfs_reg32 intr_ctrl_regs[] = { void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) { - struct dentry *q_dentry, *cq_dentry, *intr_dentry, *stats_dentry; + struct dentry *qcq_dentry, *q_dentry, *cq_dentry; + struct dentry *intr_dentry, *stats_dentry; struct ionic_dev *idev = &lif->ionic->idev; struct debugfs_regset32 *intr_ctrl_regset; struct ionic_intr_info *intr = &qcq->intr; @@ -121,21 +122,21 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) struct ionic_queue *q = &qcq->q; struct ionic_cq *cq = &qcq->cq; - qcq->dentry = debugfs_create_dir(q->name, lif->dentry); + qcq_dentry = debugfs_create_dir(q->name, lif->dentry); + if (IS_ERR_OR_NULL(qcq_dentry)) + return; + qcq->dentry = qcq_dentry; - debugfs_create_x32("total_size", 0400, qcq->dentry, &qcq->total_size); - debugfs_create_x64("base_pa", 0400, qcq->dentry, &qcq->base_pa); + debugfs_create_x64("q_base_pa", 0400, qcq_dentry, &qcq->q_base_pa); + debugfs_create_x32("q_size", 0400, qcq_dentry, &qcq->q_size); + debugfs_create_x64("cq_base_pa", 0400, qcq_dentry, &qcq->cq_base_pa); + debugfs_create_x32("cq_size", 0400, qcq_dentry, &qcq->cq_size); + debugfs_create_x64("sg_base_pa", 0400, qcq_dentry, &qcq->sg_base_pa); + debugfs_create_x32("sg_size", 0400, qcq_dentry, &qcq->sg_size); q_dentry = debugfs_create_dir("q", qcq->dentry); debugfs_create_u32("index", 0400, q_dentry, &q->index); - debugfs_create_x64("base_pa", 0400, q_dentry, &q->base_pa); - if (qcq->flags & IONIC_QCQ_F_SG) { - debugfs_create_x64("sg_base_pa", 0400, q_dentry, - &q->sg_base_pa); - debugfs_create_u32("sg_desc_size", 0400, q_dentry, - &q->sg_desc_size); - } debugfs_create_u32("num_descs", 0400, q_dentry, &q->num_descs); debugfs_create_u32("desc_size", 0400, q_dentry, &q->desc_size); debugfs_create_u32("pid", 0400, q_dentry, &q->pid); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index d83eff0ae0ac..3645673b4b18 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -21,8 +21,8 @@ static void ionic_watchdog_cb(struct timer_list *t) hb = ionic_heartbeat_check(ionic); - if (hb >= 0 && ionic->master_lif) - ionic_link_status_check_request(ionic->master_lif); + if (hb >= 0 && ionic->lif) + ionic_link_status_check_request(ionic->lif); } void ionic_init_devinfo(struct ionic *ionic) @@ -126,7 +126,7 @@ int ionic_heartbeat_check(struct ionic *ionic) /* is this a transition? */ if (fw_status != idev->last_fw_status && idev->last_fw_status != 0xff) { - struct ionic_lif *lif = ionic->master_lif; + struct ionic_lif *lif = ionic->lif; bool trigger = false; if (!fw_status || fw_status == 0xff) { @@ -482,7 +482,7 @@ int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, cq->bound_intr = intr; cq->num_descs = num_descs; cq->desc_size = desc_size; - cq->tail = cq->info; + cq->tail_idx = 0; cq->done_color = 1; cur = cq->info; @@ -522,15 +522,18 @@ unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, ionic_cq_cb cb, ionic_cq_done_cb done_cb, void *done_arg) { + struct ionic_cq_info *cq_info; unsigned int work_done = 0; if (work_to_do == 0) return 0; - while (cb(cq, cq->tail)) { - if (cq->tail->last) + cq_info = &cq->info[cq->tail_idx]; + while (cb(cq, cq_info)) { + if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; - cq->tail = cq->tail->next; + cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1); + cq_info = &cq->info[cq->tail_idx]; DEBUG_STATS_CQE_CNT(cq); if (++work_done >= work_to_do) @@ -565,8 +568,8 @@ int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, q->num_descs = num_descs; q->desc_size = desc_size; q->sg_desc_size = sg_desc_size; - q->tail = q->info; - q->head = q->tail; + q->tail_idx = 0; + q->head_idx = 0; q->pid = pid; snprintf(q->name, sizeof(q->name), "L%d-%s%u", lif->index, name, index); @@ -614,19 +617,22 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, void *cb_arg) { struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *desc_info; struct ionic_lif *lif = q->lif; - q->head->cb = cb; - q->head->cb_arg = cb_arg; - q->head = q->head->next; + desc_info = &q->info[q->head_idx]; + desc_info->cb = cb; + desc_info->cb_arg = cb_arg; + + q->head_idx = (q->head_idx + 1) & (q->num_descs - 1); dev_dbg(dev, "lif=%d qname=%s qid=%d qtype=%d p_index=%d ringdb=%d\n", q->lif->index, q->name, q->hw_type, q->hw_index, - q->head->index, ring_doorbell); + q->head_idx, ring_doorbell); if (ring_doorbell) ionic_dbell_ring(lif->kern_dbpage, q->hw_type, - q->dbval | q->head->index); + q->dbval | q->head_idx); } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) @@ -634,8 +640,8 @@ static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) unsigned int mask, tail, head; mask = q->num_descs - 1; - tail = q->tail->index; - head = q->head->index; + tail = q->tail_idx; + head = q->head_idx; return ((pos - tail) & mask) < ((head - tail) & mask); } @@ -648,18 +654,18 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, void *cb_arg; /* check for empty queue */ - if (q->tail->index == q->head->index) + if (q->tail_idx == q->head_idx) return; /* stop index must be for a descriptor that is not yet completed */ if (unlikely(!ionic_q_is_posted(q, stop_index))) dev_err(q->lif->ionic->dev, "ionic stop is not posted %s stop %u tail %u head %u\n", - q->name, stop_index, q->tail->index, q->head->index); + q->name, stop_index, q->tail_idx, q->head_idx); do { - desc_info = q->tail; - q->tail = desc_info->next; + desc_info = &q->info[q->tail_idx]; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); cb = desc_info->cb; cb_arg = desc_info->cb_arg; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index d5cba502abca..9e2ac2b8a082 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -149,7 +149,13 @@ struct ionic_dev { }; struct ionic_cq_info { - void *cq_desc; + union { + void *cq_desc; + struct ionic_txq_comp *txcq; + struct ionic_rxq_comp *rxcq; + struct ionic_admin_comp *admincq; + struct ionic_notifyq_event *notifyq; + }; struct ionic_cq_info *next; unsigned int index; bool last; @@ -169,8 +175,17 @@ struct ionic_page_info { }; struct ionic_desc_info { - void *desc; - void *sg_desc; + union { + void *desc; + struct ionic_txq_desc *txq_desc; + struct ionic_rxq_desc *rxq_desc; + struct ionic_admin_cmd *adminq_desc; + }; + union { + void *sg_desc; + struct ionic_txq_sg_desc *txq_sg_desc; + struct ionic_rxq_sg_desc *rxq_sgl_desc; + }; struct ionic_desc_info *next; unsigned int index; unsigned int left; @@ -183,22 +198,32 @@ struct ionic_desc_info { #define IONIC_QUEUE_NAME_MAX_SZ 32 struct ionic_queue { + struct device *dev; u64 dbell_count; u64 drop; u64 stop; u64 wake; struct ionic_lif *lif; struct ionic_desc_info *info; - struct ionic_desc_info *tail; - struct ionic_desc_info *head; struct ionic_dev *idev; + u16 head_idx; + u16 tail_idx; unsigned int index; unsigned int type; unsigned int hw_index; unsigned int hw_type; u64 dbval; - void *base; - void *sg_base; + union { + void *base; + struct ionic_txq_desc *txq; + struct ionic_rxq_desc *rxq; + struct ionic_admin_cmd *adminq; + }; + union { + void *sg_base; + struct ionic_txq_sg_desc *txq_sgl; + struct ionic_rxq_sg_desc *rxq_sgl; + }; dma_addr_t base_pa; dma_addr_t sg_base_pa; unsigned int num_descs; @@ -225,9 +250,9 @@ struct ionic_cq { dma_addr_t base_pa; struct ionic_lif *lif; struct ionic_cq_info *info; - struct ionic_cq_info *tail; struct ionic_queue *bound_q; struct ionic_intr_info *bound_intr; + u16 tail_idx; bool done_color; unsigned int num_descs; u64 compl_count; @@ -246,12 +271,12 @@ static inline void ionic_intr_init(struct ionic_dev *idev, static inline unsigned int ionic_q_space_avail(struct ionic_queue *q) { - unsigned int avail = q->tail->index; + unsigned int avail = q->tail_idx; - if (q->head->index >= avail) - avail += q->head->left - 1; + if (q->head_idx >= avail) + avail += q->num_descs - q->head_idx - 1; else - avail -= q->head->index + 1; + avail -= q->head_idx + 1; return avail; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index c4f4fd469fe3..8d9fb2e19cca 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -85,7 +85,7 @@ int ionic_devlink_register(struct ionic *ionic) dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); else devlink_port_type_eth_set(&ionic->dl_port, - ionic->master_lif->netdev); + ionic->lif->netdev); return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index 3c57c331729f..00aad7168915 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -454,7 +454,7 @@ static int ionic_set_coalesce(struct net_device *netdev, if (test_bit(IONIC_LIF_F_UP, lif->state)) { for (i = 0; i < lif->nxqs; i++) { - qcq = lif->rxqcqs[i].qcq; + qcq = lif->rxqcqs[i]; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, qcq->intr.index, lif->rx_coalesce_hw); @@ -471,7 +471,7 @@ static int ionic_set_coalesce(struct net_device *netdev, if (test_bit(IONIC_LIF_F_UP, lif->state)) { for (i = 0; i < lif->nxqs; i++) { - qcq = lif->txqcqs[i].qcq; + qcq = lif->txqcqs[i]; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, qcq->intr.index, lif->tx_coalesce_hw); @@ -493,18 +493,14 @@ static void ionic_get_ringparam(struct net_device *netdev, ring->rx_pending = lif->nrxq_descs; } -static void ionic_set_ringsize(struct ionic_lif *lif, void *arg) -{ - struct ethtool_ringparam *ring = arg; - - lif->ntxq_descs = ring->tx_pending; - lif->nrxq_descs = ring->rx_pending; -} - static int ionic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_queue_params qparam; + int err; + + ionic_init_queue_params(lif, &qparam); if (ring->rx_mini_pending || ring->rx_jumbo_pending) { netdev_info(netdev, "Changing jumbo or mini descriptors not supported\n"); @@ -522,7 +518,28 @@ static int ionic_set_ringparam(struct net_device *netdev, ring->rx_pending == lif->nrxq_descs) return 0; - return ionic_reset_queues(lif, ionic_set_ringsize, ring); + if (ring->tx_pending != lif->ntxq_descs) + netdev_info(netdev, "Changing Tx ring size from %d to %d\n", + lif->ntxq_descs, ring->tx_pending); + + if (ring->rx_pending != lif->nrxq_descs) + netdev_info(netdev, "Changing Rx ring size from %d to %d\n", + lif->nrxq_descs, ring->rx_pending); + + /* if we're not running, just set the values and return */ + if (!netif_running(lif->netdev)) { + lif->ntxq_descs = ring->tx_pending; + lif->nrxq_descs = ring->rx_pending; + return 0; + } + + qparam.ntxq_descs = ring->tx_pending; + qparam.nrxq_descs = ring->rx_pending; + err = ionic_reconfigure_queues(lif, &qparam); + if (err) + netdev_info(netdev, "Ring reconfiguration failed, changes canceled: %d\n", err); + + return err; } static void ionic_get_channels(struct net_device *netdev, @@ -544,32 +561,15 @@ static void ionic_get_channels(struct net_device *netdev, } } -static void ionic_set_queuecount(struct ionic_lif *lif, void *arg) -{ - struct ethtool_channels *ch = arg; - - if (ch->combined_count) { - lif->nxqs = ch->combined_count; - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { - clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); - lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; - lif->tx_coalesce_hw = lif->rx_coalesce_hw; - netdev_info(lif->netdev, "Sharing queue interrupts\n"); - } - } else { - lif->nxqs = ch->rx_count; - if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { - set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); - netdev_info(lif->netdev, "Splitting queue interrupts\n"); - } - } -} - static int ionic_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { struct ionic_lif *lif = netdev_priv(netdev); - int new_cnt; + struct ionic_queue_params qparam; + int max_cnt; + int err; + + ionic_init_queue_params(lif, &qparam); if (ch->rx_count != ch->tx_count) { netdev_info(netdev, "The rx and tx count must be equal\n"); @@ -577,20 +577,63 @@ static int ionic_set_channels(struct net_device *netdev, } if (ch->combined_count && ch->rx_count) { - netdev_info(netdev, "Use either combined_count or rx/tx_count, not both\n"); + netdev_info(netdev, "Use either combined or rx and tx, not both\n"); return -EINVAL; } - if (ch->combined_count) - new_cnt = ch->combined_count; - else - new_cnt = ch->rx_count; + max_cnt = lif->ionic->ntxqs_per_lif; + if (ch->combined_count) { + if (ch->combined_count > max_cnt) + return -EINVAL; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netdev_info(lif->netdev, "Sharing queue interrupts\n"); + else if (ch->combined_count == lif->nxqs) + return 0; + + if (lif->nxqs != ch->combined_count) + netdev_info(netdev, "Changing queue count from %d to %d\n", + lif->nxqs, ch->combined_count); - if (lif->nxqs != new_cnt) - netdev_info(netdev, "Changing queue count from %d to %d\n", - lif->nxqs, new_cnt); + qparam.nxqs = ch->combined_count; + qparam.intr_split = 0; + } else { + max_cnt /= 2; + if (ch->rx_count > max_cnt) + return -EINVAL; - return ionic_reset_queues(lif, ionic_set_queuecount, ch); + if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + netdev_info(lif->netdev, "Splitting queue interrupts\n"); + else if (ch->rx_count == lif->nxqs) + return 0; + + if (lif->nxqs != ch->rx_count) + netdev_info(netdev, "Changing queue count from %d to %d\n", + lif->nxqs, ch->rx_count); + + qparam.nxqs = ch->rx_count; + qparam.intr_split = 1; + } + + /* if we're not running, just set the values and return */ + if (!netif_running(lif->netdev)) { + lif->nxqs = qparam.nxqs; + + if (qparam.intr_split) { + set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + } else { + clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; + } + return 0; + } + + err = ionic_reconfigure_queues(lif, &qparam); + if (err) + netdev_info(netdev, "Queue reconfiguration failed, changes canceled: %d\n", err); + + return err; } static u32 ionic_get_priv_flags(struct net_device *netdev) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 26988ad7ec97..eeaa73650986 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -36,6 +36,8 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif); static void ionic_lif_handle_fw_up(struct ionic_lif *lif); static void ionic_lif_set_netdev_info(struct ionic_lif *lif); +static void ionic_txrx_deinit(struct ionic_lif *lif); +static int ionic_txrx_init(struct ionic_lif *lif); static int ionic_start_queues(struct ionic_lif *lif); static void ionic_stop_queues(struct ionic_lif *lif); static void ionic_lif_queue_identify(struct ionic_lif *lif); @@ -297,6 +299,18 @@ static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq) qcq->flags &= ~IONIC_QCQ_F_INITED; } +static void ionic_qcq_intr_free(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + if (!(qcq->flags & IONIC_QCQ_F_INTR) || qcq->intr.vector == 0) + return; + + irq_set_affinity_hint(qcq->intr.vector, NULL); + devm_free_irq(lif->ionic->dev, qcq->intr.vector, &qcq->napi); + qcq->intr.vector = 0; + ionic_intr_free(lif->ionic, qcq->intr.index); + qcq->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; +} + static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) { struct device *dev = lif->ionic->dev; @@ -306,51 +320,62 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) ionic_debugfs_del_qcq(qcq); - dma_free_coherent(dev, qcq->total_size, qcq->base, qcq->base_pa); - qcq->base = NULL; - qcq->base_pa = 0; + if (qcq->q_base) { + dma_free_coherent(dev, qcq->q_size, qcq->q_base, qcq->q_base_pa); + qcq->q_base = NULL; + qcq->q_base_pa = 0; + } - if (qcq->flags & IONIC_QCQ_F_INTR) { - irq_set_affinity_hint(qcq->intr.vector, NULL); - devm_free_irq(dev, qcq->intr.vector, &qcq->napi); - qcq->intr.vector = 0; - ionic_intr_free(lif->ionic, qcq->intr.index); + if (qcq->cq_base) { + dma_free_coherent(dev, qcq->cq_size, qcq->cq_base, qcq->cq_base_pa); + qcq->cq_base = NULL; + qcq->cq_base_pa = 0; + } + + if (qcq->sg_base) { + dma_free_coherent(dev, qcq->sg_size, qcq->sg_base, qcq->sg_base_pa); + qcq->sg_base = NULL; + qcq->sg_base_pa = 0; } - devm_kfree(dev, qcq->cq.info); - qcq->cq.info = NULL; - devm_kfree(dev, qcq->q.info); - qcq->q.info = NULL; - devm_kfree(dev, qcq); + ionic_qcq_intr_free(lif, qcq); + + if (qcq->cq.info) { + devm_kfree(dev, qcq->cq.info); + qcq->cq.info = NULL; + } + if (qcq->q.info) { + devm_kfree(dev, qcq->q.info); + qcq->q.info = NULL; + } } static void ionic_qcqs_free(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; - unsigned int i; if (lif->notifyqcq) { ionic_qcq_free(lif, lif->notifyqcq); + devm_kfree(dev, lif->notifyqcq); lif->notifyqcq = NULL; } if (lif->adminqcq) { ionic_qcq_free(lif, lif->adminqcq); + devm_kfree(dev, lif->adminqcq); lif->adminqcq = NULL; } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) - if (lif->rxqcqs[i].stats) - devm_kfree(dev, lif->rxqcqs[i].stats); + devm_kfree(dev, lif->rxqstats); + lif->rxqstats = NULL; devm_kfree(dev, lif->rxqcqs); lif->rxqcqs = NULL; } if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) - if (lif->txqcqs[i].stats) - devm_kfree(dev, lif->txqcqs[i].stats); + devm_kfree(dev, lif->txqstats); + lif->txqstats = NULL; devm_kfree(dev, lif->txqcqs); lif->txqcqs = NULL; } @@ -368,6 +393,53 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.index = src_qcq->intr.index; } +static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + int err; + + if (!(qcq->flags & IONIC_QCQ_F_INTR)) { + qcq->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; + return 0; + } + + err = ionic_intr_alloc(lif, &qcq->intr); + if (err) { + netdev_warn(lif->netdev, "no intr for %s: %d\n", + qcq->q.name, err); + goto err_out; + } + + err = ionic_bus_get_irq(lif->ionic, qcq->intr.index); + if (err < 0) { + netdev_warn(lif->netdev, "no vector for %s: %d\n", + qcq->q.name, err); + goto err_out_free_intr; + } + qcq->intr.vector = err; + ionic_intr_mask_assert(lif->ionic->idev.intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + + err = ionic_request_irq(lif, qcq); + if (err) { + netdev_warn(lif->netdev, "irq request failed %d\n", err); + goto err_out_free_intr; + } + + /* try to get the irq on the local numa node first */ + qcq->intr.cpu = cpumask_local_spread(qcq->intr.index, + dev_to_node(lif->ionic->dev)); + if (qcq->intr.cpu != -1) + cpumask_set_cpu(qcq->intr.cpu, &qcq->intr.affinity_mask); + + netdev_dbg(lif->netdev, "%s: Interrupt index %d\n", qcq->q.name, qcq->intr.index); + return 0; + +err_out_free_intr: + ionic_intr_free(lif->ionic, qcq->intr.index); +err_out: + return err; +} + static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, unsigned int index, const char *name, unsigned int flags, @@ -377,7 +449,6 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, unsigned int pid, struct ionic_qcq **qcq) { struct ionic_dev *idev = &lif->ionic->idev; - u32 q_size, cq_size, sg_size, total_size; struct device *dev = lif->ionic->dev; void *q_base, *cq_base, *sg_base; dma_addr_t cq_base_pa = 0; @@ -388,21 +459,6 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, *qcq = NULL; - q_size = num_descs * desc_size; - cq_size = num_descs * cq_desc_size; - sg_size = num_descs * sg_desc_size; - - total_size = ALIGN(q_size, PAGE_SIZE) + ALIGN(cq_size, PAGE_SIZE); - /* Note: aligning q_size/cq_size is not enough due to cq_base - * address aligning as q_base could be not aligned to the page. - * Adding PAGE_SIZE. - */ - total_size += PAGE_SIZE; - if (flags & IONIC_QCQ_F_SG) { - total_size += ALIGN(sg_size, PAGE_SIZE); - total_size += PAGE_SIZE; - } - new = devm_kzalloc(dev, sizeof(*new), GFP_KERNEL); if (!new) { netdev_err(lif->netdev, "Cannot allocate queue structure\n"); @@ -417,7 +473,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, if (!new->q.info) { netdev_err(lif->netdev, "Cannot allocate queue info\n"); err = -ENOMEM; - goto err_out; + goto err_out_free_qcq; } new->q.type = type; @@ -426,41 +482,12 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, desc_size, sg_desc_size, pid); if (err) { netdev_err(lif->netdev, "Cannot initialize queue\n"); - goto err_out; + goto err_out_free_q_info; } - if (flags & IONIC_QCQ_F_INTR) { - err = ionic_intr_alloc(lif, &new->intr); - if (err) { - netdev_warn(lif->netdev, "no intr for %s: %d\n", - name, err); - goto err_out; - } - - err = ionic_bus_get_irq(lif->ionic, new->intr.index); - if (err < 0) { - netdev_warn(lif->netdev, "no vector for %s: %d\n", - name, err); - goto err_out_free_intr; - } - new->intr.vector = err; - ionic_intr_mask_assert(idev->intr_ctrl, new->intr.index, - IONIC_INTR_MASK_SET); - - err = ionic_request_irq(lif, new); - if (err) { - netdev_warn(lif->netdev, "irq request failed %d\n", err); - goto err_out_free_intr; - } - - new->intr.cpu = cpumask_local_spread(new->intr.index, - dev_to_node(dev)); - if (new->intr.cpu != -1) - cpumask_set_cpu(new->intr.cpu, - &new->intr.affinity_mask); - } else { - new->intr.index = IONIC_INTR_INDEX_NOT_ASSIGNED; - } + err = ionic_alloc_qcq_interrupt(lif, new); + if (err) + goto err_out; new->cq.info = devm_kcalloc(dev, num_descs, sizeof(*new->cq.info), GFP_KERNEL); @@ -473,46 +500,67 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size); if (err) { netdev_err(lif->netdev, "Cannot initialize completion queue\n"); - goto err_out_free_irq; + goto err_out_free_cq_info; } - new->base = dma_alloc_coherent(dev, total_size, &new->base_pa, - GFP_KERNEL); - if (!new->base) { + new->q_size = PAGE_SIZE + (num_descs * desc_size); + new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, + GFP_KERNEL); + if (!new->q_base) { netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n"); err = -ENOMEM; - goto err_out_free_irq; + goto err_out_free_cq_info; } + q_base = PTR_ALIGN(new->q_base, PAGE_SIZE); + q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); + ionic_q_map(&new->q, q_base, q_base_pa); - new->total_size = total_size; - - q_base = new->base; - q_base_pa = new->base_pa; - - cq_base = (void *)ALIGN((uintptr_t)q_base + q_size, PAGE_SIZE); - cq_base_pa = ALIGN(q_base_pa + q_size, PAGE_SIZE); + new->cq_size = PAGE_SIZE + (num_descs * cq_desc_size); + new->cq_base = dma_alloc_coherent(dev, new->cq_size, &new->cq_base_pa, + GFP_KERNEL); + if (!new->cq_base) { + netdev_err(lif->netdev, "Cannot allocate cq DMA memory\n"); + err = -ENOMEM; + goto err_out_free_q; + } + cq_base = PTR_ALIGN(new->cq_base, PAGE_SIZE); + cq_base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE); + ionic_cq_map(&new->cq, cq_base, cq_base_pa); + ionic_cq_bind(&new->cq, &new->q); if (flags & IONIC_QCQ_F_SG) { - sg_base = (void *)ALIGN((uintptr_t)cq_base + cq_size, - PAGE_SIZE); - sg_base_pa = ALIGN(cq_base_pa + cq_size, PAGE_SIZE); + new->sg_size = PAGE_SIZE + (num_descs * sg_desc_size); + new->sg_base = dma_alloc_coherent(dev, new->sg_size, &new->sg_base_pa, + GFP_KERNEL); + if (!new->sg_base) { + netdev_err(lif->netdev, "Cannot allocate sg DMA memory\n"); + err = -ENOMEM; + goto err_out_free_cq; + } + sg_base = PTR_ALIGN(new->sg_base, PAGE_SIZE); + sg_base_pa = ALIGN(new->sg_base_pa, PAGE_SIZE); ionic_q_sg_map(&new->q, sg_base, sg_base_pa); } - ionic_q_map(&new->q, q_base, q_base_pa); - ionic_cq_map(&new->cq, cq_base, cq_base_pa); - ionic_cq_bind(&new->cq, &new->q); - *qcq = new; return 0; +err_out_free_cq: + dma_free_coherent(dev, new->cq_size, new->cq_base, new->cq_base_pa); +err_out_free_q: + dma_free_coherent(dev, new->q_size, new->q_base, new->q_base_pa); +err_out_free_cq_info: + devm_kfree(dev, new->cq.info); err_out_free_irq: - if (flags & IONIC_QCQ_F_INTR) + if (flags & IONIC_QCQ_F_INTR) { devm_free_irq(dev, new->intr.vector, &new->napi); -err_out_free_intr: - if (flags & IONIC_QCQ_F_INTR) ionic_intr_free(lif->ionic, new->intr.index); + } +err_out_free_q_info: + devm_kfree(dev, new->q.info); +err_out_free_qcq: + devm_kfree(dev, new); err_out: dev_err(dev, "qcq alloc of %s%d failed %d\n", name, index, err); return err; @@ -521,10 +569,8 @@ err_out: static int ionic_qcqs_alloc(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; - unsigned int q_list_size; unsigned int flags; int err; - int i; flags = IONIC_QCQ_F_INTR; err = ionic_qcq_alloc(lif, IONIC_QTYPE_ADMINQ, 0, "admin", flags, @@ -544,63 +590,50 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif) sizeof(union ionic_notifyq_comp), 0, lif->kern_pid, &lif->notifyqcq); if (err) - goto err_out_free_adminqcq; + goto err_out; ionic_debugfs_add_qcq(lif, lif->notifyqcq); /* Let the notifyq ride on the adminq interrupt */ ionic_link_qcq_interrupts(lif->adminqcq, lif->notifyqcq); } - q_list_size = sizeof(*lif->txqcqs) * lif->nxqs; err = -ENOMEM; - lif->txqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + lif->txqcqs = devm_kcalloc(dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); if (!lif->txqcqs) - goto err_out_free_notifyqcq; - for (i = 0; i < lif->nxqs; i++) { - lif->txqcqs[i].stats = devm_kzalloc(dev, - sizeof(struct ionic_q_stats), - GFP_KERNEL); - if (!lif->txqcqs[i].stats) - goto err_out_free_tx_stats; - } - - lif->rxqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + goto err_out; + lif->rxqcqs = devm_kcalloc(dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); if (!lif->rxqcqs) - goto err_out_free_tx_stats; - for (i = 0; i < lif->nxqs; i++) { - lif->rxqcqs[i].stats = devm_kzalloc(dev, - sizeof(struct ionic_q_stats), - GFP_KERNEL); - if (!lif->rxqcqs[i].stats) - goto err_out_free_rx_stats; - } + goto err_out; - return 0; + lif->txqstats = devm_kcalloc(dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_tx_stats), GFP_KERNEL); + if (!lif->txqstats) + goto err_out; + lif->rxqstats = devm_kcalloc(dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_rx_stats), GFP_KERNEL); + if (!lif->rxqstats) + goto err_out; -err_out_free_rx_stats: - for (i = 0; i < lif->nxqs; i++) - if (lif->rxqcqs[i].stats) - devm_kfree(dev, lif->rxqcqs[i].stats); - devm_kfree(dev, lif->rxqcqs); - lif->rxqcqs = NULL; -err_out_free_tx_stats: - for (i = 0; i < lif->nxqs; i++) - if (lif->txqcqs[i].stats) - devm_kfree(dev, lif->txqcqs[i].stats); - devm_kfree(dev, lif->txqcqs); - lif->txqcqs = NULL; -err_out_free_notifyqcq: - if (lif->notifyqcq) { - ionic_qcq_free(lif, lif->notifyqcq); - lif->notifyqcq = NULL; - } -err_out_free_adminqcq: - ionic_qcq_free(lif, lif->adminqcq); - lif->adminqcq = NULL; + return 0; +err_out: + ionic_qcqs_free(lif); return err; } +static void ionic_qcq_sanitize(struct ionic_qcq *qcq) +{ + qcq->q.tail_idx = 0; + qcq->q.head_idx = 0; + qcq->cq.tail_idx = 0; + qcq->cq.done_color = 1; + memset(qcq->q_base, 0, qcq->q_size); + memset(qcq->cq_base, 0, qcq->cq_size); + memset(qcq->sg_base, 0, qcq->sg_size); +} + static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) { struct device *dev = lif->ionic->dev; @@ -626,10 +659,10 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) unsigned int intr_index; int err; - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + if (qcq->flags & IONIC_QCQ_F_INTR) intr_index = qcq->intr.index; else - intr_index = lif->rxqcqs[q->index].qcq->intr.index; + intr_index = lif->rxqcqs[q->index]->intr.index; ctx.cmd.q_init.intr_index = cpu_to_le16(intr_index); dev_dbg(dev, "txq_init.pid %d\n", ctx.cmd.q_init.pid); @@ -640,9 +673,7 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq_init.ver %d\n", ctx.cmd.q_init.ver); dev_dbg(dev, "txq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); - q->tail = q->info; - q->head = q->tail; - cq->tail = cq->info; + ionic_qcq_sanitize(qcq); err = ionic_adminq_post_wait(lif, &ctx); if (err) @@ -697,9 +728,7 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq_init.ver %d\n", ctx.cmd.q_init.ver); dev_dbg(dev, "rxq_init.intr_index %d\n", ctx.cmd.q_init.intr_index); - q->tail = q->info; - q->head = q->tail; - cq->tail = cq->info; + ionic_qcq_sanitize(qcq); err = ionic_adminq_post_wait(lif, &ctx); if (err) @@ -1315,6 +1344,35 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa) return ionic_addr_add(netdev, mac); } +static void ionic_stop_queues_reconfig(struct ionic_lif *lif) +{ + /* Stop and clean the queues before reconfiguration */ + mutex_lock(&lif->queue_lock); + netif_device_detach(lif->netdev); + ionic_stop_queues(lif); + ionic_txrx_deinit(lif); +} + +static int ionic_start_queues_reconfig(struct ionic_lif *lif) +{ + int err; + + /* Re-init the queues after reconfiguration */ + + /* The only way txrx_init can fail here is if communication + * with FW is suddenly broken. There's not much we can do + * at this point - error messages have already been printed, + * so we can continue on and the user can eventually do a + * DOWN and UP to try to reset and clear the issue. + */ + err = ionic_txrx_init(lif); + mutex_unlock(&lif->queue_lock); + ionic_link_status_check_request(lif); + netif_device_attach(lif->netdev); + + return err; +} + static int ionic_change_mtu(struct net_device *netdev, int new_mtu) { struct ionic_lif *lif = netdev_priv(netdev); @@ -1334,9 +1392,12 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) return err; netdev->mtu = new_mtu; - err = ionic_reset_queues(lif, NULL, NULL); + /* if we're not running, nothing more to do */ + if (!netif_running(netdev)) + return 0; - return err; + ionic_stop_queues_reconfig(lif); + return ionic_start_queues_reconfig(lif); } static void ionic_tx_timeout_work(struct work_struct *ws) @@ -1345,9 +1406,14 @@ static void ionic_tx_timeout_work(struct work_struct *ws) netdev_info(lif->netdev, "Tx Timeout recovery\n"); - rtnl_lock(); - ionic_reset_queues(lif, NULL, NULL); - rtnl_unlock(); + /* if we were stopped before this scheduled job was launched, + * don't bother the queues as they are already stopped. + */ + if (!netif_running(lif->netdev)) + return; + + ionic_stop_queues_reconfig(lif); + ionic_start_queues_reconfig(lif); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -1482,7 +1548,7 @@ static void ionic_txrx_disable(struct ionic_lif *lif) if (lif->txqcqs) { for (i = 0; i < lif->nxqs; i++) { - err = ionic_qcq_disable(lif->txqcqs[i].qcq); + err = ionic_qcq_disable(lif->txqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1490,7 +1556,7 @@ static void ionic_txrx_disable(struct ionic_lif *lif) if (lif->rxqcqs) { for (i = 0; i < lif->nxqs; i++) { - err = ionic_qcq_disable(lif->rxqcqs[i].qcq); + err = ionic_qcq_disable(lif->rxqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1502,18 +1568,18 @@ static void ionic_txrx_deinit(struct ionic_lif *lif) unsigned int i; if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); - ionic_tx_flush(&lif->txqcqs[i].qcq->cq); - ionic_tx_empty(&lif->txqcqs[i].qcq->q); + for (i = 0; i < lif->nxqs && lif->txqcqs[i]; i++) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); + ionic_tx_flush(&lif->txqcqs[i]->cq); + ionic_tx_empty(&lif->txqcqs[i]->q); } } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); - ionic_rx_flush(&lif->rxqcqs[i].qcq->cq); - ionic_rx_empty(&lif->rxqcqs[i].qcq->q); + for (i = 0; i < lif->nxqs && lif->rxqcqs[i]; i++) { + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]); + ionic_rx_flush(&lif->rxqcqs[i]->cq); + ionic_rx_empty(&lif->rxqcqs[i]->q); } } lif->rx_mode = 0; @@ -1524,16 +1590,18 @@ static void ionic_txrx_free(struct ionic_lif *lif) unsigned int i; if (lif->txqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_qcq_free(lif, lif->txqcqs[i].qcq); - lif->txqcqs[i].qcq = NULL; + for (i = 0; i < lif->ionic->ntxqs_per_lif && lif->txqcqs[i]; i++) { + ionic_qcq_free(lif, lif->txqcqs[i]); + devm_kfree(lif->ionic->dev, lif->txqcqs[i]); + lif->txqcqs[i] = NULL; } } if (lif->rxqcqs) { - for (i = 0; i < lif->nxqs; i++) { - ionic_qcq_free(lif, lif->rxqcqs[i].qcq); - lif->rxqcqs[i].qcq = NULL; + for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) { + ionic_qcq_free(lif, lif->rxqcqs[i]); + devm_kfree(lif->ionic->dev, lif->rxqcqs[i]); + lif->rxqcqs[i] = NULL; } } } @@ -1561,17 +1629,16 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) sizeof(struct ionic_txq_desc), sizeof(struct ionic_txq_comp), sg_desc_sz, - lif->kern_pid, &lif->txqcqs[i].qcq); + lif->kern_pid, &lif->txqcqs[i]); if (err) goto err_out; if (flags & IONIC_QCQ_F_INTR) ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->txqcqs[i].qcq->intr.index, + lif->txqcqs[i]->intr.index, lif->tx_coalesce_hw); - lif->txqcqs[i].qcq->stats = lif->txqcqs[i].stats; - ionic_debugfs_add_qcq(lif, lif->txqcqs[i].qcq); + ionic_debugfs_add_qcq(lif, lif->txqcqs[i]); } flags = IONIC_QCQ_F_RX_STATS | IONIC_QCQ_F_SG | IONIC_QCQ_F_INTR; @@ -1581,20 +1648,19 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) sizeof(struct ionic_rxq_desc), sizeof(struct ionic_rxq_comp), sizeof(struct ionic_rxq_sg_desc), - lif->kern_pid, &lif->rxqcqs[i].qcq); + lif->kern_pid, &lif->rxqcqs[i]); if (err) goto err_out; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[i].qcq->intr.index, + lif->rxqcqs[i]->intr.index, lif->rx_coalesce_hw); if (!test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) - ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, - lif->txqcqs[i].qcq); + ionic_link_qcq_interrupts(lif->rxqcqs[i], + lif->txqcqs[i]); - lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; - ionic_debugfs_add_qcq(lif, lif->rxqcqs[i].qcq); + ionic_debugfs_add_qcq(lif, lif->rxqcqs[i]); } return 0; @@ -1611,13 +1677,13 @@ static int ionic_txrx_init(struct ionic_lif *lif) int err; for (i = 0; i < lif->nxqs; i++) { - err = ionic_lif_txq_init(lif, lif->txqcqs[i].qcq); + err = ionic_lif_txq_init(lif, lif->txqcqs[i]); if (err) goto err_out; - err = ionic_lif_rxq_init(lif, lif->rxqcqs[i].qcq); + err = ionic_lif_rxq_init(lif, lif->rxqcqs[i]); if (err) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); goto err_out; } } @@ -1631,8 +1697,8 @@ static int ionic_txrx_init(struct ionic_lif *lif) err_out: while (i--) { - ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); - ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->txqcqs[i]); + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]); } return err; @@ -1643,15 +1709,15 @@ static int ionic_txrx_enable(struct ionic_lif *lif) int i, err; for (i = 0; i < lif->nxqs; i++) { - ionic_rx_fill(&lif->rxqcqs[i].qcq->q); - err = ionic_qcq_enable(lif->rxqcqs[i].qcq); + ionic_rx_fill(&lif->rxqcqs[i]->q); + err = ionic_qcq_enable(lif->rxqcqs[i]); if (err) goto err_out; - err = ionic_qcq_enable(lif->txqcqs[i].qcq); + err = ionic_qcq_enable(lif->txqcqs[i]); if (err) { if (err != -ETIMEDOUT) - ionic_qcq_disable(lif->rxqcqs[i].qcq); + ionic_qcq_disable(lif->rxqcqs[i]); goto err_out; } } @@ -1660,10 +1726,10 @@ static int ionic_txrx_enable(struct ionic_lif *lif) err_out: while (i--) { - err = ionic_qcq_disable(lif->txqcqs[i].qcq); + err = ionic_qcq_disable(lif->txqcqs[i]); if (err == -ETIMEDOUT) break; - err = ionic_qcq_disable(lif->rxqcqs[i].qcq); + err = ionic_qcq_disable(lif->rxqcqs[i]); if (err == -ETIMEDOUT) break; } @@ -1688,7 +1754,7 @@ static int ionic_start_queues(struct ionic_lif *lif) return 0; } -int ionic_open(struct net_device *netdev) +static int ionic_open(struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); int err; @@ -1734,7 +1800,7 @@ static void ionic_stop_queues(struct ionic_lif *lif) ionic_txrx_disable(lif); } -int ionic_stop(struct net_device *netdev) +static int ionic_stop(struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); @@ -2016,35 +2082,210 @@ static const struct net_device_ops ionic_netdev_ops = { .ndo_get_vf_stats = ionic_get_vf_stats, }; -int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg) -{ - bool running; - int err = 0; +static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b) +{ + /* only swapping the queues, not the napi, flags, or other stuff */ + swap(a->q.num_descs, b->q.num_descs); + swap(a->q.base, b->q.base); + swap(a->q.base_pa, b->q.base_pa); + swap(a->q.info, b->q.info); + swap(a->q_base, b->q_base); + swap(a->q_base_pa, b->q_base_pa); + swap(a->q_size, b->q_size); + + swap(a->q.sg_base, b->q.sg_base); + swap(a->q.sg_base_pa, b->q.sg_base_pa); + swap(a->sg_base, b->sg_base); + swap(a->sg_base_pa, b->sg_base_pa); + swap(a->sg_size, b->sg_size); + + swap(a->cq.num_descs, b->cq.num_descs); + swap(a->cq.base, b->cq.base); + swap(a->cq.base_pa, b->cq.base_pa); + swap(a->cq.info, b->cq.info); + swap(a->cq_base, b->cq_base); + swap(a->cq_base_pa, b->cq_base_pa); + swap(a->cq_size, b->cq_size); +} + +int ionic_reconfigure_queues(struct ionic_lif *lif, + struct ionic_queue_params *qparam) +{ + struct ionic_qcq **tx_qcqs = NULL; + struct ionic_qcq **rx_qcqs = NULL; + unsigned int sg_desc_sz; + unsigned int flags; + int err = -ENOMEM; + unsigned int i; - mutex_lock(&lif->queue_lock); - running = netif_running(lif->netdev); - if (running) { - netif_device_detach(lif->netdev); - err = ionic_stop(lif->netdev); + /* allocate temporary qcq arrays to hold new queue structs */ + if (qparam->nxqs != lif->nxqs || qparam->ntxq_descs != lif->ntxq_descs) { + tx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->ntxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); + if (!tx_qcqs) + goto err_out; + } + if (qparam->nxqs != lif->nxqs || qparam->nrxq_descs != lif->nrxq_descs) { + rx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->nrxqs_per_lif, + sizeof(struct ionic_qcq *), GFP_KERNEL); + if (!rx_qcqs) + goto err_out; + } + + /* allocate new desc_info and rings, but leave the interrupt setup + * until later so as to not mess with the still-running queues + */ + if (lif->qtype_info[IONIC_QTYPE_TXQ].version >= 1 && + lif->qtype_info[IONIC_QTYPE_TXQ].sg_desc_sz == + sizeof(struct ionic_txq_sg_desc_v1)) + sg_desc_sz = sizeof(struct ionic_txq_sg_desc_v1); + else + sg_desc_sz = sizeof(struct ionic_txq_sg_desc); + + if (tx_qcqs) { + for (i = 0; i < qparam->nxqs; i++) { + flags = lif->txqcqs[i]->flags & ~IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, + qparam->ntxq_descs, + sizeof(struct ionic_txq_desc), + sizeof(struct ionic_txq_comp), + sg_desc_sz, + lif->kern_pid, &tx_qcqs[i]); + if (err) + goto err_out; + } + } + + if (rx_qcqs) { + for (i = 0; i < qparam->nxqs; i++) { + flags = lif->rxqcqs[i]->flags & ~IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, + qparam->nrxq_descs, + sizeof(struct ionic_rxq_desc), + sizeof(struct ionic_rxq_comp), + sizeof(struct ionic_rxq_sg_desc), + lif->kern_pid, &rx_qcqs[i]); + if (err) + goto err_out; + } + } + + /* stop and clean the queues */ + ionic_stop_queues_reconfig(lif); + + if (qparam->nxqs != lif->nxqs) { + err = netif_set_real_num_tx_queues(lif->netdev, qparam->nxqs); if (err) - goto reset_out; + goto err_out_reinit_unlock; + err = netif_set_real_num_rx_queues(lif->netdev, qparam->nxqs); + if (err) { + netif_set_real_num_tx_queues(lif->netdev, lif->nxqs); + goto err_out_reinit_unlock; + } } - if (cb) - cb(lif, arg); + /* swap new desc_info and rings, keeping existing interrupt config */ + if (tx_qcqs) { + lif->ntxq_descs = qparam->ntxq_descs; + for (i = 0; i < qparam->nxqs; i++) + ionic_swap_queues(lif->txqcqs[i], tx_qcqs[i]); + } - if (running) { - err = ionic_open(lif->netdev); - netif_device_attach(lif->netdev); + if (rx_qcqs) { + lif->nrxq_descs = qparam->nrxq_descs; + for (i = 0; i < qparam->nxqs; i++) + ionic_swap_queues(lif->rxqcqs[i], rx_qcqs[i]); } -reset_out: - mutex_unlock(&lif->queue_lock); + /* if we need to change the interrupt layout, this is the time */ + if (qparam->intr_split != test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state) || + qparam->nxqs != lif->nxqs) { + if (qparam->intr_split) { + set_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + } else { + clear_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); + lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; + lif->tx_coalesce_hw = lif->rx_coalesce_hw; + } + + /* clear existing interrupt assignments */ + for (i = 0; i < lif->ionic->ntxqs_per_lif; i++) { + ionic_qcq_intr_free(lif, lif->txqcqs[i]); + ionic_qcq_intr_free(lif, lif->rxqcqs[i]); + } + + /* re-assign the interrupts */ + for (i = 0; i < qparam->nxqs; i++) { + lif->rxqcqs[i]->flags |= IONIC_QCQ_F_INTR; + err = ionic_alloc_qcq_interrupt(lif, lif->rxqcqs[i]); + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[i]->intr.index, + lif->rx_coalesce_hw); + + if (qparam->intr_split) { + lif->txqcqs[i]->flags |= IONIC_QCQ_F_INTR; + err = ionic_alloc_qcq_interrupt(lif, lif->txqcqs[i]); + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->txqcqs[i]->intr.index, + lif->tx_coalesce_hw); + } else { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_link_qcq_interrupts(lif->rxqcqs[i], lif->txqcqs[i]); + } + } + } + + swap(lif->nxqs, qparam->nxqs); + +err_out_reinit_unlock: + /* re-init the queues, but don't loose an error code */ + if (err) + ionic_start_queues_reconfig(lif); + else + err = ionic_start_queues_reconfig(lif); + +err_out: + /* free old allocs without cleaning intr */ + for (i = 0; i < qparam->nxqs; i++) { + if (tx_qcqs && tx_qcqs[i]) { + tx_qcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, tx_qcqs[i]); + devm_kfree(lif->ionic->dev, tx_qcqs[i]); + tx_qcqs[i] = NULL; + } + if (rx_qcqs && rx_qcqs[i]) { + rx_qcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, rx_qcqs[i]); + devm_kfree(lif->ionic->dev, rx_qcqs[i]); + rx_qcqs[i] = NULL; + } + } + + /* free q array */ + if (rx_qcqs) { + devm_kfree(lif->ionic->dev, rx_qcqs); + rx_qcqs = NULL; + } + if (tx_qcqs) { + devm_kfree(lif->ionic->dev, tx_qcqs); + tx_qcqs = NULL; + } + + /* clean the unused dma and info allocations when new set is smaller + * than the full array, but leave the qcq shells in place + */ + for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } return err; } -static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index) +int ionic_lif_alloc(struct ionic *ionic) { struct device *dev = ionic->dev; union ionic_lif_identity *lid; @@ -2055,7 +2296,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lid = kzalloc(sizeof(*lid), GFP_KERNEL); if (!lid) - return ERR_PTR(-ENOMEM); + return -ENOMEM; netdev = alloc_etherdev_mqs(sizeof(*lif), ionic->ntxqs_per_lif, ionic->ntxqs_per_lif); @@ -2069,7 +2310,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif = netdev_priv(netdev); lif->netdev = netdev; - ionic->master_lif = lif; + ionic->lif = lif; netdev->netdev_ops = &ionic_netdev_ops; ionic_ethtool_set_ops(netdev); @@ -2079,7 +2320,8 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->identity = lid; lif->lif_type = IONIC_LIF_TYPE_CLASSIC; ionic_lif_identify(ionic, lif->lif_type, lif->identity); - lif->netdev->min_mtu = le32_to_cpu(lif->identity->eth.min_frame_size); + lif->netdev->min_mtu = max_t(unsigned int, ETH_MIN_MTU, + le32_to_cpu(lif->identity->eth.min_frame_size)); lif->netdev->max_mtu = le32_to_cpu(lif->identity->eth.max_frame_size) - ETH_HLEN - VLAN_HLEN; @@ -2087,7 +2329,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->nxqs = ionic->ntxqs_per_lif; lif->ionic = ionic; - lif->index = index; + lif->index = 0; lif->ntxq_descs = IONIC_DEF_TXRX_DESC; lif->nrxq_descs = IONIC_DEF_TXRX_DESC; lif->tx_budget = IONIC_TX_BUDGET_DEFAULT; @@ -2099,7 +2341,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index lif->tx_coalesce_usecs = lif->rx_coalesce_usecs; lif->tx_coalesce_hw = lif->rx_coalesce_hw; - snprintf(lif->name, sizeof(lif->name), "lif%u", index); + snprintf(lif->name, sizeof(lif->name), "lif%u", lif->index); spin_lock_init(&lif->adminq_lock); @@ -2119,7 +2361,8 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index ionic_debugfs_add_lif(lif); - /* allocate queues */ + /* allocate control queues and txrx queue arrays */ + ionic_lif_queue_identify(lif); err = ionic_qcqs_alloc(lif); if (err) goto err_out_free_lif_info; @@ -2138,9 +2381,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index } netdev_rss_key_fill(lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE); - list_add_tail(&lif->list, &ionic->lifs); - - return lif; + return 0; err_out_free_qcqs: ionic_qcqs_free(lif); @@ -2154,27 +2395,7 @@ err_out_free_netdev: err_out_free_lid: kfree(lid); - return ERR_PTR(err); -} - -int ionic_lifs_alloc(struct ionic *ionic) -{ - struct ionic_lif *lif; - - INIT_LIST_HEAD(&ionic->lifs); - - /* only build the first lif, others are for later features */ - set_bit(0, ionic->lifbits); - - lif = ionic_lif_alloc(ionic, 0); - if (IS_ERR_OR_NULL(lif)) { - clear_bit(0, ionic->lifbits); - return -ENOMEM; - } - - ionic_lif_queue_identify(lif); - - return 0; + return err; } static void ionic_lif_reset(struct ionic_lif *lif) @@ -2209,7 +2430,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) ionic_txrx_deinit(lif); ionic_txrx_free(lif); } - ionic_lifs_deinit(ionic); + ionic_lif_deinit(lif); ionic_reset(ionic); ionic_qcqs_free(lif); @@ -2232,7 +2453,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) if (err) goto err_out; - err = ionic_lifs_init(ionic); + err = ionic_lif_init(lif); if (err) goto err_qcqs_free; @@ -2261,14 +2482,14 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) err_txrx_free: ionic_txrx_free(lif); err_lifs_deinit: - ionic_lifs_deinit(ionic); + ionic_lif_deinit(lif); err_qcqs_free: ionic_qcqs_free(lif); err_out: dev_err(ionic->dev, "FW Up: LIFs restart failed - err %d\n", err); } -static void ionic_lif_free(struct ionic_lif *lif) +void ionic_lif_free(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; @@ -2297,23 +2518,10 @@ static void ionic_lif_free(struct ionic_lif *lif) /* free netdev & lif */ ionic_debugfs_del_lif(lif); - list_del(&lif->list); free_netdev(lif->netdev); } -void ionic_lifs_free(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - - ionic_lif_free(lif); - } -} - -static void ionic_lif_deinit(struct ionic_lif *lif) +void ionic_lif_deinit(struct ionic_lif *lif) { if (!test_and_clear_bit(IONIC_LIF_F_INITED, lif->state)) return; @@ -2334,17 +2542,6 @@ static void ionic_lif_deinit(struct ionic_lif *lif) ionic_lif_reset(lif); } -void ionic_lifs_deinit(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - ionic_lif_deinit(lif); - } -} - static int ionic_lif_adminq_init(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; @@ -2490,7 +2687,7 @@ static int ionic_station_set(struct ionic_lif *lif) return 0; } -static int ionic_lif_init(struct ionic_lif *lif) +int ionic_lif_init(struct ionic_lif *lif) { struct ionic_dev *idev = &lif->ionic->idev; struct device *dev = lif->ionic->dev; @@ -2580,22 +2777,6 @@ err_out_free_dbid: return err; } -int ionic_lifs_init(struct ionic *ionic) -{ - struct list_head *cur, *tmp; - struct ionic_lif *lif; - int err; - - list_for_each_safe(cur, tmp, &ionic->lifs) { - lif = list_entry(cur, struct ionic_lif, list); - err = ionic_lif_init(lif); - if (err) - return err; - } - - return 0; -} - static void ionic_lif_notify_work(struct work_struct *ws) { } @@ -2644,45 +2825,41 @@ static int ionic_lif_notify(struct notifier_block *nb, return NOTIFY_DONE; } -int ionic_lifs_register(struct ionic *ionic) +int ionic_lif_register(struct ionic_lif *lif) { int err; - INIT_WORK(&ionic->nb_work, ionic_lif_notify_work); + INIT_WORK(&lif->ionic->nb_work, ionic_lif_notify_work); - ionic->nb.notifier_call = ionic_lif_notify; + lif->ionic->nb.notifier_call = ionic_lif_notify; - err = register_netdevice_notifier(&ionic->nb); + err = register_netdevice_notifier(&lif->ionic->nb); if (err) - ionic->nb.notifier_call = NULL; + lif->ionic->nb.notifier_call = NULL; /* only register LIF0 for now */ - err = register_netdev(ionic->master_lif->netdev); + err = register_netdev(lif->netdev); if (err) { - dev_err(ionic->dev, "Cannot register net device, aborting\n"); + dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); return err; } - ionic->master_lif->registered = true; - ionic_lif_set_netdev_info(ionic->master_lif); + lif->registered = true; + ionic_lif_set_netdev_info(lif); return 0; } -void ionic_lifs_unregister(struct ionic *ionic) +void ionic_lif_unregister(struct ionic_lif *lif) { - if (ionic->nb.notifier_call) { - unregister_netdevice_notifier(&ionic->nb); - cancel_work_sync(&ionic->nb_work); - ionic->nb.notifier_call = NULL; + if (lif->ionic->nb.notifier_call) { + unregister_netdevice_notifier(&lif->ionic->nb); + cancel_work_sync(&lif->ionic->nb_work); + lif->ionic->nb.notifier_call = NULL; } - /* There is only one lif ever registered in the - * current model, so don't bother searching the - * ionic->lif for candidates to unregister - */ - if (ionic->master_lif && - ionic->master_lif->netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(ionic->master_lif->netdev); + if (lif->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(lif->netdev); + lif->registered = false; } static void ionic_lif_queue_identify(struct ionic_lif *lif) @@ -2801,7 +2978,7 @@ int ionic_lif_identify(struct ionic *ionic, u8 lif_type, return 0; } -int ionic_lifs_size(struct ionic *ionic) +int ionic_lif_size(struct ionic *ionic) { struct ionic_identity *ident = &ionic->ident; unsigned int nintrs, dev_nintrs; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 1ee3b14c8d50..e1e6ff1a0918 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -56,35 +56,28 @@ struct ionic_napi_stats { u64 work_done_cntr[IONIC_MAX_NUM_NAPI_CNTR]; }; -struct ionic_q_stats { - union { - struct ionic_tx_stats tx; - struct ionic_rx_stats rx; - }; -}; - struct ionic_qcq { - void *base; - dma_addr_t base_pa; - unsigned int total_size; + void *q_base; + dma_addr_t q_base_pa; + u32 q_size; + void *cq_base; + dma_addr_t cq_base_pa; + u32 cq_size; + void *sg_base; + dma_addr_t sg_base_pa; + u32 sg_size; struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; struct napi_struct napi; struct ionic_napi_stats napi_stats; - struct ionic_q_stats *stats; unsigned int flags; struct dentry *dentry; }; -struct ionic_qcqst { - struct ionic_qcq *qcq; - struct ionic_q_stats *stats; -}; - #define q_to_qcq(q) container_of(q, struct ionic_qcq, q) -#define q_to_tx_stats(q) (&q_to_qcq(q)->stats->tx) -#define q_to_rx_stats(q) (&q_to_qcq(q)->stats->rx) +#define q_to_tx_stats(q) (&(q)->lif->txqstats[(q)->index]) +#define q_to_rx_stats(q) (&(q)->lif->rxqstats[(q)->index]) #define napi_to_qcq(napi) container_of(napi, struct ionic_qcq, napi) #define napi_to_cq(napi) (&napi_to_qcq(napi)->cq) @@ -170,8 +163,10 @@ struct ionic_lif { spinlock_t adminq_lock; /* lock for AdminQ operations */ struct ionic_qcq *adminqcq; struct ionic_qcq *notifyqcq; - struct ionic_qcqst *txqcqs; - struct ionic_qcqst *rxqcqs; + struct ionic_qcq **txqcqs; + struct ionic_tx_stats *txqstats; + struct ionic_qcq **rxqcqs; + struct ionic_rx_stats *rxqstats; u64 last_eid; unsigned int neqs; unsigned int nxqs; @@ -212,12 +207,21 @@ struct ionic_lif { struct work_struct tx_timeout_work; }; -#define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) -#define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) -#define lif_to_txstats(lif, i) ((lif)->txqcqs[i].stats->tx) -#define lif_to_rxstats(lif, i) ((lif)->rxqcqs[i].stats->rx) -#define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) -#define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) +struct ionic_queue_params { + unsigned int nxqs; + unsigned int ntxq_descs; + unsigned int nrxq_descs; + unsigned int intr_split; +}; + +static inline void ionic_init_queue_params(struct ionic_lif *lif, + struct ionic_queue_params *qparam) +{ + qparam->nxqs = lif->nxqs; + qparam->ntxq_descs = lif->ntxq_descs; + qparam->nrxq_descs = lif->nrxq_descs; + qparam->intr_split = test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state); +} static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) { @@ -242,34 +246,33 @@ void ionic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *ns); void ionic_lif_deferred_enqueue(struct ionic_deferred *def, struct ionic_deferred_work *work); -int ionic_lifs_alloc(struct ionic *ionic); -void ionic_lifs_free(struct ionic *ionic); -void ionic_lifs_deinit(struct ionic *ionic); -int ionic_lifs_init(struct ionic *ionic); -int ionic_lifs_register(struct ionic *ionic); -void ionic_lifs_unregister(struct ionic *ionic); +int ionic_lif_alloc(struct ionic *ionic); +int ionic_lif_init(struct ionic_lif *lif); +void ionic_lif_free(struct ionic_lif *lif); +void ionic_lif_deinit(struct ionic_lif *lif); +int ionic_lif_register(struct ionic_lif *lif); +void ionic_lif_unregister(struct ionic_lif *lif); int ionic_lif_identify(struct ionic *ionic, u8 lif_type, union ionic_lif_identity *lif_ident); -int ionic_lifs_size(struct ionic *ionic); +int ionic_lif_size(struct ionic *ionic); int ionic_lif_rss_config(struct ionic_lif *lif, u16 types, const u8 *key, const u32 *indir); +int ionic_reconfigure_queues(struct ionic_lif *lif, + struct ionic_queue_params *qparam); -int ionic_open(struct net_device *netdev); -int ionic_stop(struct net_device *netdev); -int ionic_reset_queues(struct ionic_lif *lif, ionic_reset_cb cb, void *arg); - -static inline void debug_stats_txq_post(struct ionic_qcq *qcq, - struct ionic_txq_desc *desc, bool dbell) +static inline void debug_stats_txq_post(struct ionic_queue *q, bool dbell) { - u8 num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) - & IONIC_TXQ_DESC_NSGE_MASK); + struct ionic_txq_desc *desc = &q->txq[q->head_idx]; + u8 num_sg_elems; - qcq->q.dbell_count += dbell; + q->dbell_count += dbell; + num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) + & IONIC_TXQ_DESC_NSGE_MASK); if (num_sg_elems > (IONIC_MAX_NUM_SG_CNTR - 1)) num_sg_elems = IONIC_MAX_NUM_SG_CNTR - 1; - qcq->stats->tx.sg_cntr[num_sg_elems]++; + q->lif->txqstats[q->index].sg_cntr[num_sg_elems]++; } static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, @@ -284,10 +287,9 @@ static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, } #define DEBUG_STATS_CQE_CNT(cq) ((cq)->compl_count++) -#define DEBUG_STATS_RX_BUFF_CNT(qcq) ((qcq)->stats->rx.buffers_posted++) +#define DEBUG_STATS_RX_BUFF_CNT(q) ((q)->lif->rxqstats[q->index].buffers_posted++) #define DEBUG_STATS_INTR_REARM(intr) ((intr)->rearm_count++) -#define DEBUG_STATS_TXQ_POST(qcq, txdesc, dbell) \ - debug_stats_txq_post(qcq, txdesc, dbell) +#define DEBUG_STATS_TXQ_POST(q, dbell) debug_stats_txq_post(q, dbell) #define DEBUG_STATS_NAPI_POLL(qcq, work_done) \ debug_stats_napi_poll(qcq, work_done) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index df5b9bcc3aba..2b72a51be1d0 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -181,15 +181,17 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) static void ionic_adminq_flush(struct ionic_lif *lif) { - struct ionic_queue *adminq = &lif->adminqcq->q; + struct ionic_queue *q = &lif->adminqcq->q; + struct ionic_desc_info *desc_info; spin_lock(&lif->adminq_lock); - while (adminq->tail != adminq->head) { - memset(adminq->tail->desc, 0, sizeof(union ionic_adminq_cmd)); - adminq->tail->cb = NULL; - adminq->tail->cb_arg = NULL; - adminq->tail = adminq->tail->next; + while (q->tail_idx != q->head_idx) { + desc_info = &q->info[q->tail_idx]; + memset(desc_info->desc, 0, sizeof(union ionic_adminq_cmd)); + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); } spin_unlock(&lif->adminq_lock); } @@ -245,7 +247,8 @@ static void ionic_adminq_cb(struct ionic_queue *q, static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { - struct ionic_queue *adminq; + struct ionic_desc_info *desc_info; + struct ionic_queue *q; int err = 0; WARN_ON(in_interrupt()); @@ -253,10 +256,10 @@ static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) if (!lif->adminqcq) return -EIO; - adminq = &lif->adminqcq->q; + q = &lif->adminqcq->q; spin_lock(&lif->adminq_lock); - if (!ionic_q_has_space(adminq, 1)) { + if (!ionic_q_has_space(q, 1)) { err = -ENOSPC; goto err_out; } @@ -265,13 +268,14 @@ static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) if (err) goto err_out; - memcpy(adminq->head->desc, &ctx->cmd, sizeof(ctx->cmd)); + desc_info = &q->info[q->head_idx]; + memcpy(desc_info->desc, &ctx->cmd, sizeof(ctx->cmd)); dev_dbg(&lif->netdev->dev, "post admin queue command:\n"); dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, &ctx->cmd, sizeof(ctx->cmd), true); - ionic_q_post(adminq, true, ionic_adminq_cb, ctx); + ionic_q_post(q, true, ionic_adminq_cb, ctx); err_out: spin_unlock(&lif->adminq_lock); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index 2a1885da58a6..ff20a2ac4c2f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -179,36 +179,28 @@ static const struct ionic_stat_desc ionic_dbg_napi_stats_desc[] = { static void ionic_get_lif_stats(struct ionic_lif *lif, struct ionic_lif_sw_stats *stats) { - struct ionic_tx_stats *tstats; - struct ionic_rx_stats *rstats; + struct ionic_tx_stats *txstats; + struct ionic_rx_stats *rxstats; struct rtnl_link_stats64 ns; - struct ionic_qcq *txqcq; - struct ionic_qcq *rxqcq; int q_num; memset(stats, 0, sizeof(*stats)); for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txqcq = lif_to_txqcq(lif, q_num); - if (txqcq && txqcq->stats) { - tstats = &txqcq->stats->tx; - stats->tx_packets += tstats->pkts; - stats->tx_bytes += tstats->bytes; - stats->tx_tso += tstats->tso; - stats->tx_tso_bytes += tstats->tso_bytes; - stats->tx_csum_none += tstats->csum_none; - stats->tx_csum += tstats->csum; - } - - rxqcq = lif_to_rxqcq(lif, q_num); - if (rxqcq && rxqcq->stats) { - rstats = &rxqcq->stats->rx; - stats->rx_packets += rstats->pkts; - stats->rx_bytes += rstats->bytes; - stats->rx_csum_none += rstats->csum_none; - stats->rx_csum_complete += rstats->csum_complete; - stats->rx_csum_error += rstats->csum_error; - } + txstats = &lif->txqstats[q_num]; + stats->tx_packets += txstats->pkts; + stats->tx_bytes += txstats->bytes; + stats->tx_tso += txstats->tso; + stats->tx_tso_bytes += txstats->tso_bytes; + stats->tx_csum_none += txstats->csum_none; + stats->tx_csum += txstats->csum; + + rxstats = &lif->rxqstats[q_num]; + stats->rx_packets += rxstats->pkts; + stats->rx_bytes += rxstats->bytes; + stats->rx_csum_none += rxstats->csum_none; + stats->rx_csum_complete += rxstats->csum_complete; + stats->rx_csum_error += rxstats->csum_error; } ionic_get_stats64(lif->netdev, &ns); @@ -371,7 +363,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - txstats = &lif_to_txstats(lif, q_num); + txstats = &lif->txqstats[q_num]; for (i = 0; i < IONIC_NUM_TX_STATS; i++) { **buf = IONIC_READ_STAT64(txstats, @@ -381,7 +373,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) if (test_bit(IONIC_LIF_F_UP, lif->state) && test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state)) { - txqcq = lif_to_txqcq(lif, q_num); + txqcq = lif->txqcqs[q_num]; for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { **buf = IONIC_READ_STAT64(&txqcq->q, &ionic_txq_stats_desc[i]); @@ -405,7 +397,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) } for (q_num = 0; q_num < MAX_Q(lif); q_num++) { - rxstats = &lif_to_rxstats(lif, q_num); + rxstats = &lif->rxqstats[q_num]; for (i = 0; i < IONIC_NUM_RX_STATS; i++) { **buf = IONIC_READ_STAT64(rxstats, @@ -415,7 +407,7 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) if (test_bit(IONIC_LIF_F_UP, lif->state) && test_bit(IONIC_LIF_F_SW_DEBUG_STATS, lif->state)) { - rxqcq = lif_to_rxqcq(lif, q_num); + rxqcq = lif->rxqcqs[q_num]; for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { **buf = IONIC_READ_STAT64(&rxqcq->cq, &ionic_dbg_cq_stats_desc[i]); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 8107d32c2767..c3291decd4c3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,7 +22,7 @@ static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, ionic_desc_cb cb_func, void *cb_arg) { - DEBUG_STATS_TXQ_POST(q_to_qcq(q), q->head->desc, ring_dbell); + DEBUG_STATS_TXQ_POST(q, ring_dbell); ionic_q_post(q, ring_dbell, cb_func, cb_arg); } @@ -32,7 +32,7 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, { ionic_q_post(q, ring_dbell, cb_func, cb_arg); - DEBUG_STATS_RX_BUFF_CNT(q_to_qcq(q)); + DEBUG_STATS_RX_BUFF_CNT(q); } static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) @@ -49,7 +49,7 @@ static struct sk_buff *ionic_rx_skb_alloc(struct ionic_queue *q, struct sk_buff *skb; netdev = lif->netdev; - stats = q_to_rx_stats(q); + stats = &q->lif->rxqstats[q->index]; if (frags) skb = napi_get_frags(&q_to_qcq(q)->napi); @@ -235,14 +235,14 @@ static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) return false; /* check for empty queue */ - if (q->tail->index == q->head->index) + if (q->tail_idx == q->head_idx) return false; - desc_info = q->tail; + desc_info = &q->info[q->tail_idx]; if (desc_info->index != le16_to_cpu(comp->comp_index)) return false; - q->tail = desc_info->next; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); /* clean the related q entry, only one per qc completion */ ionic_rx_clean(q, desc_info, cq_info, desc_info->cb_arg); @@ -338,7 +338,7 @@ void ionic_rx_fill(struct ionic_queue *q) for (i = ionic_q_space_avail(q); i; i--) { remain_len = len; - desc_info = q->head; + desc_info = &q->info[q->head_idx]; desc = desc_info->desc; sg_desc = desc_info->sg_desc; page_info = &desc_info->pages[0]; @@ -387,7 +387,7 @@ void ionic_rx_fill(struct ionic_queue *q) } ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, - q->dbval | q->head->index); + q->dbval | q->head_idx); } static void ionic_rx_fill_cb(void *arg) @@ -397,25 +397,29 @@ static void ionic_rx_fill_cb(void *arg) void ionic_rx_empty(struct ionic_queue *q) { - struct ionic_desc_info *cur; + struct ionic_desc_info *desc_info; struct ionic_rxq_desc *desc; unsigned int i; + u16 idx; - for (cur = q->tail; cur != q->head; cur = cur->next) { - desc = cur->desc; + idx = q->tail_idx; + while (idx != q->head_idx) { + desc_info = &q->info[idx]; + desc = desc_info->desc; desc->addr = 0; desc->len = 0; - for (i = 0; i < cur->npages; i++) { - if (likely(cur->pages[i].page)) { - ionic_rx_page_free(q, cur->pages[i].page, - cur->pages[i].dma_addr); - cur->pages[i].page = NULL; - cur->pages[i].dma_addr = 0; + for (i = 0; i < desc_info->npages; i++) { + if (likely(desc_info->pages[i].page)) { + ionic_rx_page_free(q, desc_info->pages[i].page, + desc_info->pages[i].dma_addr); + desc_info->pages[i].page = NULL; + desc_info->pages[i].dma_addr = 0; } } - cur->cb_arg = NULL; + desc_info->cb_arg = NULL; + idx = (idx + 1) & (q->num_descs - 1); } } @@ -502,7 +506,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; - txcq = &lif->txqcqs[qi].qcq->cq; + txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, lif->tx_budget, ionic_tx_service, NULL, NULL); @@ -630,9 +634,9 @@ static bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) * several q entries completed for each cq completion */ do { - desc_info = q->tail; - q->tail = desc_info->next; - ionic_tx_clean(q, desc_info, cq->tail, desc_info->cb_arg); + desc_info = &q->info[q->tail_idx]; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); + ionic_tx_clean(q, desc_info, cq_info, desc_info->cb_arg); desc_info->cb = NULL; desc_info->cb_arg = NULL; } while (desc_info->index != le16_to_cpu(comp->comp_index)); @@ -658,9 +662,9 @@ void ionic_tx_empty(struct ionic_queue *q) int done = 0; /* walk the not completed tx entries, if any */ - while (q->head != q->tail) { - desc_info = q->tail; - q->tail = desc_info->next; + while (q->head_idx != q->tail_idx) { + desc_info = &q->info[q->tail_idx]; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); ionic_tx_clean(q, desc_info, NULL, desc_info->cb_arg); desc_info->cb = NULL; desc_info->cb_arg = NULL; @@ -748,8 +752,8 @@ static void ionic_tx_tso_post(struct ionic_queue *q, struct ionic_txq_desc *desc static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, struct ionic_txq_sg_elem **elem) { - struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; - struct ionic_txq_desc *desc = q->head->desc; + struct ionic_txq_sg_desc *sg_desc = q->info[q->head_idx].txq_sg_desc; + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; *elem = sg_desc->elems; return desc; @@ -758,13 +762,13 @@ static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) { struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_desc_info *abort = q->head; + struct ionic_desc_info *rewind_desc_info; struct device *dev = q->lif->ionic->dev; - struct ionic_desc_info *rewind = abort; struct ionic_txq_sg_elem *elem; struct ionic_txq_desc *desc; unsigned int frag_left = 0; unsigned int offset = 0; + u16 abort = q->head_idx; unsigned int len_left; dma_addr_t desc_addr; unsigned int hdrlen; @@ -772,6 +776,7 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) unsigned int seglen; u64 total_bytes = 0; u64 total_pkts = 0; + u16 rewind = abort; unsigned int left; unsigned int len; unsigned int mss; @@ -916,19 +921,20 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) return 0; err_out_abort: - while (rewind->desc != q->head->desc) { - ionic_tx_clean(q, rewind, NULL, NULL); - rewind = rewind->next; + while (rewind != q->head_idx) { + rewind_desc_info = &q->info[rewind]; + ionic_tx_clean(q, rewind_desc_info, NULL, NULL); + rewind = (rewind + 1) & (q->num_descs - 1); } - q->head = abort; + q->head_idx = abort; return -ENOMEM; } static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) { + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_txq_desc *desc = q->head->desc; struct device *dev = q->lif->ionic->dev; dma_addr_t dma_addr; bool has_vlan; @@ -967,8 +973,8 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) { + struct ionic_txq_desc *desc = q->info[q->head_idx].txq_desc; struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_txq_desc *desc = q->head->desc; struct device *dev = q->lif->ionic->dev; dma_addr_t dma_addr; bool has_vlan; @@ -1002,7 +1008,7 @@ static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb) { - struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + struct ionic_txq_sg_desc *sg_desc = q->info[q->head_idx].txq_sg_desc; unsigned int len_left = skb->len - skb_headlen(skb); struct ionic_txq_sg_elem *elem = sg_desc->elems; struct ionic_tx_stats *stats = q_to_tx_stats(q); @@ -1111,9 +1117,9 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - if (unlikely(!lif_to_txqcq(lif, queue_index))) + if (unlikely(queue_index >= lif->nxqs)) queue_index = 0; - q = lif_to_txq(lif, queue_index); + q = &lif->txqcqs[queue_index]->q; ndescs = ionic_tx_descs_needed(q, skb); if (ndescs < 0) diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 8f743d80760b..4366c7a8de95 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -80,7 +80,7 @@ config QED select CRC8 select NET_DEVLINK help - This enables the support for ... + This enables the support for Marvell FastLinQ adapters family. config QED_LL2 bool @@ -100,7 +100,8 @@ config QEDE depends on QED imply PTP_1588_CLOCK help - This enables the support for ... + This enables the support for Marvell FastLinQ adapters family, + ethernet driver. config QED_RDMA bool diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index f947b105cf14..8251755ec18c 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -9,6 +9,7 @@ qed-y := \ qed_dcbx.o \ qed_debug.o \ qed_dev.o \ + qed_devlink.o \ qed_hw.o \ qed_init_fw_funcs.o \ qed_init_ops.o \ diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index b2a7b53ee760..f34b25a79449 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -807,6 +807,7 @@ struct qed_dev { struct qed_llh_info *p_llh_info; /* Linux specific here */ + struct qed_dev_info common_dev_info; struct qede_dev *edev; struct pci_dev *pdev; u32 flags; @@ -849,7 +850,6 @@ struct qed_dev { u32 rdma_max_srq_sge; u16 tunn_feature_mask; - struct devlink *dl; bool iwarp_cmt; }; @@ -981,6 +981,7 @@ void qed_bw_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt); u32 qed_unzip_data(struct qed_hwfn *p_hwfn, u32 input_len, u8 *input_buf, u32 max_size, u8 *unzip_buf); +int qed_recovery_process(struct qed_dev *cdev); void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn); void qed_hw_error_occurred(struct qed_hwfn *p_hwfn, enum qed_hw_err_type err_type); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index b3c9ebaf2280..00f2d7f13de6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -3973,6 +3973,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) struct qed_mcp_link_speed_params *ext_speed; struct qed_mcp_link_capabilities *p_caps; struct qed_mcp_link_params *link; + int i; /* Read global nvm_cfg address */ nvm_cfg_addr = qed_rd(p_hwfn, p_ptt, MISC_REG_GEN_PURP_CR0); @@ -4290,6 +4291,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) __set_bit(QED_DEV_CAP_ROCE, &p_hwfn->hw_info.device_capabilities); + /* Read device serial number information from shmem */ + addr = MCP_REG_SCRATCH + nvm_cfg1_offset + + offsetof(struct nvm_cfg1, glob) + + offsetof(struct nvm_cfg1_glob, serial_number); + + for (i = 0; i < 4; i++) + p_hwfn->hw_info.part_num[i] = qed_rd(p_hwfn, p_ptt, addr + i * 4); + return qed_mcp_fill_shmem_func_info(p_hwfn, p_ptt); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c new file mode 100644 index 000000000000..cf7f4da68e69 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Marvell/Qlogic FastLinQ NIC driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ + +#include <linux/kernel.h> +#include <linux/qed/qed_if.h> +#include <linux/vmalloc.h> +#include "qed.h" +#include "qed_devlink.h" + +enum qed_devlink_param_id { + QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + QED_DEVLINK_PARAM_ID_IWARP_CMT, +}; + +struct qed_fw_fatal_ctx { + enum qed_hw_err_type err_type; +}; + +int qed_report_fatal_error(struct devlink *devlink, enum qed_hw_err_type err_type) +{ + struct qed_devlink *qdl = devlink_priv(devlink); + struct qed_fw_fatal_ctx fw_fatal_ctx = { + .err_type = err_type, + }; + + if (qdl->fw_reporter) + devlink_health_report(qdl->fw_reporter, + "Fatal error occurred", &fw_fatal_ctx); + + return 0; +} + +static int +qed_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qdl = devlink_health_reporter_priv(reporter); + struct qed_fw_fatal_ctx *fw_fatal_ctx = priv_ctx; + struct qed_dev *cdev = qdl->cdev; + u32 dbg_data_buf_size; + u8 *p_dbg_data_buf; + int err; + + /* Having context means that was a dump request after fatal, + * so we enable extra debugging while gathering the dump, + * just in case + */ + cdev->print_dbg_data = fw_fatal_ctx ? true : false; + + dbg_data_buf_size = qed_dbg_all_data_size(cdev); + p_dbg_data_buf = vzalloc(dbg_data_buf_size); + if (!p_dbg_data_buf) { + DP_NOTICE(cdev, + "Failed to allocate memory for a debug data buffer\n"); + return -ENOMEM; + } + + err = qed_dbg_all_data(cdev, p_dbg_data_buf); + if (err) { + DP_NOTICE(cdev, "Failed to obtain debug data\n"); + vfree(p_dbg_data_buf); + return err; + } + + err = devlink_fmsg_binary_pair_put(fmsg, "dump_data", + p_dbg_data_buf, dbg_data_buf_size); + + vfree(p_dbg_data_buf); + + return err; +} + +static int +qed_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qdl = devlink_health_reporter_priv(reporter); + struct qed_dev *cdev = qdl->cdev; + + qed_recovery_process(cdev); + + return 0; +} + +static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = { + .name = "fw_fatal", + .recover = qed_fw_fatal_reporter_recover, + .dump = qed_fw_fatal_reporter_dump, +}; + +#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000 + +void qed_fw_reporters_create(struct devlink *devlink) +{ + struct qed_devlink *dl = devlink_priv(devlink); + + dl->fw_reporter = devlink_health_reporter_create(devlink, &qed_fw_fatal_reporter_ops, + QED_REPORTER_FW_GRACEFUL_PERIOD, dl); + if (IS_ERR(dl->fw_reporter)) { + DP_NOTICE(dl->cdev, "Failed to create fw reporter, err = %ld\n", + PTR_ERR(dl->fw_reporter)); + dl->fw_reporter = NULL; + } +} + +void qed_fw_reporters_destroy(struct devlink *devlink) +{ + struct qed_devlink *dl = devlink_priv(devlink); + struct devlink_health_reporter *rep; + + rep = dl->fw_reporter; + + if (!IS_ERR_OR_NULL(rep)) + devlink_health_reporter_destroy(rep); +} + +static int qed_dl_param_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct qed_devlink *qed_dl = devlink_priv(dl); + struct qed_dev *cdev; + + cdev = qed_dl->cdev; + ctx->val.vbool = cdev->iwarp_cmt; + + return 0; +} + +static int qed_dl_param_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct qed_devlink *qed_dl = devlink_priv(dl); + struct qed_dev *cdev; + + cdev = qed_dl->cdev; + cdev->iwarp_cmt = ctx->val.vbool; + + return 0; +} + +static const struct devlink_param qed_devlink_params[] = { + DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT, + "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + qed_dl_param_get, qed_dl_param_set, NULL), +}; + +static int qed_devlink_info_get(struct devlink *devlink, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct qed_devlink *qed_dl = devlink_priv(devlink); + struct qed_dev *cdev = qed_dl->cdev; + struct qed_dev_info *dev_info; + char buf[100]; + int err; + + dev_info = &cdev->common_dev_info; + + err = devlink_info_driver_name_put(req, KBUILD_MODNAME); + if (err) + return err; + + memcpy(buf, cdev->hwfns[0].hw_info.part_num, sizeof(cdev->hwfns[0].hw_info.part_num)); + buf[sizeof(cdev->hwfns[0].hw_info.part_num)] = 0; + + if (buf[0]) { + err = devlink_info_board_serial_number_put(req, buf); + if (err) + return err; + } + + snprintf(buf, sizeof(buf), "%d.%d.%d.%d", + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_3), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_2), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_1), + GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_0)); + + err = devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, buf); + if (err) + return err; + + snprintf(buf, sizeof(buf), "%d.%d.%d.%d", + dev_info->fw_major, + dev_info->fw_minor, + dev_info->fw_rev, + dev_info->fw_eng); + + return devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_APP, buf); +} + +static const struct devlink_ops qed_dl_ops = { + .info_get = qed_devlink_info_get, +}; + +struct devlink *qed_devlink_register(struct qed_dev *cdev) +{ + union devlink_param_value value; + struct qed_devlink *qdevlink; + struct devlink *dl; + int rc; + + dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink)); + if (!dl) + return ERR_PTR(-ENOMEM); + + qdevlink = devlink_priv(dl); + qdevlink->cdev = cdev; + + rc = devlink_register(dl, &cdev->pdev->dev); + if (rc) + goto err_free; + + rc = devlink_params_register(dl, qed_devlink_params, + ARRAY_SIZE(qed_devlink_params)); + if (rc) + goto err_unregister; + + value.vbool = false; + devlink_param_driverinit_value_set(dl, + QED_DEVLINK_PARAM_ID_IWARP_CMT, + value); + + devlink_params_publish(dl); + cdev->iwarp_cmt = false; + + qed_fw_reporters_create(dl); + + return dl; + +err_unregister: + devlink_unregister(dl); + +err_free: + devlink_free(dl); + + return ERR_PTR(rc); +} + +void qed_devlink_unregister(struct devlink *devlink) +{ + if (!devlink) + return; + + qed_fw_reporters_destroy(devlink); + + devlink_params_unregister(devlink, qed_devlink_params, + ARRAY_SIZE(qed_devlink_params)); + + devlink_unregister(devlink); + devlink_free(devlink); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.h b/drivers/net/ethernet/qlogic/qed/qed_devlink.h new file mode 100644 index 000000000000..ccc7d1d1bfd4 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Marvell/Qlogic FastLinQ NIC driver + * + * Copyright (C) 2020 Marvell International Ltd. + */ +#ifndef _QED_DEVLINK_H +#define _QED_DEVLINK_H + +#include <linux/qed/qed_if.h> +#include <net/devlink.h> + +struct devlink *qed_devlink_register(struct qed_dev *cdev); +void qed_devlink_unregister(struct devlink *devlink); + +void qed_fw_reporters_create(struct devlink *devlink); +void qed_fw_reporters_destroy(struct devlink *devlink); + +int qed_report_fatal_error(struct devlink *dl, enum qed_hw_err_type err_type); + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 2558cb680db3..db5d003770ba 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -39,6 +39,7 @@ #include "qed_hw.h" #include "qed_selftest.h" #include "qed_debug.h" +#include "qed_devlink.h" #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) @@ -478,6 +479,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, } dev_info->mtu = hw_info->mtu; + cdev->common_dev_info = *dev_info; return 0; } @@ -510,107 +512,6 @@ static int qed_set_power_state(struct qed_dev *cdev, pci_power_t state) return 0; } -struct qed_devlink { - struct qed_dev *cdev; -}; - -enum qed_devlink_param_id { - QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, - QED_DEVLINK_PARAM_ID_IWARP_CMT, -}; - -static int qed_dl_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct qed_devlink *qed_dl; - struct qed_dev *cdev; - - qed_dl = devlink_priv(dl); - cdev = qed_dl->cdev; - ctx->val.vbool = cdev->iwarp_cmt; - - return 0; -} - -static int qed_dl_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct qed_devlink *qed_dl; - struct qed_dev *cdev; - - qed_dl = devlink_priv(dl); - cdev = qed_dl->cdev; - cdev->iwarp_cmt = ctx->val.vbool; - - return 0; -} - -static const struct devlink_param qed_devlink_params[] = { - DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT, - "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - qed_dl_param_get, qed_dl_param_set, NULL), -}; - -static const struct devlink_ops qed_dl_ops; - -static int qed_devlink_register(struct qed_dev *cdev) -{ - union devlink_param_value value; - struct qed_devlink *qed_dl; - struct devlink *dl; - int rc; - - dl = devlink_alloc(&qed_dl_ops, sizeof(*qed_dl)); - if (!dl) - return -ENOMEM; - - qed_dl = devlink_priv(dl); - - cdev->dl = dl; - qed_dl->cdev = cdev; - - rc = devlink_register(dl, &cdev->pdev->dev); - if (rc) - goto err_free; - - rc = devlink_params_register(dl, qed_devlink_params, - ARRAY_SIZE(qed_devlink_params)); - if (rc) - goto err_unregister; - - value.vbool = false; - devlink_param_driverinit_value_set(dl, - QED_DEVLINK_PARAM_ID_IWARP_CMT, - value); - - devlink_params_publish(dl); - cdev->iwarp_cmt = false; - - return 0; - -err_unregister: - devlink_unregister(dl); - -err_free: - cdev->dl = NULL; - devlink_free(dl); - - return rc; -} - -static void qed_devlink_unregister(struct qed_dev *cdev) -{ - if (!cdev->dl) - return; - - devlink_params_unregister(cdev->dl, qed_devlink_params, - ARRAY_SIZE(qed_devlink_params)); - - devlink_unregister(cdev->dl); - devlink_free(cdev->dl); -} - /* probing */ static struct qed_dev *qed_probe(struct pci_dev *pdev, struct qed_probe_params *params) @@ -639,12 +540,6 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev, } DP_INFO(cdev, "PCI init completed successfully\n"); - rc = qed_devlink_register(cdev); - if (rc) { - DP_INFO(cdev, "Failed to register devlink.\n"); - goto err2; - } - rc = qed_hw_prepare(cdev, QED_PCI_DEFAULT); if (rc) { DP_ERR(cdev, "hw prepare failed\n"); @@ -674,8 +569,6 @@ static void qed_remove(struct qed_dev *cdev) qed_set_power_state(cdev, PCI_D3hot); - qed_devlink_unregister(cdev); - qed_free_cdev(cdev); } @@ -2924,7 +2817,7 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode) return status; } -static int qed_recovery_process(struct qed_dev *cdev) +int qed_recovery_process(struct qed_dev *cdev) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt; @@ -3112,6 +3005,9 @@ const struct qed_common_ops qed_common_ops_pass = { .get_link = &qed_get_current_link, .drain = &qed_drain, .update_msglvl = &qed_init_dp, + .devlink_register = qed_devlink_register, + .devlink_unregister = qed_devlink_unregister, + .report_fatal_error = qed_report_fatal_error, .dbg_all_data = &qed_dbg_all_data, .dbg_all_data_size = &qed_dbg_all_data_size, .chain_alloc = &qed_chain_alloc, diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index a4bcde522cdf..4394a4d77224 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1151,7 +1151,6 @@ qed_rdma_destroy_cq(void *rdma_cxt, DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", in_params->icid); p_ramrod_res = - (struct rdma_destroy_cq_output_params *) dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, sizeof(struct rdma_destroy_cq_output_params), &ramrod_res_phys, GFP_KERNEL); diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 803c1fcca8ad..3efc5899f656 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -172,6 +172,7 @@ struct qede_dev { struct qed_dev *cdev; struct net_device *ndev; struct pci_dev *pdev; + struct devlink *devlink; u32 dp_module; u8 dp_level; @@ -263,6 +264,7 @@ struct qede_dev { struct bpf_prog *xdp_prog; + enum qed_hw_err_type last_err_type; unsigned long err_flags; #define QEDE_ERR_IS_HANDLED 31 #define QEDE_ERR_ATTN_CLR_EN 0 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 140a392a81bb..20d2296beb79 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1170,10 +1170,23 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, rc = -ENOMEM; goto err2; } + + edev->devlink = qed_ops->common->devlink_register(cdev); + if (IS_ERR(edev->devlink)) { + DP_NOTICE(edev, "Cannot register devlink\n"); + edev->devlink = NULL; + /* Go on, we can live without devlink */ + } } else { struct net_device *ndev = pci_get_drvdata(pdev); edev = netdev_priv(ndev); + + if (edev->devlink) { + struct qed_devlink *qdl = devlink_priv(edev->devlink); + + qdl->cdev = cdev; + } edev->cdev = cdev; memset(&edev->stats, 0, sizeof(edev->stats)); memcpy(&edev->dev_info, &dev_info, sizeof(dev_info)); @@ -1225,7 +1238,10 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, err4: qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY)); err3: - free_netdev(edev->ndev); + if (mode != QEDE_PROBE_RECOVERY) + free_netdev(edev->ndev); + else + edev->cdev = NULL; err2: qed_ops->common->slowpath_stop(cdev); err1: @@ -1296,6 +1312,11 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) qed_ops->common->slowpath_stop(cdev); if (system_state == SYSTEM_POWER_OFF) return; + + if (mode != QEDE_REMOVE_RECOVERY && edev->devlink) { + qed_ops->common->devlink_unregister(edev->devlink); + edev->devlink = NULL; + } qed_ops->common->remove(cdev); edev->cdev = NULL; @@ -2455,7 +2476,8 @@ static int qede_close(struct net_device *ndev) qede_unload(edev, QEDE_UNLOAD_NORMAL, false); - edev->ops->common->update_drv_state(edev->cdev, false); + if (edev->cdev) + edev->ops->common->update_drv_state(edev->cdev, false); return 0; } @@ -2577,19 +2599,12 @@ static void qede_atomic_hw_err_handler(struct qede_dev *edev) static void qede_generic_hw_err_handler(struct qede_dev *edev) { - struct qed_dev *cdev = edev->cdev; - DP_NOTICE(edev, "Generic sleepable HW error handling started - err_flags 0x%lx\n", edev->err_flags); - /* Trigger a recovery process. - * This is placed in the sleep requiring section just to make - * sure it is the last one, and that all the other operations - * were completed. - */ - if (test_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags)) - edev->ops->common->recovery_process(cdev); + if (edev->devlink) + edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type); clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags); @@ -2643,6 +2658,7 @@ static void qede_schedule_hw_err_handler(void *dev, return; } + edev->last_err_type = err_type; qede_set_hw_err_flags(edev, err_type); qede_atomic_hw_err_handler(edev); set_bit(QEDE_SP_HW_ERR, &edev->sp_flags); diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c index 375a844cd27c..362b4f5c162c 100644 --- a/drivers/net/ethernet/qualcomm/qca_uart.c +++ b/drivers/net/ethernet/qualcomm/qca_uart.c @@ -167,7 +167,7 @@ static void qca_tty_wakeup(struct serdev_device *serdev) schedule_work(&qca->tx_work); } -static struct serdev_device_ops qca_serdev_ops = { +static const struct serdev_device_ops qca_serdev_ops = { .receive_buf = qca_tty_receive, .write_wakeup = qca_tty_wakeup, }; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d1da92ac7fbe..c427865d51a4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -617,7 +617,6 @@ struct rtl8169_private { struct work_struct work; } wk; - unsigned irq_enabled:1; unsigned supports_gmii:1; unsigned aspm_manageable:1; dma_addr_t counters_phys_addr; @@ -1280,12 +1279,10 @@ static void rtl_irq_disable(struct rtl8169_private *tp) RTL_W32(tp, IntrMask_8125, 0); else RTL_W16(tp, IntrMask, 0); - tp->irq_enabled = 0; } static void rtl_irq_enable(struct rtl8169_private *tp) { - tp->irq_enabled = 1; if (rtl_is_8125(tp)) RTL_W32(tp, IntrMask_8125, tp->irq_mask); else @@ -4541,8 +4538,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) struct rtl8169_private *tp = dev_instance; u32 status = rtl_get_events(tp); - if (!tp->irq_enabled || (status & 0xffff) == 0xffff || - !(status & tp->irq_mask)) + if ((status & 0xffff) == 0xffff || !(status & tp->irq_mask)) return IRQ_NONE; if (unlikely(status & SYSErr)) { @@ -4596,10 +4592,8 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) rtl_tx(dev, tp, budget); - if (work_done < budget) { - napi_complete_done(napi, work_done); + if (work_done < budget && napi_complete_done(napi, work_done)) rtl_irq_enable(tp); - } return work_done; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 99f7aae102ce..adc8c8f3b5fc 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -162,7 +162,7 @@ static int ravb_get_mdio_data(struct mdiobb_ctrl *ctrl) } /* MDIO bus control struct */ -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = ravb_set_mdc, .set_mdio_dir = ravb_set_mdio_dir, diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f45331ed90b0..586642c33d2b 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1202,7 +1202,7 @@ static void sh_mdc_ctrl(struct mdiobb_ctrl *ctrl, int bit) } /* mdio bus control struct */ -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = sh_mdc_ctrl, .set_mdio_dir = sh_mmd_ctrl, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 4b0b2cf026a5..0b4bcac53f18 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3955,7 +3955,6 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .start_stats = efx_port_dummy_op_void, .pull_stats = efx_port_dummy_op_void, .stop_stats = efx_port_dummy_op_void, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = efx_ef10_push_irq_moderation, .reconfigure_mac = efx_ef10_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, @@ -4066,7 +4065,6 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .start_stats = efx_mcdi_mac_start_stats, .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = efx_ef10_push_irq_moderation, .reconfigure_mac = efx_ef10_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c index 9729983f4840..c54b7f8243f3 100644 --- a/drivers/net/ethernet/sfc/ef100.c +++ b/drivers/net/ethernet/sfc/ef100.c @@ -142,7 +142,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Temporarily map new BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -160,7 +160,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Put old BAR back. */ rc = efx_init_io(efx, previous_bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, previous_bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -334,7 +334,7 @@ static int ef100_pci_parse_xilinx_cap(struct efx_nic *efx, int vndr_cap, /* Temporarily map BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -495,7 +495,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev, /* Set up basic I/O (BAR mappings etc) */ rc = efx_init_io(efx, fcw.bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, fcw.bar)); if (rc) goto fail; diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 206d70f9d95b..19fe86b3b316 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -431,18 +431,18 @@ static int ef100_reset(struct efx_nic *efx, enum reset_type reset_type) /* A RESET_TYPE_ALL will cause filters to be removed, so we remove filters * and reprobe after reset to avoid removing filters twice */ - down_read(&efx->filter_sem); + down_write(&efx->filter_sem); ef100_filter_table_down(efx); - up_read(&efx->filter_sem); + up_write(&efx->filter_sem); rc = efx_mcdi_reset(efx, reset_type); if (rc) return rc; netif_device_attach(efx->net_dev); - down_read(&efx->filter_sem); + down_write(&efx->filter_sem); rc = ef100_filter_table_up(efx); - up_read(&efx->filter_sem); + up_write(&efx->filter_sem); if (rc) return rc; @@ -739,6 +739,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, @@ -820,6 +821,7 @@ const struct efx_nic_type ef100_vf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 4ffda7782f68..12a91c559aa2 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -50,8 +50,7 @@ static int efx_ethtool_phys_id(struct net_device *net_dev, return 1; /* cycle on/off once per second */ } - efx->type->set_id_led(efx, mode); - return 0; + return efx_mcdi_set_id_led(efx, mode); } static int efx_ethtool_get_regs_len(struct net_device *net_dev) diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index d07eeaad9bdf..0d9795fb9356 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -863,13 +863,8 @@ static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue, bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err; bool rx_ev_frm_trunc, rx_ev_tobe_disc; bool rx_ev_other_err, rx_ev_pause_frm; - bool rx_ev_hdr_type, rx_ev_mcast_pkt; - unsigned rx_ev_pkt_type; - rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); - rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC); - rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE); rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BUF_OWNER_ID_ERR); rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event, @@ -918,6 +913,8 @@ static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue, rx_ev_tobe_disc ? " [TOBE_DISC]" : "", rx_ev_pause_frm ? " [PAUSE]" : ""); } +#else + (void) rx_ev_other_err; #endif if (efx->net_dev->features & NETIF_F_RXALL) @@ -2592,7 +2589,6 @@ int efx_farch_filter_remove_safe(struct efx_nic *efx, enum efx_farch_filter_table_id table_id; struct efx_farch_filter_table *table; unsigned int filter_idx; - struct efx_farch_filter_spec *spec; int rc; table_id = efx_farch_filter_id_table_id(filter_id); @@ -2604,7 +2600,6 @@ int efx_farch_filter_remove_safe(struct efx_nic *efx, if (filter_idx >= table->size) return -ENOENT; down_write(&state->lock); - spec = &table->spec[filter_idx]; rc = efx_farch_filter_remove(efx, table, filter_idx, priority); up_write(&state->lock); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 5467819aef6e..be6bfd6b7ec7 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1868,10 +1868,9 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx) return efx_mcdi_exit_assertion(efx); } -void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) +int efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) { MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_ID_LED_IN_LEN); - int rc; BUILD_BUG_ON(EFX_LED_OFF != MC_CMD_LED_OFF); BUILD_BUG_ON(EFX_LED_ON != MC_CMD_LED_ON); @@ -1881,8 +1880,7 @@ void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) MCDI_SET_DWORD(inbuf, SET_ID_LED_IN_STATE, mode); - rc = efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), - NULL, 0, NULL); + return efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), NULL, 0, NULL); } static int efx_mcdi_reset_func(struct efx_nic *efx) diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 658cf345420d..8aed65018964 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -348,7 +348,7 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, int efx_new_mcdi_nvram_test_all(struct efx_nic *efx); int efx_mcdi_nvram_test_all(struct efx_nic *efx); int efx_mcdi_handle_assertion(struct efx_nic *efx); -void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +int efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out); int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index dcb741d8bd11..338ebb0402be 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -846,6 +846,7 @@ struct efx_async_filter_insertion { * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds * @timer_max_ns: Interrupt timer maximum value, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues + * @irqs_hooked: Channel interrupts are hooked * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues * @irq_rx_moderation_us: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags @@ -1004,6 +1005,7 @@ struct efx_nic { unsigned int timer_quantum_ns; unsigned int timer_max_ns; bool irq_rx_adaptive; + bool irqs_hooked; unsigned int irq_mod_step_us; unsigned int irq_rx_moderation_us; u32 msg_enable; @@ -1215,7 +1217,6 @@ struct efx_udp_tunnel { * @start_stats: Start the regular fetching of statistics * @pull_stats: Pull stats from the NIC and wait until they arrive. * @stop_stats: Stop the regular fetching of statistics - * @set_id_led: Set state of identifying LED or revert to automatic function * @push_irq_moderation: Apply interrupt moderation value * @reconfigure_port: Push loopback/power/txdis changes to the MAC and PHY * @prepare_enable_fc_tx: Prepare MAC to enable pause frame TX (may be %NULL) @@ -1360,7 +1361,6 @@ struct efx_nic_type { void (*start_stats)(struct efx_nic *efx); void (*pull_stats)(struct efx_nic *efx); void (*stop_stats)(struct efx_nic *efx); - void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode); void (*push_irq_moderation)(struct efx_channel *channel); int (*reconfigure_port)(struct efx_nic *efx); void (*prepare_enable_fc_tx)(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d994d136bb03..d1e908846f5d 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -129,6 +129,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) #endif } + efx->irqs_hooked = true; return 0; fail2: @@ -154,6 +155,8 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) efx->net_dev->rx_cpu_rmap = NULL; #endif + if (!efx->irqs_hooked) + return; if (EFX_INT_MODE_USE_MSI(efx)) { /* Disable MSI/MSI-X interrupts */ efx_for_each_channel(channel, efx) @@ -163,6 +166,7 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) /* Disable legacy interrupt */ free_irq(efx->legacy_irq, efx); } + efx->irqs_hooked = false; } /* Register dump */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index ef9bca92b0b7..5e29284c89c9 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -849,6 +849,7 @@ void efx_remove_filters(struct efx_nic *efx) efx_for_each_channel(channel, efx) { cancel_delayed_work_sync(&channel->filter_work); kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; } #endif down_write(&efx->filter_sem); diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index e71d6d37a317..34b9c7d50c4e 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -67,7 +67,7 @@ static const char *const efx_interrupt_mode_names[] = { STRING_TABLE_LOOKUP(efx->interrupt_mode, efx_interrupt_mode) /** - * efx_loopback_state - persistent state during a loopback selftest + * struct efx_loopback_state - persistent state during a loopback selftest * @flush: Drop all packets in efx_loopback_rx_packet * @packet_count: Number of packets being used in this test * @skbs: An array of skbs transmitted diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index a7ea630bb5e6..16347a6d0c47 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -994,7 +994,6 @@ const struct efx_nic_type siena_a0_nic_type = { .start_stats = efx_mcdi_mac_start_stats, .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, - .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = siena_push_irq_moderation, .reconfigure_mac = siena_mac_reconfigure, .check_mac_fault = efx_mcdi_mac_check_fault, diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 9a47c5aec91a..53f14c5a9e02 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -3,7 +3,7 @@ config STMMAC_ETH tristate "STMicroelectronics Multi-Gigabit Ethernet driver" depends on HAS_IOMEM && HAS_DMA select MII - select MDIO_XPCS + select PCS_XPCS select PAGE_POOL select PHYLINK select CRC32 @@ -209,6 +209,16 @@ config DWMAC_IMX8 device driver. This driver is used for i.MX8 series like iMX8MP/iMX8DXL GMAC ethernet controller. +config DWMAC_INTEL_PLAT + tristate "Intel dwmac support" + depends on OF && COMMON_CLK + depends on STMMAC_ETH + help + Support for ethernet controllers on Intel SoCs + + This selects the Intel platform specific glue layer support for + the stmmac device driver. This driver is used for the Intel Keem Bay + SoC. endif config DWMAC_INTEL diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 295615ab36a7..24e6145d4eae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_DWMAC_STM32) += dwmac-stm32.o obj-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o obj-$(CONFIG_DWMAC_SUN8I) += dwmac-sun8i.o obj-$(CONFIG_DWMAC_DWC_QOS_ETH) += dwmac-dwc-qos-eth.o +obj-$(CONFIG_DWMAC_INTEL_PLAT) += dwmac-intel-plat.o obj-$(CONFIG_DWMAC_GENERIC) += dwmac-generic.o obj-$(CONFIG_DWMAC_IMX8) += dwmac-imx.o stmmac-platform-objs:= stmmac_platform.o diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 127f75862962..acc5e3fc1c2f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -15,7 +15,7 @@ #include <linux/netdevice.h> #include <linux/stmmac.h> #include <linux/phy.h> -#include <linux/mdio-xpcs.h> +#include <linux/pcs/pcs-xpcs.h> #include <linux/module.h> #if IS_ENABLED(CONFIG_VLAN_8021Q) #define STMMAC_VLAN_TAG_USED diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c new file mode 100644 index 000000000000..ccac7bf2a9d3 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Intel DWMAC platform driver + * + * Copyright(C) 2020 Intel Corporation + */ + +#include <linux/ethtool.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/stmmac.h> + +#include "stmmac.h" +#include "stmmac_platform.h" + +struct intel_dwmac { + struct device *dev; + struct clk *tx_clk; + const struct intel_dwmac_data *data; +}; + +struct intel_dwmac_data { + void (*fix_mac_speed)(void *priv, unsigned int speed); + unsigned long ptp_ref_clk_rate; + unsigned long tx_clk_rate; + bool tx_clk_en; +}; + +static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed) +{ + struct intel_dwmac *dwmac = priv; + unsigned long rate; + int ret; + + rate = clk_get_rate(dwmac->tx_clk); + + switch (speed) { + case SPEED_1000: + rate = 125000000; + break; + + case SPEED_100: + rate = 25000000; + break; + + case SPEED_10: + rate = 2500000; + break; + + default: + dev_err(dwmac->dev, "Invalid speed\n"); + break; + } + + ret = clk_set_rate(dwmac->tx_clk, rate); + if (ret) + dev_err(dwmac->dev, "Failed to configure tx clock rate\n"); +} + +static const struct intel_dwmac_data kmb_data = { + .fix_mac_speed = kmb_eth_fix_mac_speed, + .ptp_ref_clk_rate = 200000000, + .tx_clk_rate = 125000000, + .tx_clk_en = true, +}; + +static const struct of_device_id intel_eth_plat_match[] = { + { .compatible = "intel,keembay-dwmac", .data = &kmb_data }, + { } +}; +MODULE_DEVICE_TABLE(of, intel_eth_plat_match); + +static int intel_eth_plat_probe(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + const struct of_device_id *match; + struct intel_dwmac *dwmac; + unsigned long rate; + int ret; + + plat_dat = priv->plat; + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; + + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) { + dev_err(&pdev->dev, "dt configuration failed\n"); + return PTR_ERR(plat_dat); + } + + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } + + dwmac->dev = &pdev->dev; + dwmac->tx_clk = NULL; + + match = of_match_device(intel_eth_plat_match, &pdev->dev); + if (match && match->data) { + dwmac->data = (const struct intel_dwmac_data *)match->data; + + if (dwmac->data->fix_mac_speed) + plat_dat->fix_mac_speed = dwmac->data->fix_mac_speed; + + /* Enable TX clock */ + if (dwmac->data->tx_clk_en) { + dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk"); + if (IS_ERR(dwmac->tx_clk)) + goto err_remove_config_dt; + + clk_prepare_enable(dwmac->tx_clk); + + /* Check and configure TX clock rate */ + rate = clk_get_rate(dwmac->tx_clk); + if (dwmac->data->tx_clk_rate && + rate != dwmac->data->tx_clk_rate) { + rate = dwmac->data->tx_clk_rate; + ret = clk_set_rate(dwmac->tx_clk, rate); + if (ret) { + dev_err(&pdev->dev, + "Failed to set tx_clk\n"); + return ret; + } + } + } + + /* Check and configure PTP ref clock rate */ + rate = clk_get_rate(plat_dat->clk_ptp_ref); + if (dwmac->data->ptp_ref_clk_rate && + rate != dwmac->data->ptp_ref_clk_rate) { + rate = dwmac->data->ptp_ref_clk_rate; + ret = clk_set_rate(plat_dat->clk_ptp_ref, rate); + if (ret) { + dev_err(&pdev->dev, + "Failed to set clk_ptp_ref\n"); + return ret; + } + } + } + + plat_dat->bsp_priv = dwmac; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) { + if (dwmac->tx_clk) + clk_disable_unprepare(dwmac->tx_clk); + + goto err_remove_config_dt; + } + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; +} + +static int intel_eth_plat_remove(struct platform_device *pdev) +{ + struct intel_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev); + int ret; + + ret = stmmac_pltfr_remove(pdev); + + if (dwmac->tx_clk) + clk_disable_unprepare(dwmac->tx_clk); + + return ret; +} + +static struct platform_driver intel_eth_plat_driver = { + .probe = intel_eth_plat_probe, + .remove = intel_eth_plat_remove, + .driver = { + .name = "intel-eth-plat", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = intel_eth_plat_match, + }, +}; +module_platform_driver(intel_eth_plat_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel DWMAC platform driver"); diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index eeb8518c8a84..b7093975b14c 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -2965,9 +2965,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* It is guaranteed that the returned buffer will be at least * PAGE_SIZE aligned. */ - gp->init_block = (struct gem_init_block *) - dma_alloc_coherent(&pdev->dev, sizeof(struct gem_init_block), - &gp->gblock_dvma, GFP_KERNEL); + gp->init_block = dma_alloc_coherent(&pdev->dev, sizeof(struct gem_init_block), + &gp->gblock_dvma, GFP_KERNEL); if (!gp->init_block) { pr_err("Cannot allocate init block, aborting\n"); err = -ENOMEM; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c59a289e428c..75056c14b161 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -83,6 +83,8 @@ struct am65_cpts_regs { #define AM65_CPTS_CONTROL_HW8_TS_PUSH_EN BIT(15) #define AM65_CPTS_CONTROL_HW1_TS_PUSH_OFFSET (8) +#define AM65_CPTS_CONTROL_TX_GENF_CLR_EN BIT(17) + #define AM65_CPTS_CONTROL_TS_SYNC_SEL_MASK (0xF) #define AM65_CPTS_CONTROL_TS_SYNC_SEL_SHIFT (28) @@ -748,42 +750,23 @@ EXPORT_SYMBOL_GPL(am65_cpts_rx_enable); static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { unsigned int ptp_class = ptp_classify_raw(skb); - u8 *msgtype, *data = skb->data; - unsigned int offset = 0; - __be16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; if (ptp_class == PTP_CLASS_NONE) return 0; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return 0; - if (unlikely(ptp_class & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, ptp_class); + seqid = ntohs(hdr->sequence_id); - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - *mtype_seqid = (*msgtype << AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT) & + *mtype_seqid = (msgtype << AM65_CPTS_EVENT_1_MESSAGE_TYPE_SHIFT) & AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK; - *mtype_seqid |= (ntohs(*seqid) & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK); + *mtype_seqid |= (seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK); return 1; } @@ -1005,7 +988,9 @@ struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, am65_cpts_set_add_val(cpts); - am65_cpts_write32(cpts, AM65_CPTS_CONTROL_EN | AM65_CPTS_CONTROL_64MODE, + am65_cpts_write32(cpts, AM65_CPTS_CONTROL_EN | + AM65_CPTS_CONTROL_64MODE | + AM65_CPTS_CONTROL_TX_GENF_CLR_EN, control); am65_cpts_write32(cpts, AM65_CPTS_INT_ENABLE_TS_PEND_EN, int_enable); diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 7c55d395de2c..d1fc7955d422 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -446,41 +446,22 @@ static const struct ptp_clock_info cpts_info = { static int cpts_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { unsigned int ptp_class = ptp_classify_raw(skb); - u8 *msgtype, *data = skb->data; - unsigned int offset = 0; - u16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; if (ptp_class == PTP_CLASS_NONE) return 0; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return 0; - if (unlikely(ptp_class & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, ptp_class); + seqid = ntohs(hdr->sequence_id); - seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - *mtype_seqid = (*msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT; - *mtype_seqid |= (ntohs(*seqid) & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT; + *mtype_seqid = (msgtype & MESSAGE_TYPE_MASK) << MESSAGE_TYPE_SHIFT; + *mtype_seqid |= (seqid & SEQUENCE_ID_MASK) << SEQUENCE_ID_SHIFT; return 1; } @@ -528,6 +509,11 @@ void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb) int ret; u64 ns; + /* cpts_rx_timestamp() is called before eth_type_trans(), so + * skb MAC Hdr properties are not configured yet. Hence need to + * reset skb MAC header here + */ + skb_reset_mac_header(skb); ret = cpts_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid); if (!ret) return; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 21640a035d7d..2ed1e82a8ad8 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -928,8 +928,8 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, - struct genl_info *info) +static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; @@ -956,12 +956,12 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) - return -EEXIST; + return ERR_PTR(-EEXIST); if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) - return -EOPNOTSUPP; + return ERR_PTR(-EOPNOTSUPP); if (pctx && pctx_tid) - return -EEXIST; + return ERR_PTR(-EEXIST); if (!pctx) pctx = pctx_tid; @@ -974,13 +974,13 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); - return 0; + return pctx; } pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC); if (pctx == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); sock_hold(sk); pctx->sk = sk; @@ -1018,7 +1018,7 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, break; } - return 0; + return pctx; } static void pdp_context_free(struct rcu_head *head) @@ -1036,9 +1036,12 @@ static void pdp_context_delete(struct pdp_ctx *pctx) call_rcu(&pctx->rcu_head, pdp_context_free); } +static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation); + static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) { unsigned int version; + struct pdp_ctx *pctx; struct gtp_dev *gtp; struct sock *sk; int err; @@ -1068,7 +1071,6 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) } rtnl_lock(); - rcu_read_lock(); gtp = gtp_find_dev(sock_net(skb->sk), info->attrs); if (!gtp) { @@ -1088,10 +1090,15 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = gtp_pdp_add(gtp, sk, info); + pctx = gtp_pdp_add(gtp, sk, info); + if (IS_ERR(pctx)) { + err = PTR_ERR(pctx); + } else { + gtp_tunnel_notify(pctx, GTP_CMD_NEWPDP, GFP_KERNEL); + err = 0; + } out_unlock: - rcu_read_unlock(); rtnl_unlock(); return err; } @@ -1159,6 +1166,7 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n", pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx); + gtp_tunnel_notify(pctx, GTP_CMD_DELPDP, GFP_ATOMIC); pdp_context_delete(pctx); out_unlock: @@ -1168,6 +1176,14 @@ out_unlock: static struct genl_family gtp_genl_family; +enum gtp_multicast_groups { + GTP_GENL_MCGRP, +}; + +static const struct genl_multicast_group gtp_genl_mcgrps[] = { + [GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME }, +}; + static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, int flags, u32 type, struct pdp_ctx *pctx) { @@ -1204,6 +1220,26 @@ nla_put_failure: return -EMSGSIZE; } +static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd, gfp_t allocation) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, allocation); + if (!msg) + return -ENOMEM; + + ret = gtp_genl_fill_info(msg, 0, 0, 0, cmd, pctx); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_multicast_netns(>p_genl_family, dev_net(pctx->dev), msg, + 0, GTP_GENL_MCGRP, GFP_ATOMIC); + return ret; +} + static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) { struct pdp_ctx *pctx = NULL; @@ -1334,6 +1370,8 @@ static struct genl_family gtp_genl_family __ro_after_init = { .module = THIS_MODULE, .ops = gtp_genl_ops, .n_ops = ARRAY_SIZE(gtp_genl_ops), + .mcgrps = gtp_genl_mcgrps, + .n_mcgrps = ARRAY_SIZE(gtp_genl_mcgrps), }; static int __net_init gtp_net_init(struct net *net) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 787f17e2a971..64b0a74c1523 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -367,7 +367,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, } rcu_read_unlock(); - while (unlikely(txq >= ndev->real_num_tx_queues)) + while (txq >= ndev->real_num_tx_queues) txq -= ndev->real_num_tx_queues; return txq; @@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev, int rc; skb->dev = vf_netdev; - skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; + skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); rc = dev_queue_xmit(skb); if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) { diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index 55115cfb2972..407fee841a9a 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -10,7 +10,6 @@ #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm_wakeup.h> -#include <linux/notifier.h> #include "ipa_version.h" #include "gsi.h" diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 5bca94c99006..60b7d93bb834 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -684,6 +684,13 @@ static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; +static struct net *ipvlan_get_link_net(const struct net_device *dev) +{ + struct ipvl_dev *ipvlan = netdev_priv(dev); + + return dev_net(ipvlan->phy_dev); +} + static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), @@ -691,6 +698,7 @@ static struct rtnl_link_ops ipvlan_link_ops = { .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, + .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 4942f6112e51..5da04e997989 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1269,6 +1269,9 @@ static void macvlan_port_destroy(struct net_device *dev) static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + struct nlattr *nla, *head; + int rem, len; + if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; @@ -1316,6 +1319,20 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], return -EADDRNOTAVAIL; } + if (data[IFLA_MACVLAN_MACADDR_DATA]) { + head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); + len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); + + nla_for_each_attr(nla, head, len, rem) { + if (nla_type(nla) != IFLA_MACVLAN_MACADDR || + nla_len(nla) != ETH_ALEN) + return -EINVAL; + + if (!is_valid_ether_addr(nla_data(nla))) + return -EADDRNOTAVAIL; + } + } + if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; @@ -1372,10 +1389,6 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { - if (nla_type(nla) != IFLA_MACVLAN_MACADDR || - nla_len(nla) != ETH_ALEN) - continue; - addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig new file mode 100644 index 000000000000..1299880dfe74 --- /dev/null +++ b/drivers/net/mdio/Kconfig @@ -0,0 +1,241 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# MDIO Layer Configuration +# + +menuconfig MDIO_DEVICE + tristate "MDIO bus device drivers" + help + MDIO devices and driver infrastructure code. + +if MDIO_DEVICE + +config MDIO_BUS + tristate + default m if PHYLIB=m + default MDIO_DEVICE + help + This internal symbol is used for link time dependencies and it + reflects whether the mdio_bus/mdio_device code is built as a + loadable module or built-in. + +if MDIO_BUS + +config MDIO_DEVRES + tristate + +config MDIO_SUN4I + tristate "Allwinner sun4i MDIO interface support" + depends on ARCH_SUNXI || COMPILE_TEST + help + This driver supports the MDIO interface found in the network + interface units of the Allwinner SoC that have an EMAC (A10, + A12, A10s, etc.) + +config MDIO_XGENE + tristate "APM X-Gene SoC MDIO bus controller" + depends on ARCH_XGENE || COMPILE_TEST + help + This module provides a driver for the MDIO busses found in the + APM X-Gene SoC's. + +config MDIO_ASPEED + tristate "ASPEED MDIO bus controller" + depends on ARCH_ASPEED || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM + help + This module provides a driver for the independent MDIO bus + controllers found in the ASPEED AST2600 SoC. This is a driver for the + third revision of the ASPEED MDIO register interface - the first two + revisions are the "old" and "new" interfaces found in the AST2400 and + AST2500, embedded in the MAC. For legacy reasons, FTGMAC100 driver + continues to drive the embedded MDIO controller for the AST2400 and + AST2500 SoCs, so say N if AST2600 support is not required. + +config MDIO_BITBANG + tristate "Bitbanged MDIO buses" + help + This module implements the MDIO bus protocol in software, + for use by low level drivers that export the ability to + drive the relevant pins. + + If in doubt, say N. + +config MDIO_BCM_IPROC + tristate "Broadcom iProc MDIO bus controller" + depends on ARCH_BCM_IPROC || COMPILE_TEST + depends on HAS_IOMEM && OF_MDIO + default ARCH_BCM_IPROC + help + This module provides a driver for the MDIO busses found in the + Broadcom iProc SoC's. + +config MDIO_BCM_UNIMAC + tristate "Broadcom UniMAC MDIO bus controller" + depends on HAS_IOMEM + help + This module provides a driver for the Broadcom UniMAC MDIO busses. + This hardware can be found in the Broadcom GENET Ethernet MAC + controllers as well as some Broadcom Ethernet switches such as the + Starfighter 2 switches. + +config MDIO_CAVIUM + tristate + +config MDIO_GPIO + tristate "GPIO lib-based bitbanged MDIO buses" + depends on MDIO_BITBANG + depends on GPIOLIB || COMPILE_TEST + help + Supports GPIO lib-based MDIO busses. + + To compile this driver as a module, choose M here: the module + will be called mdio-gpio. + +config MDIO_HISI_FEMAC + tristate "Hisilicon FEMAC MDIO bus controller" + depends on HAS_IOMEM && OF_MDIO + help + This module provides a driver for the MDIO busses found in the + Hisilicon SoC that have an Fast Ethernet MAC. + +config MDIO_I2C + tristate + depends on I2C + help + Support I2C based PHYs. This provides a MDIO bus bridged + to I2C to allow PHYs connected in I2C mode to be accessed + using the existing infrastructure. + + This is library mode. + +config MDIO_MVUSB + tristate "Marvell USB to MDIO Adapter" + depends on USB + select MDIO_DEVRES + help + A USB to MDIO converter present on development boards for + Marvell's Link Street family of Ethernet switches. + +config MDIO_MSCC_MIIM + tristate "Microsemi MIIM interface support" + depends on HAS_IOMEM + select MDIO_DEVRES + help + This driver supports the MIIM (MDIO) interface found in the network + switches of the Microsemi SoCs; it is recommended to switch on + CONFIG_HIGH_RES_TIMERS + +config MDIO_MOXART + tristate "MOXA ART MDIO interface support" + depends on ARCH_MOXART || COMPILE_TEST + help + This driver supports the MDIO interface found in the network + interface units of the MOXA ART SoC + +config MDIO_OCTEON + tristate "Octeon and some ThunderX SOCs MDIO buses" + depends on (64BIT && OF_MDIO) || COMPILE_TEST + depends on HAS_IOMEM + select MDIO_CAVIUM + help + This module provides a driver for the Octeon and ThunderX MDIO + buses. It is required by the Octeon and ThunderX ethernet device + drivers on some systems. + +config MDIO_IPQ4019 + tristate "Qualcomm IPQ4019 MDIO interface support" + depends on HAS_IOMEM && OF_MDIO + help + This driver supports the MDIO interface found in Qualcomm + IPQ40xx series Soc-s. + +config MDIO_IPQ8064 + tristate "Qualcomm IPQ8064 MDIO interface support" + depends on HAS_IOMEM && OF_MDIO + depends on MFD_SYSCON + help + This driver supports the MDIO interface found in the network + interface units of the IPQ8064 SoC + +config MDIO_THUNDER + tristate "ThunderX SOCs MDIO buses" + depends on 64BIT + depends on PCI + select MDIO_CAVIUM + help + This driver supports the MDIO interfaces found on Cavium + ThunderX SoCs when the MDIO bus device appears as a PCI + device. + +comment "MDIO Multiplexers" + +config MDIO_BUS_MUX + tristate + depends on OF_MDIO + help + This module provides a driver framework for MDIO bus + multiplexers which connect one of several child MDIO busses + to a parent bus. Switching between child busses is done by + device specific drivers. + +config MDIO_BUS_MUX_MESON_G12A + tristate "Amlogic G12a based MDIO bus multiplexer" + depends on ARCH_MESON || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM && COMMON_CLK + select MDIO_BUS_MUX + default m if ARCH_MESON + help + This module provides a driver for the MDIO multiplexer/glue of + the amlogic g12a SoC. The multiplexers connects either the external + or the internal MDIO bus to the parent bus. + +config MDIO_BUS_MUX_BCM_IPROC + tristate "Broadcom iProc based MDIO bus multiplexers" + depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST) + select MDIO_BUS_MUX + default ARCH_BCM_IPROC + help + This module provides a driver for MDIO bus multiplexers found in + iProc based Broadcom SoCs. This multiplexer connects one of several + child MDIO bus to a parent bus. Buses could be internal as well as + external and selection logic lies inside the same multiplexer. + +config MDIO_BUS_MUX_GPIO + tristate "GPIO controlled MDIO bus multiplexers" + depends on OF_GPIO && OF_MDIO + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexers that + are controlled via GPIO lines. The multiplexer connects one of + several child MDIO busses to a parent bus. Child bus + selection is under the control of GPIO lines. + +config MDIO_BUS_MUX_MULTIPLEXER + tristate "MDIO bus multiplexer using kernel multiplexer subsystem" + depends on OF_MDIO + select MULTIPLEXER + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexer + that is controlled via the kernel multiplexer subsystem. The + bus multiplexer connects one of several child MDIO busses to + a parent bus. Child bus selection is under the control of + the kernel multiplexer subsystem. + +config MDIO_BUS_MUX_MMIOREG + tristate "MMIO device-controlled MDIO bus multiplexers" + depends on OF_MDIO && HAS_IOMEM + select MDIO_BUS_MUX + help + This module provides a driver for MDIO bus multiplexers that + are controlled via a simple memory-mapped device, like an FPGA. + The multiplexer connects one of several child MDIO busses to a + parent bus. Child bus selection is under the control of one of + the FPGA's registers. + + Currently, only 8/16/32 bits registers are supported. + + +endif +endif diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile new file mode 100644 index 000000000000..14d1beb633c9 --- /dev/null +++ b/drivers/net/mdio/Makefile @@ -0,0 +1,27 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Linux MDIO bus drivers + +obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o +obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o +obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o +obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o +obj-$(CONFIG_MDIO_CAVIUM) += mdio-cavium.o +obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o +obj-$(CONFIG_MDIO_HISI_FEMAC) += mdio-hisi-femac.o +obj-$(CONFIG_MDIO_I2C) += mdio-i2c.o +obj-$(CONFIG_MDIO_IPQ4019) += mdio-ipq4019.o +obj-$(CONFIG_MDIO_IPQ8064) += mdio-ipq8064.o +obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o +obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o +obj-$(CONFIG_MDIO_MVUSB) += mdio-mvusb.o +obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o +obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o +obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o +obj-$(CONFIG_MDIO_XGENE) += mdio-xgene.o + +obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o +obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o +obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o +obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o +obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o +obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o diff --git a/drivers/net/phy/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index cad820568f75..cad820568f75 100644 --- a/drivers/net/phy/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/mdio/mdio-bcm-iproc.c index 77fc970cdfde..77fc970cdfde 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/mdio/mdio-bcm-iproc.c diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c index fbd36891ee64..fbd36891ee64 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/mdio/mdio-bcm-unimac.c diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/mdio/mdio-bitbang.c index 5136275c8e73..5136275c8e73 100644 --- a/drivers/net/phy/mdio-bitbang.c +++ b/drivers/net/mdio/mdio-bitbang.c diff --git a/drivers/net/phy/mdio-cavium.c b/drivers/net/mdio/mdio-cavium.c index 1afd6fc1a351..1afd6fc1a351 100644 --- a/drivers/net/phy/mdio-cavium.c +++ b/drivers/net/mdio/mdio-cavium.c diff --git a/drivers/net/phy/mdio-cavium.h b/drivers/net/mdio/mdio-cavium.h index a2245d436f5d..a2245d436f5d 100644 --- a/drivers/net/phy/mdio-cavium.h +++ b/drivers/net/mdio/mdio-cavium.h diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/mdio/mdio-gpio.c index 1b00235d7dc5..1b00235d7dc5 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/mdio/mdio-gpio.c diff --git a/drivers/net/phy/mdio-hisi-femac.c b/drivers/net/mdio/mdio-hisi-femac.c index f231c2fbb1de..f231c2fbb1de 100644 --- a/drivers/net/phy/mdio-hisi-femac.c +++ b/drivers/net/mdio/mdio-hisi-femac.c diff --git a/drivers/net/phy/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 0746e2cc39ae..09200a70b315 100644 --- a/drivers/net/phy/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -10,10 +10,9 @@ * of their settings. */ #include <linux/i2c.h> +#include <linux/mdio/mdio-i2c.h> #include <linux/phy.h> -#include "mdio-i2c.h" - /* * I2C bus addresses 0x50 and 0x51 are normally an EEPROM, which is * specified to be present in SFP modules. These correspond with PHY diff --git a/drivers/net/phy/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 1ce81ff2f41d..1ce81ff2f41d 100644 --- a/drivers/net/phy/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c diff --git a/drivers/net/phy/mdio-ipq8064.c b/drivers/net/mdio/mdio-ipq8064.c index 1bd18857e1c5..1bd18857e1c5 100644 --- a/drivers/net/phy/mdio-ipq8064.c +++ b/drivers/net/mdio/mdio-ipq8064.c diff --git a/drivers/net/phy/mdio-moxart.c b/drivers/net/mdio/mdio-moxart.c index b72c6d185175..b72c6d185175 100644 --- a/drivers/net/phy/mdio-moxart.c +++ b/drivers/net/mdio/mdio-moxart.c diff --git a/drivers/net/phy/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index 11f583fd4611..11f583fd4611 100644 --- a/drivers/net/phy/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c index 42fb5f166136..42fb5f166136 100644 --- a/drivers/net/phy/mdio-mux-bcm-iproc.c +++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/mdio/mdio-mux-gpio.c index 10a758fdc9e6..10a758fdc9e6 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/mdio/mdio-mux-gpio.c diff --git a/drivers/net/phy/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index bf86c9c7a288..bf86c9c7a288 100644 --- a/drivers/net/phy/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/mdio/mdio-mux-mmioreg.c index d1a8780e24d8..d1a8780e24d8 100644 --- a/drivers/net/phy/mdio-mux-mmioreg.c +++ b/drivers/net/mdio/mdio-mux-mmioreg.c diff --git a/drivers/net/phy/mdio-mux-multiplexer.c b/drivers/net/mdio/mdio-mux-multiplexer.c index d6564381aa3e..d6564381aa3e 100644 --- a/drivers/net/phy/mdio-mux-multiplexer.c +++ b/drivers/net/mdio/mdio-mux-multiplexer.c diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/mdio/mdio-mux.c index 6a1d3540210b..6a1d3540210b 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/mdio/mdio-mux.c diff --git a/drivers/net/phy/mdio-mvusb.c b/drivers/net/mdio/mdio-mvusb.c index d5eabddfdf51..d5eabddfdf51 100644 --- a/drivers/net/phy/mdio-mvusb.c +++ b/drivers/net/mdio/mdio-mvusb.c diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/mdio/mdio-octeon.c index d1e1009d51af..d1e1009d51af 100644 --- a/drivers/net/phy/mdio-octeon.c +++ b/drivers/net/mdio/mdio-octeon.c diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/mdio/mdio-sun4i.c index f798de3276dc..f798de3276dc 100644 --- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/mdio/mdio-sun4i.c diff --git a/drivers/net/phy/mdio-thunder.c b/drivers/net/mdio/mdio-thunder.c index 3d7eda99d34e..3d7eda99d34e 100644 --- a/drivers/net/phy/mdio-thunder.c +++ b/drivers/net/mdio/mdio-thunder.c diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c index 34990eaa3298..461207cdf5d6 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/mdio/mdio-xgene.c @@ -11,6 +11,7 @@ #include <linux/efi.h> #include <linux/if_vlan.h> #include <linux/io.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <linux/of_platform.h> #include <linux/of_net.h> @@ -18,7 +19,6 @@ #include <linux/prefetch.h> #include <linux/phy.h> #include <net/ip.h> -#include "mdio-xgene.h" static bool xgene_mdio_status; diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig new file mode 100644 index 000000000000..074fb3f5db18 --- /dev/null +++ b/drivers/net/pcs/Kconfig @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# PCS Layer Configuration +# + +menu "PCS device drivers" + +config PCS_XPCS + tristate "Synopsys DesignWare XPCS controller" + select MDIO_BUS + depends on MDIO_DEVICE + help + This module provides helper functions for Synopsys DesignWare XPCS + controllers. + +config PCS_LYNX + tristate + help + This module provides helpers to phylink for managing the Lynx PCS + which is part of the Layerscape and QorIQ Ethernet SERDES. + +endmenu diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile new file mode 100644 index 000000000000..c23146755972 --- /dev/null +++ b/drivers/net/pcs/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Linux PCS drivers + +obj-$(CONFIG_PCS_XPCS) += pcs-xpcs.o +obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c new file mode 100644 index 000000000000..c43d97682083 --- /dev/null +++ b/drivers/net/pcs/pcs-lynx.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2020 NXP + * Lynx PCS MDIO helpers + */ + +#include <linux/mdio.h> +#include <linux/phylink.h> +#include <linux/pcs-lynx.h> + +#define SGMII_CLOCK_PERIOD_NS 8 /* PCS is clocked at 125 MHz */ +#define LINK_TIMER_VAL(ns) ((u32)((ns) / SGMII_CLOCK_PERIOD_NS)) + +#define SGMII_AN_LINK_TIMER_NS 1600000 /* defined by SGMII spec */ + +#define LINK_TIMER_LO 0x12 +#define LINK_TIMER_HI 0x13 +#define IF_MODE 0x14 +#define IF_MODE_SGMII_EN BIT(0) +#define IF_MODE_USE_SGMII_AN BIT(1) +#define IF_MODE_SPEED(x) (((x) << 2) & GENMASK(3, 2)) +#define IF_MODE_SPEED_MSK GENMASK(3, 2) +#define IF_MODE_HALF_DUPLEX BIT(4) + +enum sgmii_speed { + SGMII_SPEED_10 = 0, + SGMII_SPEED_100 = 1, + SGMII_SPEED_1000 = 2, + SGMII_SPEED_2500 = 2, +}; + +#define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs) + +static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs, + struct phylink_link_state *state) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + int status, lpa; + + status = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_BMSR); + if (status < 0) + return; + + state->link = !!(status & MDIO_STAT1_LSTATUS); + state->an_complete = !!(status & MDIO_AN_STAT1_COMPLETE); + if (!state->link || !state->an_complete) + return; + + lpa = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_LPA); + if (lpa < 0) + return; + + phylink_decode_usxgmii_word(state, lpa); +} + +static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs, + struct phylink_link_state *state) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + int bmsr, lpa; + + bmsr = mdiobus_read(bus, addr, MII_BMSR); + lpa = mdiobus_read(bus, addr, MII_LPA); + if (bmsr < 0 || lpa < 0) { + state->link = false; + return; + } + + state->link = !!(bmsr & BMSR_LSTATUS); + state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); + if (!state->link) + return; + + state->speed = SPEED_2500; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + state->duplex = DUPLEX_FULL; +} + +static void lynx_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (state->interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + phylink_mii_c22_pcs_get_state(lynx->mdio, state); + break; + case PHY_INTERFACE_MODE_2500BASEX: + lynx_pcs_get_state_2500basex(lynx->mdio, state); + break; + case PHY_INTERFACE_MODE_USXGMII: + lynx_pcs_get_state_usxgmii(lynx->mdio, state); + break; + default: + break; + } + + dev_dbg(&lynx->mdio->dev, + "mode=%s/%s/%s link=%u an_enabled=%u an_complete=%u\n", + phy_modes(state->interface), + phy_speed_to_str(state->speed), + phy_duplex_to_str(state->duplex), + state->link, state->an_enabled, state->an_complete); +} + +static int lynx_pcs_config_sgmii(struct mdio_device *pcs, unsigned int mode, + const unsigned long *advertising) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + u16 if_mode; + int err; + + if_mode = IF_MODE_SGMII_EN; + if (mode == MLO_AN_INBAND) { + u32 link_timer; + + if_mode |= IF_MODE_USE_SGMII_AN; + + /* Adjust link timer for SGMII */ + link_timer = LINK_TIMER_VAL(SGMII_AN_LINK_TIMER_NS); + mdiobus_write(bus, addr, LINK_TIMER_LO, link_timer & 0xffff); + mdiobus_write(bus, addr, LINK_TIMER_HI, link_timer >> 16); + } + err = mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_SGMII_EN | IF_MODE_USE_SGMII_AN, + if_mode); + if (err) + return err; + + return phylink_mii_c22_pcs_config(pcs, mode, PHY_INTERFACE_MODE_SGMII, + advertising); +} + +static int lynx_pcs_config_usxgmii(struct mdio_device *pcs, unsigned int mode, + const unsigned long *advertising) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + + if (!phylink_autoneg_inband(mode)) { + dev_err(&pcs->dev, "USXGMII only supports in-band AN for now\n"); + return -EOPNOTSUPP; + } + + /* Configure device ability for the USXGMII Replicator */ + return mdiobus_c45_write(bus, addr, MDIO_MMD_VEND2, MII_ADVERTISE, + MDIO_USXGMII_10G | MDIO_USXGMII_LINK | + MDIO_USXGMII_FULL_DUPLEX | + ADVERTISE_SGMII | ADVERTISE_LPACK); +} + +static int lynx_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t ifmode, + const unsigned long *advertising, + bool permit) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (ifmode) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + return lynx_pcs_config_sgmii(lynx->mdio, mode, advertising); + case PHY_INTERFACE_MODE_2500BASEX: + if (phylink_autoneg_inband(mode)) { + dev_err(&lynx->mdio->dev, + "AN not supported on 3.125GHz SerDes lane\n"); + return -EOPNOTSUPP; + } + break; + case PHY_INTERFACE_MODE_USXGMII: + return lynx_pcs_config_usxgmii(lynx->mdio, mode, advertising); + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs, unsigned int mode, + int speed, int duplex) +{ + struct mii_bus *bus = pcs->bus; + u16 if_mode = 0, sgmii_speed; + int addr = pcs->addr; + + /* The PCS needs to be configured manually only + * when not operating on in-band mode + */ + if (mode == MLO_AN_INBAND) + return; + + if (duplex == DUPLEX_HALF) + if_mode |= IF_MODE_HALF_DUPLEX; + + switch (speed) { + case SPEED_1000: + sgmii_speed = SGMII_SPEED_1000; + break; + case SPEED_100: + sgmii_speed = SGMII_SPEED_100; + break; + case SPEED_10: + sgmii_speed = SGMII_SPEED_10; + break; + case SPEED_UNKNOWN: + /* Silently don't do anything */ + return; + default: + dev_err(&pcs->dev, "Invalid PCS speed %d\n", speed); + return; + } + if_mode |= IF_MODE_SPEED(sgmii_speed); + + mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK, + if_mode); +} + +/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane + * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have + * auto-negotiation of any link parameters. Electrically it is compatible with + * a single lane of XAUI. + * The hardware reference manual wants to call this mode SGMII, but it isn't + * really, since the fundamental features of SGMII: + * - Downgrading the link speed by duplicating symbols + * - Auto-negotiation + * are not there. + * The speed is configured at 1000 in the IF_MODE because the clock frequency + * is actually given by a PLL configured in the Reset Configuration Word (RCW). + * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o + * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a + * lower link speed on line side, the system-side interface remains fixed at + * 2500 Mbps and we do rate adaptation through pause frames. + */ +static void lynx_pcs_link_up_2500basex(struct mdio_device *pcs, + unsigned int mode, + int speed, int duplex) +{ + struct mii_bus *bus = pcs->bus; + int addr = pcs->addr; + u16 if_mode = 0; + + if (mode == MLO_AN_INBAND) { + dev_err(&pcs->dev, "AN not supported for 2500BaseX\n"); + return; + } + + if (duplex == DUPLEX_HALF) + if_mode |= IF_MODE_HALF_DUPLEX; + if_mode |= IF_MODE_SPEED(SGMII_SPEED_2500); + + mdiobus_modify(bus, addr, IF_MODE, + IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK, + if_mode); +} + +static void lynx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + int speed, int duplex) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + lynx_pcs_link_up_sgmii(lynx->mdio, mode, speed, duplex); + break; + case PHY_INTERFACE_MODE_2500BASEX: + lynx_pcs_link_up_2500basex(lynx->mdio, mode, speed, duplex); + break; + case PHY_INTERFACE_MODE_USXGMII: + /* At the moment, only in-band AN is supported for USXGMII + * so nothing to do in link_up + */ + break; + default: + break; + } +} + +static const struct phylink_pcs_ops lynx_pcs_phylink_ops = { + .pcs_get_state = lynx_pcs_get_state, + .pcs_config = lynx_pcs_config, + .pcs_link_up = lynx_pcs_link_up, +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio) +{ + struct lynx_pcs *lynx_pcs; + + lynx_pcs = kzalloc(sizeof(*lynx_pcs), GFP_KERNEL); + if (!lynx_pcs) + return NULL; + + lynx_pcs->mdio = mdio; + lynx_pcs->pcs.ops = &lynx_pcs_phylink_ops; + lynx_pcs->pcs.poll = true; + + return lynx_pcs; +} +EXPORT_SYMBOL(lynx_pcs_create); + +void lynx_pcs_destroy(struct lynx_pcs *pcs) +{ + kfree(pcs); +} +EXPORT_SYMBOL(lynx_pcs_destroy); + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/phy/mdio-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 0d66a8ba7eb6..1aa9903d602e 100644 --- a/drivers/net/phy/mdio-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -7,8 +7,8 @@ */ #include <linux/delay.h> +#include <linux/pcs/pcs-xpcs.h> #include <linux/mdio.h> -#include <linux/mdio-xpcs.h> #include <linux/phylink.h> #include <linux/workqueue.h> diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 726e4b240e7e..698bea312adc 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -3,246 +3,6 @@ # PHY Layer Configuration # -menuconfig MDIO_DEVICE - tristate "MDIO bus device drivers" - help - MDIO devices and driver infrastructure code. - -if MDIO_DEVICE - -config MDIO_BUS - tristate - default m if PHYLIB=m - default MDIO_DEVICE - help - This internal symbol is used for link time dependencies and it - reflects whether the mdio_bus/mdio_device code is built as a - loadable module or built-in. - -if MDIO_BUS - -config MDIO_DEVRES - tristate - -config MDIO_ASPEED - tristate "ASPEED MDIO bus controller" - depends on ARCH_ASPEED || COMPILE_TEST - depends on OF_MDIO && HAS_IOMEM - help - This module provides a driver for the independent MDIO bus - controllers found in the ASPEED AST2600 SoC. This is a driver for the - third revision of the ASPEED MDIO register interface - the first two - revisions are the "old" and "new" interfaces found in the AST2400 and - AST2500, embedded in the MAC. For legacy reasons, FTGMAC100 driver - continues to drive the embedded MDIO controller for the AST2400 and - AST2500 SoCs, so say N if AST2600 support is not required. - -config MDIO_BCM_IPROC - tristate "Broadcom iProc MDIO bus controller" - depends on ARCH_BCM_IPROC || COMPILE_TEST - depends on HAS_IOMEM && OF_MDIO - default ARCH_BCM_IPROC - help - This module provides a driver for the MDIO busses found in the - Broadcom iProc SoC's. - -config MDIO_BCM_UNIMAC - tristate "Broadcom UniMAC MDIO bus controller" - depends on HAS_IOMEM - help - This module provides a driver for the Broadcom UniMAC MDIO busses. - This hardware can be found in the Broadcom GENET Ethernet MAC - controllers as well as some Broadcom Ethernet switches such as the - Starfighter 2 switches. - -config MDIO_BITBANG - tristate "Bitbanged MDIO buses" - help - This module implements the MDIO bus protocol in software, - for use by low level drivers that export the ability to - drive the relevant pins. - - If in doubt, say N. - -config MDIO_BUS_MUX - tristate - depends on OF_MDIO - help - This module provides a driver framework for MDIO bus - multiplexers which connect one of several child MDIO busses - to a parent bus. Switching between child busses is done by - device specific drivers. - -config MDIO_BUS_MUX_BCM_IPROC - tristate "Broadcom iProc based MDIO bus multiplexers" - depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST) - select MDIO_BUS_MUX - default ARCH_BCM_IPROC - help - This module provides a driver for MDIO bus multiplexers found in - iProc based Broadcom SoCs. This multiplexer connects one of several - child MDIO bus to a parent bus. Buses could be internal as well as - external and selection logic lies inside the same multiplexer. - -config MDIO_BUS_MUX_GPIO - tristate "GPIO controlled MDIO bus multiplexers" - depends on OF_GPIO && OF_MDIO - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexers that - are controlled via GPIO lines. The multiplexer connects one of - several child MDIO busses to a parent bus. Child bus - selection is under the control of GPIO lines. - -config MDIO_BUS_MUX_MESON_G12A - tristate "Amlogic G12a based MDIO bus multiplexer" - depends on ARCH_MESON || COMPILE_TEST - depends on OF_MDIO && HAS_IOMEM && COMMON_CLK - select MDIO_BUS_MUX - default m if ARCH_MESON - help - This module provides a driver for the MDIO multiplexer/glue of - the amlogic g12a SoC. The multiplexers connects either the external - or the internal MDIO bus to the parent bus. - -config MDIO_BUS_MUX_MMIOREG - tristate "MMIO device-controlled MDIO bus multiplexers" - depends on OF_MDIO && HAS_IOMEM - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexers that - are controlled via a simple memory-mapped device, like an FPGA. - The multiplexer connects one of several child MDIO busses to a - parent bus. Child bus selection is under the control of one of - the FPGA's registers. - - Currently, only 8/16/32 bits registers are supported. - -config MDIO_BUS_MUX_MULTIPLEXER - tristate "MDIO bus multiplexer using kernel multiplexer subsystem" - depends on OF_MDIO - select MULTIPLEXER - select MDIO_BUS_MUX - help - This module provides a driver for MDIO bus multiplexer - that is controlled via the kernel multiplexer subsystem. The - bus multiplexer connects one of several child MDIO busses to - a parent bus. Child bus selection is under the control of - the kernel multiplexer subsystem. - -config MDIO_CAVIUM - tristate - -config MDIO_GPIO - tristate "GPIO lib-based bitbanged MDIO buses" - depends on MDIO_BITBANG - depends on GPIOLIB || COMPILE_TEST - help - Supports GPIO lib-based MDIO busses. - - To compile this driver as a module, choose M here: the module - will be called mdio-gpio. - -config MDIO_HISI_FEMAC - tristate "Hisilicon FEMAC MDIO bus controller" - depends on HAS_IOMEM && OF_MDIO - help - This module provides a driver for the MDIO busses found in the - Hisilicon SoC that have an Fast Ethernet MAC. - -config MDIO_I2C - tristate - depends on I2C - help - Support I2C based PHYs. This provides a MDIO bus bridged - to I2C to allow PHYs connected in I2C mode to be accessed - using the existing infrastructure. - - This is library mode. - -config MDIO_IPQ4019 - tristate "Qualcomm IPQ4019 MDIO interface support" - depends on HAS_IOMEM && OF_MDIO - help - This driver supports the MDIO interface found in Qualcomm - IPQ40xx series Soc-s. - -config MDIO_IPQ8064 - tristate "Qualcomm IPQ8064 MDIO interface support" - depends on HAS_IOMEM && OF_MDIO - depends on MFD_SYSCON - help - This driver supports the MDIO interface found in the network - interface units of the IPQ8064 SoC - -config MDIO_MOXART - tristate "MOXA ART MDIO interface support" - depends on ARCH_MOXART || COMPILE_TEST - help - This driver supports the MDIO interface found in the network - interface units of the MOXA ART SoC - -config MDIO_MSCC_MIIM - tristate "Microsemi MIIM interface support" - depends on HAS_IOMEM - select MDIO_DEVRES - help - This driver supports the MIIM (MDIO) interface found in the network - switches of the Microsemi SoCs; it is recommended to switch on - CONFIG_HIGH_RES_TIMERS - -config MDIO_MVUSB - tristate "Marvell USB to MDIO Adapter" - depends on USB - select MDIO_DEVRES - help - A USB to MDIO converter present on development boards for - Marvell's Link Street family of Ethernet switches. - -config MDIO_OCTEON - tristate "Octeon and some ThunderX SOCs MDIO buses" - depends on (64BIT && OF_MDIO) || COMPILE_TEST - depends on HAS_IOMEM - select MDIO_CAVIUM - help - This module provides a driver for the Octeon and ThunderX MDIO - buses. It is required by the Octeon and ThunderX ethernet device - drivers on some systems. - -config MDIO_SUN4I - tristate "Allwinner sun4i MDIO interface support" - depends on ARCH_SUNXI || COMPILE_TEST - help - This driver supports the MDIO interface found in the network - interface units of the Allwinner SoC that have an EMAC (A10, - A12, A10s, etc.) - -config MDIO_THUNDER - tristate "ThunderX SOCs MDIO buses" - depends on 64BIT - depends on PCI - select MDIO_CAVIUM - help - This driver supports the MDIO interfaces found on Cavium - ThunderX SoCs when the MDIO bus device appears as a PCI - device. - -config MDIO_XGENE - tristate "APM X-Gene SoC MDIO bus controller" - depends on ARCH_XGENE || COMPILE_TEST - help - This module provides a driver for the MDIO busses found in the - APM X-Gene SoC's. - -config MDIO_XPCS - tristate "Synopsys DesignWare XPCS controller" - help - This module provides helper functions for Synopsys DesignWare XPCS - controllers. - -endif -endif - config PHYLINK tristate depends on NETDEVICES @@ -285,7 +45,15 @@ config LED_TRIGGER_PHY for any speed known to the PHY. -comment "MII PHY device drivers" +config FIXED_PHY + tristate "MDIO Bus/PHY emulation with fixed speed/link PHYs" + depends on PHYLIB + select SWPHY + help + Adds the platform "fixed" MDIO Bus to cover the boards that use + PHYs that are not connected to the real MDIO bus. + + Currently tested with mpc866ads and mpc8349e-mitx. config SFP tristate "SFP cage support" @@ -293,6 +61,19 @@ config SFP depends on HWMON || HWMON=n select MDIO_I2C +comment "MII PHY device drivers" + +config AMD_PHY + tristate "AMD PHYs" + help + Currently supports the am79c874 + +config MESON_GXL_PHY + tristate "Amlogic Meson GXL Internal PHY" + depends on ARCH_MESON || COMPILE_TEST + help + Currently has a driver for the Amlogic Meson GXL Internal PHY + config ADIN_PHY tristate "Analog Devices Industrial Ethernet PHYs" help @@ -302,11 +83,6 @@ config ADIN_PHY - ADIN1300 - Robust,Industrial, Low Latency 10/100/1000 Gigabit Ethernet PHY -config AMD_PHY - tristate "AMD PHYs" - help - Currently supports the am79c874 - config AQUANTIA_PHY tristate "Aquantia PHYs" help @@ -318,6 +94,24 @@ config AX88796B_PHY Currently supports the Asix Electronics PHY found in the X-Surf 100 AX88796B package. +config BROADCOM_PHY + tristate "Broadcom 54XX PHYs" + select BCM_NET_PHYLIB + help + Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, + BCM5481, BCM54810 and BCM5482 PHYs. + +config BCM54140_PHY + tristate "Broadcom BCM54140 PHY" + depends on PHYLIB + depends on HWMON || HWMON=n + select BCM_NET_PHYLIB + help + Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. + + This driver also supports the hardware monitoring of this PHY and + exposes voltage and temperature sensors. + config BCM63XX_PHY tristate "Broadcom 63xx SOCs internal PHY" depends on BCM63XX || COMPILE_TEST @@ -332,6 +126,12 @@ config BCM7XXX_PHY Currently supports the BCM7366, BCM7439, BCM7445, and 40nm and 65nm generation of BCM7xxx Set Top Box SoCs. +config BCM84881_PHY + tristate "Broadcom BCM84881 PHY" + depends on PHYLIB + help + Support the Broadcom BCM84881 PHY. + config BCM87XX_PHY tristate "Broadcom BCM8706 and BCM8727 PHYs" help @@ -353,30 +153,6 @@ config BCM_CYGNUS_PHY config BCM_NET_PHYLIB tristate -config BROADCOM_PHY - tristate "Broadcom PHYs" - select BCM_NET_PHYLIB - help - Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464, - BCM5481, BCM54810 and BCM5482 PHYs. - -config BCM54140_PHY - tristate "Broadcom BCM54140 PHY" - depends on PHYLIB - depends on HWMON || HWMON=n - select BCM_NET_PHYLIB - help - Support the Broadcom BCM54140 Quad SGMII/QSGMII PHY. - - This driver also supports the hardware monitoring of this PHY and - exposes voltage and temperature sensors. - -config BCM84881_PHY - tristate "Broadcom BCM84881 PHY" - depends on PHYLIB - help - Support the Broadcom BCM84881 PHY. - config CICADA_PHY tristate "Cicada PHYs" help @@ -392,48 +168,16 @@ config DAVICOM_PHY help Currently supports dm9161e and dm9131 -config DP83822_PHY - tristate "Texas Instruments DP83822/825/826 PHYs" - help - Supports the DP83822, DP83825I, DP83825CM, DP83825CS, DP83825S, - DP83826C and DP83826NC PHYs. - -config DP83TC811_PHY - tristate "Texas Instruments DP83TC811 PHY" - help - Supports the DP83TC811 PHY. - -config DP83848_PHY - tristate "Texas Instruments DP83848 PHY" - help - Supports the DP83848 PHY. - -config DP83867_PHY - tristate "Texas Instruments DP83867 Gigabit PHY" - help - Currently supports the DP83867 PHY. - -config DP83869_PHY - tristate "Texas Instruments DP83869 Gigabit PHY" - help - Currently supports the DP83869 PHY. This PHY supports copper and - fiber connections. - -config FIXED_PHY - tristate "MDIO Bus/PHY emulation with fixed speed/link PHYs" - depends on PHYLIB - select SWPHY - help - Adds the platform "fixed" MDIO Bus to cover the boards that use - PHYs that are not connected to the real MDIO bus. - - Currently tested with mpc866ads and mpc8349e-mitx. - config ICPLUS_PHY tristate "ICPlus PHYs" help Currently supports the IP175C and IP1001 PHYs. +config LXT_PHY + tristate "Intel LXT PHYs" + help + Currently supports the lxt970, lxt971 + config INTEL_XWAY_PHY tristate "Intel XWAY PHYs" help @@ -447,27 +191,16 @@ config LSI_ET1011C_PHY help Supports the LSI ET1011C PHY. -config LXT_PHY - tristate "Intel LXT PHYs" - help - Currently supports the lxt970, lxt971 - config MARVELL_PHY - tristate "Marvell PHYs" + tristate "Marvell Alaska PHYs" help - Currently has a driver for the 88E1011S + Currently has a driver for the 88E1XXX config MARVELL_10G_PHY tristate "Marvell Alaska 10Gbit PHYs" help Support for the Marvell Alaska MV88X3310 and compatible PHYs. -config MESON_GXL_PHY - tristate "Amlogic Meson GXL Internal PHY" - depends on ARCH_MESON || COMPILE_TEST - help - Currently has a driver for the Amlogic Meson GXL Internal PHY - config MICREL_PHY tristate "Micrel PHYs" help @@ -518,12 +251,12 @@ config REALTEK_PHY Supports the Realtek 821x PHY. config RENESAS_PHY - tristate "Driver for Renesas PHYs" + tristate "Renesas PHYs" help Supports the Renesas PHYs uPD60620 and uPD60620A. config ROCKCHIP_PHY - tristate "Driver for Rockchip Ethernet PHYs" + tristate "Rockchip Ethernet PHYs" help Currently supports the integrated Ethernet PHY. @@ -542,6 +275,33 @@ config TERANETICS_PHY help Currently supports the Teranetics TN2020 +config DP83822_PHY + tristate "Texas Instruments DP83822/825/826 PHYs" + help + Supports the DP83822, DP83825I, DP83825CM, DP83825CS, DP83825S, + DP83826C and DP83826NC PHYs. + +config DP83TC811_PHY + tristate "Texas Instruments DP83TC811 PHY" + help + Supports the DP83TC811 PHY. + +config DP83848_PHY + tristate "Texas Instruments DP83848 PHY" + help + Supports the DP83848 PHY. + +config DP83867_PHY + tristate "Texas Instruments DP83867 Gigabit PHY" + help + Currently supports the DP83867 PHY. + +config DP83869_PHY + tristate "Texas Instruments DP83869 Gigabit PHY" + help + Currently supports the DP83869 PHY. This PHY supports copper and + fiber connections. + config VITESSE_PHY tristate "Vitesse PHYs" help diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index d84bab489a53..a13e402074cf 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Makefile for Linux PHY drivers and MDIO bus drivers +# Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ linkmode.o @@ -24,31 +24,6 @@ libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o -obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o -obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o -obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o -obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o -obj-$(CONFIG_MDIO_BUS_MUX) += mdio-mux.o -obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC) += mdio-mux-bcm-iproc.o -obj-$(CONFIG_MDIO_BUS_MUX_GPIO) += mdio-mux-gpio.o -obj-$(CONFIG_MDIO_BUS_MUX_MESON_G12A) += mdio-mux-meson-g12a.o -obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o -obj-$(CONFIG_MDIO_BUS_MUX_MULTIPLEXER) += mdio-mux-multiplexer.o -obj-$(CONFIG_MDIO_CAVIUM) += mdio-cavium.o -obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o -obj-$(CONFIG_MDIO_HISI_FEMAC) += mdio-hisi-femac.o -obj-$(CONFIG_MDIO_I2C) += mdio-i2c.o -obj-$(CONFIG_MDIO_IPQ4019) += mdio-ipq4019.o -obj-$(CONFIG_MDIO_IPQ8064) += mdio-ipq8064.o -obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o -obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o -obj-$(CONFIG_MDIO_MVUSB) += mdio-mvusb.o -obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o -obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o -obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o -obj-$(CONFIG_MDIO_XGENE) += mdio-xgene.o -obj-$(CONFIG_MDIO_XPCS) += mdio-xpcs.o - obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += mii_timestamper.o obj-$(CONFIG_SFP) += sfp.o @@ -62,32 +37,32 @@ ifdef CONFIG_HWMON aquantia-objs += aquantia_hwmon.o endif obj-$(CONFIG_AQUANTIA_PHY) += aquantia.o -obj-$(CONFIG_AX88796B_PHY) += ax88796b.o obj-$(CONFIG_AT803X_PHY) += at803x.o +obj-$(CONFIG_AX88796B_PHY) += ax88796b.o +obj-$(CONFIG_BCM54140_PHY) += bcm54140.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o +obj-$(CONFIG_BCM84881_PHY) += bcm84881.o obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o obj-$(CONFIG_BCM_CYGNUS_PHY) += bcm-cygnus.o obj-$(CONFIG_BCM_NET_PHYLIB) += bcm-phy-lib.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o -obj-$(CONFIG_BCM54140_PHY) += bcm54140.o -obj-$(CONFIG_BCM84881_PHY) += bcm84881.o obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_CORTINA_PHY) += cortina.o obj-$(CONFIG_DAVICOM_PHY) += davicom.o obj-$(CONFIG_DP83640_PHY) += dp83640.o obj-$(CONFIG_DP83822_PHY) += dp83822.o -obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_DP83869_PHY) += dp83869.o +obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o obj-$(CONFIG_FIXED_PHY) += fixed_phy.o obj-$(CONFIG_ICPLUS_PHY) += icplus.o obj-$(CONFIG_INTEL_XWAY_PHY) += intel-xway.o obj-$(CONFIG_LSI_ET1011C_PHY) += et1011c.o obj-$(CONFIG_LXT_PHY) += lxt.o -obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MARVELL_10G_PHY) += marvell10g.o +obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 101651b2de54..ed601a7e46a0 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -343,7 +343,7 @@ static int at803x_rgmii_reg_get_voltage_sel(struct regulator_dev *rdev) return (val & AT803X_DEBUG_RGMII_1V8) ? 1 : 0; } -static struct regulator_ops vddio_regulator_ops = { +static const struct regulator_ops vddio_regulator_ops = { .list_voltage = regulator_list_voltage_table, .set_voltage_sel = at803x_rgmii_reg_set_voltage_sel, .get_voltage_sel = at803x_rgmii_reg_get_voltage_sel, @@ -364,7 +364,7 @@ static const struct regulator_desc vddio_desc = { .owner = THIS_MODULE, }; -static struct regulator_ops vddh_regulator_ops = { +static const struct regulator_ops vddh_regulator_ops = { }; static const struct regulator_desc vddh_desc = { diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 50fb7d16b75a..fc3d747eba55 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -798,51 +798,32 @@ static int decode_evnt(struct dp83640_private *dp83640, return parsed; } -#define DP83640_PACKET_HASH_OFFSET 20 #define DP83640_PACKET_HASH_LEN 10 static int match(struct sk_buff *skb, unsigned int type, struct rxts *rxts) { - unsigned int offset = 0; - u8 *msgtype, *data = skb_mac_header(skb); - __be16 *seqid; + struct ptp_header *hdr; + u8 msgtype; + u16 seqid; u16 hash; /* check sequenceID, messageType, 12 bit hash of offset 20-29 */ - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: + hdr = ptp_parse_header(skb, type); + if (!hdr) return 0; - } - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) - return 0; + msgtype = ptp_get_msgtype(hdr, type); - if (unlikely(type & PTP_CLASS_V1)) - msgtype = data + offset + OFF_PTP_CONTROL; - else - msgtype = data + offset; - if (rxts->msgtype != (*msgtype & 0xf)) + if (rxts->msgtype != (msgtype & 0xf)) return 0; - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); - if (rxts->seqid != ntohs(*seqid)) + seqid = be16_to_cpu(hdr->sequence_id); + if (rxts->seqid != seqid) return 0; hash = ether_crc(DP83640_PACKET_HASH_LEN, - data + offset + DP83640_PACKET_HASH_OFFSET) >> 20; + (unsigned char *)&hdr->source_port_identity) >> 20; if (rxts->hash != hash) return 0; @@ -982,35 +963,16 @@ static void decode_status_frame(struct dp83640_private *dp83640, static int is_sync(struct sk_buff *skb, int type) { - u8 *data = skb->data, *msgtype; - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (type & PTP_CLASS_V1) - offset += OFF_PTP_CONTROL; + struct ptp_header *hdr; + u8 msgtype; - if (skb->len < offset + 1) + hdr = ptp_parse_header(skb, type); + if (!hdr) return 0; - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, type); - return (*msgtype & 0xf) == 0; + return (msgtype & 0xf) == 0; } static void dp83640_free_clocks(void) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 37643c468e19..732c8bec7452 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -23,16 +23,31 @@ #define DP83822_DEVADDR 0x1f +#define MII_DP83822_CTRL_2 0x0a +#define MII_DP83822_PHYSTS 0x10 #define MII_DP83822_PHYSCR 0x11 #define MII_DP83822_MISR1 0x12 #define MII_DP83822_MISR2 0x13 +#define MII_DP83822_FCSCR 0x14 #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f #define MII_DP83822_GENCFG 0x465 +#define MII_DP83822_SOR1 0x467 + +/* GENCFG */ +#define DP83822_SIG_DET_LOW BIT(0) + +/* Control Register 2 bits */ +#define DP83822_FX_ENABLE BIT(14) #define DP83822_HW_RESET BIT(15) #define DP83822_SW_RESET BIT(14) +/* PHY STS bits */ +#define DP83822_PHYSTS_DUPLEX BIT(2) +#define DP83822_PHYSTS_10 BIT(1) +#define DP83822_PHYSTS_LINK BIT(0) + /* PHYSCR Register Fields */ #define DP83822_PHYSCR_INT_OE BIT(0) /* Interrupt Output Enable */ #define DP83822_PHYSCR_INTEN BIT(1) /* Interrupt Enable */ @@ -83,6 +98,28 @@ #define DP83822_RX_CLK_SHIFT BIT(12) #define DP83822_TX_CLK_SHIFT BIT(11) +/* SOR1 mode */ +#define DP83822_STRAP_MODE1 0 +#define DP83822_STRAP_MODE2 BIT(0) +#define DP83822_STRAP_MODE3 BIT(1) +#define DP83822_STRAP_MODE4 GENMASK(1, 0) + +#define DP83822_COL_STRAP_MASK GENMASK(11, 10) +#define DP83822_COL_SHIFT 10 +#define DP83822_RX_ER_STR_MASK GENMASK(9, 8) +#define DP83822_RX_ER_SHIFT 8 + +#define MII_DP83822_FIBER_ADVERTISE (ADVERTISED_TP | ADVERTISED_MII | \ + ADVERTISED_FIBRE | ADVERTISED_BNC | \ + ADVERTISED_Pause | ADVERTISED_Asym_Pause | \ + ADVERTISED_100baseT_Full) + +struct dp83822_private { + bool fx_signal_det_low; + int fx_enabled; + u16 fx_sd_enable; +}; + static int dp83822_ack_interrupt(struct phy_device *phydev) { int err; @@ -197,6 +234,7 @@ static void dp83822_get_wol(struct phy_device *phydev, static int dp83822_config_intr(struct phy_device *phydev) { + struct dp83822_private *dp83822 = phydev->priv; int misr_status; int physcr_status; int err; @@ -208,13 +246,16 @@ static int dp83822_config_intr(struct phy_device *phydev) misr_status |= (DP83822_RX_ERR_HF_INT_EN | DP83822_FALSE_CARRIER_HF_INT_EN | - DP83822_ANEG_COMPLETE_INT_EN | - DP83822_DUP_MODE_CHANGE_INT_EN | - DP83822_SPEED_CHANGED_INT_EN | DP83822_LINK_STAT_INT_EN | DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); + if (!dp83822->fx_enabled) + misr_status |= DP83822_ANEG_COMPLETE_INT_EN | + DP83822_DUP_MODE_CHANGE_INT_EN | + DP83822_SPEED_CHANGED_INT_EN; + + err = phy_write(phydev, MII_DP83822_MISR1, misr_status); if (err < 0) return err; @@ -224,14 +265,16 @@ static int dp83822_config_intr(struct phy_device *phydev) return misr_status; misr_status |= (DP83822_JABBER_DET_INT_EN | - DP83822_WOL_PKT_INT_EN | DP83822_SLEEP_MODE_INT_EN | - DP83822_MDI_XOVER_INT_EN | DP83822_LB_FIFO_INT_EN | DP83822_PAGE_RX_INT_EN | - DP83822_ANEG_ERR_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); + if (!dp83822->fx_enabled) + misr_status |= DP83822_MDI_XOVER_INT_EN | + DP83822_ANEG_ERR_INT_EN | + DP83822_WOL_PKT_INT_EN; + err = phy_write(phydev, MII_DP83822_MISR2, misr_status); if (err < 0) return err; @@ -270,13 +313,60 @@ static int dp8382x_disable_wol(struct phy_device *phydev) MII_DP83822_WOL_CFG, value); } +static int dp83822_read_status(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int status = phy_read(phydev, MII_DP83822_PHYSTS); + int ctrl2; + int ret; + + if (dp83822->fx_enabled) { + if (status & DP83822_PHYSTS_LINK) { + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + } else { + ctrl2 = phy_read(phydev, MII_DP83822_CTRL_2); + if (ctrl2 < 0) + return ctrl2; + + if (!(ctrl2 & DP83822_FX_ENABLE)) { + ret = phy_write(phydev, MII_DP83822_CTRL_2, + DP83822_FX_ENABLE | ctrl2); + if (ret < 0) + return ret; + } + } + } + + ret = genphy_read_status(phydev); + if (ret) + return ret; + + if (status < 0) + return status; + + if (status & DP83822_PHYSTS_DUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + + if (status & DP83822_PHYSTS_10) + phydev->speed = SPEED_10; + else + phydev->speed = SPEED_100; + + return 0; +} + static int dp83822_config_init(struct phy_device *phydev) { + struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; int rgmii_delay; s32 rx_int_delay; s32 tx_int_delay; int err = 0; + int bmcr; if (phy_interface_is_rgmii(phydev)) { rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, @@ -302,6 +392,53 @@ static int dp83822_config_init(struct phy_device *phydev) } } + if (dp83822->fx_enabled) { + err = phy_modify(phydev, MII_DP83822_CTRL_2, + DP83822_FX_ENABLE, 1); + if (err < 0) + return err; + + /* Only allow advertising what this PHY supports */ + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + phydev->advertising); + + /* Auto neg is not supported in fiber mode */ + bmcr = phy_read(phydev, MII_BMCR); + if (bmcr < 0) + return bmcr; + + if (bmcr & BMCR_ANENABLE) { + err = phy_modify(phydev, MII_BMCR, BMCR_ANENABLE, 0); + if (err < 0) + return err; + } + phydev->autoneg = AUTONEG_DISABLE; + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported); + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->advertising); + + /* Setup fiber advertisement */ + err = phy_modify_changed(phydev, MII_ADVERTISE, + MII_DP83822_FIBER_ADVERTISE, + MII_DP83822_FIBER_ADVERTISE); + + if (err < 0) + return err; + + if (dp83822->fx_signal_det_low) { + err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_GENCFG, + DP83822_SIG_DET_LOW); + if (err) + return err; + } + } return dp8382x_disable_wol(phydev); } @@ -314,13 +451,85 @@ static int dp83822_phy_reset(struct phy_device *phydev) { int err; - err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_HW_RESET); + err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_SW_RESET); if (err < 0) return err; return phydev->drv->config_init(phydev); } +#ifdef CONFIG_OF_MDIO +static int dp83822_of_init(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + struct device *dev = &phydev->mdio.dev; + + /* Signal detection for the PHY is only enabled if the FX_EN and the + * SD_EN pins are strapped. Signal detection can only enabled if FX_EN + * is strapped otherwise signal detection is disabled for the PHY. + */ + if (dp83822->fx_enabled && dp83822->fx_sd_enable) + dp83822->fx_signal_det_low = device_property_present(dev, + "ti,link-loss-low"); + if (!dp83822->fx_enabled) + dp83822->fx_enabled = device_property_present(dev, + "ti,fiber-mode"); + + return 0; +} +#else +static int dp83822_of_init(struct phy_device *phydev) +{ + return 0; +} +#endif /* CONFIG_OF_MDIO */ + +static int dp83822_read_straps(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int fx_enabled, fx_sd_enable; + int val; + + val = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_SOR1); + if (val < 0) + return val; + + fx_enabled = (val & DP83822_COL_STRAP_MASK) >> DP83822_COL_SHIFT; + if (fx_enabled == DP83822_STRAP_MODE2 || + fx_enabled == DP83822_STRAP_MODE3) + dp83822->fx_enabled = 1; + + if (dp83822->fx_enabled) { + fx_sd_enable = (val & DP83822_RX_ER_STR_MASK) >> DP83822_RX_ER_SHIFT; + if (fx_sd_enable == DP83822_STRAP_MODE3 || + fx_sd_enable == DP83822_STRAP_MODE4) + dp83822->fx_sd_enable = 1; + } + + return 0; +} + +static int dp83822_probe(struct phy_device *phydev) +{ + struct dp83822_private *dp83822; + int ret; + + dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822), + GFP_KERNEL); + if (!dp83822) + return -ENOMEM; + + phydev->priv = dp83822; + + ret = dp83822_read_straps(phydev); + if (ret) + return ret; + + dp83822_of_init(phydev); + + return 0; +} + static int dp83822_suspend(struct phy_device *phydev) { int value; @@ -352,8 +561,10 @@ static int dp83822_resume(struct phy_device *phydev) PHY_ID_MATCH_MODEL(_id), \ .name = (_name), \ /* PHY_BASIC_FEATURES */ \ + .probe = dp83822_probe, \ .soft_reset = dp83822_phy_reset, \ .config_init = dp83822_config_init, \ + .read_status = dp83822_read_status, \ .get_wol = dp83822_get_wol, \ .set_wol = dp83822_set_wol, \ .ack_interrupt = dp83822_ack_interrupt, \ diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 1d4c012194e9..6cf9b798b710 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -958,7 +958,7 @@ static int vsc8584_macsec_del_txsa(struct macsec_context *ctx) return 0; } -static struct macsec_ops vsc8584_macsec_ops = { +static const struct macsec_ops vsc8584_macsec_ops = { .mdo_dev_open = vsc8584_macsec_dev_open, .mdo_dev_stop = vsc8584_macsec_dev_stop, .mdo_add_secy = vsc8584_macsec_add_secy, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index a4fbf3a4fa97..6bc7406a1ce7 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -1738,13 +1738,13 @@ static int __phy_write_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb, return 0; } -/* Trigger a read to the spcified MCB */ +/* Trigger a read to the specified MCB */ static int phy_update_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_READ); } -/* Trigger a write to the spcified MCB */ +/* Trigger a write to the specified MCB */ static int phy_commit_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_WRITE); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 32b4bd6a5b55..d0738302a958 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -535,8 +535,10 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, if (pl->pcs_ops) pl->pcs_ops->pcs_get_state(pl->pcs, state); - else + else if (pl->mac_ops->mac_pcs_get_state) pl->mac_ops->mac_pcs_get_state(pl->config, state); + else + state->link = 0; } /* The fixed state is... fixed except for the link state, @@ -2319,6 +2321,49 @@ static void phylink_decode_sgmii_word(struct phylink_link_state *state, } /** + * phylink_decode_usxgmii_word() - decode the USXGMII word from a MAC PCS + * @state: a pointer to a struct phylink_link_state. + * @lpa: a 16 bit value which stores the USXGMII auto-negotiation word + * + * Helper for MAC PCS supporting the USXGMII protocol and the auto-negotiation + * code word. Decode the USXGMII code word and populate the corresponding fields + * (speed, duplex) into the phylink_link_state structure. + */ +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa) +{ + switch (lpa & MDIO_USXGMII_SPD_MASK) { + case MDIO_USXGMII_10: + state->speed = SPEED_10; + break; + case MDIO_USXGMII_100: + state->speed = SPEED_100; + break; + case MDIO_USXGMII_1000: + state->speed = SPEED_1000; + break; + case MDIO_USXGMII_2500: + state->speed = SPEED_2500; + break; + case MDIO_USXGMII_5000: + state->speed = SPEED_5000; + break; + case MDIO_USXGMII_10G: + state->speed = SPEED_10000; + break; + default: + state->link = false; + return; + } + + if (lpa & MDIO_USXGMII_FULL_DUPLEX) + state->duplex = DUPLEX_FULL; + else + state->duplex = DUPLEX_HALF; +} +EXPORT_SYMBOL_GPL(phylink_decode_usxgmii_word); + +/** * phylink_mii_c22_pcs_get_state() - read the MAC PCS state * @pcs: a pointer to a &struct mdio_device. * @state: a pointer to a &struct phylink_link_state. @@ -2361,6 +2406,7 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, break; case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: phylink_decode_sgmii_word(state, lpa); break; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index c24b0e83dd32..5250dcdf46a4 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -7,6 +7,7 @@ #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/jiffies.h> +#include <linux/mdio/mdio-i2c.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> @@ -16,7 +17,6 @@ #include <linux/slab.h> #include <linux/workqueue.h> -#include "mdio-i2c.h" #include "sfp.h" #include "swphy.h" diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 74568ae16125..638e8c3d1f4a 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -21,6 +21,17 @@ #include <linux/netdevice.h> #include <linux/smscphy.h> +/* Vendor-specific PHY Definitions */ +/* EDPD NLP / crossover time configuration */ +#define PHY_EDPD_CONFIG 16 +#define PHY_EDPD_CONFIG_EXT_CROSSOVER_ 0x0001 + +/* Control/Status Indication Register */ +#define SPECIAL_CTRL_STS 27 +#define SPECIAL_CTRL_STS_OVRRD_AMDIX_ 0x8000 +#define SPECIAL_CTRL_STS_AMDIX_ENABLE_ 0x4000 +#define SPECIAL_CTRL_STS_AMDIX_STATE_ 0x2000 + struct smsc_hw_stat { const char *string; u8 reg; @@ -96,6 +107,54 @@ static int lan911x_config_init(struct phy_device *phydev) return smsc_phy_ack_interrupt(phydev); } +static int lan87xx_config_aneg(struct phy_device *phydev) +{ + int rc; + int val; + + switch (phydev->mdix_ctrl) { + case ETH_TP_MDI: + val = SPECIAL_CTRL_STS_OVRRD_AMDIX_; + break; + case ETH_TP_MDI_X: + val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_STATE_; + break; + case ETH_TP_MDI_AUTO: + val = SPECIAL_CTRL_STS_AMDIX_ENABLE_; + break; + default: + return genphy_config_aneg(phydev); + } + + rc = phy_read(phydev, SPECIAL_CTRL_STS); + if (rc < 0) + return rc; + + rc &= ~(SPECIAL_CTRL_STS_OVRRD_AMDIX_ | + SPECIAL_CTRL_STS_AMDIX_ENABLE_ | + SPECIAL_CTRL_STS_AMDIX_STATE_); + rc |= val; + phy_write(phydev, SPECIAL_CTRL_STS, rc); + + phydev->mdix = phydev->mdix_ctrl; + return genphy_config_aneg(phydev); +} + +static int lan87xx_config_aneg_ext(struct phy_device *phydev) +{ + int rc; + + /* Extend Manual AutoMDIX timer */ + rc = phy_read(phydev, PHY_EDPD_CONFIG); + if (rc < 0) + return rc; + + rc |= PHY_EDPD_CONFIG_EXT_CROSSOVER_; + phy_write(phydev, PHY_EDPD_CONFIG, rc); + return lan87xx_config_aneg(phydev); +} + /* * The LAN87xx suffers from rare absence of the ENERGYON-bit when Ethernet cable * plugs in while LAN87xx is in Energy Detect Power-Down mode. This leads to @@ -250,6 +309,9 @@ static struct phy_driver smsc_phy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { + /* This covers internal PHY (phy_id: 0x0007C0C3) for + * LAN9500 (PID: 0x9500), LAN9514 (PID: 0xec00), LAN9505 (PID: 0x9505) + */ .phy_id = 0x0007c0c0, /* OUI=0x00800f, Model#=0x0c */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8700", @@ -262,6 +324,7 @@ static struct phy_driver smsc_phy_driver[] = { .read_status = lan87xx_read_status, .config_init = smsc_phy_config_init, .soft_reset = smsc_phy_reset, + .config_aneg = lan87xx_config_aneg, /* IRQ related */ .ack_interrupt = smsc_phy_ack_interrupt, @@ -293,6 +356,9 @@ static struct phy_driver smsc_phy_driver[] = { .suspend = genphy_suspend, .resume = genphy_resume, }, { + /* This covers internal PHY (phy_id: 0x0007C0F0) for + * LAN9500A (PID: 0x9E00), LAN9505A (PID: 0x9E01) + */ .phy_id = 0x0007c0f0, /* OUI=0x00800f, Model#=0x0f */ .phy_id_mask = 0xfffffff0, .name = "SMSC LAN8710/LAN8720", @@ -306,6 +372,7 @@ static struct phy_driver smsc_phy_driver[] = { .read_status = lan87xx_read_status, .config_init = smsc_phy_config_init, .soft_reset = smsc_phy_reset, + .config_aneg = lan87xx_config_aneg_ext, /* IRQ related */ .ack_interrupt = smsc_phy_ack_interrupt, diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index a7fbc3ccd29e..0863f01937b3 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -345,6 +345,8 @@ config USB_NET_SMSC75XX config USB_NET_SMSC95XX tristate "SMSC LAN95XX based USB 2.0 10/100 ethernet devices" depends on USB_USBNET + select PHYLIB + select SMSC_PHY select BITREVERSE select CRC16 select CRC32 diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index bb4ccbda031a..601fb40a2a0a 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -18,10 +18,12 @@ #include <linux/usb/usbnet.h> #include <linux/slab.h> #include <linux/of_net.h> +#include <linux/mdio.h> +#include <linux/phy.h> #include "smsc95xx.h" #define SMSC_CHIPNAME "smsc95xx" -#define SMSC_DRIVER_VERSION "1.0.6" +#define SMSC_DRIVER_VERSION "2.0.0" #define HS_USB_PKT_SIZE (512) #define FS_USB_PKT_SIZE (64) #define DEFAULT_HS_BURST_CAP_SIZE (16 * 1024 + 5 * HS_USB_PKT_SIZE) @@ -49,10 +51,7 @@ #define SUSPEND_ALLMODES (SUSPEND_SUSPEND0 | SUSPEND_SUSPEND1 | \ SUSPEND_SUSPEND2 | SUSPEND_SUSPEND3) -#define CARRIER_CHECK_DELAY (2 * HZ) - struct smsc95xx_priv { - u32 chip_id; u32 mac_cr; u32 hash_hi; u32 hash_lo; @@ -60,10 +59,8 @@ struct smsc95xx_priv { spinlock_t mac_cr_lock; u8 features; u8 suspend_flags; - u8 mdix_ctrl; - bool link_ok; - struct delayed_work carrier_check; - struct usbnet *dev; + struct mii_bus *mdiobus; + struct phy_device *phydev; }; static bool turbo_mode = true; @@ -173,10 +170,14 @@ static int __must_check __smsc95xx_phy_wait_not_busy(struct usbnet *dev, return -EIO; } -static int __smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx, +static u32 mii_address_cmd(int phy_id, int idx, u16 op) +{ + return (phy_id & 0x1f) << 11 | (idx & 0x1f) << 6 | op; +} + +static int __smsc95xx_mdio_read(struct usbnet *dev, int phy_id, int idx, int in_pm) { - struct usbnet *dev = netdev_priv(netdev); u32 val, addr; int ret; @@ -185,14 +186,12 @@ static int __smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx, /* confirm MII not busy */ ret = __smsc95xx_phy_wait_not_busy(dev, in_pm); if (ret < 0) { - netdev_warn(dev->net, "MII is busy in smsc95xx_mdio_read\n"); + netdev_warn(dev->net, "%s: MII is busy\n", __func__); goto done; } /* set the address, index & direction (read from PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = (phy_id << 11) | (idx << 6) | MII_READ_ | MII_BUSY_; + addr = mii_address_cmd(phy_id, idx, MII_READ_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { netdev_warn(dev->net, "Error writing MII_ADDR\n"); @@ -218,10 +217,9 @@ done: return ret; } -static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, +static void __smsc95xx_mdio_write(struct usbnet *dev, int phy_id, int idx, int regval, int in_pm) { - struct usbnet *dev = netdev_priv(netdev); u32 val, addr; int ret; @@ -230,7 +228,7 @@ static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, /* confirm MII not busy */ ret = __smsc95xx_phy_wait_not_busy(dev, in_pm); if (ret < 0) { - netdev_warn(dev->net, "MII is busy in smsc95xx_mdio_write\n"); + netdev_warn(dev->net, "%s: MII is busy\n", __func__); goto done; } @@ -242,9 +240,7 @@ static void __smsc95xx_mdio_write(struct net_device *netdev, int phy_id, } /* set the address, index & direction (write to PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = (phy_id << 11) | (idx << 6) | MII_WRITE_ | MII_BUSY_; + addr = mii_address_cmd(phy_id, idx, MII_WRITE_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { netdev_warn(dev->net, "Error writing MII_ADDR\n"); @@ -261,27 +257,34 @@ done: mutex_unlock(&dev->phy_mutex); } -static int smsc95xx_mdio_read_nopm(struct net_device *netdev, int phy_id, - int idx) +static int smsc95xx_mdio_read_nopm(struct usbnet *dev, int idx) { - return __smsc95xx_mdio_read(netdev, phy_id, idx, 1); + struct smsc95xx_priv *pdata = dev->driver_priv; + + return __smsc95xx_mdio_read(dev, pdata->phydev->mdio.addr, idx, 1); } -static void smsc95xx_mdio_write_nopm(struct net_device *netdev, int phy_id, - int idx, int regval) +static void smsc95xx_mdio_write_nopm(struct usbnet *dev, int idx, int regval) { - __smsc95xx_mdio_write(netdev, phy_id, idx, regval, 1); + struct smsc95xx_priv *pdata = dev->driver_priv; + + __smsc95xx_mdio_write(dev, pdata->phydev->mdio.addr, idx, regval, 1); } -static int smsc95xx_mdio_read(struct net_device *netdev, int phy_id, int idx) +static int smsc95xx_mdiobus_read(struct mii_bus *bus, int phy_id, int idx) { - return __smsc95xx_mdio_read(netdev, phy_id, idx, 0); + struct usbnet *dev = bus->priv; + + return __smsc95xx_mdio_read(dev, phy_id, idx, 0); } -static void smsc95xx_mdio_write(struct net_device *netdev, int phy_id, int idx, - int regval) +static int smsc95xx_mdiobus_write(struct mii_bus *bus, int phy_id, int idx, + u16 regval) { - __smsc95xx_mdio_write(netdev, phy_id, idx, regval, 0); + struct usbnet *dev = bus->priv; + + __smsc95xx_mdio_write(dev, phy_id, idx, regval, 0); + return 0; } static int __must_check smsc95xx_wait_eeprom(struct usbnet *dev) @@ -455,7 +458,7 @@ static unsigned int smsc95xx_hash(char addr[ETH_ALEN]) static void smsc95xx_set_multicast(struct net_device *netdev) { struct usbnet *dev = netdev_priv(netdev); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; int ret; @@ -511,22 +514,23 @@ static void smsc95xx_set_multicast(struct net_device *netdev) netdev_warn(dev->net, "failed to initiate async write to MAC_CR\n"); } -static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, - u16 lcladv, u16 rmtadv) +static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev) { u32 flow = 0, afc_cfg; + struct smsc95xx_priv *pdata = dev->driver_priv; + bool tx_pause, rx_pause; int ret = smsc95xx_read_reg(dev, AFC_CFG, &afc_cfg); if (ret < 0) return ret; - if (duplex == DUPLEX_FULL) { - u8 cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv); + if (pdata->phydev->duplex == DUPLEX_FULL) { + phy_get_pause(pdata->phydev, &tx_pause, &rx_pause); - if (cap & FLOW_CTRL_RX) + if (rx_pause) flow = 0xFFFF0002; - if (cap & FLOW_CTRL_TX) { + if (tx_pause) { afc_cfg |= 0xF; flow |= 0xFFFF0000; } else { @@ -534,8 +538,8 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, } netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s\n", - cap & FLOW_CTRL_RX ? "enabled" : "disabled", - cap & FLOW_CTRL_TX ? "enabled" : "disabled"); + rx_pause ? "enabled" : "disabled", + tx_pause ? "enabled" : "disabled"); } else { netif_dbg(dev, link, dev->net, "half duplex\n"); afc_cfg |= 0xF; @@ -550,33 +554,16 @@ static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev, u8 duplex, static int smsc95xx_link_reset(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - struct mii_if_info *mii = &dev->mii; - struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; - u16 lcladv, rmtadv; int ret; - /* clear interrupt status */ - ret = smsc95xx_mdio_read(dev->net, mii->phy_id, PHY_INT_SRC); - if (ret < 0) - return ret; - ret = smsc95xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_); if (ret < 0) return ret; - mii_check_media(mii, 1, 1); - mii_ethtool_gset(&dev->mii, &ecmd); - lcladv = smsc95xx_mdio_read(dev->net, mii->phy_id, MII_ADVERTISE); - rmtadv = smsc95xx_mdio_read(dev->net, mii->phy_id, MII_LPA); - - netif_dbg(dev, link, dev->net, - "speed: %u duplex: %d lcladv: %04x rmtadv: %04x\n", - ethtool_cmd_speed(&ecmd), ecmd.duplex, lcladv, rmtadv); - spin_lock_irqsave(&pdata->mac_cr_lock, flags); - if (ecmd.duplex != DUPLEX_FULL) { + if (pdata->phydev->duplex != DUPLEX_FULL) { pdata->mac_cr &= ~MAC_CR_FDPX_; pdata->mac_cr |= MAC_CR_RCVOWN_; } else { @@ -589,7 +576,7 @@ static int smsc95xx_link_reset(struct usbnet *dev) if (ret < 0) return ret; - ret = smsc95xx_phy_update_flowcontrol(dev, ecmd.duplex, lcladv, rmtadv); + ret = smsc95xx_phy_update_flowcontrol(dev); if (ret < 0) netdev_warn(dev->net, "Error updating PHY flow control\n"); @@ -616,44 +603,6 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb) intdata); } -static void set_carrier(struct usbnet *dev, bool link) -{ - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - - if (pdata->link_ok == link) - return; - - pdata->link_ok = link; - - if (link) - usbnet_link_change(dev, 1, 0); - else - usbnet_link_change(dev, 0, 0); -} - -static void check_carrier(struct work_struct *work) -{ - struct smsc95xx_priv *pdata = container_of(work, struct smsc95xx_priv, - carrier_check.work); - struct usbnet *dev = pdata->dev; - int ret; - - if (pdata->suspend_flags != 0) - return; - - ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMSR); - if (ret < 0) { - netdev_warn(dev->net, "Failed to read MII_BMSR\n"); - return; - } - if (ret & BMSR_LSTATUS) - set_carrier(dev, 1); - else - set_carrier(dev, 0); - - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); -} - /* Enable or disable Tx & Rx checksum offload engines */ static int smsc95xx_set_features(struct net_device *netdev, netdev_features_t features) @@ -747,7 +696,7 @@ static void smsc95xx_ethtool_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; wolinfo->supported = SUPPORTED_WAKE; wolinfo->wolopts = pdata->wolopts; @@ -757,7 +706,7 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; int ret; if (wolinfo->wolopts & ~SUPPORTED_WAKE) @@ -772,108 +721,15 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, return ret; } -static int get_mdix_status(struct net_device *net) -{ - struct usbnet *dev = netdev_priv(net); - u32 val; - int buf; - - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, SPECIAL_CTRL_STS); - if (buf & SPECIAL_CTRL_STS_OVRRD_AMDIX_) { - if (buf & SPECIAL_CTRL_STS_AMDIX_ENABLE_) - return ETH_TP_MDI_AUTO; - else if (buf & SPECIAL_CTRL_STS_AMDIX_STATE_) - return ETH_TP_MDI_X; - } else { - buf = smsc95xx_read_reg(dev, STRAP_STATUS, &val); - if (val & STRAP_STATUS_AMDIX_EN_) - return ETH_TP_MDI_AUTO; - } - - return ETH_TP_MDI; -} - -static void set_mdix_status(struct net_device *net, __u8 mdix_ctrl) -{ - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int buf; - - if ((pdata->chip_id == ID_REV_CHIP_ID_9500A_) || - (pdata->chip_id == ID_REV_CHIP_ID_9530_) || - (pdata->chip_id == ID_REV_CHIP_ID_89530_) || - (pdata->chip_id == ID_REV_CHIP_ID_9730_)) { - /* Extend Manual AutoMDIX timer for 9500A/9500Ai */ - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - PHY_EDPD_CONFIG); - buf |= PHY_EDPD_CONFIG_EXT_CROSSOVER_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - PHY_EDPD_CONFIG, buf); - } - - if (mdix_ctrl == ETH_TP_MDI) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf |= SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } else if (mdix_ctrl == ETH_TP_MDI_X) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf |= SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - buf |= SPECIAL_CTRL_STS_AMDIX_STATE_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } else if (mdix_ctrl == ETH_TP_MDI_AUTO) { - buf = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS); - buf &= ~SPECIAL_CTRL_STS_OVRRD_AMDIX_; - buf &= ~(SPECIAL_CTRL_STS_AMDIX_ENABLE_ | - SPECIAL_CTRL_STS_AMDIX_STATE_); - buf |= SPECIAL_CTRL_STS_AMDIX_ENABLE_; - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, - SPECIAL_CTRL_STS, buf); - } - pdata->mdix_ctrl = mdix_ctrl; -} - -static int smsc95xx_get_link_ksettings(struct net_device *net, - struct ethtool_link_ksettings *cmd) +static u32 smsc95xx_get_link(struct net_device *net) { - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int retval; - - retval = usbnet_get_link_ksettings(net, cmd); - - cmd->base.eth_tp_mdix = pdata->mdix_ctrl; - cmd->base.eth_tp_mdix_ctrl = pdata->mdix_ctrl; - - return retval; -} - -static int smsc95xx_set_link_ksettings(struct net_device *net, - const struct ethtool_link_ksettings *cmd) -{ - struct usbnet *dev = netdev_priv(net); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - int retval; - - if (pdata->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl) - set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl); - - retval = usbnet_set_link_ksettings(net, cmd); - - return retval; + phy_read_status(net->phydev); + return net->phydev->link; } static const struct ethtool_ops smsc95xx_ethtool_ops = { - .get_link = usbnet_get_link, - .nway_reset = usbnet_nway_reset, + .get_link = smsc95xx_get_link, + .nway_reset = phy_ethtool_nway_reset, .get_drvinfo = usbnet_get_drvinfo, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, @@ -884,19 +740,17 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_regs = smsc95xx_ethtool_getregs, .get_wol = smsc95xx_ethtool_get_wol, .set_wol = smsc95xx_ethtool_set_wol, - .get_link_ksettings = smsc95xx_get_link_ksettings, - .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { - struct usbnet *dev = netdev_priv(netdev); - if (!netif_running(netdev)) return -EINVAL; - return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); + return phy_mii_ioctl(netdev->phydev, rq, cmd); } static void smsc95xx_init_mac_address(struct usbnet *dev) @@ -942,7 +796,7 @@ static int smsc95xx_set_mac_address(struct usbnet *dev) /* starts the TX path */ static int smsc95xx_start_tx_path(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; int ret; @@ -962,7 +816,7 @@ static int smsc95xx_start_tx_path(struct usbnet *dev) /* Starts the Receive path */ static int smsc95xx_start_rx_path(struct usbnet *dev, int in_pm) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; unsigned long flags; spin_lock_irqsave(&pdata->mac_cr_lock, flags); @@ -972,54 +826,9 @@ static int smsc95xx_start_rx_path(struct usbnet *dev, int in_pm) return __smsc95xx_write_reg(dev, MAC_CR, pdata->mac_cr, in_pm); } -static int smsc95xx_phy_initialize(struct usbnet *dev) -{ - int bmcr, ret, timeout = 0; - - /* Initialize MII structure */ - dev->mii.dev = dev->net; - dev->mii.mdio_read = smsc95xx_mdio_read; - dev->mii.mdio_write = smsc95xx_mdio_write; - dev->mii.phy_id_mask = 0x1f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = SMSC95XX_INTERNAL_PHY_ID; - - /* reset phy and wait for reset to complete */ - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, BMCR_RESET); - - do { - msleep(10); - bmcr = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, MII_BMCR); - timeout++; - } while ((bmcr & BMCR_RESET) && (timeout < 100)); - - if (timeout >= 100) { - netdev_warn(dev->net, "timeout on PHY Reset"); - return -EIO; - } - - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, - ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | - ADVERTISE_PAUSE_ASYM); - - /* read to clear */ - ret = smsc95xx_mdio_read(dev->net, dev->mii.phy_id, PHY_INT_SRC); - if (ret < 0) { - netdev_warn(dev->net, "Failed to read PHY_INT_SRC during init\n"); - return ret; - } - - smsc95xx_mdio_write(dev->net, dev->mii.phy_id, PHY_INT_MASK, - PHY_INT_MASK_DEFAULT_); - mii_nway_restart(&dev->mii); - - netif_dbg(dev, ifup, dev->net, "phy initialised successfully\n"); - return 0; -} - static int smsc95xx_reset(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 read_buf, write_buf, burst_cap; int ret = 0, timeout; @@ -1198,12 +1007,6 @@ static int smsc95xx_reset(struct usbnet *dev) smsc95xx_set_multicast(dev->net); - ret = smsc95xx_phy_initialize(dev); - if (ret < 0) { - netdev_warn(dev->net, "Failed to init PHY\n"); - return ret; - } - ret = smsc95xx_read_reg(dev, INT_EP_CTL, &read_buf); if (ret < 0) return ret; @@ -1247,7 +1050,8 @@ static const struct net_device_ops smsc95xx_netdev_ops = { static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) { - struct smsc95xx_priv *pdata = NULL; + struct smsc95xx_priv *pdata; + bool is_internal_phy; u32 val; int ret; @@ -1259,13 +1063,12 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) return ret; } - dev->data[0] = (unsigned long)kzalloc(sizeof(struct smsc95xx_priv), - GFP_KERNEL); - - pdata = (struct smsc95xx_priv *)(dev->data[0]); + pdata = kzalloc(sizeof(*pdata), GFP_KERNEL); if (!pdata) return -ENOMEM; + dev->driver_priv = pdata; + spin_lock_init(&pdata->mac_cr_lock); /* LAN95xx devices do not alter the computed checksum of 0 to 0xffff. @@ -1290,15 +1093,50 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) if (ret) goto free_pdata; + pdata->mdiobus = mdiobus_alloc(); + if (!pdata->mdiobus) { + ret = -ENOMEM; + goto free_pdata; + } + + ret = smsc95xx_read_reg(dev, HW_CFG, &val); + if (ret < 0) + goto free_mdio; + + is_internal_phy = !(val & HW_CFG_PSEL_); + if (is_internal_phy) + pdata->mdiobus->phy_mask = ~(1u << SMSC95XX_INTERNAL_PHY_ID); + + pdata->mdiobus->priv = dev; + pdata->mdiobus->read = smsc95xx_mdiobus_read; + pdata->mdiobus->write = smsc95xx_mdiobus_write; + pdata->mdiobus->name = "smsc95xx-mdiobus"; + pdata->mdiobus->parent = &dev->udev->dev; + + snprintf(pdata->mdiobus->id, ARRAY_SIZE(pdata->mdiobus->id), + "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); + + ret = mdiobus_register(pdata->mdiobus); + if (ret) { + netdev_err(dev->net, "Could not register MDIO bus\n"); + goto free_mdio; + } + + pdata->phydev = phy_find_first(pdata->mdiobus); + if (!pdata->phydev) { + netdev_err(dev->net, "no PHY found\n"); + ret = -ENODEV; + goto unregister_mdio; + } + + pdata->phydev->is_internal = is_internal_phy; + /* detect device revision as different features may be available */ ret = smsc95xx_read_reg(dev, ID_REV, &val); if (ret < 0) - goto free_pdata; + goto unregister_mdio; val >>= 16; - pdata->chip_id = val; - pdata->mdix_ctrl = get_mdix_status(dev->net); - if ((val == ID_REV_CHIP_ID_9500A_) || (val == ID_REV_CHIP_ID_9530_) || (val == ID_REV_CHIP_ID_89530_) || (val == ID_REV_CHIP_ID_9730_)) pdata->features = (FEATURE_8_WAKEUP_FILTERS | @@ -1314,12 +1152,13 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->min_mtu = ETH_MIN_MTU; dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + return 0; - pdata->dev = dev; - INIT_DELAYED_WORK(&pdata->carrier_check, check_carrier); - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); +unregister_mdio: + mdiobus_unregister(pdata->mdiobus); - return 0; +free_mdio: + mdiobus_free(pdata->mdiobus); free_pdata: kfree(pdata); @@ -1328,15 +1167,47 @@ free_pdata: static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - - if (pdata) { - cancel_delayed_work_sync(&pdata->carrier_check); - netif_dbg(dev, ifdown, dev->net, "free pdata\n"); - kfree(pdata); - pdata = NULL; - dev->data[0] = 0; + struct smsc95xx_priv *pdata = dev->driver_priv; + + mdiobus_unregister(pdata->mdiobus); + mdiobus_free(pdata->mdiobus); + netif_dbg(dev, ifdown, dev->net, "free pdata\n"); + kfree(pdata); +} + +static void smsc95xx_handle_link_change(struct net_device *net) +{ + phy_print_status(net->phydev); +} + +static int smsc95xx_start_phy(struct usbnet *dev) +{ + struct smsc95xx_priv *pdata = dev->driver_priv; + struct net_device *net = dev->net; + int ret; + + ret = smsc95xx_reset(dev); + if (ret < 0) + return ret; + + ret = phy_connect_direct(net, pdata->phydev, + &smsc95xx_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (ret) { + netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id); + return ret; } + + phy_attached_info(net->phydev); + phy_start(net->phydev); + return 0; +} + +static int smsc95xx_disconnect_phy(struct usbnet *dev) +{ + phy_stop(dev->net->phydev); + phy_disconnect(dev->net->phydev); + return 0; } static u32 smsc_crc(const u8 *buffer, size_t len, int filter) @@ -1347,39 +1218,37 @@ static u32 smsc_crc(const u8 *buffer, size_t len, int filter) static int smsc95xx_enable_phy_wakeup_interrupts(struct usbnet *dev, u16 mask) { - struct mii_if_info *mii = &dev->mii; int ret; netdev_dbg(dev->net, "enabling PHY wakeup interrupts\n"); /* read to clear */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_INT_SRC); + ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_SRC); if (ret < 0) return ret; /* enable interrupt source */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_INT_MASK); + ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_MASK); if (ret < 0) return ret; ret |= mask; - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_INT_MASK, ret); + smsc95xx_mdio_write_nopm(dev, PHY_INT_MASK, ret); return 0; } static int smsc95xx_link_ok_nopm(struct usbnet *dev) { - struct mii_if_info *mii = &dev->mii; int ret; /* first, a dummy read, needed to latch some MII phys */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, MII_BMSR); + ret = smsc95xx_mdio_read_nopm(dev, MII_BMSR); if (ret < 0) return ret; - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, MII_BMSR); + ret = smsc95xx_mdio_read_nopm(dev, MII_BMSR); if (ret < 0) return ret; @@ -1388,7 +1257,7 @@ static int smsc95xx_link_ok_nopm(struct usbnet *dev) static int smsc95xx_enter_suspend0(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1427,8 +1296,7 @@ static int smsc95xx_enter_suspend0(struct usbnet *dev) static int smsc95xx_enter_suspend1(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); - struct mii_if_info *mii = &dev->mii; + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1436,17 +1304,17 @@ static int smsc95xx_enter_suspend1(struct usbnet *dev) * compatibility with non-standard link partners */ if (pdata->features & FEATURE_PHY_NLP_CROSSOVER) - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_EDPD_CONFIG, - PHY_EDPD_CONFIG_DEFAULT); + smsc95xx_mdio_write_nopm(dev, PHY_EDPD_CONFIG, + PHY_EDPD_CONFIG_DEFAULT); /* enable energy detect power-down mode */ - ret = smsc95xx_mdio_read_nopm(dev->net, mii->phy_id, PHY_MODE_CTRL_STS); + ret = smsc95xx_mdio_read_nopm(dev, PHY_MODE_CTRL_STS); if (ret < 0) return ret; ret |= MODE_CTRL_STS_EDPWRDOWN_; - smsc95xx_mdio_write_nopm(dev->net, mii->phy_id, PHY_MODE_CTRL_STS, ret); + smsc95xx_mdio_write_nopm(dev, PHY_MODE_CTRL_STS, ret); /* enter SUSPEND1 mode */ ret = smsc95xx_read_reg_nopm(dev, PM_CTRL, &val); @@ -1475,7 +1343,7 @@ static int smsc95xx_enter_suspend1(struct usbnet *dev) static int smsc95xx_enter_suspend2(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1497,7 +1365,7 @@ static int smsc95xx_enter_suspend2(struct usbnet *dev) static int smsc95xx_enter_suspend3(struct usbnet *dev) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val; int ret; @@ -1536,7 +1404,7 @@ static int smsc95xx_enter_suspend3(struct usbnet *dev) static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; int ret; if (!netif_running(dev->net)) { @@ -1584,7 +1452,7 @@ static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up) static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; u32 val, link_up; int ret; @@ -1594,8 +1462,6 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) return ret; } - cancel_delayed_work_sync(&pdata->carrier_check); - if (pdata->suspend_flags) { netdev_warn(dev->net, "error during last resume\n"); pdata->suspend_flags = 0; @@ -1839,10 +1705,6 @@ done: if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); - if (ret) - schedule_delayed_work(&pdata->carrier_check, - CARRIER_CHECK_DELAY); - return ret; } @@ -1855,14 +1717,13 @@ static int smsc95xx_resume(struct usb_interface *intf) u32 val; BUG_ON(!dev); - pdata = (struct smsc95xx_priv *)(dev->data[0]); + pdata = dev->driver_priv; suspend_flags = pdata->suspend_flags; netdev_dbg(dev->net, "resume suspend_flags=0x%02x\n", suspend_flags); /* do this first to ensure it's cleared even in error case */ pdata->suspend_flags = 0; - schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY); if (suspend_flags & SUSPEND_ALLMODES) { /* clear wake-up sources */ @@ -1893,6 +1754,7 @@ static int smsc95xx_resume(struct usb_interface *intf) if (ret < 0) netdev_warn(dev->net, "usbnet_resume error\n"); + phy_init_hw(pdata->phydev); return ret; } @@ -2075,7 +1937,7 @@ static struct sk_buff *smsc95xx_tx_fixup(struct usbnet *dev, static int smsc95xx_manage_power(struct usbnet *dev, int on) { - struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); + struct smsc95xx_priv *pdata = dev->driver_priv; dev->intf->needs_remote_wakeup = on; @@ -2098,7 +1960,8 @@ static const struct driver_info smsc95xx_info = { .bind = smsc95xx_bind, .unbind = smsc95xx_unbind, .link_reset = smsc95xx_link_reset, - .reset = smsc95xx_reset, + .reset = smsc95xx_start_phy, + .stop = smsc95xx_disconnect_phy, .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 9edd94679283..dca97cd7c4e7 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1295,3 +1295,4 @@ static struct platform_driver ucc_hdlc_driver = { module_platform_driver(ucc_hdlc_driver); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION(DRV_DESC); diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c index 40c04ea1200a..2fde439543fb 100644 --- a/drivers/net/wan/sbni.c +++ b/drivers/net/wan/sbni.c @@ -260,11 +260,12 @@ static int __init sbni_init(struct net_device *dev) return sbni_isa_probe( dev ); /* otherwise we have to perform search our adapter */ - if( io[ num ] != -1 ) - dev->base_addr = io[ num ], + if( io[ num ] != -1 ) { + dev->base_addr = io[ num ]; dev->irq = irq[ num ]; - else if( scandone || io[ 0 ] != -1 ) + } else if( scandone || io[ 0 ] != -1 ) { return -ENODEV; + } /* if io[ num ] contains non-zero address, then that is on ISA bus */ if( dev->base_addr ) @@ -399,12 +400,13 @@ sbni_probe1( struct net_device *dev, unsigned long ioaddr, int irq ) nl->maxframe = DEFAULT_FRAME_LEN; nl->csr1.rate = baud[ num ]; - if( (nl->cur_rxl_index = rxl[ num ]) == -1 ) + if( (nl->cur_rxl_index = rxl[ num ]) == -1 ) { /* autotune rxl */ - nl->cur_rxl_index = DEF_RXL, + nl->cur_rxl_index = DEF_RXL; nl->delta_rxl = DEF_RXL_DELTA; - else + } else { nl->delta_rxl = 0; + } nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ]; if( inb( ioaddr + CSR0 ) & 0x01 ) nl->state |= FL_SLOW_MODE; @@ -512,13 +514,15 @@ sbni_interrupt( int irq, void *dev_id ) do { repeat = 0; - if( inb( dev->base_addr + CSR0 ) & (RC_RDY | TR_RDY) ) - handle_channel( dev ), + if( inb( dev->base_addr + CSR0 ) & (RC_RDY | TR_RDY) ) { + handle_channel( dev ); repeat = 1; + } if( nl->second && /* second channel present */ - (inb( nl->second->base_addr+CSR0 ) & (RC_RDY | TR_RDY)) ) - handle_channel( nl->second ), + (inb( nl->second->base_addr+CSR0 ) & (RC_RDY | TR_RDY)) ) { + handle_channel( nl->second ); repeat = 1; + } } while( repeat ); if( nl->second ) @@ -610,11 +614,12 @@ recv_frame( struct net_device *dev ) nl->state |= FL_PREV_OK; if( framelen > 4 ) nl->in_stats.all_rx_number++; - } else - nl->state &= ~FL_PREV_OK, - change_level( dev ), - nl->in_stats.all_rx_number++, + } else { + nl->state &= ~FL_PREV_OK; + change_level( dev ); + nl->in_stats.all_rx_number++; nl->in_stats.bad_rx_number++; + } return !frame_ok || framelen > 4; } @@ -689,9 +694,10 @@ download_data( struct net_device *dev, u32 *crc_p ) *crc_p = calc_crc32( *crc_p, skb->data + nl->outpos, len ); /* if packet too short we should write some more bytes to pad */ - for( len = nl->framelen - len; len--; ) - outb( 0, dev->base_addr + DAT ), + for( len = nl->framelen - len; len--; ) { + outb( 0, dev->base_addr + DAT ); *crc_p = CRC32( 0, *crc_p ); + } } @@ -703,9 +709,10 @@ upload_data( struct net_device *dev, unsigned framelen, unsigned frameno, int frame_ok; - if( is_first ) - nl->wait_frameno = frameno, + if( is_first ) { + nl->wait_frameno = frameno; nl->inppos = 0; + } if( nl->wait_frameno == frameno ) { @@ -717,33 +724,35 @@ upload_data( struct net_device *dev, unsigned framelen, unsigned frameno, * error was occurred... drop entire packet */ else if( (frame_ok = skip_tail( dev->base_addr, framelen, crc )) - != 0 ) - nl->wait_frameno = 0, - nl->inppos = 0, + != 0 ) { + nl->wait_frameno = 0; + nl->inppos = 0; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.rx_errors++, + nl->master->stats.rx_errors++; nl->master->stats.rx_missed_errors++; #else - dev->stats.rx_errors++, + dev->stats.rx_errors++; dev->stats.rx_missed_errors++; #endif + } /* now skip all frames until is_first != 0 */ } else frame_ok = skip_tail( dev->base_addr, framelen, crc ); - if( is_first && !frame_ok ) + if( is_first && !frame_ok ) { /* * Frame has been broken, but we had already stored * is_first... Drop entire packet. */ - nl->wait_frameno = 0, + nl->wait_frameno = 0; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.rx_errors++, + nl->master->stats.rx_errors++; nl->master->stats.rx_crc_errors++; #else - dev->stats.rx_errors++, + dev->stats.rx_errors++; dev->stats.rx_crc_errors++; #endif + } return frame_ok; } @@ -782,17 +791,18 @@ interpret_ack( struct net_device *dev, unsigned ack ) if( nl->state & FL_WAIT_ACK ) { nl->outpos += nl->framelen; - if( --nl->tx_frameno ) + if( --nl->tx_frameno ) { nl->framelen = min_t(unsigned int, nl->maxframe, nl->tx_buf_p->len - nl->outpos); - else - send_complete( dev ), + } else { + send_complete( dev ); #ifdef CONFIG_SBNI_MULTILINE netif_wake_queue( nl->master ); #else netif_wake_queue( dev ); #endif + } } } @@ -872,16 +882,17 @@ drop_xmit_queue( struct net_device *dev ) { struct net_local *nl = netdev_priv(dev); - if( nl->tx_buf_p ) - dev_kfree_skb_any( nl->tx_buf_p ), - nl->tx_buf_p = NULL, + if( nl->tx_buf_p ) { + dev_kfree_skb_any( nl->tx_buf_p ); + nl->tx_buf_p = NULL; #ifdef CONFIG_SBNI_MULTILINE - nl->master->stats.tx_errors++, + nl->master->stats.tx_errors++; nl->master->stats.tx_carrier_errors++; #else - dev->stats.tx_errors++, + dev->stats.tx_errors++; dev->stats.tx_carrier_errors++; #endif + } nl->tx_frameno = 0; nl->framelen = 0; @@ -1327,12 +1338,13 @@ sbni_ioctl( struct net_device *dev, struct ifreq *ifr, int cmd ) spin_lock( &nl->lock ); flags = *(struct sbni_flags*) &ifr->ifr_ifru; - if( flags.fixed_rxl ) - nl->delta_rxl = 0, + if( flags.fixed_rxl ) { + nl->delta_rxl = 0; nl->cur_rxl_index = flags.rxl; - else - nl->delta_rxl = DEF_RXL_DELTA, + } else { + nl->delta_rxl = DEF_RXL_DELTA; nl->cur_rxl_index = DEF_RXL; + } nl->csr1.rxl = rxl_tab[ nl->cur_rxl_index ]; nl->csr1.rate = flags.rate; @@ -1526,13 +1538,16 @@ sbni_setup( char *p ) (*dest[ parm ])[ n ] = simple_strtol( p, &p, 0 ); if( !*p || *p == ')' ) return 1; - if( *p == ';' ) - ++p, ++n, parm = 0; - else if( *p++ != ',' ) + if( *p == ';' ) { + ++p; + ++n; + parm = 0; + } else if( *p++ != ',' ) { break; - else + } else { if( ++parm >= 5 ) break; + } } bad_param: pr_err("Error in sbni kernel parameter!\n"); diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c index 29053bec694e..8e3b1c717c10 100644 --- a/drivers/net/wan/slic_ds26522.c +++ b/drivers/net/wan/slic_ds26522.c @@ -22,8 +22,6 @@ #include <linux/io.h> #include "slic_ds26522.h" -#define DRV_NAME "ds26522" - #define SLIC_TRANS_LEN 1 #define SLIC_TWO_LEN 2 #define SLIC_THREE_LEN 3 diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 3c0c33a9f30c..b37902222517 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -2019,8 +2019,8 @@ static void ath10k_mac_vif_ap_csa_count_down(struct ath10k_vif *arvif) if (!arvif->is_up) return; - if (!ieee80211_csa_is_complete(vif)) { - ieee80211_csa_update_counter(vif); + if (!ieee80211_beacon_cntdwn_is_complete(vif)) { + ieee80211_beacon_update_cntdwn(vif); ret = ath10k_mac_setup_bcn_tmpl(arvif); if (ret) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index a81a1ab2de19..b661d4ec5d52 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -3878,7 +3878,7 @@ void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb) * actual channel switch is done */ if (arvif->vif->csa_active && - ieee80211_csa_is_complete(arvif->vif)) { + ieee80211_beacon_cntdwn_is_complete(arvif->vif)) { ieee80211_csa_finish(arvif->vif); continue; } diff --git a/drivers/net/wireless/ath/ath11k/thermal.c b/drivers/net/wireless/ath/ath11k/thermal.c index 5a7e150c621b..c96b26f39a25 100644 --- a/drivers/net/wireless/ath/ath11k/thermal.c +++ b/drivers/net/wireless/ath/ath11k/thermal.c @@ -53,7 +53,7 @@ ath11k_thermal_set_cur_throttle_state(struct thermal_cooling_device *cdev, return ret; } -static struct thermal_cooling_device_ops ath11k_thermal_ops = { +static const struct thermal_cooling_device_ops ath11k_thermal_ops = { .get_max_state = ath11k_thermal_get_max_throttle_state, .get_cur_state = ath11k_thermal_get_cur_throttle_state, .set_cur_state = ath11k_thermal_set_cur_throttle_state, diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 8e3437a65673..9fffa37f1e2e 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -1593,8 +1593,8 @@ int ath11k_wmi_bcn_tmpl(struct ath11k *ar, u32 vdev_id, FIELD_PREP(WMI_TLV_LEN, sizeof(*cmd) - TLV_HDR_SIZE); cmd->vdev_id = vdev_id; cmd->tim_ie_offset = offs->tim_offset; - cmd->csa_switch_count_offset = offs->csa_counter_offs[0]; - cmd->ext_csa_switch_count_offset = offs->csa_counter_offs[1]; + cmd->csa_switch_count_offset = offs->cntdwn_counter_offs[0]; + cmd->ext_csa_switch_count_offset = offs->cntdwn_counter_offs[1]; cmd->buf_len = bcn->len; ptr = skb->data + sizeof(*cmd); diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index e36f947e19fc..4daaf9b67d5f 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -365,7 +365,7 @@ bool ath9k_csa_is_finished(struct ath_softc *sc, struct ieee80211_vif *vif) if (!vif || !vif->csa_active) return false; - if (!ieee80211_csa_is_complete(vif)) + if (!ieee80211_beacon_cntdwn_is_complete(vif)) return false; ieee80211_csa_finish(vif); diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c index f20c839aeda2..c745897aa3d6 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c @@ -514,7 +514,7 @@ bool ath9k_htc_csa_is_finished(struct ath9k_htc_priv *priv) if (!vif || !vif->csa_active) return false; - if (!ieee80211_csa_is_complete(vif)) + if (!ieee80211_beacon_cntdwn_is_complete(vif)) return false; ieee80211_csa_finish(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index b78992e341d5..81bc05d70267 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1300,8 +1300,8 @@ static void iwl_mvm_csa_count_down(struct iwl_mvm *mvm, mvmvif->csa_countdown = true; - if (!ieee80211_csa_is_complete(csa_vif)) { - int c = ieee80211_csa_update_counter(csa_vif); + if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) { + int c = ieee80211_beacon_update_cntdwn(csa_vif); iwl_mvm_mac_ctxt_beacon_changed(mvm, csa_vif); if (csa_vif->p2p && @@ -1543,7 +1543,7 @@ void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm, if (notif->csa_counter != IWL_PROBE_RESP_DATA_NO_CSA && notif->csa_counter >= 1) - ieee80211_csa_set_counter(vif, notif->csa_counter); + ieee80211_beacon_set_cntdwn(vif, notif->csa_counter); } void iwl_mvm_channel_switch_noa_notif(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 1babc4bb5194..8abb57012240 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -172,7 +172,7 @@ static void iwl_mvm_csa_noa_start(struct iwl_mvm *mvm) * So we just do nothing here and the switch * will be performed on the last TBTT. */ - if (!ieee80211_csa_is_complete(csa_vif)) { + if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) { IWL_WARN(mvm, "CSA NOA started too early\n"); goto out_unlock; } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 9dd9d73f4484..dce3bc9c9f84 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1699,7 +1699,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, rcu_dereference(vif->chanctx_conf)->def.chan); } - if (vif->csa_active && ieee80211_csa_is_complete(vif)) + if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif)) ieee80211_csa_finish(vif); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 3d4bf72700a5..fbfb991ebd90 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -1095,7 +1095,7 @@ EXPORT_SYMBOL_GPL(mt76_get_txpower); static void __mt76_csa_finish(void *priv, u8 *mac, struct ieee80211_vif *vif) { - if (vif->csa_active && ieee80211_csa_is_complete(vif)) + if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif)) ieee80211_csa_finish(vif); } @@ -1120,7 +1120,7 @@ __mt76_csa_check(void *priv, u8 *mac, struct ieee80211_vif *vif) if (!vif->csa_active) return; - dev->csa_complete |= ieee80211_csa_is_complete(vif); + dev->csa_complete |= ieee80211_beacon_cntdwn_is_complete(vif); } void mt76_csa_check(struct mt76_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index d0cbb283982f..084982eb6abd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -650,12 +650,12 @@ mt7615_mcu_add_beacon_offload(struct mt7615_dev *dev, memcpy(req.pkt + MT_TXD_SIZE, skb->data, skb->len); req.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); req.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset); - if (offs.csa_counter_offs[0]) { + if (offs.cntdwn_counter_offs[0]) { u16 csa_offs; - csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4; + csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4; req.csa_ie_pos = cpu_to_le16(csa_offs); - req.csa_cnt = skb->data[offs.csa_counter_offs[0]]; + req.csa_cnt = skb->data[offs.cntdwn_counter_offs[0]]; } dev_kfree_skb(skb); @@ -1713,10 +1713,10 @@ mt7615_mcu_uni_add_beacon_offload(struct mt7615_dev *dev, req.beacon_tlv.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); req.beacon_tlv.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset); - if (offs.csa_counter_offs[0]) { + if (offs.cntdwn_counter_offs[0]) { u16 csa_offs; - csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4; + csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4; req.beacon_tlv.csa_ie_pos = cpu_to_le16(csa_offs); } dev_kfree_skb(skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index eaed5ef05401..ac8ec257da03 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -2282,7 +2282,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb, struct bss_info_bcn *bcn, struct ieee80211_mutable_offsets *offs) { - if (offs->csa_counter_offs[0]) { + if (offs->cntdwn_counter_offs[0]) { struct tlv *tlv; struct bss_info_bcn_csa *csa; @@ -2290,7 +2290,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb, sizeof(*csa), &bcn->sub_ntlv, &bcn->len); csa = (struct bss_info_bcn_csa *)tlv; - csa->cnt = skb->data[offs->csa_counter_offs[0]]; + csa->cnt = skb->data[offs->cntdwn_counter_offs[0]]; } } @@ -2312,8 +2312,8 @@ mt7915_mcu_beacon_cont(struct mt7915_dev *dev, struct sk_buff *rskb, cont->pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len); cont->tim_ofs = cpu_to_le16(offs->tim_offset); - if (offs->csa_counter_offs[0]) - cont->csa_ofs = cpu_to_le16(offs->csa_counter_offs[0] - 4); + if (offs->cntdwn_counter_offs[0]) + cont->csa_ofs = cpu_to_le16(offs->cntdwn_counter_offs[0] - 4); buf = (u8 *)tlv + sizeof(*cont); mt7915_mac_write_txwi(dev, (__le32 *)buf, skb, wcid, NULL, diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index f25f1ec5f9e9..807eae04c1e3 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -331,8 +331,7 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, - skb->len - 2, GFP_KERNEL); + transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); if (!transaction) return -ENOMEM; diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index 6586378cacb0..c8bdf078d111 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -315,8 +315,7 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; - transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, - skb->len - 2, GFP_KERNEL); + transaction = devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); if (!transaction) return -ENOMEM; diff --git a/drivers/of/address.c b/drivers/of/address.c index 590493e04b01..da4f7341323f 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -128,15 +128,29 @@ static unsigned int of_bus_pci_get_flags(const __be32 *addr) * PCI bus specific translator */ +static bool of_node_is_pcie(struct device_node *np) +{ + bool is_pcie = of_node_name_eq(np, "pcie"); + + if (is_pcie) + pr_warn_once("%pOF: Missing device_type\n", np); + + return is_pcie; +} + static int of_bus_pci_match(struct device_node *np) { /* * "pciex" is PCI Express * "vci" is for the /chaos bridge on 1st-gen PCI powermacs * "ht" is hypertransport + * + * If none of the device_type match, and that the node name is + * "pcie", accept the device as PCI (with a warning). */ return of_node_is_type(np, "pci") || of_node_is_type(np, "pciex") || - of_node_is_type(np, "vci") || of_node_is_type(np, "ht"); + of_node_is_type(np, "vci") || of_node_is_type(np, "ht") || + of_node_is_pcie(np); } static void of_bus_pci_count_cells(struct device_node *np, @@ -985,6 +999,11 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz /* Don't error out as we'd break some existing DTs */ continue; } + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } dma_offset = range.cpu_addr - range.bus_addr; /* Take lower and upper limits */ diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 9d7fb45b1786..9668ea04cc80 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -893,8 +893,10 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) * have OPP table for the device, while others don't and * opp_set_rate() just needs to behave like clk_set_rate(). */ - if (!_get_opp_count(opp_table)) - return 0; + if (!_get_opp_count(opp_table)) { + ret = 0; + goto put_opp_table; + } if (!opp_table->required_opp_tables && !opp_table->regulators && !opp_table->paths) { @@ -905,7 +907,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) ret = _set_opp_bw(opp_table, NULL, dev, true); if (ret) - return ret; + goto put_opp_table; if (opp_table->regulator_enabled) { regulator_disable(opp_table->regulators[0]); @@ -932,10 +934,13 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) /* Return early if nothing to do */ if (old_freq == freq) { - dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", - __func__, freq); - ret = 0; - goto put_opp_table; + if (!opp_table->required_opp_tables && !opp_table->regulators && + !opp_table->paths) { + dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", + __func__, freq); + ret = 0; + goto put_opp_table; + } } /* diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index b59f84918fe0..c9e790c74051 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -83,21 +83,19 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); struct pci_dev *pdev; - struct zpci_bus *zbus = zdev->zbus; int rc; if (!zpci_fn_configured(zdev->state)) return -EIO; - pdev = pci_get_slot(zbus->bus, zdev->devfn); - if (pdev) { - if (pci_num_vf(pdev)) - return -EBUSY; - - pci_stop_and_remove_bus_device_locked(pdev); + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev && pci_num_vf(pdev)) { pci_dev_put(pdev); + return -EBUSY; } + zpci_remove_device(zdev); + rc = zpci_disable_device(zdev); if (rc) return rc; diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 64ebed129dbf..f357f9a32b3a 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -556,13 +556,14 @@ int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, return -1; for (i = 0; i < num_clients; i++) { - if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - clients[i]->dma_ops == &dma_virt_ops) { +#ifdef CONFIG_DMA_VIRT_OPS + if (clients[i]->dma_ops == &dma_virt_ops) { if (verbose) dev_warn(clients[i], "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n"); return -1; } +#endif pci_client = find_parent_pci_dev(clients[i]); if (!pci_client) { @@ -842,9 +843,10 @@ static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap, * this should never happen because it will be prevented * by the check in pci_p2pdma_distance_many() */ - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - dev->dma_ops == &dma_virt_ops)) +#ifdef CONFIG_DMA_VIRT_OPS + if (WARN_ON_ONCE(dev->dma_ops == &dma_virt_ops)) return 0; +#endif for_each_sg(sg, s, nents, i) { paddr = sg_phys(s); diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 73aaae5574ed..e020faff7da5 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -142,16 +142,15 @@ static int idtcm_strverscmp(const char *ver1, const char *ver2) return result; } -static int idtcm_xfer(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count, - bool write) +static int idtcm_xfer_read(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) { struct i2c_client *client = idtcm->client; struct i2c_msg msg[2]; int cnt; - char *fmt = "i2c_transfer failed at %d in %s for %s, at addr: %04X!\n"; + char *fmt = "i2c_transfer failed at %d in %s, at addr: %04X!\n"; msg[0].addr = client->addr; msg[0].flags = 0; @@ -159,7 +158,7 @@ static int idtcm_xfer(struct idtcm *idtcm, msg[0].buf = ®addr; msg[1].addr = client->addr; - msg[1].flags = write ? 0 : I2C_M_RD; + msg[1].flags = I2C_M_RD; msg[1].len = count; msg[1].buf = buf; @@ -170,7 +169,6 @@ static int idtcm_xfer(struct idtcm *idtcm, fmt, __LINE__, __func__, - write ? "write" : "read", regaddr); return cnt; } else if (cnt != 2) { @@ -182,6 +180,37 @@ static int idtcm_xfer(struct idtcm *idtcm, return 0; } +static int idtcm_xfer_write(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) +{ + struct i2c_client *client = idtcm->client; + /* we add 1 byte for device register */ + u8 msg[IDTCM_MAX_WRITE_COUNT + 1]; + int cnt; + char *fmt = "i2c_master_send failed at %d in %s, at addr: %04X!\n"; + + if (count > IDTCM_MAX_WRITE_COUNT) + return -EINVAL; + + msg[0] = regaddr; + memcpy(&msg[1], buf, count); + + cnt = i2c_master_send(client, msg, count + 1); + + if (cnt < 0) { + dev_err(&client->dev, + fmt, + __LINE__, + __func__, + regaddr); + return cnt; + } + + return 0; +} + static int idtcm_page_offset(struct idtcm *idtcm, u8 val) { u8 buf[4]; @@ -195,7 +224,7 @@ static int idtcm_page_offset(struct idtcm *idtcm, u8 val) buf[2] = 0x10; buf[3] = 0x20; - err = idtcm_xfer(idtcm, PAGE_ADDR, buf, sizeof(buf), 1); + err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf)); if (err) { idtcm->page_offset = 0xff; @@ -223,11 +252,12 @@ static int _idtcm_rdwr(struct idtcm *idtcm, err = idtcm_page_offset(idtcm, hi); if (err) - goto out; + return err; - err = idtcm_xfer(idtcm, lo, buf, count, write); -out: - return err; + if (write) + return idtcm_xfer_write(idtcm, lo, buf, count); + + return idtcm_xfer_read(idtcm, lo, buf, count); } static int idtcm_read(struct idtcm *idtcm, diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index ffae56c5d97f..82840d72364a 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -55,6 +55,8 @@ #define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) +#define IDTCM_MAX_WRITE_COUNT (512) + /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index 7711651ff19e..4700ffbdfced 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -93,9 +93,6 @@ MODULE_LICENSE("GPL"); #define TC_E2E_PTP_V2 2 #define TC_P2P_PTP_V2 3 -#define OFF_PTP_CLOCK_ID 20 -#define OFF_PTP_PORT_NUM 28 - #define PHY_SPEED_10 0 #define PHY_SPEED_100 1 #define PHY_SPEED_1000 2 @@ -443,57 +440,41 @@ static void ines_link_state(struct mii_timestamper *mii_ts, static bool ines_match(struct sk_buff *skb, unsigned int ptp_class, struct ines_timestamp *ts, struct device *dev) { - u8 *msgtype, *data = skb_mac_header(skb); - unsigned int offset = 0; - __be16 *portn, *seqid; - __be64 *clkid; + struct ptp_header *hdr; + u16 portn, seqid; + u8 msgtype; + u64 clkid; if (unlikely(ptp_class & PTP_CLASS_V1)) return false; - if (ptp_class & PTP_CLASS_VLAN) - offset += VLAN_HLEN; - - switch (ptp_class & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return false; - } - - if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid)) + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) return false; - msgtype = data + offset; - clkid = (__be64 *)(data + offset + OFF_PTP_CLOCK_ID); - portn = (__be16 *)(data + offset + OFF_PTP_PORT_NUM); - seqid = (__be16 *)(data + offset + OFF_PTP_SEQUENCE_ID); + msgtype = ptp_get_msgtype(hdr, ptp_class); + clkid = be64_to_cpup((__be64 *)&hdr->source_port_identity.clock_identity.id[0]); + portn = be16_to_cpu(hdr->source_port_identity.port_number); + seqid = be16_to_cpu(hdr->sequence_id); - if (tag_to_msgtype(ts->tag & 0x7) != (*msgtype & 0xf)) { + if (tag_to_msgtype(ts->tag & 0x7) != msgtype) { dev_dbg(dev, "msgtype mismatch ts %hhu != skb %hhu\n", - tag_to_msgtype(ts->tag & 0x7), *msgtype & 0xf); + tag_to_msgtype(ts->tag & 0x7), msgtype); return false; } - if (cpu_to_be64(ts->clkid) != *clkid) { + if (ts->clkid != clkid) { dev_dbg(dev, "clkid mismatch ts %llx != skb %llx\n", - cpu_to_be64(ts->clkid), *clkid); + ts->clkid, clkid); return false; } - if (ts->portnum != ntohs(*portn)) { + if (ts->portnum != portn) { dev_dbg(dev, "portn mismatch ts %hu != skb %hu\n", - ts->portnum, ntohs(*portn)); + ts->portnum, portn); return false; } - if (ts->seqid != ntohs(*seqid)) { + if (ts->seqid != seqid) { dev_dbg(dev, "seqid mismatch ts %hu != skb %hu\n", - ts->seqid, ntohs(*seqid)); + ts->seqid, seqid); return false; } @@ -663,8 +644,7 @@ static void ines_txtstamp(struct mii_timestamper *mii_ts, spin_unlock_irqrestore(&port->lock, flags); - if (old_skb) - kfree_skb(old_skb); + kfree_skb(old_skb); schedule_delayed_work(&port->ts_work, 1); } @@ -694,35 +674,16 @@ static void ines_txtstamp_work(struct work_struct *work) static bool is_sync_pdelay_resp(struct sk_buff *skb, int type) { - u8 *data = skb->data, *msgtype; - unsigned int offset = 0; - - if (type & PTP_CLASS_VLAN) - offset += VLAN_HLEN; + struct ptp_header *hdr; + u8 msgtype; - switch (type & PTP_CLASS_PMASK) { - case PTP_CLASS_IPV4: - offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN; - break; - case PTP_CLASS_IPV6: - offset += ETH_HLEN + IP6_HLEN + UDP_HLEN; - break; - case PTP_CLASS_L2: - offset += ETH_HLEN; - break; - default: - return 0; - } - - if (type & PTP_CLASS_V1) - offset += OFF_PTP_CONTROL; - - if (skb->len < offset + 1) - return 0; + hdr = ptp_parse_header(skb, type); + if (!hdr) + return false; - msgtype = data + offset; + msgtype = ptp_get_msgtype(hdr, type); - switch ((*msgtype & 0xf)) { + switch ((msgtype & 0xf)) { case SYNC: case PDELAY_RESP: return true; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 94edbb33d0d1..aca022239b33 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -677,6 +677,11 @@ static int slow_eval_known_fn(struct subchannel *sch, void *data) rc = css_evaluate_known_subchannel(sch, 1); if (rc == -EAGAIN) css_schedule_eval(sch->schid); + /* + * The loop might take long time for platforms with lots of + * known devices. Allow scheduling here. + */ + cond_resched(); } return 0; } diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index ecfd6d152e86..da46af682af8 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -420,12 +420,6 @@ struct qeth_qdio_out_buffer { struct qeth_card; -enum qeth_out_q_states { - QETH_OUT_Q_UNLOCKED, - QETH_OUT_Q_LOCKED, - QETH_OUT_Q_LOCKED_FLUSH, -}; - #define QETH_CARD_STAT_ADD(_c, _stat, _val) ((_c)->stats._stat += (_val)) #define QETH_CARD_STAT_INC(_c, _stat) QETH_CARD_STAT_ADD(_c, _stat, 1) @@ -486,12 +480,12 @@ struct qeth_qdio_out_q { struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q]; struct qdio_outbuf_state *bufstates; /* convenience pointer */ struct qeth_out_q_stats stats; + spinlock_t lock; u8 next_buf_to_fill; u8 max_elements; u8 queue_no; u8 do_pack; struct qeth_card *card; - atomic_t state; /* * number of buffers that are currently filled (PRIMED) * -> these buffers are hardware-owned @@ -680,6 +674,11 @@ struct qeth_card_blkt { int inter_packet_jumbo; }; +enum qeth_pnso_mode { + QETH_PNSO_NONE, + QETH_PNSO_BRIDGEPORT, +}; + #define QETH_BROADCAST_WITH_ECHO 0x01 #define QETH_BROADCAST_WITHOUT_ECHO 0x02 struct qeth_card_info { @@ -696,6 +695,7 @@ struct qeth_card_info { /* no bitfield, we take a pointer on these two: */ u8 has_lp2lp_cso_v6; u8 has_lp2lp_cso_v4; + enum qeth_pnso_mode pnso_mode; enum qeth_card_types type; enum qeth_link_types link_type; int broadcast_capable; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index bba1b54b8aa3..26bc8c15ffb8 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2702,6 +2702,7 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) card->qdio.out_qs[i] = queue; queue->card = card; queue->queue_no = i; + spin_lock_init(&queue->lock); timer_setup(&queue->timer, qeth_tx_completion_timer, 0); queue->coalesce_usecs = QETH_TX_COALESCE_USECS; queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; @@ -3068,7 +3069,6 @@ static int qeth_init_qdio_queues(struct qeth_card *card) queue->bulk_max = qeth_tx_select_bulk_max(card, queue); atomic_set(&queue->used_buffers, 0); atomic_set(&queue->set_pci_flags_count, 0); - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); netdev_tx_reset_queue(netdev_get_tx_queue(card->dev, i)); } return 0; @@ -3549,8 +3549,9 @@ static unsigned int qeth_rx_refill_queue(struct qeth_card *card, static void qeth_buffer_reclaim_work(struct work_struct *work) { - struct qeth_card *card = container_of(work, struct qeth_card, - buffer_reclaim_work.work); + struct qeth_card *card = container_of(to_delayed_work(work), + struct qeth_card, + buffer_reclaim_work); local_bh_disable(); napi_schedule(&card->napi); @@ -3740,37 +3741,31 @@ static void qeth_flush_queue(struct qeth_qdio_out_q *queue) static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) { - int index; - int flush_cnt = 0; - int q_was_packing = 0; - /* * check if weed have to switch to non-packing mode or if * we have to get a pci flag out on the queue */ if ((atomic_read(&queue->used_buffers) <= QETH_LOW_WATERMARK_PACK) || !atomic_read(&queue->set_pci_flags_count)) { - if (atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH) == - QETH_OUT_Q_UNLOCKED) { - /* - * If we get in here, there was no action in - * do_send_packet. So, we check if there is a - * packing buffer to be flushed here. - */ - index = queue->next_buf_to_fill; - q_was_packing = queue->do_pack; - /* queue->do_pack may change */ - barrier(); - flush_cnt += qeth_switch_to_nonpacking_if_needed(queue); - if (!flush_cnt && - !atomic_read(&queue->set_pci_flags_count)) - flush_cnt += qeth_prep_flush_pack_buffer(queue); + unsigned int index, flush_cnt; + bool q_was_packing; + + spin_lock(&queue->lock); + + index = queue->next_buf_to_fill; + q_was_packing = queue->do_pack; + + flush_cnt = qeth_switch_to_nonpacking_if_needed(queue); + if (!flush_cnt && !atomic_read(&queue->set_pci_flags_count)) + flush_cnt = qeth_prep_flush_pack_buffer(queue); + + if (flush_cnt) { + qeth_flush_buffers(queue, index, flush_cnt); if (q_was_packing) QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_cnt); - if (flush_cnt) - qeth_flush_buffers(queue, index, flush_cnt); - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); } + + spin_unlock(&queue->lock); } } @@ -4282,29 +4277,22 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, unsigned int offset, unsigned int hd_len, int elements_needed) { + unsigned int start_index = queue->next_buf_to_fill; struct qeth_qdio_out_buffer *buffer; unsigned int next_element; struct netdev_queue *txq; bool stopped = false; - int start_index; int flush_count = 0; int do_pack = 0; - int tmp; int rc = 0; - /* spin until we get the queue ... */ - while (atomic_cmpxchg(&queue->state, QETH_OUT_Q_UNLOCKED, - QETH_OUT_Q_LOCKED) != QETH_OUT_Q_UNLOCKED); - start_index = queue->next_buf_to_fill; buffer = queue->bufs[queue->next_buf_to_fill]; /* Just a sanity check, the wake/stop logic should ensure that we always * get a free buffer. */ - if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) { - atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); + if (atomic_read(&buffer->state) != QETH_QDIO_BUF_EMPTY) return -EBUSY; - } txq = netdev_get_tx_queue(card->dev, skb_get_queue_mapping(skb)); @@ -4327,8 +4315,6 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, QETH_QDIO_BUF_EMPTY) { qeth_flush_buffers(queue, start_index, flush_count); - atomic_set(&queue->state, - QETH_OUT_Q_UNLOCKED); rc = -EBUSY; goto out; } @@ -4360,31 +4346,8 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, if (flush_count) qeth_flush_buffers(queue, start_index, flush_count); - else if (!atomic_read(&queue->set_pci_flags_count)) - atomic_xchg(&queue->state, QETH_OUT_Q_LOCKED_FLUSH); - /* - * queue->state will go from LOCKED -> UNLOCKED or from - * LOCKED_FLUSH -> LOCKED if output_handler wanted to 'notify' us - * (switch packing state or flush buffer to get another pci flag out). - * In that case we will enter this loop - */ - while (atomic_dec_return(&queue->state)) { - start_index = queue->next_buf_to_fill; - /* check if we can go back to non-packing state */ - tmp = qeth_switch_to_nonpacking_if_needed(queue); - /* - * check if we need to flush a packing buffer to get a pci - * flag out on the queue - */ - if (!tmp && !atomic_read(&queue->set_pci_flags_count)) - tmp = qeth_prep_flush_pack_buffer(queue); - if (tmp) { - qeth_flush_buffers(queue, start_index, tmp); - flush_count += tmp; - } - } + out: - /* at this point the queue is UNLOCKED again */ if (do_pack) QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_count); @@ -4458,8 +4421,10 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, } else { /* TODO: drop skb_orphan() once TX completion is fast enough */ skb_orphan(skb); + spin_lock(&queue->lock); rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, hd_len, elements); + spin_unlock(&queue->lock); } if (rc && !push_len) diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index b459def0fb26..6541bab96822 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -719,15 +719,8 @@ struct qeth_sbp_port_entry { struct net_if_token token; } __packed; -struct qeth_sbp_query_ports { - __u8 primary_bp_supported; - __u8 secondary_bp_supported; - __u8 num_entries; - __u8 entry_length; - struct qeth_sbp_port_entry entry[]; -} __packed; - -struct qeth_sbp_state_change { +/* For IPA_SBP_QUERY_BRIDGE_PORTS, IPA_SBP_BRIDGE_PORT_STATE_CHANGE */ +struct qeth_sbp_port_data { __u8 primary_bp_supported; __u8 secondary_bp_supported; __u8 num_entries; @@ -741,8 +734,7 @@ struct qeth_ipacmd_setbridgeport { union { struct qeth_sbp_query_cmds_supp query_cmds_supp; struct qeth_sbp_set_primary set_primary; - struct qeth_sbp_query_ports query_ports; - struct qeth_sbp_state_change state_change; + struct qeth_sbp_port_data port_data; } data; } __packed; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8b342a88ff5c..b5bef5345dd6 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -273,6 +273,17 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, return qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN); } +static void qeth_l2_set_pnso_mode(struct qeth_card *card, + enum qeth_pnso_mode mode) +{ + spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card))); + WRITE_ONCE(card->info.pnso_mode, mode); + spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card))); + + if (mode == QETH_PNSO_NONE) + drain_workqueue(card->event_wq); +} + static void qeth_l2_stop_card(struct qeth_card *card) { QETH_CARD_TEXT(card, 2, "stopcard"); @@ -290,7 +301,7 @@ static void qeth_l2_stop_card(struct qeth_card *card) qeth_qdio_clear_card(card, 0); qeth_clear_working_pool_list(card); - flush_workqueue(card->event_wq); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); qeth_flush_local_addrs(card); card->info.promisc_mode = 0; } @@ -810,8 +821,6 @@ static void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card) if (card->options.sbp.hostnotification) { if (qeth_bridgeport_an_set(card, 1)) card->options.sbp.hostnotification = 0; - } else { - qeth_bridgeport_an_set(card, 0); } } @@ -1090,15 +1099,14 @@ static void qeth_bridge_emit_host_event(struct qeth_card *card, struct qeth_bridge_state_data { struct work_struct worker; struct qeth_card *card; - struct qeth_sbp_state_change qports; + u8 role; + u8 state; }; static void qeth_bridge_state_change_worker(struct work_struct *work) { struct qeth_bridge_state_data *data = container_of(work, struct qeth_bridge_state_data, worker); - /* We are only interested in the first entry - local port */ - struct qeth_sbp_port_entry *entry = &data->qports.entry[0]; char env_locrem[32]; char env_role[32]; char env_state[32]; @@ -1109,22 +1117,16 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) NULL }; - /* Role should not change by itself, but if it did, */ - /* information from the hardware is authoritative. */ - mutex_lock(&data->card->sbp_lock); - data->card->options.sbp.role = entry->role; - mutex_unlock(&data->card->sbp_lock); - snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); snprintf(env_role, sizeof(env_role), "ROLE=%s", - (entry->role == QETH_SBP_ROLE_NONE) ? "none" : - (entry->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : - (entry->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : + (data->role == QETH_SBP_ROLE_NONE) ? "none" : + (data->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : + (data->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : "<INVALID>"); snprintf(env_state, sizeof(env_state), "STATE=%s", - (entry->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : - (entry->state == QETH_SBP_STATE_STANDBY) ? "standby" : - (entry->state == QETH_SBP_STATE_ACTIVE) ? "active" : + (data->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : + (data->state == QETH_SBP_STATE_STANDBY) ? "standby" : + (data->state == QETH_SBP_STATE_ACTIVE) ? "active" : "<INVALID>"); kobject_uevent_env(&data->card->gdev->dev.kobj, KOBJ_CHANGE, env); @@ -1134,10 +1136,8 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) static void qeth_bridge_state_change(struct qeth_card *card, struct qeth_ipa_cmd *cmd) { - struct qeth_sbp_state_change *qports = - &cmd->data.sbp.data.state_change; + struct qeth_sbp_port_data *qports = &cmd->data.sbp.data.port_data; struct qeth_bridge_state_data *data; - int extrasize; QETH_CARD_TEXT(card, 2, "brstchng"); if (qports->num_entries == 0) { @@ -1148,34 +1148,50 @@ static void qeth_bridge_state_change(struct qeth_card *card, QETH_CARD_TEXT_(card, 2, "BPsz%04x", qports->entry_length); return; } - extrasize = sizeof(struct qeth_sbp_port_entry) * qports->num_entries; - data = kzalloc(sizeof(struct qeth_bridge_state_data) + extrasize, - GFP_ATOMIC); + + data = kzalloc(sizeof(*data), GFP_ATOMIC); if (!data) { QETH_CARD_TEXT(card, 2, "BPSalloc"); return; } INIT_WORK(&data->worker, qeth_bridge_state_change_worker); data->card = card; - memcpy(&data->qports, qports, - sizeof(struct qeth_sbp_state_change) + extrasize); + /* Information for the local port: */ + data->role = qports->entry[0].role; + data->state = qports->entry[0].state; + queue_work(card->event_wq, &data->worker); } struct qeth_addr_change_data { - struct work_struct worker; + struct delayed_work dwork; struct qeth_card *card; struct qeth_ipacmd_addr_change ac_event; }; static void qeth_addr_change_event_worker(struct work_struct *work) { - struct qeth_addr_change_data *data = - container_of(work, struct qeth_addr_change_data, worker); + struct delayed_work *dwork = to_delayed_work(work); + struct qeth_addr_change_data *data; + struct qeth_card *card; int i; + data = container_of(dwork, struct qeth_addr_change_data, dwork); + card = data->card; + QETH_CARD_TEXT(data->card, 4, "adrchgew"); + + if (READ_ONCE(card->info.pnso_mode) == QETH_PNSO_NONE) + goto free; + if (data->ac_event.lost_event_mask) { + /* Potential re-config in progress, try again later: */ + if (!mutex_trylock(&card->sbp_lock)) { + queue_delayed_work(card->event_wq, dwork, + msecs_to_jiffies(100)); + return; + } + dev_info(&data->card->gdev->dev, "Address change notification stopped on %s (%s)\n", data->card->dev->name, @@ -1184,8 +1200,9 @@ static void qeth_addr_change_event_worker(struct work_struct *work) : (data->ac_event.lost_event_mask == 0x02) ? "Bridge port state change" : "Unknown reason"); - mutex_lock(&data->card->sbp_lock); + data->card->options.sbp.hostnotification = 0; + card->info.pnso_mode = QETH_PNSO_NONE; mutex_unlock(&data->card->sbp_lock); qeth_bridge_emit_host_event(data->card, anev_abort, 0, NULL, NULL); @@ -1199,6 +1216,8 @@ static void qeth_addr_change_event_worker(struct work_struct *work) &entry->token, &entry->addr_lnid); } + +free: kfree(data); } @@ -1210,6 +1229,9 @@ static void qeth_addr_change_event(struct qeth_card *card, struct qeth_addr_change_data *data; int extrasize; + if (card->info.pnso_mode == QETH_PNSO_NONE) + return; + QETH_CARD_TEXT(card, 4, "adrchgev"); if (cmd->hdr.return_code != 0x0000) { if (cmd->hdr.return_code == 0x0010) { @@ -1229,11 +1251,11 @@ static void qeth_addr_change_event(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "ACNalloc"); return; } - INIT_WORK(&data->worker, qeth_addr_change_event_worker); + INIT_DELAYED_WORK(&data->dwork, qeth_addr_change_event_worker); data->card = card; memcpy(&data->ac_event, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(card->event_wq, &data->worker); + queue_delayed_work(card->event_wq, &data->dwork, 0); } /* SETBRIDGEPORT support; sending commands */ @@ -1418,8 +1440,8 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; - struct qeth_sbp_query_ports *qports = &cmd->data.sbp.data.query_ports; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; + struct qeth_sbp_port_data *qports; int rc; QETH_CARD_TEXT(card, 2, "brqprtcb"); @@ -1427,6 +1449,7 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, if (rc) return rc; + qports = &cmd->data.sbp.data.port_data; if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) { QETH_CARD_TEXT_(card, 2, "SBPs%04x", qports->entry_length); return -EINVAL; @@ -1554,9 +1577,14 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable) if (enable) { qeth_bridge_emit_host_event(card, anev_reset, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_BRIDGEPORT); rc = qeth_l2_pnso(card, 1, qeth_bridgeport_an_set_cb, card); - } else + if (rc) + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } else { rc = qeth_l2_pnso(card, 0, NULL, NULL); + qeth_l2_set_pnso_mode(card, QETH_PNSO_NONE); + } return rc; } diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 86bcae992f72..4695d25e54f2 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -157,6 +157,7 @@ static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, rc = -EBUSY; else if (qeth_card_hw_is_reachable(card)) { rc = qeth_bridgeport_an_set(card, enable); + /* sbp_lock ensures ordering vs notifications-stopped events */ if (!rc) card->options.sbp.hostnotification = enable; } else diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index fe44b0249e34..95df638de616 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -314,7 +314,8 @@ static int qeth_l3_setdelip_cb(struct qeth_card *card, struct qeth_reply *reply, } static int qeth_l3_send_setdelmc(struct qeth_card *card, - struct qeth_ipaddr *addr, int ipacmd) + struct qeth_ipaddr *addr, + enum qeth_ipa_cmds ipacmd) { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index c795f22249d8..140186fe1d1e 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -434,7 +434,7 @@ static void zfcp_fsf_req_complete(struct zfcp_fsf_req *req) return; } - del_timer(&req->timer); + del_timer_sync(&req->timer); zfcp_fsf_protstatus_eval(req); zfcp_fsf_fsfstatus_eval(req); req->handler(req); @@ -867,7 +867,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req) req->qdio_req.qdio_outb_usage = atomic_read(&qdio->req_q_free); req->issued = get_tod_clock(); if (zfcp_qdio_send(qdio, &req->qdio_req)) { - del_timer(&req->timer); + del_timer_sync(&req->timer); /* lookup request again, list might have changed */ zfcp_reqlist_find_rm(adapter->req_list, req_id); zfcp_erp_adapter_reopen(adapter, 0, "fsrs__1"); diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h index 91eb6901815c..e1d7de63e8f8 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.h +++ b/drivers/scsi/qla2xxx/qla_dbg.h @@ -380,5 +380,8 @@ extern int qla24xx_soft_reset(struct qla_hw_data *); static inline int ql_mask_match(uint level) { + if (ql2xextended_error_logging == 1) + ql2xextended_error_logging = QL_DBG_DEFAULT1_MASK; + return (level & ql2xextended_error_logging) == level; } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 8c92af5e4390..1bc090d8a71b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3880,6 +3880,7 @@ struct qla_hw_data { uint32_t scm_supported_f:1; /* Enabled in Driver */ uint32_t scm_enabled:1; + uint32_t max_req_queue_warned:1; } flags; uint16_t max_exchg; diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index df670fba2ab8..de9fd7f688d0 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -1505,11 +1505,11 @@ qla2x00_prep_ct_fdmi_req(struct ct_sns_pkt *p, uint16_t cmd, static uint qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) { + uint speeds = 0; + if (IS_CNA_CAPABLE(ha)) return FDMI_PORT_SPEED_10GB; if (IS_QLA28XX(ha) || IS_QLA27XX(ha)) { - uint speeds = 0; - if (ha->max_supported_speed == 2) { if (ha->min_supported_speed <= 6) speeds |= FDMI_PORT_SPEED_64GB; @@ -1536,9 +1536,16 @@ qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) } return speeds; } - if (IS_QLA2031(ha)) - return FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| - FDMI_PORT_SPEED_4GB; + if (IS_QLA2031(ha)) { + if ((ha->pdev->subsystem_vendor == 0x103C) && + (ha->pdev->subsystem_device == 0x8002)) { + speeds = FDMI_PORT_SPEED_16GB; + } else { + speeds = FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| + FDMI_PORT_SPEED_4GB; + } + return speeds; + } if (IS_QLA25XX(ha)) return FDMI_PORT_SPEED_8GB|FDMI_PORT_SPEED_4GB| FDMI_PORT_SPEED_2GB|FDMI_PORT_SPEED_1GB; @@ -3436,7 +3443,6 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp) list_for_each_entry(fcport, &vha->vp_fcports, list) { if ((fcport->flags & FCF_FABRIC_DEVICE) != 0) { fcport->scan_state = QLA_FCPORT_SCAN; - fcport->logout_on_delete = 0; } } goto login_logout; @@ -3532,10 +3538,22 @@ login_logout: } if (fcport->scan_state != QLA_FCPORT_FOUND) { + bool do_delete = false; + + if (fcport->scan_needed && + fcport->disc_state == DSC_LOGIN_PEND) { + /* Cable got disconnected after we sent + * a login. Do delete to prevent timeout. + */ + fcport->logout_on_delete = 1; + do_delete = true; + } + fcport->scan_needed = 0; - if ((qla_dual_mode_enabled(vha) || - qla_ini_mode_enabled(vha)) && - atomic_read(&fcport->state) == FCS_ONLINE) { + if (((qla_dual_mode_enabled(vha) || + qla_ini_mode_enabled(vha)) && + atomic_read(&fcport->state) == FCS_ONLINE) || + do_delete) { if (fcport->loop_id != FC_NO_LOOP_ID) { if (fcport->flags & FCF_FCP2_DEVICE) fcport->logout_on_delete = 0; @@ -3736,6 +3754,18 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res) unsigned long flags; const char *name = sp->name; + if (res == QLA_OS_TIMER_EXPIRED) { + /* switch is ignoring all commands. + * This might be a zone disable behavior. + * This means we hit 64s timeout. + * 22s GPNFT + 44s Abort = 64s + */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: Switch Zone check please .\n", + name); + qla2x00_mark_all_devices_lost(vha); + } + /* * We are in an Interrupt context, queue up this * sp for GNNFT_DONE work. This will allow all diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 27bcd346af7c..ab5275dbc338 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2024,8 +2024,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, res = DID_ERROR << 16; } } - ql_dbg(ql_dbg_user, vha, 0x503f, - "ELS IOCB Done -%s error hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", + ql_dbg(ql_dbg_disc, vha, 0x503f, + "ELS IOCB Done -%s hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", type, sp->handle, comp_status, fw_status[1], fw_status[2], le32_to_cpu(ese->total_byte_count)); goto els_ct_done; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 73883435ab58..226f1428d3e5 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -334,14 +334,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (time_after(jiffies, wait_time)) break; - /* - * Check if it's UNLOADING, cause we cannot poll in - * this case, or else a NULL pointer dereference - * is triggered. - */ - if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) - return QLA_FUNCTION_TIMEOUT; - /* Check for pending interrupts. */ qla2x00_poll(ha->rsp_q_map[0]); @@ -5240,7 +5232,7 @@ qla2x00_read_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t *data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_1|MBX_0; mcp->in_mb = MBX_3|MBX_2|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5428,7 +5420,7 @@ qla2x00_write_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5700,7 +5692,7 @@ qla24xx_set_fcp_prio(scsi_qla_host_t *vha, uint16_t loop_id, uint16_t priority, mcp->mb[9] = vha->vp_idx; mcp->out_mb = MBX_9|MBX_4|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_4|MBX_3|MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (mb != NULL) { @@ -5787,7 +5779,7 @@ qla82xx_mbx_intr_enable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -5822,7 +5814,7 @@ qla82xx_mbx_intr_disable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6014,7 +6006,7 @@ qla81xx_set_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) if (IS_QLA8031(ha)) mcp->out_mb |= MBX_6|MBX_5|MBX_4|MBX_3; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6050,7 +6042,7 @@ qla81xx_get_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) mcp->in_mb = MBX_2|MBX_1|MBX_0; if (IS_QLA8031(ha)) mcp->in_mb |= MBX_6|MBX_5|MBX_4|MBX_3; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index fa695a4007f8..90bbc61f361b 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -536,6 +536,11 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, struct nvme_private *priv = fd->private; struct qla_nvme_rport *qla_rport = rport->private; + if (!priv) { + /* nvme association has been torn down */ + return rval; + } + fcport = qla_rport->fcport; if (!qpair || !fcport || (qpair && !qpair->fw_started) || @@ -687,7 +692,15 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha) tmpl = &qla_nvme_fc_transport; WARN_ON(vha->nvme_local_port); - WARN_ON(ha->max_req_queues < 3); + + if (ha->max_req_queues < 3) { + if (!ha->flags.max_req_queue_warned) + ql_log(ql_log_info, vha, 0x2120, + "%s: Disabling FC-NVME due to lack of free queue pairs (%d).\n", + __func__, ha->max_req_queues); + ha->flags.max_req_queue_warned = 1; + return ret; + } qla_nvme_fc_transport.max_hw_queues = min((uint8_t)(qla_nvme_fc_transport.max_hw_queues), diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 9b59f032a569..8da00ba54aec 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2017,6 +2017,11 @@ skip_pio: /* Determine queue resources */ ha->max_req_queues = ha->max_rsp_queues = 1; ha->msix_count = QLA_BASE_VECTORS; + + /* Check if FW supports MQ or not */ + if (!(ha->fw_attributes & BIT_6)) + goto mqiobase_exit; + if (!ql2xmqsupport || !ql2xnvmeenable || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha))) goto mqiobase_exit; @@ -2829,10 +2834,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) /* This may fail but that's ok */ pci_enable_pcie_error_reporting(pdev); - /* Turn off T10-DIF when FC-NVMe is enabled */ - if (ql2xnvmeenable) - ql2xenabledif = 0; - ha = kzalloc(sizeof(struct qla_hw_data), GFP_KERNEL); if (!ha) { ql_log_pci(ql_log_fatal, pdev, 0x0009, diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index fbb80a043b4f..90289162dbd4 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1270,7 +1270,7 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) qla24xx_chk_fcp_state(sess); - ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, + ql_dbg(ql_dbg_disc, sess->vha, 0xe001, "Scheduling sess %p for deletion %8phC\n", sess, sess->port_name); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 064ed680c053..139f0073da37 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5490,9 +5490,11 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, u64 d = ktime_get_boottime_ns() - ns_from_boot; if (kt <= d) { /* elapsed duration >= kt */ + spin_lock_irqsave(&sqp->qc_lock, iflags); sqcp->a_cmnd = NULL; atomic_dec(&devip->num_in_q); clear_bit(k, sqp->in_use_bm); + spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (new_sd_dp) kfree(sd_dp); /* call scsi_done() from this thread */ diff --git a/drivers/scsi/ufs/ti-j721e-ufs.c b/drivers/scsi/ufs/ti-j721e-ufs.c index 46bb905b4d6a..eafe0db98d54 100644 --- a/drivers/scsi/ufs/ti-j721e-ufs.c +++ b/drivers/scsi/ufs/ti-j721e-ufs.c @@ -38,6 +38,7 @@ static int ti_j721e_ufs_probe(struct platform_device *pdev) /* Select MPHY refclk frequency */ clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { + ret = PTR_ERR(clk); dev_err(dev, "Cannot claim MPHY clock.\n"); goto clk_err; } diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 29cd017c1aa0..1755dd6b04ae 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -212,7 +212,7 @@ static int ufs_mtk_wait_link_state(struct ufs_hba *hba, u32 state, ktime_t timeout, time_checked; u32 val; - timeout = ktime_add_us(ktime_get(), ms_to_ktime(max_wait_ms)); + timeout = ktime_add_ms(ktime_get(), max_wait_ms); do { time_checked = ktime_get(); ufshcd_writel(hba, 0x20, REG_UFS_DEBUG_SEL); diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f407b13883ac..5a95a7bfbab0 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -44,11 +44,23 @@ static int ufs_intel_link_startup_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_ehl_init(struct ufs_hba *hba) +{ + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + return 0; +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .link_startup_notify = ufs_intel_link_startup_notify, }; +static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_ehl_init, + .link_startup_notify = ufs_intel_link_startup_notify, +}; + #ifdef CONFIG_PM_SLEEP /** * ufshcd_pci_suspend - suspend power management function @@ -177,8 +189,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = { static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VENDOR_ID_SAMSUNG, 0xC00C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { PCI_VDEVICE(INTEL, 0x9DFA), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 307622284239..da199fa7a3e0 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1561,6 +1561,7 @@ unblock_reqs: int ufshcd_hold(struct ufs_hba *hba, bool async) { int rc = 0; + bool flush_result; unsigned long flags; if (!ufshcd_is_clkgating_allowed(hba)) @@ -1592,7 +1593,9 @@ start: break; } spin_unlock_irqrestore(hba->host->host_lock, flags); - flush_work(&hba->clk_gating.ungate_work); + flush_result = flush_work(&hba->clk_gating.ungate_work); + if (hba->clk_gating.is_suspended && !flush_result) + goto out; spin_lock_irqsave(hba->host->host_lock, flags); goto start; } @@ -5941,7 +5944,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) */ static irqreturn_t ufshcd_intr(int irq, void *__hba) { - u32 intr_status, enabled_intr_status; + u32 intr_status, enabled_intr_status = 0; irqreturn_t retval = IRQ_NONE; struct ufs_hba *hba = __hba; int retries = hba->nutrs; @@ -5955,7 +5958,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) * read, make sure we handle them by checking the interrupt status * again in a loop until we process all of the reqs before returning. */ - do { + while (intr_status && retries--) { enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); if (intr_status) @@ -5964,9 +5967,9 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) retval |= ufshcd_sl_intr(hba, enabled_intr_status); intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); - } while (intr_status && --retries); + } - if (retval == IRQ_NONE) { + if (enabled_intr_status && retval == IRQ_NONE) { dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n", __func__, intr_status); ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: "); @@ -6434,14 +6437,8 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } - if (!(reg & (1 << tag))) { - dev_err(hba->dev, - "%s: cmd was completed, but without a notifying intr, tag = %d", - __func__, tag); - } - /* Print Transfer Request of aborted task */ - dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); + dev_info(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); /* * Print detailed info about aborted request. @@ -6462,6 +6459,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) } hba->req_abort_count++; + if (!(reg & (1 << tag))) { + dev_err(hba->dev, + "%s: cmd was completed, but without a notifying intr, tag = %d", + __func__, tag); + goto cleanup; + } + /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { err = -EIO; @@ -6492,7 +6496,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) /* command completed already */ dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n", __func__, tag); - goto out; + goto cleanup; } else { dev_err(hba->dev, "%s: no response from device. tag = %d, err %d\n", @@ -6526,6 +6530,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } +cleanup: scsi_dma_unmap(cmd); spin_lock_irqsave(host->host_lock, flags); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index b2ef18f1b746..363589c0bd37 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -520,6 +520,12 @@ enum ufshcd_quirks { * OCS FATAL ERROR with device error through sense data */ UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR = 1 << 10, + + /* + * This quirk needs to be enabled if the host controller has + * auto-hibernate capability but it doesn't work. + */ + UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 = 1 << 11, }; enum ufshcd_caps { @@ -803,7 +809,8 @@ return true; static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba) { - return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT); + return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8); } static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba) diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index c3008e423f59..c6ea760ea5f0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -1017,4 +1017,7 @@ config SPI_SLAVE_SYSTEM_CONTROL endif # SPI_SLAVE +config SPI_DYNAMIC + def_bool ACPI || OF_DYNAMIC || SPI_SLAVE + endif # SPI diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 4c643dfc7fbb..d4b33b358a31 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -13,6 +13,7 @@ #include <linux/iopoll.h> #include <linux/module.h> #include <linux/of_platform.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/spi/spi.h> @@ -441,7 +442,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, { u32 div, mbrdiv; - div = DIV_ROUND_UP(spi->clk_rate, speed_hz); + /* Ensure spi->clk_rate is even */ + div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz); /* * SPI framework set xfer->speed_hz to master->max_speed_hz if @@ -467,20 +469,27 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, /** * stm32h7_spi_prepare_fthlv - Determine FIFO threshold level * @spi: pointer to the spi controller data structure + * @xfer_len: length of the message to be transferred */ -static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) +static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len) { - u32 fthlv, half_fifo; + u32 fthlv, half_fifo, packet; /* data packet should not exceed 1/2 of fifo space */ half_fifo = (spi->fifo_size / 2); + /* data_packet should not exceed transfer length */ + if (half_fifo > xfer_len) + packet = xfer_len; + else + packet = half_fifo; + if (spi->cur_bpw <= 8) - fthlv = half_fifo; + fthlv = packet; else if (spi->cur_bpw <= 16) - fthlv = half_fifo / 2; + fthlv = packet / 2; else - fthlv = half_fifo / 4; + fthlv = packet / 4; /* align packet size with data registers access */ if (spi->cur_bpw > 8) @@ -488,6 +497,9 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) else fthlv -= (fthlv % 4); /* multiple of 4 */ + if (!fthlv) + fthlv = 1; + return fthlv; } @@ -966,13 +978,13 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0))) stm32h7_spi_read_rxfifo(spi, false); - writel_relaxed(mask, spi->base + STM32H7_SPI_IFCR); + writel_relaxed(sr & mask, spi->base + STM32H7_SPI_IFCR); spin_unlock_irqrestore(&spi->lock, flags); if (end) { - spi_finalize_current_transfer(master); stm32h7_spi_disable(spi); + spi_finalize_current_transfer(master); } return IRQ_HANDLED; @@ -1393,7 +1405,7 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi) cfg1_setb |= (bpw << STM32H7_SPI_CFG1_DSIZE_SHIFT) & STM32H7_SPI_CFG1_DSIZE; - spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi); + spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi, spi->cur_xferlen); fthlv = spi->cur_fthlv - 1; cfg1_clrb |= STM32H7_SPI_CFG1_FTHLV; @@ -1585,39 +1597,33 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, unsigned long flags; unsigned int comm_type; int nb_words, ret = 0; + int mbr; spin_lock_irqsave(&spi->lock, flags); - if (spi->cur_bpw != transfer->bits_per_word) { - spi->cur_bpw = transfer->bits_per_word; - spi->cfg->set_bpw(spi); - } - - if (spi->cur_speed != transfer->speed_hz) { - int mbr; + spi->cur_xferlen = transfer->len; - /* Update spi->cur_speed with real clock speed */ - mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, - spi->cfg->baud_rate_div_min, - spi->cfg->baud_rate_div_max); - if (mbr < 0) { - ret = mbr; - goto out; - } + spi->cur_bpw = transfer->bits_per_word; + spi->cfg->set_bpw(spi); - transfer->speed_hz = spi->cur_speed; - stm32_spi_set_mbr(spi, mbr); + /* Update spi->cur_speed with real clock speed */ + mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, + spi->cfg->baud_rate_div_min, + spi->cfg->baud_rate_div_max); + if (mbr < 0) { + ret = mbr; + goto out; } + transfer->speed_hz = spi->cur_speed; + stm32_spi_set_mbr(spi, mbr); + comm_type = stm32_spi_communication_type(spi_dev, transfer); - if (spi->cur_comm != comm_type) { - ret = spi->cfg->set_mode(spi, comm_type); + ret = spi->cfg->set_mode(spi, comm_type); + if (ret < 0) + goto out; - if (ret < 0) - goto out; - - spi->cur_comm = comm_type; - } + spi->cur_comm = comm_type; if (spi->cfg->set_data_idleness) spi->cfg->set_data_idleness(spi, transfer->len); @@ -1635,8 +1641,6 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, goto out; } - spi->cur_xferlen = transfer->len; - dev_dbg(spi->dev, "transfer communication mode set to %d\n", spi->cur_comm); dev_dbg(spi->dev, @@ -1996,6 +2000,8 @@ static int stm32_spi_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); + pinctrl_pm_select_sleep_state(&pdev->dev); + return 0; } @@ -2007,13 +2013,18 @@ static int stm32_spi_runtime_suspend(struct device *dev) clk_disable_unprepare(spi->clk); - return 0; + return pinctrl_pm_select_sleep_state(dev); } static int stm32_spi_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct stm32_spi *spi = spi_master_get_devdata(master); + int ret; + + ret = pinctrl_pm_select_default_state(dev); + if (ret) + return ret; return clk_prepare_enable(spi->clk); } @@ -2043,10 +2054,23 @@ static int stm32_spi_resume(struct device *dev) return ret; ret = spi_master_resume(master); - if (ret) + if (ret) { clk_disable_unprepare(spi->clk); + return ret; + } - return ret; + ret = pm_runtime_get_sync(dev); + if (ret) { + dev_err(dev, "Unable to power device:%d\n", ret); + return ret; + } + + spi->cfg->config(spi); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; } #endif diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 6626587e77b4..dc12af018350 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -475,6 +475,12 @@ static LIST_HEAD(spi_controller_list); */ static DEFINE_MUTEX(board_lock); +/* + * Prevents addition of devices with same chip select and + * addition of devices below an unregistering controller. + */ +static DEFINE_MUTEX(spi_add_lock); + /** * spi_alloc_device - Allocate a new SPI device * @ctlr: Controller to which device is connected @@ -554,7 +560,6 @@ static int spi_dev_check(struct device *dev, void *data) */ int spi_add_device(struct spi_device *spi) { - static DEFINE_MUTEX(spi_add_lock); struct spi_controller *ctlr = spi->controller; struct device *dev = ctlr->dev.parent; int status; @@ -582,6 +587,13 @@ int spi_add_device(struct spi_device *spi) goto done; } + /* Controller may unregister concurrently */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC) && + !device_is_registered(&ctlr->dev)) { + status = -ENODEV; + goto done; + } + /* Descriptors take precedence */ if (ctlr->cs_gpiods) spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select]; @@ -2795,6 +2807,10 @@ void spi_unregister_controller(struct spi_controller *ctlr) struct spi_controller *found; int id = ctlr->bus_num; + /* Prevent addition of new devices, unregister existing ones */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_lock(&spi_add_lock); + device_for_each_child(&ctlr->dev, NULL, __unregister); /* First make sure that this controller was ever added */ @@ -2815,6 +2831,9 @@ void spi_unregister_controller(struct spi_controller *ctlr) if (found == ctlr) idr_remove(&spi_master_idr, id); mutex_unlock(&board_lock); + + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_unlock(&spi_add_lock); } EXPORT_SYMBOL_GPL(spi_unregister_controller); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 86a02aff8735..61ca8ab165dc 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -33,12 +33,14 @@ struct vfio_pci_ioeventfd { struct list_head next; + struct vfio_pci_device *vdev; struct virqfd *virqfd; void __iomem *addr; uint64_t data; loff_t pos; int bar; int count; + bool test_mem; }; struct vfio_pci_irq_ctx { diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 916b184df3a5..9e353c484ace 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -37,17 +37,70 @@ #define vfio_ioread8 ioread8 #define vfio_iowrite8 iowrite8 +#define VFIO_IOWRITE(size) \ +static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + vfio_iowrite##size(val, io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOWRITE(8) +VFIO_IOWRITE(16) +VFIO_IOWRITE(32) +#ifdef iowrite64 +VFIO_IOWRITE(64) +#endif + +#define VFIO_IOREAD(size) \ +static int vfio_pci_ioread##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + *val = vfio_ioread##size(io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOREAD(8) +VFIO_IOREAD(16) +VFIO_IOREAD(32) + /* * Read or write from an __iomem region (MMIO or I/O port) with an excluded * range which is inaccessible. The excluded range drops writes and fills * reads with -1. This is intended for handling MSI-X vector tables and * leftover space for ROM BARs. */ -static ssize_t do_io_rw(void __iomem *io, char __user *buf, +static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, size_t x_end, bool iswrite) { ssize_t done = 0; + int ret; while (count) { size_t fillable, filled; @@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 4)) return -EFAULT; - vfio_iowrite32(val, io + off); + ret = vfio_pci_iowrite32(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread32(io + off); + ret = vfio_pci_ioread32(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 4)) return -EFAULT; @@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 2)) return -EFAULT; - vfio_iowrite16(val, io + off); + ret = vfio_pci_iowrite16(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread16(io + off); + ret = vfio_pci_ioread16(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 2)) return -EFAULT; @@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 1)) return -EFAULT; - vfio_iowrite8(val, io + off); + ret = vfio_pci_iowrite8(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread8(io + off); + ret = vfio_pci_ioread8(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 1)) return -EFAULT; @@ -178,14 +249,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, count = min(count, (size_t)(end - pos)); - if (res->flags & IORESOURCE_MEM) { - down_read(&vdev->memory_lock); - if (!__vfio_pci_memory_enabled(vdev)) { - up_read(&vdev->memory_lock); - return -EIO; - } - } - if (bar == PCI_ROM_RESOURCE) { /* * The ROM can fill less space than the BAR, so we start the @@ -213,7 +276,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, x_end = vdev->msix_offset + vdev->msix_size; } - done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite); + done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); if (done >= 0) *ppos += done; @@ -221,9 +285,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, if (bar == PCI_ROM_RESOURCE) pci_unmap_rom(pdev, io); out: - if (res->flags & IORESOURCE_MEM) - up_read(&vdev->memory_lock); - return done; } @@ -278,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, return ret; } - done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite); + /* + * VGA MMIO is a legacy, non-BAR resource that hopefully allows + * probing, so we don't currently worry about access in relation + * to the memory enable bit in the command register. + */ + done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); vga_put(vdev->pdev, rsrc); @@ -296,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) switch (ioeventfd->count) { case 1: - vfio_iowrite8(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_iowrite16(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_iowrite32(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_iowrite64(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #endif } @@ -378,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, goto out_unlock; } + ioeventfd->vdev = vdev; ioeventfd->addr = vdev->barmap[bar] + pos; ioeventfd->data = data; ioeventfd->pos = pos; ioeventfd->bar = bar; ioeventfd->count = count; + ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, NULL, NULL, &ioeventfd->virqfd, fd); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6990fc711a80..c992973cc2d5 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1424,13 +1424,16 @@ static int vfio_bus_type(struct device *dev, void *data) static int vfio_iommu_replay(struct vfio_iommu *iommu, struct vfio_domain *domain) { - struct vfio_domain *d; + struct vfio_domain *d = NULL; struct rb_node *n; unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; int ret; /* Arbitrarily pick the first domain in the list for lookups */ - d = list_first_entry(&iommu->domain_list, struct vfio_domain, next); + if (!list_empty(&iommu->domain_list)) + d = list_first_entry(&iommu->domain_list, + struct vfio_domain, next); + n = rb_first(&iommu->dma_list); for (; n; n = rb_next(n)) { @@ -1448,6 +1451,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, phys_addr_t p; dma_addr_t i; + if (WARN_ON(!d)) { /* mapped w/o a domain?! */ + ret = -EINVAL; + goto unwind; + } + phys = iommu_iova_to_phys(d->domain, iova); if (WARN_ON(!phys)) { @@ -1477,7 +1485,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, if (npage <= 0) { WARN_ON(!npage); ret = (int)npage; - return ret; + goto unwind; } phys = pfn << PAGE_SHIFT; @@ -1486,14 +1494,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, ret = iommu_map(domain->domain, iova, phys, size, dma->prot | domain->prot); - if (ret) - return ret; + if (ret) { + if (!dma->iommu_mapped) + vfio_unpin_pages_remote(dma, iova, + phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, + true); + goto unwind; + } iova += size; } + } + + /* All dmas are now mapped, defer to second tree walk for unwind */ + for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma->iommu_mapped = true; } + return 0; + +unwind: + for (; n; n = rb_prev(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma_addr_t iova; + + if (dma->iommu_mapped) { + iommu_unmap(domain->domain, dma->iova, dma->size); + continue; + } + + iova = dma->iova; + while (iova < dma->iova + dma->size) { + phys_addr_t phys, p; + size_t size; + dma_addr_t i; + + phys = iommu_iova_to_phys(domain->domain, iova); + if (!phys) { + iova += PAGE_SIZE; + continue; + } + + size = PAGE_SIZE; + p = phys + size; + i = iova + size; + while (i < dma->iova + dma->size && + p == iommu_iova_to_phys(domain->domain, i)) { + size += PAGE_SIZE; + p += PAGE_SIZE; + i += PAGE_SIZE; + } + + iommu_unmap(domain->domain, iova, size); + vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, true); + } + } + + return ret; } /* diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 65491ae74808..e57c00824965 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -453,7 +453,7 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - if (efi_enabled(EFI_BOOT) && + if (efi_enabled(EFI_MEMMAP) && !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) { if ((efifb_fix.smem_start + efifb_fix.smem_len) > (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) { diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index b79879aacc02..7b784af604fd 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -382,15 +382,17 @@ void afs_dynroot_depopulate(struct super_block *sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); - inode_lock(root->d_inode); - - /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { - if (subdir->d_fsdata) { - subdir->d_fsdata = NULL; - dput(subdir); + if (root) { + inode_lock(root->d_inode); + + /* Remove all the pins for dirs created for manually added cells */ + list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + if (subdir->d_fsdata) { + subdir->d_fsdata = NULL; + dput(subdir); + } } - } - inode_unlock(root->d_inode); + inode_unlock(root->d_inode); + } } diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 24fd163c6323..97cab12b0a6c 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -235,6 +235,7 @@ int afs_put_operation(struct afs_operation *op) afs_end_cursor(&op->ac); afs_put_serverlist(op->net, op->server_list); afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op); + key_put(op->key); kfree(op); return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 061dd202979d..d468ed9981e0 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3157,6 +3157,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 12eebcdea9c8..e0decff22ae2 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1994,9 +1994,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) * not already there, and calling reverse_path_check() * during ep_insert(). */ - if (list_empty(&epi->ffd.file->f_tfile_llink)) + if (list_empty(&epi->ffd.file->f_tfile_llink)) { + get_file(epi->ffd.file); list_add(&epi->ffd.file->f_tfile_llink, &tfile_check_list); + } } } mutex_unlock(&ep->mtx); @@ -2040,6 +2042,7 @@ static void clear_tfile_check_list(void) file = list_first_entry(&tfile_check_list, struct file, f_tfile_llink); list_del_init(&file->f_tfile_llink); + fput(file); } INIT_LIST_HEAD(&tfile_check_list); } @@ -2200,25 +2203,22 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; - if (ep_loop_check(ep, tf.file) != 0) { - clear_tfile_check_list(); + if (ep_loop_check(ep, tf.file) != 0) goto error_tgt_fput; - } - } else + } else { + get_file(tf.file); list_add(&tf.file->f_tfile_llink, &tfile_check_list); + } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); - if (error) { -out_del: - list_del(&tf.file->f_tfile_llink); + if (error) goto error_tgt_fput; - } if (is_file_epoll(tf.file)) { tep = tf.file->private_data; error = epoll_mutex_lock(&tep->mtx, 1, nonblock); if (error) { mutex_unlock(&ep->mtx); - goto out_del; + goto error_tgt_fput; } } } @@ -2239,8 +2239,6 @@ out_del: error = ep_insert(ep, epds, tf.file, fd, full_check); } else error = -EEXIST; - if (full_check) - clear_tfile_check_list(); break; case EPOLL_CTL_DEL: if (epi) @@ -2263,8 +2261,10 @@ out_del: mutex_unlock(&ep->mtx); error_tgt_fput: - if (full_check) + if (full_check) { + clear_tfile_check_list(); mutex_unlock(&epmutex); + } fdput(tf); error_fput: diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 1afa5a4bcb5f..619dd35ddd48 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -110,7 +110,7 @@ config EXT4_KUNIT_TESTS This builds the ext4 KUnit tests. KUnit tests run during boot and output the results to the debug log - in TAP format (http://testanything.org/). Only useful for kernel devs + in TAP format (https://testanything.org/). Only useful for kernel devs running KUnit test harness and are not for inclusion into a production build. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1ba46d87cdf1..48c3df47748d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -413,7 +413,8 @@ verified: * Return buffer_head on success or an ERR_PTR in case of failure. */ struct buffer_head * -ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) +ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, + bool ignore_locked) { struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -441,6 +442,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) return ERR_PTR(-ENOMEM); } + if (ignore_locked && buffer_locked(bh)) { + /* buffer under IO already, return if called for prefetching */ + put_bh(bh); + return NULL; + } + if (bitmap_uptodate(bh)) goto verify; @@ -487,10 +494,11 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) * submit the buffer_head for reading */ set_buffer_new(bh); - trace_ext4_read_block_bitmap_load(sb, block_group); + trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); + submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO | + (ignore_locked ? REQ_RAHEAD : 0), bh); return bh; verify: err = ext4_validate_block_bitmap(sb, desc, block_group, bh); @@ -534,7 +542,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) struct buffer_head *bh; int err; - bh = ext4_read_block_bitmap_nowait(sb, block_group); + bh = ext4_read_block_bitmap_nowait(sb, block_group, false); if (IS_ERR(bh)) return bh; err = ext4_wait_block_bitmap(sb, block_group, bh); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 16e9b2fda03a..c54ba52f2dd4 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -24,6 +24,7 @@ struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; + u32 ino; }; static struct kmem_cache *ext4_system_zone_cachep; @@ -45,7 +46,8 @@ void ext4_exit_system_zone(void) static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { - if ((entry1->start_blk + entry1->count) == entry2->start_blk) + if ((entry1->start_blk + entry1->count) == entry2->start_blk && + entry1->ino == entry2->ino) return 1; return 0; } @@ -66,9 +68,9 @@ static void release_system_zone(struct ext4_system_blocks *system_blks) */ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, u32 ino) { - struct ext4_system_zone *new_entry = NULL, *entry; + struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node = NULL; @@ -79,30 +81,21 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, n = &(*n)->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = &(*n)->rb_right; - else { - if (start_blk + count > (entry->start_blk + - entry->count)) - entry->count = (start_blk + count - - entry->start_blk); - new_node = *n; - new_entry = rb_entry(new_node, struct ext4_system_zone, - node); - break; - } + else /* Unexpected overlap of system zones. */ + return -EFSCORRUPTED; } - if (!new_entry) { - new_entry = kmem_cache_alloc(ext4_system_zone_cachep, - GFP_KERNEL); - if (!new_entry) - return -ENOMEM; - new_entry->start_blk = start_blk; - new_entry->count = count; - new_node = &new_entry->node; - - rb_link_node(new_node, parent, n); - rb_insert_color(new_node, &system_blks->root); - } + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_entry->ino = ino; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &system_blks->root); /* Can we merge to the left? */ node = rb_prev(new_node); @@ -151,40 +144,6 @@ static void debug_print_tree(struct ext4_sb_info *sbi) printk(KERN_CONT "\n"); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with filesystem metadata blocks. - */ -static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, - struct ext4_system_blocks *system_blks, - ext4_fsblk_t start_blk, - unsigned int count) -{ - struct ext4_system_zone *entry; - struct rb_node *n; - - if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || - (start_blk + count < start_blk) || - (start_blk + count > ext4_blocks_count(sbi->s_es))) - return 0; - - if (system_blks == NULL) - return 1; - - n = system_blks->root.rb_node; - while (n) { - entry = rb_entry(n, struct ext4_system_zone, node); - if (start_blk + count - 1 < entry->start_blk) - n = n->rb_left; - else if (start_blk >= (entry->start_blk + entry->count)) - n = n->rb_right; - else - return 0; - } - return 1; -} - static int ext4_protect_reserved_inode(struct super_block *sb, struct ext4_system_blocks *system_blks, u32 ino) @@ -214,19 +173,18 @@ static int ext4_protect_reserved_inode(struct super_block *sb, if (n == 0) { i++; } else { - if (!ext4_data_block_valid_rcu(sbi, system_blks, - map.m_pblk, n)) { - err = -EFSCORRUPTED; - __ext4_error(sb, __func__, __LINE__, -err, - map.m_pblk, "blocks %llu-%llu " - "from inode %u overlap system zone", - map.m_pblk, - map.m_pblk + map.m_len - 1, ino); + err = add_system_zone(system_blks, map.m_pblk, n, ino); + if (err < 0) { + if (err == -EFSCORRUPTED) { + __ext4_error(sb, __func__, __LINE__, + -err, map.m_pblk, + "blocks %llu-%llu from inode %u overlap system zone", + map.m_pblk, + map.m_pblk + map.m_len - 1, + ino); + } break; } - err = add_system_zone(system_blks, map.m_pblk, n); - if (err < 0) - break; i += n; } } @@ -262,14 +220,6 @@ int ext4_setup_system_zone(struct super_block *sb) int flex_size = ext4_flex_bg_size(sbi); int ret; - if (!test_opt(sb, BLOCK_VALIDITY)) { - if (sbi->system_blks) - ext4_release_system_zone(sb); - return 0; - } - if (sbi->system_blks) - return 0; - system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); if (!system_blks) return -ENOMEM; @@ -277,22 +227,25 @@ int ext4_setup_system_zone(struct super_block *sb) for (i=0; i < ngroups; i++) { cond_resched(); if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(system_blks, + ((i < 5) || ((i % flex_size) == 0))) { + ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1); + ext4_bg_num_gdb(sb, i) + 1, 0); + if (ret) + goto err; + } gdp = ext4_get_group_desc(sb, i, NULL); ret = add_system_zone(system_blks, - ext4_block_bitmap(sb, gdp), 1); + ext4_block_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, - ext4_inode_bitmap(sb, gdp), 1); + ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group); + sbi->s_itb_per_group, 0); if (ret) goto err; } @@ -341,11 +294,24 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_system_blocks *system_blks; - int ret; + struct ext4_system_zone *entry; + struct rb_node *n; + int ret = 1; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count < start_blk) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; /* * Lock the system zone to prevent it being released concurrently @@ -354,8 +320,22 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, */ rcu_read_lock(); system_blks = rcu_dereference(sbi->system_blks); - ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk, - count); + if (system_blks == NULL) + goto out_rcu; + + n = system_blks->root.rb_node; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else { + ret = (entry->ino == inode->i_ino); + break; + } + } +out_rcu: rcu_read_unlock(); return ret; } @@ -374,8 +354,7 @@ int ext4_check_blockref(const char *function, unsigned int line, while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { + unlikely(!ext4_inode_block_valid(inode, blk, 1))) { ext4_error_inode(inode, function, line, blk, "invalid block"); return -EFSCORRUPTED; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 42f5060f3cdf..523e00d7b392 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -434,10 +434,36 @@ struct flex_groups { #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x725BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x624BC0FF /* User modifiable flags */ - -/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ +/* User modifiable flags */ +#define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \ + EXT4_UNRM_FL | \ + EXT4_COMPR_FL | \ + EXT4_SYNC_FL | \ + EXT4_IMMUTABLE_FL | \ + EXT4_APPEND_FL | \ + EXT4_NODUMP_FL | \ + EXT4_NOATIME_FL | \ + EXT4_JOURNAL_DATA_FL | \ + EXT4_NOTAIL_FL | \ + EXT4_DIRSYNC_FL | \ + EXT4_TOPDIR_FL | \ + EXT4_EXTENTS_FL | \ + 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \ + EXT4_DAX_FL | \ + EXT4_PROJINHERIT_FL | \ + EXT4_CASEFOLD_FL) + +/* User visible flags */ +#define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \ + EXT4_DIRTY_FL | \ + EXT4_COMPRBLK_FL | \ + EXT4_NOCOMPR_FL | \ + EXT4_ENCRYPT_FL | \ + EXT4_INDEX_FL | \ + EXT4_VERITY_FL | \ + EXT4_INLINE_DATA_FL) + +/* Flags we can manipulate with through FS_IOC_FSSETXATTR */ #define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ EXT4_IMMUTABLE_FL | \ EXT4_APPEND_FL | \ @@ -669,8 +695,6 @@ enum { /* * ioctl commands */ -#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS -#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT4_IOC_GETVERSION _IOR('f', 3, long) #define EXT4_IOC_SETVERSION _IOW('f', 4, long) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION @@ -687,17 +711,11 @@ enum { #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) #define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) -#define EXT4_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY -#define EXT4_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT -#define EXT4_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY /* ioctl codes 19--39 are reserved for fscrypt */ #define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40) #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) -#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR -#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR - #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) /* @@ -722,8 +740,6 @@ enum { /* * ioctl commands in 32 bit emulation */ -#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) @@ -1054,6 +1070,7 @@ struct ext4_inode_info { struct timespec64 i_crtime; /* mballoc */ + atomic_t i_prealloc_active; struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; @@ -1172,6 +1189,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ +#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ @@ -1501,10 +1519,13 @@ struct ext4_sb_info { unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; + unsigned int s_mb_max_inode_prealloc; unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; + unsigned int s_mb_prefetch; + unsigned int s_mb_prefetch_limit; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ @@ -1572,6 +1593,8 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + atomic_t s_warning_count; + atomic_t s_msg_count; /* Encryption context for '-o test_dummy_encryption' */ struct fscrypt_dummy_context s_dummy_enc_ctx; @@ -1585,6 +1608,9 @@ struct ext4_sb_info { #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif + /* Record the errseq of the backing block device */ + errseq_t s_bdev_wb_err; + spinlock_t s_bdev_wb_lock; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -2313,9 +2339,15 @@ struct ext4_lazy_init { struct mutex li_list_mtx; }; +enum ext4_li_mode { + EXT4_LI_MODE_PREFETCH_BBITMAP, + EXT4_LI_MODE_ITABLE, +}; + struct ext4_li_request { struct super_block *lr_super; - struct ext4_sb_info *lr_sbi; + enum ext4_li_mode lr_mode; + ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; @@ -2446,7 +2478,8 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, - ext4_group_t block_group); + ext4_group_t block_group, + bool ignore_locked); extern int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh); @@ -2651,9 +2684,15 @@ extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern int ext4_mb_reserve_blocks(struct super_block *, int); -extern void ext4_discard_preallocations(struct inode *); +extern void ext4_discard_preallocations(struct inode *, unsigned int); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); +extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, + ext4_group_t group, + unsigned int nr, int *cnt); +extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr); + extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); @@ -2765,8 +2804,7 @@ extern int ext4_search_dir(struct buffer_head *bh, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir); -extern int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +extern int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2924,12 +2962,6 @@ do { \ #endif -extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, - __u32 compat); -extern int ext4_update_rocompat_feature(handle_t *handle, - struct super_block *sb, __u32 rocompat); -extern int ext4_update_incompat_feature(handle_t *handle, - struct super_block *sb, __u32 incompat); extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -3145,6 +3177,7 @@ struct ext4_group_info { (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) +#define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) @@ -3159,6 +3192,8 @@ struct ext4_group_info { (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \ + (test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 @@ -3363,9 +3398,9 @@ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +extern int ext4_inode_block_valid(struct inode *inode, + ext4_fsblk_t start_blk, + unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 0c76cdd44d90..760b9ee49dc0 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -195,6 +195,28 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line, jbd2_journal_abort_handle(handle); } +static void ext4_check_bdev_write_error(struct super_block *sb) +{ + struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + /* + * If the block device has write error flag, it may have failed to + * async write out metadata buffers in the background. In this case, + * we could read old data from disk and write it out again, which + * may lead to on-disk filesystem inconsistency. + */ + if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) { + spin_lock(&sbi->s_bdev_wb_lock); + err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err); + spin_unlock(&sbi->s_bdev_wb_lock); + if (err) + ext4_error_err(sb, -err, + "Error while async write back metadata"); + } +} + int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct buffer_head *bh) { @@ -202,6 +224,9 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, might_sleep(); + if (bh->b_bdev->bd_super) + ext4_check_bdev_write_error(bh->b_bdev->bd_super); + if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 221f240eae60..a0481582187a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -340,7 +340,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, @@ -348,7 +348,7 @@ static int ext4_valid_extent_idx(struct inode *inode, { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, @@ -507,14 +507,10 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - if (!ext4_has_feature_journal(inode->i_sb) || - (inode->i_ino != - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; - } + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries @@ -693,10 +689,8 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) { - if (path->p_bh) { - brelse(path->p_bh); - path->p_bh = NULL; - } + brelse(path->p_bh); + path->p_bh = NULL; } } @@ -1915,7 +1909,7 @@ out: /* * ext4_ext_insert_extent: - * tries to merge requsted extent into the existing extent or + * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ @@ -3125,7 +3119,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states - * of which are deterimined by split_flag. + * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. @@ -3650,7 +3644,7 @@ static int ext4_split_convert_extents(handle_t *handle, eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit - * zeroout only if extent is fully insde i_size or new_size. + * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; @@ -4272,7 +4266,7 @@ got_allocated_blocks: * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, @@ -4495,7 +4489,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Round up offset. This is not fallocate, we neet to zero out + * Round up offset. This is not fallocate, we need to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the * range. @@ -5299,7 +5293,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) } down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); @@ -5313,7 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); @@ -5445,7 +5439,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { @@ -5579,7 +5573,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; - /* Do we have somthing to swap ? */ + /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto finish; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 129cc1dd6b79..7d61069531d3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -145,10 +145,9 @@ static int ext4_release_file(struct inode *inode, struct file *filp) /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) && (atomic_read(&inode->i_writecount) == 1) && - !EXT4_I(inode)->i_reserved_data_blocks) - { + !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); } if (is_dx(inode) && filp->private_data) @@ -428,6 +427,10 @@ restart: */ if (*ilock_shared && (!IS_NOSEC(inode) || *extend || !ext4_overwrite_io(inode, offset, count))) { + if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } inode_unlock_shared(inode); *ilock_shared = false; inode_lock(inode); @@ -812,7 +815,7 @@ out: return err; } -static int ext4_file_open(struct inode * inode, struct file * filp) +static int ext4_file_open(struct inode *inode, struct file *filp) { int ret; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 3e133793a5a3..2924261226e0 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -233,7 +233,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_HALF_MD4_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_HALF_MD4: p = name; while (len > 0) { @@ -247,7 +247,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_TEA_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_TEA: p = name; while (len > 0) { diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index be2b66eb65f7..80c9f33800be 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -858,8 +858,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { + if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); @@ -1004,8 +1003,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, if (!nr) continue; /* A hole */ - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { + if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", @@ -1182,21 +1180,21 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } @@ -1436,7 +1434,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: if (++n >= n2) break; @@ -1445,7 +1443,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: if (++n >= n2) break; @@ -1454,7 +1452,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c3a1ad2db122..75c97bca0815 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -276,7 +276,7 @@ static int ext4_create_inline_data(handle_t *handle, len = 0; } - /* Insert the the xttr entry. */ + /* Insert the xttr entry. */ i.value = value; i.value_len = len; @@ -1706,7 +1706,7 @@ int ext4_delete_inline_entry(handle_t *handle, if (err) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, bh, + err = ext4_generic_delete_entry(dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 44bad4bb8831..3a196d81f594 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -383,7 +383,7 @@ void ext4_da_update_reserve_space(struct inode *inode, */ if ((ei->i_reserved_data_blocks == 0) && !inode_is_open_for_write(inode)) - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); } static int __check_block_validity(struct inode *inode, const char *func, @@ -394,8 +394,7 @@ static int __check_block_validity(struct inode *inode, const char *func, (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, @@ -3288,7 +3287,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) if (PageChecked(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, wait); + return jbd2_journal_try_to_free_buffers(journal, page); else return try_to_free_buffers(page); } @@ -4056,7 +4055,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (stop_block > first_block) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, first_block, stop_block - first_block); @@ -4163,7 +4162,7 @@ int ext4_truncate(struct inode *inode) trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return 0; + goto out_trace; if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); @@ -4172,16 +4171,14 @@ int ext4_truncate(struct inode *inode) int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); - if (err) - return err; - if (has_inline) - return 0; + if (err || has_inline) + goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { if (ext4_inode_attach_jinode(inode) < 0) - return 0; + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) @@ -4190,8 +4187,10 @@ int ext4_truncate(struct inode *inode) credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_trace; + } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); @@ -4211,7 +4210,7 @@ int ext4_truncate(struct inode *inode) down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); @@ -4242,6 +4241,7 @@ out_stop: err = err2; ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); return err; } @@ -4760,7 +4760,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 999cf6add39c..36eca3bc036a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -202,7 +202,7 @@ static long swap_inode_boot_loader(struct super_block *sb, reset_inode_seed(inode); reset_inode_seed(inode_bl); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { @@ -819,12 +819,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); - case EXT4_IOC_GETFLAGS: + case FS_IOC_GETFLAGS: flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~EXT4_PROJINHERIT_FL; return put_user(flags, (int __user *) arg); - case EXT4_IOC_SETFLAGS: { + case FS_IOC_SETFLAGS: { int err; if (!inode_owner_or_capable(inode)) @@ -1129,12 +1129,12 @@ resizefs_out: case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); - case EXT4_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); - case EXT4_IOC_GET_ENCRYPTION_PWSALT: { + case FS_IOC_GET_ENCRYPTION_PWSALT: { #ifdef CONFIG_FS_ENCRYPTION int err, err2; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1174,7 +1174,7 @@ resizefs_out: return -EOPNOTSUPP; #endif } - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); @@ -1236,7 +1236,7 @@ resizefs_out: case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); - case EXT4_IOC_FSGETXATTR: + case FS_IOC_FSGETXATTR: { struct fsxattr fa; @@ -1247,7 +1247,7 @@ resizefs_out: return -EFAULT; return 0; } - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSSETXATTR: { struct fsxattr fa, old_fa; int err; @@ -1313,11 +1313,11 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { - case EXT4_IOC32_GETFLAGS: - cmd = EXT4_IOC_GETFLAGS; + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; break; - case EXT4_IOC32_SETFLAGS: - cmd = EXT4_IOC_SETFLAGS; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; break; case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; @@ -1361,9 +1361,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: - case EXT4_IOC_SET_ENCRYPTION_POLICY: - case EXT4_IOC_GET_ENCRYPTION_PWSALT: - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: @@ -1377,8 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: - case EXT4_IOC_FSGETXATTR: - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSGETXATTR: + case FS_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c0a331e2feb0..132c118d12e1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -922,7 +922,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) bh[i] = NULL; continue; } - bh[i] = ext4_read_block_bitmap_nowait(sb, group); + bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; @@ -1279,9 +1279,6 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - BUG_ON(e4b->bd_bitmap_page == NULL); - BUG_ON(e4b->bd_buddy_page == NULL); - return 0; err: @@ -1743,10 +1740,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, } -/* - * regular allocator, for general purposes allocation - */ - static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) @@ -2119,13 +2112,11 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - free = grp->bb_free; - if (free == 0) - return false; - if (cr <= 2 && free < ac->ac_g_ex.fe_len) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + free = grp->bb_free; + if (free == 0) return false; fragments = grp->bb_fragments; @@ -2142,8 +2133,10 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ((group % flex_size) == 0)) return false; - if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) || - (free / fragments) >= ac->ac_g_ex.fe_len) + if (free < ac->ac_g_ex.fe_len) + return false; + + if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) return true; if (grp->bb_largest_free_order < ac->ac_2order) @@ -2177,6 +2170,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; @@ -2195,7 +2189,25 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); + struct ext4_group_desc *gdp = + ext4_get_group_desc(sb, group, NULL); + int ret; + + /* cr=0/1 is a very optimistic search to find large + * good chunks almost for free. If buddy data is not + * ready, then this optimization makes no sense. But + * we never skip the first block group in a flex_bg, + * since this gets used for metadata block allocation, + * and we want to make sure we locate metadata blocks + * in the first block group in the flex_bg if possible. + */ + if (cr < 2 && + (!sbi->s_log_groups_per_flex || + ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) + return 0; + ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } @@ -2209,15 +2221,95 @@ out: return ret; } +/* + * Start prefetching @nr block bitmaps starting at @group. + * Return the next group which needs to be prefetched. + */ +ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, + unsigned int nr, int *cnt) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct buffer_head *bh; + struct blk_plug plug; + + blk_start_plug(&plug); + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + /* + * Prefetch block groups with free blocks; but don't + * bother if it is marked uninitialized on disk, since + * it won't require I/O to read. Also only try to + * prefetch once, so we avoid getblk() call, which can + * be expensive. + */ + if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + bh = ext4_read_block_bitmap_nowait(sb, group, true); + if (bh && !IS_ERR(bh)) { + if (!buffer_uptodate(bh) && cnt) + (*cnt)++; + brelse(bh); + } + } + if (++group >= ngroups) + group = 0; + } + blk_finish_plug(&plug); + return group; +} + +/* + * Prefetching reads the block bitmap into the buffer cache; but we + * need to make sure that the buddy bitmap in the page cache has been + * initialized. Note that ext4_mb_init_group() will block if the I/O + * is not yet completed, or indeed if it was not initiated by + * ext4_mb_prefetch did not start the I/O. + * + * TODO: We should actually kick off the buddy bitmap setup in a work + * queue when the buffer I/O is completed, so that we don't block + * waiting for the block allocation bitmap read to finish when + * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). + */ +void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr) +{ + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + if (!group) + group = ext4_get_groups_count(sb); + group--; + grp = ext4_get_group_info(sb, group); + + if (EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + if (ext4_mb_init_group(sb, group, GFP_NOFS)) + break; + } + } +} + static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { - ext4_group_t ngroups, group, i; + ext4_group_t prefetch_grp = 0, ngroups, group, i; int cr = -1; int err = 0, first_err = 0; + unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; + int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); @@ -2237,8 +2329,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) goto out; /* - * ac->ac2_order is set only if the fe_len is a power of 2 - * if ac2_order is set we also set criteria to 0 so that we + * ac->ac_2order is set only if the fe_len is a power of 2 + * if ac->ac_2order is set we also set criteria to 0 so that we * try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); @@ -2282,6 +2374,7 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; + prefetch_grp = group; for (i = 0; i < ngroups; group++, i++) { int ret = 0; @@ -2293,6 +2386,29 @@ repeat: if (group >= ngroups) group = 0; + /* + * Batch reads of the block allocation bitmaps + * to get multiple READs in flight; limit + * prefetching at cr=0/1, otherwise mballoc can + * spend a lot of time loading imperfect groups + */ + if ((prefetch_grp == group) && + (cr > 1 || + prefetch_ios < sbi->s_mb_prefetch_limit)) { + unsigned int curr_ios = prefetch_ios; + + nr = sbi->s_mb_prefetch; + if (ext4_has_feature_flex_bg(sb)) { + nr = (group / sbi->s_mb_prefetch) * + sbi->s_mb_prefetch; + nr = nr + sbi->s_mb_prefetch - group; + } + prefetch_grp = ext4_mb_prefetch(sb, group, + nr, &prefetch_ios); + if (prefetch_ios == curr_ios) + nr = 0; + } + /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { @@ -2341,22 +2457,24 @@ repeat: * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ - ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) - printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n"); */ + lost = atomic_inc_return(&sbi->s_mb_lost_chunks); + mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", + ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len, lost); + ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = 3; - atomic_inc(&sbi->s_mb_lost_chunks); goto repeat; } } @@ -2367,6 +2485,10 @@ out: mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); + + if (nr) + ext4_mb_prefetch_fini(sb, prefetch_grp, nr); + return err; } @@ -2439,7 +2561,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_printf(seq, " ]\n"); + seq_puts(seq, " ]\n"); return 0; } @@ -2613,6 +2735,26 @@ static int ext4_mb_init_backend(struct super_block *sb) goto err_freebuddy; } + if (ext4_has_feature_flex_bg(sb)) { + /* a single flex group is supposed to be read by a single IO */ + sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex; + sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ + } else { + sbi->s_mb_prefetch = 32; + } + if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch = ext4_get_groups_count(sb); + /* now many real IOs to prefetch within a single allocation at cr=0 + * given cr=0 is an CPU-related optimization we shouldn't try to + * load too many groups, at some point we should start to use what + * we've got in memory. + * with an average random access time 5ms, it'd take a second to get + * 200 groups (* N with flex_bg), so let's make this limit 4 + */ + sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; + if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); + return 0; err_freebuddy: @@ -2736,6 +2878,7 @@ int ext4_mb_init(struct super_block *sb) sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; + sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file @@ -3090,7 +3233,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (!ext4_data_block_valid(sbi, block, len)) { + if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error @@ -3674,6 +3817,26 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } +static void ext4_mb_mark_pa_deleted(struct super_block *sb, + struct ext4_prealloc_space *pa) +{ + struct ext4_inode_info *ei; + + if (pa->pa_deleted) { + ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", + pa->pa_type, pa->pa_pstart, pa->pa_lstart, + pa->pa_len); + return; + } + + pa->pa_deleted = 1; + + if (pa->pa_type == MB_INODE_PA) { + ei = EXT4_I(pa->pa_inode); + atomic_dec(&ei->i_prealloc_active); + } +} + static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; @@ -3706,7 +3869,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, return; } - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; @@ -3830,6 +3993,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); + atomic_inc(&ei->i_prealloc_active); } /* @@ -4040,7 +4204,7 @@ repeat: } /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); /* we can trust pa_free ... */ free += pa->pa_free; @@ -4103,7 +4267,7 @@ out_dbg: * * FIXME!! Make sure it is valid at all the call sites */ -void ext4_discard_preallocations(struct inode *inode) +void ext4_discard_preallocations(struct inode *inode, unsigned int needed) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; @@ -4121,15 +4285,19 @@ void ext4_discard_preallocations(struct inode *inode) mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); - trace_ext4_discard_preallocations(inode); + trace_ext4_discard_preallocations(inode, + atomic_read(&ei->i_prealloc_active), needed); INIT_LIST_HEAD(&list); + if (needed == 0) + needed = UINT_MAX; + repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); - while (!list_empty(&ei->i_prealloc_list)) { - pa = list_entry(ei->i_prealloc_list.next, + while (!list_empty(&ei->i_prealloc_list) && needed) { + pa = list_entry(ei->i_prealloc_list.prev, struct ext4_prealloc_space, pa_inode_list); BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); @@ -4146,10 +4314,11 @@ repeat: } if (pa->pa_deleted == 0) { - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &list); + needed--; continue; } @@ -4399,7 +4568,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ac->ac_g_ex = ac->ac_o_ex; ac->ac_flags = ar->flags; - /* we have to define context: we'll we work with a file or + /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); @@ -4450,7 +4619,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); @@ -4549,10 +4718,29 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) } /* + * if per-inode prealloc list is too long, trim some PA + */ +static void ext4_mb_trim_inode_pa(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int count, delta; + + count = atomic_read(&ei->i_prealloc_active); + delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1; + if (count > sbi->s_mb_max_inode_prealloc + delta) { + count -= sbi->s_mb_max_inode_prealloc; + ext4_discard_preallocations(inode, count); + } +} + +/* * release all resource we used in allocation */ static int ext4_mb_release_context(struct ext4_allocation_context *ac) { + struct inode *inode = ac->ac_inode; + struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { @@ -4564,21 +4752,31 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); + + /* + * We want to add the pa to the right bucket. + * Remove it from the list and while adding + * make sure the list to which we are adding + * doesn't grow big. + */ + if (likely(pa->pa_free)) { + spin_lock(pa->pa_obj_lock); + list_del_rcu(&pa->pa_inode_list); + spin_unlock(pa->pa_obj_lock); + ext4_mb_add_n_trim(ac); + } } - } - if (pa) { - /* - * We want to add the pa to the right bucket. - * Remove it from the list and while adding - * make sure the list to which we are adding - * doesn't grow big. - */ - if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) { + + if (pa->pa_type == MB_INODE_PA) { + /* + * treat per-inode prealloc list as a lru list, then try + * to trim the least recently used PA. + */ spin_lock(pa->pa_obj_lock); - list_del_rcu(&pa->pa_inode_list); + list_move(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); - ext4_mb_add_n_trim(ac); } + ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) @@ -4588,6 +4786,7 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); + ext4_mb_trim_inode_pa(inode); return 0; } @@ -4915,7 +5114,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_data_block_valid(sbi, block, count)) { + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 6b4d17c2935d..e75b4749aa1c 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -73,6 +73,10 @@ */ #define MB_DEFAULT_GROUP_PREALLOC 512 +/* + * maximum length of inode prealloc list + */ +#define MB_DEFAULT_MAX_INODE_PREALLOC 512 struct ext4_free_data { /* this links the free block information from sb_info */ diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1ed86fb6c302..0d601b822875 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, out: if (*moved_len) { - ext4_discard_preallocations(orig_inode); - ext4_discard_preallocations(donor_inode); + ext4_discard_preallocations(orig_inode, 0); + ext4_discard_preallocations(donor_inode, 0); } ext4_ext_drop_refs(path); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 56738b538ddf..153a9fbe1dd0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1396,8 +1396,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf, + buf_size, offset)) return -1; *res_dir = de; return 1; @@ -1858,7 +1858,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); - /* Split the existing block in the middle, size-wise */ + /* Ensure that neither split block is over half full */ size = 0; move = 0; for (i = count-1; i >= 0; i--) { @@ -1868,8 +1868,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, size += map[i].size; move++; } - /* map index at which we will split */ - split = count - move; + /* + * map index at which we will split + * + * If the sum of active entries didn't exceed half the block size, just + * split it in half by count; each resulting block will have at least + * half the space free. + */ + if (i > 0) + split = count - move; + else + split = count/2; + hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n", @@ -2455,8 +2465,7 @@ cleanup: * ext4_generic_delete_entry deletes a directory entry by merging it * with the previous entry */ -int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2472,7 +2481,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) @@ -2517,8 +2526,7 @@ static int ext4_delete_entry(handle_t *handle, if (unlikely(err)) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, - bh, bh->b_data, + err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data, dir->i_sb->s_blocksize, csum_size); if (err) goto out; @@ -3193,30 +3201,33 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) * in separate transaction */ retval = dquot_initialize(dir); if (retval) - return retval; + goto out_trace; retval = dquot_initialize(d_inode(dentry)); if (retval) - return retval; + goto out_trace; - retval = -ENOENT; bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); - if (IS_ERR(bh)) - return PTR_ERR(bh); - if (!bh) - goto end_unlink; + if (IS_ERR(bh)) { + retval = PTR_ERR(bh); + goto out_trace; + } + if (!bh) { + retval = -ENOENT; + goto out_trace; + } inode = d_inode(dentry); - retval = -EFSCORRUPTED; - if (le32_to_cpu(de->inode) != inode->i_ino) - goto end_unlink; + if (le32_to_cpu(de->inode) != inode->i_ino) { + retval = -EFSCORRUPTED; + goto out_bh; + } handle = ext4_journal_start(dir, EXT4_HT_DIR, EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_unlink; + goto out_bh; } if (IS_DIRSYNC(dir)) @@ -3224,12 +3235,12 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto end_unlink; + goto out_handle; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto end_unlink; + goto out_handle; if (inode->i_nlink == 0) ext4_warning_inode(inode, "Deleting file '%.*s' with no links", dentry->d_name.len, dentry->d_name.name); @@ -3251,10 +3262,11 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) d_invalidate(dentry); #endif -end_unlink: +out_handle: + ext4_journal_stop(handle); +out_bh: brelse(bh); - if (handle) - ext4_journal_stop(handle); +out_trace: trace_ext4_unlink_exit(dentry, retval); return retval; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index f2df2db0786c..f014c5e473a9 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -140,7 +140,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; case STEP_VERITY: if (ctx->enabled_steps & (1 << STEP_VERITY)) { INIT_WORK(&ctx->work, verity_work); @@ -148,7 +148,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; default: __read_end_io(ctx->bio); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0907f907c47d..ea425b49b345 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static int ext4_commit_super(struct super_block *sb, int sync); -static void ext4_mark_recovery_complete(struct super_block *sb, +static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); -static void ext4_clear_journal_err(struct super_block *sb, - struct ext4_super_block *es); +static int ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); @@ -744,6 +744,7 @@ void __ext4_msg(struct super_block *sb, struct va_format vaf; va_list args; + atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; @@ -754,9 +755,12 @@ void __ext4_msg(struct super_block *sb, va_end(args); } -#define ext4_warning_ratelimit(sb) \ - ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), \ - "EXT4-fs warning") +static int ext4_warning_ratelimit(struct super_block *sb) +{ + atomic_inc(&EXT4_SB(sb)->s_warning_count); + return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), + "EXT4-fs warning"); +} void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) @@ -1123,6 +1127,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) inode_set_iversion(&ei->vfs_inode, 1); spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); + atomic_set(&ei->i_prealloc_active, 0); spin_lock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); @@ -1216,7 +1221,7 @@ void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -1288,8 +1293,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, if (!page_has_buffers(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_DIRECT_RECLAIM); + return jbd2_journal_try_to_free_buffers(journal, page); + return try_to_free_buffers(page); } @@ -1522,6 +1527,7 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, + Opt_prefetch_block_bitmaps, }; static const match_table_t tokens = { @@ -1614,6 +1620,7 @@ static const match_table_t tokens = { {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ + {Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1831,6 +1838,8 @@ static const struct mount_opts { {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_STRING}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, + {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, + MOPT_SET}, {Opt_err, 0, 0} }; @@ -3213,15 +3222,34 @@ static void print_daily_error_info(struct timer_list *t) static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; - ext4_group_t group, ngroups; - struct super_block *sb; + struct super_block *sb = elr->lr_super; + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t group = elr->lr_next_group; unsigned long timeout = 0; + unsigned int prefetch_ios = 0; int ret = 0; - sb = elr->lr_super; - ngroups = EXT4_SB(sb)->s_groups_count; + if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { + elr->lr_next_group = ext4_mb_prefetch(sb, group, + EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios); + if (prefetch_ios) + ext4_mb_prefetch_fini(sb, elr->lr_next_group, + prefetch_ios); + trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, + prefetch_ios); + if (group >= elr->lr_next_group) { + ret = 1; + if (elr->lr_first_not_zeroed != ngroups && + !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { + elr->lr_next_group = elr->lr_first_not_zeroed; + elr->lr_mode = EXT4_LI_MODE_ITABLE; + ret = 0; + } + } + return ret; + } - for (group = elr->lr_next_group; group < ngroups; group++) { + for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; @@ -3239,9 +3267,10 @@ static int ext4_run_li_request(struct ext4_li_request *elr) timeout = jiffies; ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); + trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { timeout = (jiffies - timeout) * - elr->lr_sbi->s_li_wait_mult; + EXT4_SB(elr->lr_super)->s_li_wait_mult; elr->lr_timeout = timeout; } elr->lr_next_sched = jiffies + elr->lr_timeout; @@ -3256,15 +3285,11 @@ static int ext4_run_li_request(struct ext4_li_request *elr) */ static void ext4_remove_li_request(struct ext4_li_request *elr) { - struct ext4_sb_info *sbi; - if (!elr) return; - sbi = elr->lr_sbi; - list_del(&elr->lr_request); - sbi->s_li_request = NULL; + EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } @@ -3473,7 +3498,6 @@ static int ext4_li_info_new(void) static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { - struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); @@ -3481,8 +3505,13 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, return NULL; elr->lr_super = sb; - elr->lr_sbi = sbi; - elr->lr_next_group = start; + elr->lr_first_not_zeroed = start; + if (test_opt(sb, PREFETCH_BLOCK_BITMAPS)) + elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; + else { + elr->lr_mode = EXT4_LI_MODE_ITABLE; + elr->lr_next_group = start; + } /* * Randomize first schedule time of the request to @@ -3512,8 +3541,9 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (first_not_zeroed == ngroups || sb_rdonly(sb) || - !test_opt(sb, INIT_INODE_TABLE)) + if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) && + (first_not_zeroed == ngroups || sb_rdonly(sb) || + !test_opt(sb, INIT_INODE_TABLE))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); @@ -4710,11 +4740,13 @@ no_journal: ext4_set_resv_clusters(sb); - err = ext4_setup_system_zone(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize system " - "zone (%d)", err); - goto failed_mount4a; + if (test_opt(sb, BLOCK_VALIDITY)) { + err = ext4_setup_system_zone(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)", err); + goto failed_mount4a; + } } ext4_ext_init(sb); @@ -4777,12 +4809,23 @@ no_journal: } #endif /* CONFIG_QUOTA */ + /* + * Save the original bdev mapping's wb_err value which could be + * used to detect the metadata async write error. + */ + spin_lock_init(&sbi->s_bdev_wb_lock); + if (!sb_rdonly(sb)) + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + sb->s_bdev->bd_super = sb; EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); - ext4_mark_recovery_complete(sb, es); + err = ext4_mark_recovery_complete(sb, es); + if (err) + goto failed_mount8; } if (EXT4_SB(sb)->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) @@ -4816,6 +4859,8 @@ no_journal: ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); + atomic_set(&sbi->s_warning_count, 0); + atomic_set(&sbi->s_msg_count, 0); kfree(orig_data); return 0; @@ -4825,10 +4870,8 @@ cantfind_ext4: ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; -#ifdef CONFIG_QUOTA failed_mount8: ext4_unregister_sysfs(sb); -#endif failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -4968,7 +5011,8 @@ static journal_t *ext4_get_journal(struct super_block *sb, struct inode *journal_inode; journal_t *journal; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (!journal_inode) @@ -4998,7 +5042,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, struct ext4_super_block *es; struct block_device *bdev; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) @@ -5089,8 +5134,10 @@ static int ext4_load_journal(struct super_block *sb, dev_t journal_dev; int err = 0; int really_read_only; + int journal_dev_ro; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5100,7 +5147,31 @@ static int ext4_load_journal(struct super_block *sb, } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); - really_read_only = bdev_read_only(sb->s_bdev); + if (journal_inum && journal_dev) { + ext4_msg(sb, KERN_ERR, + "filesystem has both journal inode and journal device!"); + return -EINVAL; + } + + if (journal_inum) { + journal = ext4_get_journal(sb, journal_inum); + if (!journal) + return -EINVAL; + } else { + journal = ext4_get_dev_journal(sb, journal_dev); + if (!journal) + return -EINVAL; + } + + journal_dev_ro = bdev_read_only(journal->j_dev); + really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; + + if (journal_dev_ro && !sb_rdonly(sb)) { + ext4_msg(sb, KERN_ERR, + "journal device read-only, try mounting with '-o ro'"); + err = -EROFS; + goto err_out; + } /* * Are we loading a blank journal or performing recovery after a @@ -5115,27 +5186,14 @@ static int ext4_load_journal(struct super_block *sb, ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); - return -EROFS; + err = -EROFS; + goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } - if (journal_inum && journal_dev) { - ext4_msg(sb, KERN_ERR, "filesystem has both journal " - "and inode journals!"); - return -EINVAL; - } - - if (journal_inum) { - if (!(journal = ext4_get_journal(sb, journal_inum))) - return -EINVAL; - } else { - if (!(journal = ext4_get_dev_journal(sb, journal_dev))) - return -EINVAL; - } - if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); @@ -5155,12 +5213,16 @@ static int ext4_load_journal(struct super_block *sb, if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); - jbd2_journal_destroy(journal); - return err; + goto err_out; } EXT4_SB(sb)->s_journal = journal; - ext4_clear_journal_err(sb, es); + err = ext4_clear_journal_err(sb, es); + if (err) { + EXT4_SB(sb)->s_journal = NULL; + jbd2_journal_destroy(journal); + return err; + } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5171,6 +5233,10 @@ static int ext4_load_journal(struct super_block *sb, } return 0; + +err_out: + jbd2_journal_destroy(journal); + return err; } static int ext4_commit_super(struct super_block *sb, int sync) @@ -5183,13 +5249,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) return error; /* - * The superblock bh should be mapped, but it might not be if the - * device was hot-removed. Not much we can do but fail the I/O. - */ - if (!buffer_mapped(sbh)) - return error; - - /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system @@ -5256,26 +5315,32 @@ static int ext4_commit_super(struct super_block *sb, int sync) * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ -static void ext4_mark_recovery_complete(struct super_block *sb, - struct ext4_super_block *es) +static int ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es) { + int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { - BUG_ON(journal != NULL); - return; + if (journal != NULL) { + ext4_error(sb, "Journal got removed while the fs was " + "mounted!"); + return -EFSCORRUPTED; + } + return 0; } jbd2_journal_lock_updates(journal); - if (jbd2_journal_flush(journal) < 0) + err = jbd2_journal_flush(journal); + if (err < 0) goto out; if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } - out: jbd2_journal_unlock_updates(journal); + return err; } /* @@ -5283,14 +5348,17 @@ out: * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ -static void ext4_clear_journal_err(struct super_block *sb, +static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; - BUG_ON(!ext4_has_feature_journal(sb)); + if (!ext4_has_feature_journal(sb)) { + ext4_error(sb, "Journal got removed while the fs was mounted!"); + return -EFSCORRUPTED; + } journal = EXT4_SB(sb)->s_journal; @@ -5315,6 +5383,7 @@ static void ext4_clear_journal_err(struct super_block *sb, jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } + return 0; } /* @@ -5457,7 +5526,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) { struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long old_sb_flags; + unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; int enable_quota = 0; ext4_group_t g; @@ -5500,6 +5569,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal && sbi->s_journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from *flags to s_flags + */ + vfs_flags = SB_LAZYTIME | SB_I_VERSION; + sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; goto restore_opts; @@ -5553,9 +5630,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } - if (*flags & SB_LAZYTIME) - sb->s_flags |= SB_LAZYTIME; - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; @@ -5585,8 +5659,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - if (sbi->s_journal) + if (sbi->s_journal) { + /* + * We let remount-ro finish even if marking fs + * as clean failed... + */ ext4_mark_recovery_complete(sb, es); + } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); } else { @@ -5629,13 +5708,24 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } /* + * Update the original bdev mapping's wb_err value + * which could be used to detect the metadata async + * write error. + */ + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + + /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ - if (sbi->s_journal) - ext4_clear_journal_err(sb, es); + if (sbi->s_journal) { + err = ext4_clear_journal_err(sb, es); + if (err) + goto restore_opts; + } sbi->s_mount_state = le16_to_cpu(es->s_state); err = ext4_setup_super(sb, es, 0); @@ -5665,7 +5755,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_register_li_request(sb, first_not_zeroed); } - ext4_setup_system_zone(sb); + /* + * Handle creation of system zone data early because it can fail. + * Releasing of existing data is done when we are sure remount will + * succeed. + */ + if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) { + err = ext4_setup_system_zone(sb); + if (err) + goto restore_opts; + } + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb, 1); if (err) @@ -5686,8 +5786,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } #endif + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); + + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from s_flags to *flags + */ + *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; @@ -5701,6 +5809,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 6c9fc9e21c13..bfabb799fa45 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -189,6 +189,9 @@ static struct ext4_attr ext4_attr_##_name = { \ #define EXT4_RW_ATTR_SBI_UL(_name,_elname) \ EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname) +#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname) + #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ @@ -215,6 +218,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); @@ -226,6 +230,8 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); #ifdef CONFIG_EXT4_DEBUG EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail); #endif +EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count); +EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count); EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode); EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode); @@ -240,6 +246,8 @@ EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32); EXT4_ATTR(first_error_time, 0444, first_error_time); EXT4_ATTR(last_error_time, 0444, last_error_time); EXT4_ATTR(journal_task, 0444, journal_task); +EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); +EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); static unsigned int old_bump_val = 128; EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); @@ -257,6 +265,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_order2_req), ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), + ATTR_LIST(mb_max_inode_prealloc), ATTR_LIST(max_writeback_mb_bump), ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), @@ -267,6 +276,8 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(msg_ratelimit_interval_ms), ATTR_LIST(msg_ratelimit_burst), ATTR_LIST(errors_count), + ATTR_LIST(warning_count), + ATTR_LIST(msg_count), ATTR_LIST(first_error_ino), ATTR_LIST(last_error_ino), ATTR_LIST(first_error_block), @@ -283,6 +294,8 @@ static struct attribute *ext4_attrs[] = { #ifdef CONFIG_EXT4_DEBUG ATTR_LIST(simulate_fail), #endif + ATTR_LIST(mb_prefetch), + ATTR_LIST(mb_prefetch_limit), NULL, }; ATTRIBUTE_GROUPS(ext4); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 7d2f6576d954..cba4b877c606 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1356,8 +1356,7 @@ retry: block = 0; while (wsize < bufsize) { - if (bh != NULL) - brelse(bh); + brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); diff --git a/fs/io_uring.c b/fs/io_uring.c index dc506b75659c..1fd03a38400c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -540,7 +540,6 @@ enum { REQ_F_ISREG_BIT, REQ_F_COMP_LOCKED_BIT, REQ_F_NEED_CLEANUP_BIT, - REQ_F_OVERFLOW_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_NO_FILE_TABLE_BIT, @@ -583,8 +582,6 @@ enum { REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), - /* in overflow list */ - REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ @@ -946,7 +943,8 @@ static void io_get_req_task(struct io_kiocb *req) static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | + REQ_F_INFLIGHT)) __io_clean_op(req); } @@ -1366,7 +1364,6 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, compl.list); list_move(&req->compl.list, &list); - req->flags &= ~REQ_F_OVERFLOW; if (cqe) { WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, req->result); @@ -1419,7 +1416,6 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } io_clean_op(req); - req->flags |= REQ_F_OVERFLOW; req->result = res; req->compl.cflags = cflags; refcount_inc(&req->refs); @@ -1563,17 +1559,6 @@ static bool io_dismantle_req(struct io_kiocb *req) if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - if (req->flags & REQ_F_INFLIGHT) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - if (waitqueue_active(&ctx->inflight_wait)) - wake_up(&ctx->inflight_wait); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - } - return io_req_clean_work(req); } @@ -2819,22 +2804,15 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; ssize_t ret; u8 opcode; - if (req->io) { - struct io_async_rw *iorw = &req->io->rw; - - *iovec = NULL; - return iov_iter_count(&iorw->iter); - } - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; @@ -2848,10 +2826,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { if (req->flags & REQ_F_BUFFER_SELECT) { buf = io_rw_buffer_select(req, &sqe_len, needs_lock); - if (IS_ERR(buf)) { - *iovec = NULL; + if (IS_ERR(buf)) return PTR_ERR(buf); - } req->rw.len = sqe_len; } @@ -2879,6 +2855,16 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); } +static ssize_t io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) +{ + if (!req->io) + return __io_import_iovec(rw, req, iovec, iter, needs_lock); + *iovec = NULL; + return iov_iter_count(&req->io->rw.iter); +} + /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -3001,11 +2987,8 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw, ssize_t ret; iorw->iter.iov = iorw->fast_iov; - /* reset ->io around the iovec import, we don't want to use it */ - req->io = NULL; - ret = io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, + ret = __io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, &iorw->iter, !force_nonblock); - req->io = container_of(iorw, struct io_async_ctx, rw); if (unlikely(ret < 0)) return ret; @@ -3074,27 +3057,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, return 1; } -static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, - struct wait_page_queue *wait, - wait_queue_func_t func, - void *data) -{ - /* Can't support async wakeup with polled IO */ - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) { - wait->wait.func = func; - wait->wait.private = data; - wait->wait.flags = 0; - INIT_LIST_HEAD(&wait->wait.entry); - kiocb->ki_flags |= IOCB_WAITQ; - kiocb->ki_waitq = wait; - return 0; - } - - return -EOPNOTSUPP; -} - /* * This controls whether a given IO request should be armed for async page * based retry. If we return false here, the request is handed to the async @@ -3109,16 +3071,17 @@ static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, */ static bool io_rw_should_retry(struct io_kiocb *req) { + struct wait_page_queue *wait = &req->io->rw.wpq; struct kiocb *kiocb = &req->rw.kiocb; - int ret; /* never retry for NOWAIT, we just complete with -EAGAIN */ if (req->flags & REQ_F_NOWAIT) return false; /* Only for buffered IO */ - if (kiocb->ki_flags & IOCB_DIRECT) + if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) return false; + /* * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks @@ -3126,14 +3089,15 @@ static bool io_rw_should_retry(struct io_kiocb *req) if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; - ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq, - io_async_buf_func, req); - if (!ret) { - io_get_req_task(req); - return true; - } + wait->wait.func = io_async_buf_func; + wait->wait.private = req; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_waitq = wait; - return false; + io_get_req_task(req); + return true; } static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) @@ -3238,6 +3202,7 @@ done: kiocb_done(kiocb, ret, cs); ret = 0; out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -3334,6 +3299,7 @@ copy_iov: return -EAGAIN; } out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -4932,6 +4898,12 @@ static bool io_arm_poll_handler(struct io_kiocb *req) mask |= POLLIN | POLLRDNORM; if (def->pollout) mask |= POLLOUT | POLLWRNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + mask |= POLLERR | POLLPRI; ipt.pt._qproc = io_async_queue_proc; @@ -5653,6 +5625,18 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } + + if (req->flags & REQ_F_INFLIGHT) { + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + req->flags &= ~REQ_F_INFLIGHT; + } } static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, @@ -7979,7 +7963,13 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); - queue_work(system_wq, &ctx->exit_work); + /* + * Use system_unbound_wq to avoid spawning tons of event kworkers + * if we're exiting a ton of rings at the same time. It just adds + * noise and overhead, there's no discernable change in runtime + * over using system_wq. + */ + queue_work(system_unbound_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) @@ -8063,6 +8053,33 @@ static bool io_timeout_remove_link(struct io_ring_ctx *ctx, return found; } +static bool io_cancel_link_cb(struct io_wq_work *work, void *data) +{ + return io_match_link(container_of(work, struct io_kiocb, work), data); +} + +static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + enum io_wq_cancel cret; + + /* cancel this particular work, if it's running */ + cret = io_wq_cancel_work(ctx->io_wq, &req->work); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* find links that hold this pending, cancel those */ + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_link_cb, req, true); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* if we have a poll link holding this pending, cancel that */ + if (io_poll_remove_link(ctx, req)) + return; + + /* final option, timeout link is holding this req pending */ + io_timeout_remove_link(ctx, req); +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { @@ -8094,35 +8111,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, /* We need to keep going until we don't find a matching req */ if (!cancel_req) break; - - if (cancel_req->flags & REQ_F_OVERFLOW) { - spin_lock_irq(&ctx->completion_lock); - list_del(&cancel_req->compl.list); - cancel_req->flags &= ~REQ_F_OVERFLOW; - - io_cqring_mark_overflow(ctx); - WRITE_ONCE(ctx->rings->cq_overflow, - atomic_inc_return(&ctx->cached_cq_overflow)); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - /* - * Put inflight ref and overflow ref. If that's - * all we had, then we're done with this request. - */ - if (refcount_sub_and_test(2, &cancel_req->refs)) { - io_free_req(cancel_req); - finish_wait(&ctx->inflight_wait, &wait); - continue; - } - } else { - io_wq_cancel_work(ctx->io_wq, &cancel_req->work); - /* could be a link, check and remove if it is */ - if (!io_poll_remove_link(ctx, cancel_req)) - io_timeout_remove_link(ctx, cancel_req); - io_put_req(cancel_req); - } - + /* cancel this request, or head link requests */ + io_attempt_cancel(ctx, cancel_req); + io_put_req(cancel_req); schedule(); finish_wait(&ctx->inflight_wait, &wait); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e4944436e733..17fdc482f554 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1285,7 +1285,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ -static void journal_fail_superblock (journal_t *journal) +static void journal_fail_superblock(journal_t *journal) { struct buffer_head *bh = journal->j_sb_buffer; brelse(bh); @@ -1367,8 +1367,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) int ret; /* Buffer got discarded which means block device got invalidated */ - if (!buffer_mapped(bh)) + if (!buffer_mapped(bh)) { + unlock_buffer(bh); return -EIO; + } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) @@ -1815,7 +1817,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features () - Check if features specified are used. + *int jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1825,7 +1827,7 @@ int jbd2_journal_destroy(journal_t *journal) * features. Return true (non-zero) if it does. **/ -int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; @@ -1860,7 +1862,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, * all of a given set of features on this journal. Return true * (non-zero) if it can. */ -int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) @@ -1882,7 +1884,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com } /** - * int jbd2_journal_set_features () - Mark a given journal feature in the superblock + * int jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1893,7 +1895,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com * */ -int jbd2_journal_set_features (journal_t *journal, unsigned long compat, +int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 2ed278f0dced..faa97d748474 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -690,14 +690,11 @@ static int do_one_pass(journal_t *journal, * number. */ if (pass == PASS_SCAN && jbd2_has_feature_checksum(journal)) { - int chksum_err, chksum_seen; struct commit_header *cbh = (struct commit_header *)bh->b_data; unsigned found_chksum = be32_to_cpu(cbh->h_chksum[0]); - chksum_err = chksum_seen = 0; - if (info->end_transaction) { journal->j_failed_commit = info->end_transaction; @@ -705,42 +702,23 @@ static int do_one_pass(journal_t *journal, break; } - if (crc32_sum == found_chksum && - cbh->h_chksum_type == JBD2_CRC32_CHKSUM && - cbh->h_chksum_size == - JBD2_CRC32_CHKSUM_SIZE) - chksum_seen = 1; - else if (!(cbh->h_chksum_type == 0 && - cbh->h_chksum_size == 0 && - found_chksum == 0 && - !chksum_seen)) - /* - * If fs is mounted using an old kernel and then - * kernel with journal_chksum is used then we - * get a situation where the journal flag has - * checksum flag set but checksums are not - * present i.e chksum = 0, in the individual - * commit blocks. - * Hence to avoid checksum failures, in this - * situation, this extra check is added. - */ - chksum_err = 1; - - if (chksum_err) { - info->end_transaction = next_commit_ID; - - if (!jbd2_has_feature_async_commit(journal)) { - journal->j_failed_commit = - next_commit_ID; - brelse(bh); - break; - } - } + /* Neither checksum match nor unused? */ + if (!((crc32_sum == found_chksum && + cbh->h_chksum_type == + JBD2_CRC32_CHKSUM && + cbh->h_chksum_size == + JBD2_CRC32_CHKSUM_SIZE) || + (cbh->h_chksum_type == 0 && + cbh->h_chksum_size == 0 && + found_chksum == 0))) + goto chksum_error; + crc32_sum = ~0; } if (pass == PASS_SCAN && !jbd2_commit_block_csum_verify(journal, bh->b_data)) { + chksum_error: info->end_transaction = next_commit_ID; if (!jbd2_has_feature_async_commit(journal)) { diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e91aad3637a2..43985738aa86 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2026,6 +2026,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { + J_ASSERT_JH(jh, jh->b_transaction != NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; } @@ -2078,10 +2081,6 @@ out: * int jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free - * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit - * code to release the buffers. - * * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN @@ -2112,11 +2111,11 @@ out: * * Return 0 on failure, 1 on success */ -int jbd2_journal_try_to_free_buffers(journal_t *journal, - struct page *page, gfp_t gfp_mask) +int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) { struct buffer_head *head; struct buffer_head *bh; + bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); @@ -2141,11 +2140,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; + + /* + * If we free a metadata buffer which has been failed to + * write out, the jbd2 checkpoint procedure will not detect + * this failure and may lead to filesystem inconsistency + * after cleanup journal tail. + */ + if (buffer_write_io_error(bh)) { + pr_err("JBD2: Error while async write back metadata bh %llu.", + (unsigned long long)bh->b_blocknr); + has_write_io_error = true; + } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); busy: + if (has_write_io_error) + jbd2_journal_abort(journal, -EIO); + return ret; } @@ -2572,6 +2586,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + + /* + * b_transaction must be set, otherwise the new b_transaction won't + * be holding jh reference + */ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index 6b2b4362089e..b57b3ffcbc32 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -217,10 +217,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos, size_t limit; limit = romfs_maxsize(sb); - if (pos >= limit) + if (pos >= limit || buflen > limit - pos) return -EIO; - if (buflen > limit - pos) - buflen = limit - pos; #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 76bb1c846845..8a19773b5a0b 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -87,7 +87,11 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - bio = bio_alloc(GFP_NOIO, page_count); + if (page_count <= BIO_MAX_PAGES) + bio = bio_alloc(GFP_NOIO, page_count); + else + bio = bio_kmalloc(GFP_NOIO, page_count); + if (!bio) return -ENOMEM; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a2710e654b64..3215023d4852 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -132,6 +132,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5a3ce2a24794..6e87225600ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask); -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 016b96b384bd..52635e91143b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags); +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); bool dma_free_from_pool(struct device *dev, void *start, size_t size); int diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a44789d027cc..dda61d150a13 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb) return 0; } -/* can not be used in TCP layer after tcp_v6_fill_cb */ -static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if defined(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) - return true; -#endif - return false; -} - struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; @@ -345,17 +334,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - int ancestor_size = sizeof(struct inet_sock); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); - - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - #define __ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4aaa29772bb0..08f904943ab2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1381,7 +1381,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 898cbf00332a..3a88b699b758 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -358,6 +358,12 @@ static inline int mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, return mdiobus_read(bus, prtad, mdiobus_c45_addr(devad, regnum)); } +static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, + u16 regnum, u16 val) +{ + return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/drivers/net/phy/mdio-i2c.h b/include/linux/mdio/mdio-i2c.h index b1d27f7cd23f..b1d27f7cd23f 100644 --- a/drivers/net/phy/mdio-i2c.h +++ b/include/linux/mdio/mdio-i2c.h diff --git a/drivers/net/phy/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h index 8af93ada8b64..8af93ada8b64 100644 --- a/drivers/net/phy/mdio-xgene.h +++ b/include/linux/mdio/mdio-xgene.h diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..7657c6432a69 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,8 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define PROTO_CMSG_DATA_ONLY 0x0001 + #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -135,6 +137,7 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; + unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d088dd866825..7f9fcfd15942 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -640,10 +640,14 @@ struct netdev_queue { extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; +/* + * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns + * == 1 : For initns only + * == 2 : For none. + */ static inline bool net_has_fallback_tunnels(const struct net *net) { - return net == &init_net || - !IS_ENABLED(CONFIG_SYSCTL) || + return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) || !sysctl_fb_tunnels_only_for_init_net; } @@ -2193,6 +2197,22 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +static inline void net_prefetch(void *p) +{ + prefetch(p); +#if L1_CACHE_BYTES < 128 + prefetch((u8 *)p + L1_CACHE_BYTES); +#endif +} + +static inline void net_prefetchw(void *p) +{ + prefetchw(p); +#if L1_CACHE_BYTES < 128 + prefetchw((u8 *)p + L1_CACHE_BYTES); +#endif +} + void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h new file mode 100644 index 000000000000..a6440d6ebe95 --- /dev/null +++ b/include/linux/pcs-lynx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2020 NXP + * Lynx PCS helpers + */ + +#ifndef __LINUX_PCS_LYNX_H +#define __LINUX_PCS_LYNX_H + +#include <linux/mdio.h> +#include <linux/phylink.h> + +struct lynx_pcs { + struct phylink_pcs pcs; + struct mdio_device *mdio; +}; + +struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); + +void lynx_pcs_destroy(struct lynx_pcs *pcs); + +#endif /* __LINUX_PCS_LYNX_H */ diff --git a/include/linux/mdio-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 9a841aa5982d..351c1c9aedc5 100644 --- a/include/linux/mdio-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -4,8 +4,8 @@ * Synopsys DesignWare XPCS helpers */ -#ifndef __LINUX_MDIO_XPCS_H -#define __LINUX_MDIO_XPCS_H +#ifndef __LINUX_PCS_XPCS_H +#define __LINUX_PCS_XPCS_H #include <linux/phy.h> #include <linux/phylink.h> @@ -29,7 +29,7 @@ struct mdio_xpcs_ops { int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); }; -#if IS_ENABLED(CONFIG_MDIO_XPCS) +#if IS_ENABLED(CONFIG_PCS_XPCS) struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); #else static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) @@ -38,4 +38,4 @@ static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) } #endif -#endif /* __LINUX_MDIO_XPCS_H */ +#endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a124c21e3204..e8cbc2e795d5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ +#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) +#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c36fb41a7d90..d81a714cfbbd 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -490,4 +490,7 @@ void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); + +void phylink_decode_usxgmii_word(struct phylink_link_state *state, + uint16_t lpa); #endif diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index dd00fa41f7e7..8437307cca8c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -36,7 +36,6 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 -#define OFF_PTP_CONTROL 32 /* PTPv1 only */ /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 @@ -44,6 +43,30 @@ #define OFF_IHL 14 #define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2) +struct clock_identity { + u8 id[8]; +} __packed; + +struct port_identity { + struct clock_identity clock_identity; + __be16 port_number; +} __packed; + +struct ptp_header { + u8 tsmt; /* transportSpecific | messageType */ + u8 ver; /* reserved | versionPTP */ + __be16 message_length; + u8 domain_number; + u8 reserved1; + u8 flag_field[2]; + __be64 correction; + __be32 reserved2; + struct port_identity source_port_identity; + __be16 sequence_id; + u8 control; + u8 log_message_interval; +} __packed; + #if defined(CONFIG_NET_PTP_CLASSIFY) /** * ptp_classify_raw - classify a PTP packet @@ -57,6 +80,46 @@ */ unsigned int ptp_classify_raw(const struct sk_buff *skb); +/** + * ptp_parse_header - Get pointer to the PTP v2 header + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function takes care of the VLAN, UDP, IPv4 and IPv6 headers. The length + * is checked. + * + * Note, internally skb_mac_header() is used. Make sure that the @skb is + * initialized accordingly. + * + * Return: Pointer to the ptp v2 header or NULL if not found + */ +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type); + +/** + * ptp_get_msgtype - Extract ptp message type from given header + * @hdr: ptp header + * @type: type of the packet (see ptp_classify_raw()) + * + * This function returns the message type for a given ptp header. It takes care + * of the different ptp header versions (v1 or v2). + * + * Return: The message type + */ +static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, + unsigned int type) +{ + u8 msgtype; + + if (unlikely(type & PTP_CLASS_V1)) { + /* msg type is located at the control field for ptp v1 */ + msgtype = hdr->control; + } else { + msgtype = hdr->tsmt & 0x0f; + } + + return msgtype; +} + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -66,5 +129,10 @@ static inline unsigned int ptp_classify_raw(struct sk_buff *skb) { return PTP_CLASS_NONE; } +static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb, + unsigned int type) +{ + return NULL; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..56fa55841d39 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -21,6 +21,7 @@ #include <linux/qed/common_hsi.h> #include <linux/qed/qed_chain.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <net/devlink.h> enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -779,6 +780,11 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_NVM_MAX, }; +struct qed_devlink { + struct qed_dev *cdev; + struct devlink_health_reporter *fw_reporter; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -844,10 +850,9 @@ struct qed_common_ops { struct qed_dev* (*probe)(struct pci_dev *dev, struct qed_probe_params *params); - void (*remove)(struct qed_dev *cdev); + void (*remove)(struct qed_dev *cdev); - int (*set_power_state)(struct qed_dev *cdev, - pci_power_t state); + int (*set_power_state)(struct qed_dev *cdev, pci_power_t state); void (*set_name) (struct qed_dev *cdev, char name[]); @@ -855,50 +860,51 @@ struct qed_common_ops { * PF params required for the call before slowpath_start is * documented within the qed_pf_params structure definition. */ - void (*update_pf_params)(struct qed_dev *cdev, - struct qed_pf_params *params); - int (*slowpath_start)(struct qed_dev *cdev, - struct qed_slowpath_params *params); + void (*update_pf_params)(struct qed_dev *cdev, + struct qed_pf_params *params); - int (*slowpath_stop)(struct qed_dev *cdev); + int (*slowpath_start)(struct qed_dev *cdev, + struct qed_slowpath_params *params); + + int (*slowpath_stop)(struct qed_dev *cdev); /* Requests to use `cnt' interrupts for fastpath. * upon success, returns number of interrupts allocated for fastpath. */ - int (*set_fp_int)(struct qed_dev *cdev, - u16 cnt); + int (*set_fp_int)(struct qed_dev *cdev, u16 cnt); /* Fills `info' with pointers required for utilizing interrupts */ - int (*get_fp_int)(struct qed_dev *cdev, - struct qed_int_info *info); - - u32 (*sb_init)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - void *sb_virt_addr, - dma_addr_t sb_phy_addr, - u16 sb_id, - enum qed_sb_type type); - - u32 (*sb_release)(struct qed_dev *cdev, - struct qed_sb_info *sb_info, - u16 sb_id, - enum qed_sb_type type); - - void (*simd_handler_config)(struct qed_dev *cdev, - void *token, - int index, - void (*handler)(void *)); - - void (*simd_handler_clean)(struct qed_dev *cdev, - int index); - int (*dbg_grc)(struct qed_dev *cdev, - void *buffer, u32 *num_dumped_bytes); + int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info); + + u32 (*sb_init)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + void *sb_virt_addr, + dma_addr_t sb_phy_addr, + u16 sb_id, + enum qed_sb_type type); + + u32 (*sb_release)(struct qed_dev *cdev, + struct qed_sb_info *sb_info, + u16 sb_id, + enum qed_sb_type type); + + void (*simd_handler_config)(struct qed_dev *cdev, + void *token, + int index, + void (*handler)(void *)); + + void (*simd_handler_clean)(struct qed_dev *cdev, int index); + + int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes); int (*dbg_grc_size)(struct qed_dev *cdev); - int (*dbg_all_data) (struct qed_dev *cdev, void *buffer); + int (*dbg_all_data)(struct qed_dev *cdev, void *buffer); - int (*dbg_all_data_size) (struct qed_dev *cdev); + int (*dbg_all_data_size)(struct qed_dev *cdev); + + int (*report_fatal_error)(struct devlink *devlink, + enum qed_hw_err_type err_type); /** * @brief can_link_change - can the instance change the link or not @@ -1137,6 +1143,10 @@ struct qed_common_ops { * */ int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); + + struct devlink* (*devlink_register)(struct qed_dev *cdev); + + void (*devlink_unregister)(struct devlink *devlink); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ba3f6c15ad2b..18f783dcd55f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -97,7 +97,8 @@ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr); +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d9e6b9fbd95b..c9bce9bba511 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -678,7 +678,10 @@ struct cfg80211_bitrate_mask { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; + u16 he_mcs[NL80211_HE_NSS_MAX]; enum nl80211_txrate_gi gi; + enum nl80211_he_gi he_gi; + enum nl80211_he_ltf he_ltf; } control[NUM_NL80211_BANDS]; }; diff --git a/include/net/dst.h b/include/net/dst.h index 6ae2e625050d..8ea8812b0b41 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst) static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { - return dst_metric(dst, RTAX_LOCK) & (1<<metric); + return dst_metric(dst, RTAX_LOCK) & (1 << metric); } static inline void dst_hold(struct dst_entry *dst) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a3702d1d4875..89163ef8cf4b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -296,13 +296,6 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to, memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } -#if !(IS_ENABLED(CONFIG_IPV6)) -static inline void inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); -} -#endif int inet_sk_rebuild_header(struct sock *sk); diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index d7a7f7c81e7b..8fce558b5fea 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -63,6 +63,9 @@ struct ipv6_stub { int encap_type); #endif struct neigh_table *nd_tbl; + + int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)); }; extern const struct ipv6_stub *ipv6_stub __read_mostly; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 66e2bfd165e8..ec148b3e9c41 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3736,7 +3736,7 @@ enum ieee80211_reconfig_type { * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is - * 1 using ieee80211_csa_is_complete() after the beacon has been + * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. @@ -4763,21 +4763,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); -#define IEEE80211_MAX_CSA_COUNTERS_NUM 2 +#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element - * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets - * to CSA counters. This array can contain zero values which + * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets + * to countdown counters. This array can contain zero values which * should be ignored. */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; - u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; }; /** @@ -4846,31 +4846,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, } /** - * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter + * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * The csa counter should be updated after each beacon transmission. + * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this - * function after each beacon transmission to sync mac80211's csa counters. + * function after each beacon transmission to sync mac80211's beacon countdown. * - * Return: new csa counter value + * Return: new countdown value */ -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif); +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif); /** - * ieee80211_csa_set_counter - request mac80211 to set csa counter + * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * - * The csa counter can be changed by the device, this API should be + * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * - * It should never be used together with ieee80211_csa_update_counter(), + * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch @@ -4883,13 +4883,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter); void ieee80211_csa_finish(struct ieee80211_vif *vif); /** - * ieee80211_csa_is_complete - find out if counters reached 1 + * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * This function returns whether the channel switch counters reached zero. + * This function returns whether the countdown reached zero. */ -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif); - +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif); /** * ieee80211_proberesp_get - retrieve a Probe Response template diff --git a/include/net/sock.h b/include/net/sock.h index 18423cc9cde8..7dd3051551fb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1478,7 +1478,7 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; - return size<= sk->sk_forward_alloc || + return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 1f967b4e22f6..e85d564446c6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -942,16 +942,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); #endif -static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (!net->ipv4.sysctl_tcp_l3mdev_accept && - skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) - return true; -#endif - return false; -} - /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index cc41d692ae8e..4c8b99ec8606 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -746,24 +746,29 @@ TRACE_EVENT(ext4_mb_release_group_pa, ); TRACE_EVENT(ext4_discard_preallocations, - TP_PROTO(struct inode *inode), + TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed), - TP_ARGS(inode), + TP_ARGS(inode, len, needed), TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, len ) + __field( unsigned int, needed ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; + __entry->len = len; + __entry->needed = needed; ), - TP_printk("dev %d,%d ino %lu", + TP_printk("dev %d,%d ino %lu len: %u needed %u", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino) + (unsigned long) __entry->ino, __entry->len, + __entry->needed) ); TRACE_EVENT(ext4_mb_discard_preallocations, @@ -1312,18 +1317,34 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, +TRACE_EVENT(ext4_read_block_bitmap_load, + TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), - TP_PROTO(struct super_block *sb, unsigned long group), + TP_ARGS(sb, group, prefetch), - TP_ARGS(sb, group) + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( bool, prefetch ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->prefetch = prefetch; + ), + + TP_printk("dev %d,%d group %u prefetch %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->prefetch) ); TRACE_EVENT(ext4_direct_IO_enter, @@ -2726,6 +2747,50 @@ TRACE_EVENT(ext4_error, __entry->function, __entry->line) ); +TRACE_EVENT(ext4_prefetch_bitmaps, + TP_PROTO(struct super_block *sb, ext4_group_t group, + ext4_group_t next, unsigned int prefetch_ios), + + TP_ARGS(sb, group, next, prefetch_ios), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( __u32, next ) + __field( __u32, ios ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->next = next; + __entry->ios = prefetch_ios; + ), + + TP_printk("dev %d,%d group %u next %u ios %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->next, __entry->ios) +); + +TRACE_EVENT(ext4_lazy_itable_init, + TP_PROTO(struct super_block *sb, ext4_group_t group), + + TP_ARGS(sb, group), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + ), + + TP_printk("dev %d,%d group %u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a613750d5515..8dda13880957 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -776,7 +776,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1042,14 +1042,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1156,7 +1156,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index c7d66755d212..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#define GTP_GENL_MCGRP_NAME "gtp" + enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 060b4d1f3129..a91044328bc9 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -75,7 +75,7 @@ struct pppol2tpv3in6_addr { }; /* Socket options: - * DEBUG - bitmask of debug message categories + * DEBUG - bitmask of debug message categories (not used) * SENDSEQ - 0 => don't send packets with sequence numbers * 1 => send packets with sequence numbers * RECVSEQ - 0 => receive packet sequence numbers are optional diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 61158f5a1a5b..88a0d32b8c07 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -108,7 +108,7 @@ enum { L2TP_ATTR_VLAN_ID, /* u16 (not used) */ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */ - L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */ + L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags (not used) */ L2TP_ATTR_RECV_SEQ, /* u8 */ L2TP_ATTR_SEND_SEQ, /* u8 */ L2TP_ATTR_LNS_MODE, /* u8 */ @@ -177,7 +177,9 @@ enum l2tp_seqmode { }; /** - * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions + * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions. + * + * Unused. * * @L2TP_MSG_DEBUG: verbose debug (if compiled in) * @L2TP_MSG_CONTROL: userspace - kernel interface diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 631f3a997b3c..0584e0d349f0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -252,9 +252,13 @@ * DOC: SAE authentication offload * * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they - * support offloading SAE authentication for WPA3-Personal networks. In - * %NL80211_CMD_CONNECT the password for SAE should be specified using - * %NL80211_ATTR_SAE_PASSWORD. + * support offloading SAE authentication for WPA3-Personal networks in station + * mode. Similarly @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag can be set by + * drivers indicating the offload support in AP mode. + * + * The password for SAE should be specified using %NL80211_ATTR_SAE_PASSWORD in + * %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP for station and AP mode + * respectively. */ /** @@ -647,13 +651,9 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * When establishing a security association, drivers that support 4 way - * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when - * the 4 way handshake is completed successfully. * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. - * When a security association was established with the new AP (e.g. if - * the FT protocol was used for roaming or the driver completed the 4 way - * handshake), this event should be followed by an + * When a security association was established on an 802.1X network using + * fast transition, this event should be followed by an * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other @@ -1067,13 +1067,11 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * %NL80211_ATTR_MAC. - * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way - * handshake was completed successfully by the driver. The BSSID is - * specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake - * offload should send this event after indicating 802.11 association with - * %NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed - * %NL80211_CMD_DISCONNECT should be indicated instead. - * + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was + * completed successfully. Drivers that support 4 way handshake offload + * should send this event after indicating 802.1X FT assocation with + * %NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT + * should be indicated instead. * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request * and RX notification. This command is used both as a request to transmit * a control port frame and as a notification that a control port frame @@ -2082,10 +2080,10 @@ enum nl80211_commands { * operation). * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information * for the time while performing a channel switch. - * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel - * switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). - * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel - * switch counters in the probe response (%NL80211_ATTR_PROBE_RESP). + * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel + * switch or color change counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL). + * @NL80211_ATTR_CNTDWN_OFFS_PRESP: An array of offsets (u16) to the channel + * switch or color change counters in the probe response (%NL80211_ATTR_PROBE_RESP). * * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32. * As specified in the &enum nl80211_rxmgmt_flags. @@ -2821,8 +2819,8 @@ enum nl80211_attrs { NL80211_ATTR_CH_SWITCH_COUNT, NL80211_ATTR_CH_SWITCH_BLOCK_TX, NL80211_ATTR_CSA_IES, - NL80211_ATTR_CSA_C_OFF_BEACON, - NL80211_ATTR_CSA_C_OFF_PRESP, + NL80211_ATTR_CNTDWN_OFFS_BEACON, + NL80211_ATTR_CNTDWN_OFFS_PRESP, NL80211_ATTR_RXMGMT_FLAGS, @@ -3009,6 +3007,8 @@ enum nl80211_attrs { #define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA +#define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON +#define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP /* * Allow user space programs to use #ifdef on new attributes by defining them @@ -3187,6 +3187,18 @@ enum nl80211_he_gi { }; /** + * enum nl80211_he_ltf - HE long training field + * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec + * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec + * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec + */ +enum nl80211_he_ltf { + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_2XLTF, + NL80211_RATE_INFO_HE_4XLTF, +}; + +/** * enum nl80211_he_ru_alloc - HE RU allocation values * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation @@ -4741,6 +4753,10 @@ enum nl80211_key_attributes { * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection, * see &struct nl80211_txrate_vht * @NL80211_TXRATE_GI: configure GI, see &enum nl80211_txrate_gi + * @NL80211_TXRATE_HE: HE rates allowed for TX rate selection, + * see &struct nl80211_txrate_he + * @NL80211_TXRATE_HE_GI: configure HE GI, 0.8us, 1.6us and 3.2us. + * @NL80211_TXRATE_HE_LTF: configure HE LTF, 1XLTF, 2XLTF and 4XLTF. * @__NL80211_TXRATE_AFTER_LAST: internal * @NL80211_TXRATE_MAX: highest TX rate attribute */ @@ -4750,6 +4766,9 @@ enum nl80211_tx_rate_attributes { NL80211_TXRATE_HT, NL80211_TXRATE_VHT, NL80211_TXRATE_GI, + NL80211_TXRATE_HE, + NL80211_TXRATE_HE_GI, + NL80211_TXRATE_HE_LTF, /* keep last */ __NL80211_TXRATE_AFTER_LAST, @@ -4767,6 +4786,15 @@ struct nl80211_txrate_vht { __u16 mcs[NL80211_VHT_NSS_MAX]; }; +#define NL80211_HE_NSS_MAX 8 +/** + * struct nl80211_txrate_he - HE MCS/NSS txrate bitmap + * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.) + */ +struct nl80211_txrate_he { + __u16 mcs[NL80211_HE_NSS_MAX]; +}; + enum nl80211_txrate_gi { NL80211_TXRATE_DEFAULT_GI, NL80211_TXRATE_FORCE_SGI, @@ -5821,6 +5849,9 @@ enum nl80211_feature_flags { * handshake with PSK in AP mode (PSK is passed as part of the start AP * command). * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication + * in AP mode (SAE password is passed as part of the start AP command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5878,6 +5909,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS, NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index aeec7e174188..30833bbf3019 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq) iter_priv->done_stop = true; } +/* maximum visited objects before bailing out */ +#define MAX_ITER_OBJECTS 1000000 + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; - int err = 0; + int err = 0, num_objs = 0; void *p; mutex_lock(&seq->lock); @@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, while (1) { loff_t pos = seq->index; + num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { @@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, if (seq->count >= size) break; + if (num_objs >= MAX_ITER_OBJECTS) { + if (offs == 0) { + err = -EAGAIN; + seq->op->stop(seq, p); + goto done; + } + break; + } + err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 232df29793e9..99af4cea1102 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, rcu_read_lock(); retry: - pid = idr_get_next(&ns->idr, tid); + pid = find_ge_pid(*tid, ns); if (pid) { + *tid = pid_nr_ns(pid, ns); task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ++*tid; @@ -178,10 +179,11 @@ again: f = fcheck_files(curr_files, curr_fd); if (!f) continue; + if (!get_file_rcu(f)) + continue; /* set info->fd */ info->fd = curr_fd; - get_file(f); rcu_read_unlock(); return f; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index bb0041e99659..db6ef07aec3b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev) return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, u64 *phys_limit) { u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); @@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, return 0; } -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <= min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); @@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, size, &page, gfp); - if (!ret) + u64 phys_mask; + + gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); + page = dma_alloc_from_pool(dev, size, &ret, gfp, + dma_coherent_ok); + if (!page) return NULL; goto done; } diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 6bc74a2d5127..06582b488e31 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -3,7 +3,9 @@ * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2020 Google LLC */ +#include <linux/cma.h> #include <linux/debugfs.h> +#include <linux/dma-contiguous.h> #include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> #include <linux/init.h> @@ -55,6 +57,29 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size) pool_size_kernel += size; } +static bool cma_in_zone(gfp_t gfp) +{ + unsigned long size; + phys_addr_t end; + struct cma *cma; + + cma = dev_get_cma_area(NULL); + if (!cma) + return false; + + size = cma_get_size(cma); + if (!size) + return false; + + /* CMA can't cross zone boundaries, see cma_activate_area() */ + end = cma_get_base(cma) + size - 1; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return end <= DMA_BIT_MASK(zone_dma_bits); + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return end <= DMA_BIT_MASK(32); + return true; +} + static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, gfp_t gfp) { @@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, do { pool_size = 1 << (PAGE_SHIFT + order); - page = alloc_pages(gfp, order); + if (cma_in_zone(gfp)) + page = dma_alloc_from_contiguous(NULL, 1 << order, + order, false); + if (!page) + page = alloc_pages(gfp, order); } while (!page && order-- > 0); if (!page) goto out; @@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void) } postcore_initcall(dma_atomic_pool_init); -static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev) +static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { - u64 phys_mask; - gfp_t gfp; - - gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); - if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA) + if (prev == NULL) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return atomic_pool_dma32; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return atomic_pool_dma; + return atomic_pool_kernel; + } + if (prev == atomic_pool_kernel) + return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; + if (prev == atomic_pool_dma32) return atomic_pool_dma; - if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32) - return atomic_pool_dma32; - return atomic_pool_kernel; + return NULL; } -static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool) +static struct page *__dma_alloc_from_pool(struct device *dev, size_t size, + struct gen_pool *pool, void **cpu_addr, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { - if (bad_pool == atomic_pool_kernel) - return atomic_pool_dma32 ? : atomic_pool_dma; + unsigned long addr; + phys_addr_t phys; - if (bad_pool == atomic_pool_dma32) - return atomic_pool_dma; + addr = gen_pool_alloc(pool, size); + if (!addr) + return NULL; - return NULL; -} + phys = gen_pool_virt_to_phys(pool, addr); + if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) { + gen_pool_free(pool, addr, size); + return NULL; + } -static inline struct gen_pool *dma_guess_pool(struct device *dev, - struct gen_pool *bad_pool) -{ - if (bad_pool) - return dma_get_safer_pool(bad_pool); + if (gen_pool_avail(pool) < atomic_pool_size) + schedule_work(&atomic_pool_work); - return dma_guess_pool_from_device(dev); + *cpu_addr = (void *)addr; + memset(*cpu_addr, 0, size); + return pfn_to_page(__phys_to_pfn(phys)); } -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags) +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t gfp, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { struct gen_pool *pool = NULL; - unsigned long val = 0; - void *ptr = NULL; - phys_addr_t phys; - - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) { - WARN(1, "Failed to get suitable pool for %s\n", - dev_name(dev)); - break; - } - - val = gen_pool_alloc(pool, size); - if (!val) - continue; - - phys = gen_pool_virt_to_phys(pool, val); - if (dma_coherent_ok(dev, phys, size)) - break; - - gen_pool_free(pool, val, size); - val = 0; - } - - - if (val) { - *ret_page = pfn_to_page(__phys_to_pfn(phys)); - ptr = (void *)val; - memset(ptr, 0, size); + struct page *page; - if (gen_pool_avail(pool) < atomic_pool_size) - schedule_work(&atomic_pool_work); + while ((pool = dma_guess_pool(pool, gfp))) { + page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, + phys_addr_ok); + if (page) + return page; } - return ptr; + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + return NULL; } bool dma_free_from_pool(struct device *dev, void *start, size_t size) { struct gen_pool *pool = NULL; - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) - return false; - - if (gen_pool_has_addr(pool, (unsigned long)start, size)) { - gen_pool_free(pool, (unsigned long)start, size); - return true; - } + while ((pool = dma_guess_pool(pool, 0))) { + if (!gen_pool_has_addr(pool, (unsigned long)start, size)) + continue; + gen_pool_free(pool, (unsigned long)start, size); + return true; } + + return false; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 9852e0d62d95..fcae019158ca 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -65,7 +65,8 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, syscall_enter_audit(regs, syscall); - return ret ? : syscall; + /* The above might have changed the syscall number */ + return ret ? : syscall_get_nr(current, regs); } noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 649fd53dc9ad..0e18aaf23a7b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); diff --git a/kernel/relay.c b/kernel/relay.c index 72fe443ea78f..fb4e0c530c08 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -197,6 +197,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } diff --git a/lib/Makefile b/lib/Makefile index e290fc5707ea..a4a4c6864f51 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -15,11 +15,16 @@ KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n KCOV_INSTRUMENT_fault-inject.o := n +# string.o implements standard library functions like memset/memcpy etc. +# Use -ffreestanding to ensure that the compiler does not try to "optimize" +# them into calls to themselves. +CFLAGS_string.o := -ffreestanding + # Early boot use of cmdline, don't instrument it ifdef CONFIG_AMD_MEM_ENCRYPT KASAN_SANITIZE_string.o := n -CFLAGS_string.o := -fno-stack-protector +CFLAGS_string.o += -fno-stack-protector endif # Used by KCSAN while enabled, avoid recursion. diff --git a/lib/nlattr.c b/lib/nlattr.c index 665bdaff02c8..80ff9fe83696 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -834,8 +834,7 @@ EXPORT_SYMBOL(__nla_reserve); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { - if (nla_need_padding_for_64bit(skb)) - nla_align_64bit(skb, padattr); + nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index aabf65d4d91b..1f87aec9ab5c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -655,7 +655,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_show; - cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]), + cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* Add the events.local file */ @@ -664,7 +664,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_local_show; cft->file_offset = offsetof(struct hugetlb_cgroup, - events_local_file[idx]), + events_local_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* NULL terminate the last cft */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 15a9af791014..e749e568e1ea 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -466,7 +466,7 @@ int __khugepaged_enter(struct mm_struct *mm) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); + VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; diff --git a/mm/memory.c b/mm/memory.c index 3a7779d9891d..602f4283122f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4247,6 +4247,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cd8d8f0326fc..0608f7f1236d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1302,6 +1302,11 @@ static void free_pcppages_bulk(struct zone *zone, int count, struct page *page, *tmp; LIST_HEAD(head); + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); while (count) { struct list_head *list; @@ -7888,7 +7893,7 @@ int __meminit init_per_zone_wmark_min(void) return 0; } -core_initcall(init_per_zone_wmark_min) +postcore_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 2a99df7beeb3..2613371945b7 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "rodata_test: " fmt +#include <linux/rodata_test.h> #include <linux/uaccess.h> #include <asm/sections.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b482d240f9a2..be4724b916b3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -104,6 +104,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); + + cond_resched(); } while (pmd++, addr = next, addr != end); } diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a4faf5f904d9..206d0b424712 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -27,6 +27,7 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> +#include <linux/prandom.h> #include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index d35aca0e969a..79a7dfc32e76 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -20,6 +20,7 @@ #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/nl80211.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 0f8495b9eeb1..11c3f98ba938 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -20,6 +20,7 @@ #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 91a04ca373dc..5c41cc52bc53 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1795,7 +1795,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); - /* backbone_gw is unreferenced in the report work function function + /* backbone_gw is unreferenced in the report work function * if queue_work() call was successful */ if (!ret) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9fdbe3068153..9a47ef8b95c4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -306,7 +306,7 @@ free: * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb * to NULL; 3) Error: Return false and free skb. * - * Return: true when the packet is merged or buffered, false when skb is not not + * Return: true when the packet is merged or buffered, false when skb is not * used. */ bool batadv_frag_skb_buffer(struct sk_buff **skb, diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index fa06b51c0144..dad99641df2a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -599,7 +599,7 @@ out: /* report to the other components the maximum amount of bytes that * batman-adv can send over the wire (without considering the payload * overhead). For example, this value is used by TT to compute the - * maximum local table table size + * maximum local table size */ atomic_set(&bat_priv->packet_size_max, min_mtu); @@ -977,23 +977,6 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) } /** - * batadv_hardif_remove_interfaces() - Remove all hard interfaces - */ -void batadv_hardif_remove_interfaces(void) -{ - struct batadv_hard_iface *hard_iface, *hard_iface_tmp; - - rtnl_lock(); - list_for_each_entry_safe(hard_iface, hard_iface_tmp, - &batadv_hardif_list, list) { - list_del_rcu(&hard_iface->list); - batadv_hardif_generation++; - batadv_hardif_remove_interface(hard_iface); - } - rtnl_unlock(); -} - -/** * batadv_hard_if_event_softif() - Handle events for soft interfaces * @event: NETDEV_* event to handle * @net_dev: net_device which generated an event diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index bad2e50135e8..b1855d9d0b06 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -100,7 +100,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net *net, const char *iface_name); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, enum batadv_hard_if_cleanup autodel); -void batadv_hardif_remove_interfaces(void); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_release(struct kref *ref); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 519c08c2cfba..70fee9b42e25 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -137,7 +137,6 @@ static void __exit batadv_exit(void) batadv_netlink_unregister(); rtnl_link_unregister(&batadv_link_ops); unregister_netdevice_notifier(&batadv_hard_if_notifier); - batadv_hardif_remove_interfaces(); flush_workqueue(batadv_event_workqueue); destroy_workqueue(batadv_event_workqueue); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 0393bb9ed3d0..a47dc332d796 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2020.3" +#define BATADV_SOURCE_VERSION "2020.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index bdc4a1fba1c6..1622c3f5898f 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -207,7 +207,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; /* TODO: ask the bridge if a multicast router is present (the bridge - * is capable of performing proper RFC4286 multicast multicast router + * is capable of performing proper RFC4286 multicast router * discovery) instead of searching for a ff02::2 listener here */ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 48d707850f3e..61ddd6d709a0 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -26,8 +26,8 @@ #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/printk.h> -#include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -250,7 +250,7 @@ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) /** * batadv_nc_packet_free() - frees nc packet * @nc_packet: the nc packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped */ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet, bool dropped) diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index d267b94800d6..87017332b567 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -461,7 +461,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 23833a0ba5e6..9d3974ba11ed 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -649,7 +649,7 @@ static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv, /** * batadv_interface_add_vid() - ndo_add_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the new vlan * * Set up all the internal structures for handling the new vlan on top of the @@ -707,7 +707,7 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, /** * batadv_interface_kill_vid() - ndo_kill_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the deleted vlan * * Destroy all the internal structures used to handle the vlan identified by vid diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ed519efa3c36..965336a3b89d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1492,7 +1492,7 @@ struct batadv_tp_vars { /** @unacked_lock: protect unacked_list */ spinlock_t unacked_lock; - /** @last_recv_time: time time (jiffies) a msg was received */ + /** @last_recv_time: time (jiffies) a msg was received */ unsigned long last_recv_time; /** @refcount: number of context where the object is used */ @@ -1996,7 +1996,7 @@ struct batadv_tt_change_node { */ struct batadv_tt_req_node { /** - * @addr: mac address address of the originator this request was sent to + * @addr: mac address of the originator this request was sent to */ u8 addr[ETH_ALEN]; diff --git a/net/core/datagram.c b/net/core/datagram.c index 639745d4f3b9..9fcaa544f11a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; + struct page *last_head = NULL; size_t start; ssize_t copied; unsigned long truesize; - int n = 0; + int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } - while (copied) { + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - skb_fill_page_desc(skb, frag++, pages[n], start, size); - start = 0; + struct page *head = compound_head(pages[n]); + + start += (pages[n] - head) << PAGE_SHIFT; copied -= size; n++; + if (frag) { + skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1]; + + if (head == skb_frag_page(last) && + start == skb_frag_off(last) + skb_frag_size(last)) { + skb_frag_size_add(last, size); + /* We combined this page, we need to release + * a reference. Since compound pages refcount + * is shared among many pages, batch the refcount + * adjustments to limit false sharing. + */ + last_head = head; + refs++; + continue; + } + } + if (refs) { + page_ref_sub(last_head, refs); + refs = 0; + } + skb_fill_page_desc(skb, frag++, head, start, size); } + if (refs) + page_ref_sub(last_head, refs); } return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index b5d1129d8310..d42c9ea0c3c0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8742,13 +8742,15 @@ struct bpf_xdp_link { int flags; }; -static enum bpf_xdp_mode dev_xdp_mode(u32 flags) +static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; - return XDP_MODE_SKB; + if (flags & XDP_FLAGS_SKB_MODE) + return XDP_MODE_SKB; + return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) @@ -8896,7 +8898,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack return -EINVAL; } - mode = dev_xdp_mode(flags); + mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); @@ -8984,7 +8986,7 @@ static int dev_xdp_detach_link(struct net_device *dev, ASSERT_RTNL(); - mode = dev_xdp_mode(link->flags); + mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; @@ -9080,7 +9082,7 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, goto out_unlock; } - mode = dev_xdp_mode(xdp_link->flags); + mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); @@ -9164,7 +9166,7 @@ out_put_dev: int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { - enum bpf_xdp_mode mode = dev_xdp_mode(flags); + enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; diff --git a/net/core/devlink.c b/net/core/devlink.c index e5feb87beca7..58c8bb07fa19 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5895,6 +5895,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; + mutex_lock(&devlink->lock); list_for_each_entry(port, &devlink->port_list, list) { mutex_lock(&port->reporters_lock); list_for_each_entry(reporter, &port->reporter_list, list) { @@ -5909,12 +5910,14 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&port->reporters_lock); + mutex_unlock(&devlink->lock); goto out; } idx++; } mutex_unlock(&port->reporters_lock); } + mutex_unlock(&devlink->lock); } out: mutex_unlock(&devlink_mutex); @@ -7555,11 +7558,11 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; spin_lock_init(&devlink_port->type_lock); + INIT_LIST_HEAD(&devlink_port->reporter_list); + mutex_init(&devlink_port->reporters_lock); list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); - INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); @@ -7576,13 +7579,13 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; - WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); list_del(&devlink_port->list); mutex_unlock(&devlink->lock); + WARN_ON(!list_empty(&devlink_port->reporter_list)); + mutex_destroy(&devlink_port->reporters_lock); } EXPORT_SYMBOL_GPL(devlink_port_unregister); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index d964a5147f22..e33fde06d528 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ptp_classify_raw); +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type) +{ + u8 *ptr = skb_mac_header(skb); + + if (type & PTP_CLASS_VLAN) + ptr += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + ptr += IPV4_HLEN(ptr) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + ptr += IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + break; + default: + return NULL; + } + + ptr += ETH_HLEN; + + /* Ensure that the entire header is present in this packet. */ + if (ptr + sizeof(struct ptp_header) > skb->data + skb->len) + return NULL; + + return (struct ptp_header *)ptr; +} +EXPORT_SYMBOL_GPL(ptp_parse_header); + void __init ptp_classifier_init(void) { static struct sock_filter ptp_filter[] __initdata = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2f7dd689bccc..a5c11aae9c89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5986,9 +5986,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - if (k == 0) { - /* split line is in frag list */ - pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask); + /* split line is in frag list */ + if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { + /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ + if (skb_has_frag_list(skb)) + kfree_skb_list(skb_shinfo(skb)->frag_list); + kfree(data); + return -ENOMEM; } skb_release_data(skb); diff --git a/net/core/sock.c b/net/core/sock.c index e4f40b175acb..64d2aec5ed45 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -413,18 +413,6 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } -static void sock_warn_obsolete_bsdism(const char *name) -{ - static int warned; - static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", - warncomm, name); - warned++; - } -} - static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -984,7 +972,6 @@ set_sndbuf: break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); break; case SO_PASSCRED: @@ -1387,7 +1374,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); break; case SO_TIMESTAMP_OLD: diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6ada114bbcca..d86d8d11cfe4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -22,7 +22,7 @@ #include <net/busy_poll.h> #include <net/pkt_sched.h> -static int two __maybe_unused = 2; +static int two = 2; static int three = 3; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; @@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "devconf_inherit_init_net", @@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = { { } }; +static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) +{ + /* fallback tunnels for initns only */ + if (!strncmp(str, "initns", 6)) + sysctl_fb_tunnels_only_for_init_net = 1; + /* no fallback tunnels anywhere */ + else if (!strncmp(str, "none", 4)) + sysctl_fb_tunnels_only_for_init_net = 2; + + return 1; +} +__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); + static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 0a72510d5de1..8f3dd3b1d2d0 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -274,7 +274,7 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) /** * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection * This routine is called when the peer acknowledges the receipt of Ack Vectors - * up to and including @ackno. While based on on section A.3 of RFC 4340, here + * up to and including @ackno. While based on section A.3 of RFC 4340, here * are additional precautions to prevent corrupted buffer state. In particular, * we use tail_ackno to identify outdated records; it always marks the earliest * packet of group (2) in 11.4.2. diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index aef72f6a2829..b9ee1a4a8955 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -608,7 +608,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, */ if (hc->rx_x_recv > 0) break; - /* fall through */ + fallthrough; case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) diff --git a/net/dccp/feat.c b/net/dccp/feat.c index afc071ea1271..788dd629c420 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1407,7 +1407,8 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Negotiation during connection setup */ case DCCP_LISTEN: - server = true; /* fall through */ + server = true; + fallthrough; case DCCP_REQUESTING: switch (opt) { case DCCPO_CHANGE_L: diff --git a/net/dccp/input.c b/net/dccp/input.c index bd9cfdb67436..2cbb757a894f 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -64,7 +64,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) */ if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) break; - /* fall through */ + fallthrough; case DCCP_REQUESTING: case DCCP_ACTIVE_CLOSEREQ: dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); @@ -76,7 +76,7 @@ static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSE); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSE: /* * Retransmitted Close: we have already enqueued the first one. @@ -113,7 +113,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) queued = 1; dccp_fin(sk, skb); dccp_set_state(sk, DCCP_PASSIVE_CLOSEREQ); - /* fall through */ + fallthrough; case DCCP_PASSIVE_CLOSEREQ: sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); } @@ -530,7 +530,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* @@ -684,7 +684,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Step 8: if using Ack Vectors, mark packet acknowledgeable */ dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); - /* fall through */ + fallthrough; case DCCP_RESPOND: queued = dccp_rcv_respond_partopen_state_process(sk, skb, dh, len); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 9c28c8251125..d8f3751a512b 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -731,7 +731,7 @@ int dccp_invalid_packet(struct sk_buff *skb) return 1; } /* - * If P.Data Offset is too too large for packet, drop packet and return + * If P.Data Offset is too large for packet, drop packet and return */ if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); diff --git a/net/dccp/options.c b/net/dccp/options.c index 51aaba7a5d45..d24cad05001e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -225,7 +225,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ - /* fall through */ + fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) diff --git a/net/dccp/output.c b/net/dccp/output.c index 6433187a5cc4..50e6d5699bb2 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -62,7 +62,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) switch (dcb->dccpd_type) { case DCCP_PKT_DATA: set_ack = 0; - /* fall through */ + fallthrough; case DCCP_PKT_DATAACK: case DCCP_PKT_RESET: break; @@ -72,12 +72,12 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* Use ISS on the first (non-retransmitted) Request. */ if (icsk->icsk_retransmits == 0) dcb->dccpd_seq = dp->dccps_iss; - /* fall through */ + fallthrough; case DCCP_PKT_SYNC: case DCCP_PKT_SYNCACK: ackno = dcb->dccpd_ack_seq; - /* fall through */ + fallthrough; default: /* * Set owner/destructor: some skbs are allocated via @@ -481,7 +481,7 @@ struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb) case DCCP_RESET_CODE_PACKET_ERROR: dhr->dccph_reset_data[0] = rxdh->dccph_type; break; - case DCCP_RESET_CODE_OPTION_ERROR: /* fall through */ + case DCCP_RESET_CODE_OPTION_ERROR: case DCCP_RESET_CODE_MANDATORY_ERROR: memcpy(dhr->dccph_reset_data, dcb->dccpd_reset_data, 3); break; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index d148ab1530e5..6d705d90c614 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -101,7 +101,7 @@ void dccp_set_state(struct sock *sk, const int state) if (inet_csk(sk)->icsk_bind_hash != NULL && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); - /* fall through */ + fallthrough; default: if (oldstate == DCCP_OPEN) DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); @@ -834,7 +834,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, case DCCP_PKT_CLOSEREQ: if (!(flags & MSG_PEEK)) dccp_finish_passive_close(sk); - /* fall through */ + fallthrough; case DCCP_PKT_RESET: dccp_pr_debug("found fin (%s) ok!\n", dccp_packet_name(dh->dccph_type)); @@ -960,7 +960,7 @@ static void dccp_terminate_connection(struct sock *sk) case DCCP_PARTOPEN: dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); - /* fall through */ + fallthrough; case DCCP_OPEN: dccp_send_close(sk, 1); @@ -969,7 +969,7 @@ static void dccp_terminate_connection(struct sock *sk) next_state = DCCP_ACTIVE_CLOSEREQ; else next_state = DCCP_CLOSING; - /* fall through */ + fallthrough; default: dccp_set_state(sk, next_state); } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 0e06dfc32273..927c796d7682 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -85,7 +85,7 @@ static void dccp_retransmit_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); /* - * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was + * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 4e632dc987d8..495635f152ba 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1]; @@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); ethnl_features_to_bitmap(old_active, dev->features); + ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); @@ -261,17 +264,15 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) goto out_rtnl; } - /* set req_wanted bits not in req_mask from old_active */ + /* set req_wanted bits not in req_mask from old_wanted */ bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT); - bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT); - bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT); - if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) { - ret = 0; - goto out_rtnl; + bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT); + bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT); + if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) { + dev->wanted_features &= ~dev->hw_features; + dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features; + __netdev_update_features(dev); } - - dev->wanted_features = ethnl_bitmap_to_features(req_wanted); - __netdev_update_features(dev); ethnl_features_to_bitmap(new_active, dev->features); mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 925b5731bf0c..d497ca064ef7 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -3025,13 +3025,14 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) case TCP_V4_FLOW: case TCP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_TCP; + match->mask.basic.ip_proto = 0xff; break; case UDP_V4_FLOW: case UDP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_UDP; + match->mask.basic.ip_proto = 0xff; break; } - match->mask.basic.ip_proto = 0xff; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 60db5a6487cc..87983e70f03f 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,13 +661,13 @@ config TCP_CONG_BBR BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to maximize network utilization and minimize queues. It builds an explicit - model of the the bottleneck delivery rate and path round-trip - propagation delay. It tolerates packet loss and delay unrelated to - congestion. It can operate over LAN, WAN, cellular, wifi, or cable - modem links. It can coexist with flows that use loss-based congestion - control, and can operate with shallow buffers, deep buffers, - bufferbloat, policers, or AQM schemes that do not provide a delay - signal. It requires the fq ("Fair Queue") pacing packet scheduler. + model of the bottleneck delivery rate and path round-trip propagation + delay. It tolerates packet loss and delay unrelated to congestion. It + can operate over LAN, WAN, cellular, wifi, or cable modem links. It can + coexist with flows that use loss-based congestion control, and can + operate with shallow buffers, deep buffers, bufferbloat, policers, or + AQM schemes that do not provide a delay signal. It requires the fq + ("Fair Queue") pacing packet scheduler. choice prompt "Default TCP congestion control" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4307503a6f0b..b7260c8cef2e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1017,6 +1017,7 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index abd083415f89..5308cfa3de62 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -237,7 +237,7 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ @@ -429,7 +429,7 @@ next_proto: /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index cf36f955bfe6..8f2e974a1e4d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -690,9 +690,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_unlock(); } - tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | + tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) | IPTOS_PREC_INTERNETCONTROL) : - iph->tos; + iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) @@ -784,7 +784,7 @@ EXPORT_SYMBOL(icmp_ndo_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 239e54474b65..8cbe74313f38 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -228,7 +228,7 @@ static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk) static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const __be32 daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -277,15 +277,13 @@ static struct sock *inet_lhash2_lookup(struct net *net, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, - dif, sdif, exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 948747aac4e2..da1b5038bdfd 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -47,32 +47,32 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, unsigned char *iph = skb_network_header(skb); memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options)); - memcpy(iph+sizeof(struct iphdr), opt->__data, opt->optlen); + memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen); opt = &(IPCB(skb)->opt); if (opt->srr) - memcpy(iph+opt->srr+iph[opt->srr+1]-4, &daddr, 4); + memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); if (!is_frag) { if (opt->rr_needaddr) - ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt); + ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); if (opt->ts_needaddr) - ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt); + ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); if (opt->ts_needtime) { __be32 midtime; midtime = inet_current_timestamp(); - memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4); + memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } return; } if (opt->rr) { - memset(iph+opt->rr, IPOPT_NOP, iph[opt->rr+1]); + memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]); opt->rr = 0; opt->rr_needaddr = 0; } if (opt->ts) { - memset(iph+opt->ts, IPOPT_NOP, iph[opt->ts+1]); + memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]); opt->ts = 0; opt->ts_needaddr = opt->ts_needtime = 0; } @@ -495,26 +495,29 @@ EXPORT_SYMBOL(ip_options_compile); void ip_options_undo(struct ip_options *opt) { if (opt->srr) { - unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr); - memmove(optptr+7, optptr+3, optptr[1]-7); - memcpy(optptr+3, &opt->faddr, 4); + unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr); + + memmove(optptr + 7, optptr + 3, optptr[1] - 7); + memcpy(optptr + 3, &opt->faddr, 4); } if (opt->rr_needaddr) { - unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr); + optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } if (opt->ts) { - unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr); + if (opt->ts_needtime) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); - if ((optptr[3]&0xF) == IPOPT_TS_PRESPEC) + memset(&optptr[optptr[2] - 1], 0, 4); + if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC) optptr[2] -= 4; } if (opt->ts_needaddr) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 61f802d5350c..b931d0b02e49 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -996,7 +996,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; + maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1351,7 +1351,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (cork->flags & IPCORK_OPT) opt = cork->opt; - if (!(rt->dst.dev->features&NETIF_F_SG)) + if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1536,7 +1536,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_select_ident(net, skb, sk); if (opt) { - iph->ihl += opt->optlen>>2; + iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt, 0); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d2c223554ff7..ec6036713e2c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1124,8 +1124,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, dev_put(dev); err = -EINVAL; - if (sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; inet->uc_index = ifindex; @@ -1189,7 +1188,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, err = -EINVAL; if (sk->sk_bound_dev_if && mreq.imr_ifindex != sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + midx != sk->sk_bound_dev_if) break; inet->mc_index = mreq.imr_ifindex; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index cc8049b100b2..bf9d4cd2d6e5 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -133,12 +133,9 @@ static struct nexthop *nexthop_alloc(void) static struct nh_group *nexthop_grp_alloc(u16 num_nh) { - size_t sz = offsetof(struct nexthop, nh_grp) - + sizeof(struct nh_group) - + sizeof(struct nh_grp_entry) * num_nh; struct nh_group *nhg; - nhg = kzalloc(sz, GFP_KERNEL); + nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; @@ -279,7 +276,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && - nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) + nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; @@ -446,7 +443,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], unsigned int i, j; u8 nhg_fdb = 0; - if (len & (sizeof(struct nexthop_grp) - 1)) { + if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; @@ -800,7 +797,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, return; } - newg->has_v4 = nhg->has_v4; + newg->has_v4 = false; newg->mpath = nhg->mpath; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; @@ -809,12 +806,18 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { + struct nh_info *nhi; + /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + newg->has_v4 = true; + list_del(&nhges[i].nh_list); new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; @@ -961,6 +964,23 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, return 0; } +static void nh_group_v4_update(struct nh_group *nhg) +{ + struct nh_grp_entry *nhges; + bool has_v4 = false; + int i; + + nhges = nhg->nh_entries; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_info *nhi; + + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + has_v4 = true; + } + nhg->has_v4 = has_v4; +} + static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) @@ -984,6 +1004,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); + /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially + * update IPv4 indication in all the groups using the nexthop. + */ + if (oldi->family == AF_INET && newi->family == AF_INET6) { + struct nh_grp_entry *nhge; + + list_for_each_entry(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + struct nh_group *nhg; + + nhg = rtnl_dereference(nhp->nh_grp); + nh_group_v4_update(nhg); + } + } + return 0; } @@ -1101,7 +1136,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, while (1) { struct nexthop *nh; - next = rtnl_dereference(*pp); + next = *pp; if (!next) break; @@ -1187,6 +1222,9 @@ static struct nexthop *nexthop_create_group(struct net *net, struct nexthop *nh; int i; + if (WARN_ON(!num_nh)) + return ERR_PTR(-EINVAL); + nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index df6fbefe44d4..248856b301c4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -293,7 +293,8 @@ EXPORT_SYMBOL_GPL(ping_close); /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, - struct sockaddr *uaddr, int addr_len) { + struct sockaddr *uaddr, int addr_len) +{ struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; @@ -310,10 +311,10 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); - if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; + else + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || @@ -383,20 +384,6 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) } } -static void ping_clear_saddr(struct sock *sk, int dif) -{ - sk->sk_bound_dev_if = dif; - if (sk->sk_family == AF_INET) { - struct inet_sock *isk = inet_sk(sk); - isk->inet_rcv_saddr = isk->inet_saddr = 0; -#if IS_ENABLED(CONFIG_IPV6) - } else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); - memset(&np->saddr, 0, sizeof(np->saddr)); -#endif - } -} /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. @@ -420,12 +407,13 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; err = -EADDRINUSE; - ping_set_saddr(sk, uaddr); snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); if (ping_get_port(sk, snum) != 0) { - ping_clear_saddr(sk, dif); + /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ + sk->sk_bound_dev_if = dif; goto out; } + ping_set_saddr(sk, uaddr); pr_debug("after bind(): num = %hu, dif = %d\n", isk->inet_num, @@ -647,7 +635,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, } int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, - void *user_icmph, size_t icmph_len) { + void *user_icmph, size_t icmph_len) +{ u8 type, code; if (len > 0xFFFF) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6fd4330287c2..dfba39473b1d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -260,11 +260,12 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) err = EHOSTUNREACH; if (code > NR_ICMP_UNREACH) break; - err = icmp_err_convert[code].errno; - harderr = icmp_err_convert[code].fatal; if (code == ICMP_FRAG_NEEDED) { harderr = inet->pmtudisc != IP_PMTUDISC_DONT; err = EMSGSIZE; + } else { + err = icmp_err_convert[code].errno; + harderr = icmp_err_convert[code].fatal; } } @@ -611,7 +612,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and - * and uc_index is set. oif is most likely set + * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8ca6bcab7b03..2c05b863ae43 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -623,7 +623,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) u32 hval; net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32) daddr, fnhe_hashrnd); + hval = jhash_1word((__force u32)daddr, fnhe_hashrnd); return hash_32(hval, FNHE_HASH_SHIFT); } @@ -1013,13 +1013,14 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; - u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; + u32 old_mtu; if (ip_mtu_locked(dst)) return; + old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; @@ -1061,7 +1062,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); @@ -1078,7 +1079,7 @@ EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1096,7 +1097,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; @@ -1126,7 +1127,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu); + __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) @@ -1151,7 +1152,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1167,7 +1168,7 @@ EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); @@ -1307,7 +1308,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) static unsigned int ipv4_mtu(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *) dst; + const struct rtable *rt = (const struct rtable *)dst; unsigned int mtu = rt->rt_pmtu; if (!mtu || time_after_eq(jiffies, rt->dst.expires)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 631a5ee0dd4e..af27cfa9d8d3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -575,7 +575,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is - * is already accepted it is treated as a connected one below. + * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 6cebf412d590..5842081bc8a2 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -10,7 +10,7 @@ #include <net/tcp.h> /* These factors derived from the recommended values in the aer: - * .01 and and 7/8. + * .01 and 7/8. */ #define TCP_SCALABLE_AI_CNT 100U #define TCP_SCALABLE_MD_SCALE 3 diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e88efba07551..09f0a23d1a01 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1170,7 +1170,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and - * and uc_index is set. oif is most likely set + * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8e761b8c47c6..01146b66d666 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1893,12 +1893,13 @@ EXPORT_SYMBOL(ipv6_chk_addr); * 2. does the address exist on the specific device * (skip_dev_check = false) */ -int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, - const struct net_device *dev, bool skip_dev_check, - int strict, u32 banned_flags) +static struct net_device * +__ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); - const struct net_device *l3mdev; + struct net_device *l3mdev, *ndev; struct inet6_ifaddr *ifp; u32 ifp_flags; @@ -1909,10 +1910,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, dev = NULL; hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) + ndev = ifp->idev->dev; + if (!net_eq(dev_net(ndev), net)) continue; - if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev) + if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; /* Decouple optimistic from tentative for evaluation here. @@ -1923,15 +1925,23 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && - (!dev || ifp->idev->dev == dev || + (!dev || ndev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock(); - return 1; + return ndev; } } rcu_read_unlock(); - return 0; + return NULL; +} + +int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) +{ + return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check, + strict, banned_flags) ? 1 : 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); @@ -1990,35 +2000,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix); * * The caller should be protected by RCU, or RTNL. */ -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr) +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev) { - unsigned int hash = inet6_addr_hash(net, addr); - struct inet6_ifaddr *ifp, *result = NULL; - struct net_device *dev = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (net_eq(dev_net(ifp->idev->dev), net) && - ipv6_addr_equal(&ifp->addr, addr)) { - result = ifp; - break; - } - } - - if (!result) { - struct rt6_info *rt; - - rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); - if (rt) { - dev = rt->dst.dev; - ip6_rt_put(rt); - } - } else { - dev = result->idev->dev; - } - rcu_read_unlock(); - - return dev; + return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1, + IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_dev_find); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9ebf3fe0d2b1..c70c192bc91b 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt, return -EAFNOSUPPORT; } +static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) +{ + kfree_skb(skb); + return -EAFNOSUPPORT; +} + const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, @@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, + .ipv6_fragment = eafnosupport_ipv6_fragment, }; EXPORT_SYMBOL_GPL(ipv6_stub); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0306509ab063..e648fbebb167 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -661,6 +661,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, @@ -1026,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .xfrm6_rcv_encap = xfrm6_rcv_encap, #endif .nd_tbl = &nd_tbl, + .ipv6_fragment = ip6_fragment, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2d3add9e6116..55c290d55605 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet6_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, dif, sdif, - exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 25a90f3f705c..44d68ed70f24 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1812,10 +1812,14 @@ static struct fib6_node *fib6_repair_tree(struct net *net, children = 0; child = NULL; - if (fn_r) - child = fn_r, children |= 1; - if (fn_l) - child = fn_l, children |= 2; + if (fn_r) { + child = fn_r; + children |= 1; + } + if (fn_l) { + child = fn_l; + children |= 2; + } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f635914f42ec..a0217e5bf3bc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -915,7 +915,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, struct metadata_dst *tun_dst, bool log_ecn_err) { - return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate, + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb); + + dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; + if (tpi->proto == htons(ETH_P_IP)) + dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; + + return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile index 399a7e5db2f4..cf8f27071d3f 100644 --- a/net/l2tp/Makefile +++ b/net/l2tp/Makefile @@ -5,6 +5,8 @@ obj-$(CONFIG_L2TP) += l2tp_core.o +CFLAGS_l2tp_core.o += -I$(src) + # Build l2tp as modules if L2TP is M obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 701fc72ad9f4..560c687f5457 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -61,6 +61,10 @@ #include <linux/atomic.h> #include "l2tp_core.h" +#include "trace.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" #define L2TP_DRV_VERSION "V2.0" @@ -151,6 +155,7 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } @@ -159,6 +164,8 @@ static void l2tp_session_free(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; + trace_free_session(session); + if (tunnel) { if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) goto out; @@ -381,6 +388,8 @@ int l2tp_session_register(struct l2tp_session *session, hlist_add_head(&session->hlist, head); write_unlock_bh(&tunnel->hlist_lock); + trace_register_session(session); + return 0; err_tlock_pnlock: @@ -409,10 +418,6 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", - session->name, ns, L2TP_SKB_CB(skbp)->ns, - skb_queue_len(&session->reorder_q)); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } @@ -445,9 +450,7 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; - - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n", - session->name, session->nr); + trace_session_seqnum_update(session); } /* call private receive handler */ @@ -472,37 +475,27 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { - if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + /* If the packet has been pending on the queue for too long, discard it */ + if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } - if (L2TP_SKB_CB(skb)->has_seq) { + if (cb->has_seq) { if (session->reorder_skip) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: advancing nr to next pkt: %u -> %u", - session->name, session->nr, - L2TP_SKB_CB(skb)->ns); session->reorder_skip = 0; - session->nr = L2TP_SKB_CB(skb)->ns; + session->nr = cb->ns; + trace_session_seqnum_reset(session); } - if (L2TP_SKB_CB(skb)->ns != session->nr) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: holding oos pkt %u len %d, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + if (cb->ns != session->nr) goto out; - } } __skb_unlink(skb, &session->reorder_q); @@ -535,14 +528,13 @@ static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { - if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %u len %d discarded, outside window, nr=%u\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr); + trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } @@ -559,10 +551,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ - if (L2TP_SKB_CB(skb)->ns == session->nr) { + if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { - u32 nr_oos = L2TP_SKB_CB(skb)->ns; + u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) @@ -573,17 +565,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: %d oos packets received. Resetting sequence numbers\n", - session->name, session->nr_oos_count); } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); @@ -660,16 +645,14 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int length) { struct l2tp_tunnel *tunnel = session->tunnel; - u32 ns = 0, nr = 0; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -686,32 +669,21 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { - ns = ntohs(*(__be16 *)ptr); - ptr += 2; - nr = ntohs(*(__be16 *)ptr); - ptr += 2; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; + ptr += 2; + /* Skip past nr in the header */ + ptr += 2; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, nr=%u, session nr=%u\n", - session->name, ns, nr, session->nr); } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { - ns = l2h & 0x00ffffff; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; - - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, session nr=%u\n", - session->name, ns, session->nr); } ptr += 4; } @@ -722,9 +694,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * configure it so. */ if (!session->lns_mode && !session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to enable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } @@ -733,9 +703,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -746,15 +715,12 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to disable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -847,22 +813,11 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); + pr_warn_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); goto error; } - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - /* Point to L2TP header */ optr = skb->data; ptr = skb->data; @@ -873,9 +828,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); + pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); goto error; } @@ -883,12 +837,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) length = skb->len; /* If type is control packet, it is handled by userspace. */ - if (hdrflags & L2TP_HDRFLAG_T) { - l2tp_dbg(tunnel, L2TP_MSG_DATA, - "%s: recv control packet, len=%d\n", - tunnel->name, length); + if (hdrflags & L2TP_HDRFLAG_T) goto error; - } /* Skip flags */ ptr += 2; @@ -917,9 +867,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); + pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); goto error; } @@ -953,9 +902,6 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!tunnel) goto pass_up; - l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", - tunnel->name, skb->len); - if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; @@ -993,8 +939,7 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) *bufp++ = 0; session->ns++; session->ns &= 0xffff; - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } return bufp - optr; @@ -1030,9 +975,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); @@ -1049,23 +992,6 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int len = skb->len; int error; - /* Debug */ - if (session->send_seq) - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes, ns=%u\n", - session->name, data_len, session->ns - 1); - else - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes\n", - session->name, data_len); - - if (session->debug & L2TP_MSG_DATA) { - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - unsigned char *datap = skb->data + uhlen; - - pr_debug("%s: xmit\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, - datap, min_t(size_t, 32, len - uhlen)); - } - /* Queue the packet to IP for output */ skb->ignore_df = 1; skb_dst_drop(skb); @@ -1195,8 +1121,6 @@ static void l2tp_tunnel_destruct(struct sock *sk) if (!tunnel) goto end; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1255,9 +1179,6 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) struct hlist_node *tmp; struct l2tp_session *session; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n", - tunnel->name); - write_lock_bh(&tunnel->hlist_lock); tunnel->acpt_newsess = false; for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { @@ -1265,9 +1186,6 @@ again: hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) { session = hlist_entry(walk, struct l2tp_session, hlist); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: closing session\n", session->name); - hlist_del_init(&session->hlist); if (test_and_set_bit(0, &session->dead)) @@ -1483,16 +1401,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS; tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); rwlock_init(&tunnel->hlist_lock); tunnel->acpt_newsess = true; - if (cfg) - tunnel->debug = cfg->debug; - tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); @@ -1597,6 +1511,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + trace_register_tunnel(tunnel); + if (tunnel->fd >= 0) sockfd_put(sock); @@ -1617,6 +1533,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_register); void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { + trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } @@ -1628,6 +1545,7 @@ void l2tp_session_delete(struct l2tp_session *session) if (test_and_set_bit(0, &session->dead)) return; + trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) @@ -1686,12 +1604,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn INIT_HLIST_NODE(&session->hlist); INIT_HLIST_NODE(&session->global_hlist); - /* Inherit debug options from tunnel */ - session->debug = tunnel->debug; - if (cfg) { session->pwtype = cfg->pw_type; - session->debug = cfg->debug; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 3468d6b177a0..07249c5f22ef 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -51,7 +51,6 @@ struct l2tp_session_cfg { unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ @@ -66,6 +65,7 @@ struct l2tp_session_cfg { * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into * an additional per-net ("global") hashlist. */ +#define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; @@ -90,14 +90,13 @@ struct l2tp_session { struct hlist_node hlist; /* hash list node */ refcount_t ref_count; - char name[32]; /* for logging */ + char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence numbers? */ unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ int reorder_timeout; /* configured reorder timeout (in jiffies) */ int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; @@ -131,7 +130,6 @@ struct l2tp_session { /* L2TP tunnel configuration */ struct l2tp_tunnel_cfg { - int debug; /* bitmask of debug message categories */ enum l2tp_encap_type encap; /* Used only for kernel-created sockets */ @@ -154,6 +152,7 @@ struct l2tp_tunnel_cfg { * Maintains a hashlist of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ +#define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ @@ -170,8 +169,7 @@ struct l2tp_tunnel { u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ - char name[20]; /* for logging */ - int debug; /* bitmask of debug message categories */ + char name[L2TP_TUNNEL_NAME_MAX]; /* for logging */ enum l2tp_encap_type encap; struct l2tp_stats stats; @@ -337,19 +335,6 @@ static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, str return 0; } -#define l2tp_printk(ptr, type, func, fmt, ...) \ -do { \ - if (((ptr)->debug) & (type)) \ - func(fmt, ##__VA_ARGS__); \ -} while (0) - -#define l2tp_warn(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_warn, fmt, ##__VA_ARGS__) -#define l2tp_info(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_info, fmt, ##__VA_ARGS__) -#define l2tp_dbg(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_L2TP_PWTYPE(type) \ MODULE_ALIAS("net-l2tp-type-" __stringify(type)) diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 96cb9601c21b..bca75bef8282 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -167,7 +167,7 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0, refcount_read(&tunnel->ref_count)); seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -192,7 +192,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " offset 0 l2specific %hu/%hu\n", session->l2specific_type, l2tp_get_l2specific_len(session)); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 7ed2b4eced94..657edad1263e 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -128,17 +128,6 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, struct net_device *dev; struct l2tp_eth *priv; - if (session->debug & L2TP_MSG_DATA) { - unsigned int length; - - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: eth recv\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - if (!pskb_may_pull(skb, ETH_HLEN)) goto error; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index df2a35b5714a..7086d97f293c 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -118,7 +118,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -147,20 +146,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bc757bc7e264..409ea8927f6c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -131,7 +131,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -160,20 +159,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index def78eebca4c..31a1e27eab20 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -229,9 +229,6 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info goto out; } - if (attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(attrs[L2TP_ATTR_DEBUG]); - ret = -EINVAL; switch (cfg.encap) { case L2TP_ENCAPTYPE_UDP: @@ -307,9 +304,6 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); @@ -400,7 +394,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) || nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap)) goto nla_put_failure; @@ -605,9 +599,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); } - if (info->attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) cfg.recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -689,9 +680,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -730,7 +718,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype)) goto nla_put_failure; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 13c3153b40d6..450637ffa557 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -237,17 +237,9 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to ppp\n", - session->name, data_len); - po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to L2TP socket\n", - session->name, data_len); - if (sock_queue_rcv_skb(sk, skb) < 0) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); @@ -259,7 +251,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int no_sock: rcu_read_unlock(); - l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name); + pr_warn_ratelimited("%s: no socket in recv\n", session->name); kfree_skb(skb); } @@ -710,7 +702,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (!tunnel) { struct l2tp_tunnel_cfg tcfg = { .encap = L2TP_ENCAPTYPE_UDP, - .debug = 0, }; /* Prevent l2tp_tunnel_register() from trying to set up @@ -840,8 +831,6 @@ out_no_ppp: drop_refcnt = false; sk->sk_state = PPPOX_CONNECTED; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n", - session->name); end: if (error) { @@ -1157,9 +1146,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - tunnel->debug = val; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ break; default: @@ -1185,9 +1172,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->recv_seq = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set recv_seq=%d\n", - session->name, session->recv_seq); break; case PPPOL2TP_SO_SENDSEQ: @@ -1203,9 +1187,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } l2tp_session_set_header_len(session, session->tunnel->version); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set send_seq=%d\n", - session->name, session->send_seq); break; case PPPOL2TP_SO_LNSMODE: @@ -1214,22 +1195,14 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->lns_mode = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set lns_mode=%d\n", - session->name, session->lns_mode); break; case PPPOL2TP_SO_DEBUG: - session->debug = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - session->name, session->debug); + /* Session debug flags option is deprecated */ break; case PPPOL2TP_SO_REORDERTO: session->reorder_timeout = msecs_to_jiffies(val); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set reorder_timeout=%d\n", - session->name, session->reorder_timeout); break; default: @@ -1297,9 +1270,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - *val = tunnel->debug; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ + *val = 0; break; default: @@ -1321,32 +1293,23 @@ static int pppol2tp_session_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_RECVSEQ: *val = session->recv_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get recv_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_SENDSEQ: *val = session->send_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get send_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_LNSMODE: *val = session->lns_mode; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get lns_mode=%d\n", session->name, *val); break; case PPPOL2TP_SO_DEBUG: - *val = session->debug; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get debug=%d\n", - session->name, *val); + /* Session debug flags option is deprecated */ + *val = 0; break; case PPPOL2TP_SO_REORDERTO: *val = (int)jiffies_to_msecs(session->reorder_timeout); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get reorder_timeout=%d\n", session->name, *val); break; default: @@ -1534,7 +1497,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -1580,7 +1543,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n", session->nr, session->ns, diff --git a/net/l2tp/trace.h b/net/l2tp/trace.h new file mode 100644 index 000000000000..8596eaa12a2e --- /dev/null +++ b/net/l2tp/trace.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM l2tp + +#if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_L2TP_H + +#include <linux/tracepoint.h> +#include <linux/l2tp.h> +#include "l2tp_core.h" + +#define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e } +#define show_encap_type_name(val) \ + __print_symbolic(val, \ + encap_type_name(UDP), \ + encap_type_name(IP)) + +#define pw_type_name(p) { L2TP_PWTYPE_##p, #p } +#define show_pw_type_name(val) \ + __print_symbolic(val, \ + pw_type_name(ETH_VLAN), \ + pw_type_name(ETH), \ + pw_type_name(PPP), \ + pw_type_name(PPP_AC), \ + pw_type_name(IP)) + +DECLARE_EVENT_CLASS(tunnel_only_evt, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +DECLARE_EVENT_CLASS(session_only_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +TRACE_EVENT(register_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + __field(int, fd) + __field(u32, tid) + __field(u32, ptid) + __field(int, version) + __field(enum l2tp_encap_type, encap) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + __entry->fd = tunnel->fd; + __entry->tid = tunnel->tunnel_id; + __entry->ptid = tunnel->peer_tunnel_id; + __entry->version = tunnel->version; + __entry->encap = tunnel->encap; + ), + TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d", + __entry->name, + __entry->fd > 0 ? "managed" : "unmanaged", + show_encap_type_name(__entry->encap), + __entry->version, + __entry->tid, + __entry->ptid, + __entry->fd) +); + +DEFINE_EVENT(tunnel_only_evt, delete_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +DEFINE_EVENT(tunnel_only_evt, free_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +TRACE_EVENT(register_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, tid) + __field(u32, ptid) + __field(u32, sid) + __field(u32, psid) + __field(enum l2tp_pwtype, pwtype) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0; + __entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0; + __entry->sid = session->session_id; + __entry->psid = session->peer_session_id; + __entry->pwtype = session->pwtype; + ), + TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u", + __entry->name, + show_pw_type_name(__entry->pwtype), + __entry->sid, + __entry->psid, + __entry->sid, + __entry->psid) +); + +DEFINE_EVENT(session_only_evt, delete_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, free_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_seqnum_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, ns) + __field(u32, nr) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->ns = session->ns; + __entry->nr = session->nr; + ), + TP_printk("%s: ns=%u nr=%u", + __entry->name, + __entry->ns, + __entry->nr) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_update, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_pkt_discard_evt, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, pkt_ns) + __field(u32, my_nr) + __field(u32, reorder_q_len) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->pkt_ns = pkt_ns, + __entry->my_nr = session->nr; + __entry->reorder_q_len = skb_queue_len(&session->reorder_q); + ), + TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u", + __entry->name, + __entry->pkt_ns, + __entry->my_nr, + __entry->reorder_q_len) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +#endif /* _TRACE_L2TP_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 313ba97acae3..cd4cf84a7f99 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -350,7 +350,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, sta->sta.addr, tid); /* We have no API to update the timeout value in the * driver so reject the timeout update if the timeout - * changed. If if did not change, i.e., no real update, + * changed. If it did not change, i.e., no real update, * just reply with success. */ rcu_read_lock(); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 87fddd84c621..b4e39e31a985 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -826,9 +826,9 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, memcpy(new->data, resp, resp_len); if (csa) - memcpy(new->csa_counter_offsets, csa->counter_offsets_presp, + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); rcu_assign_pointer(sdata->u.ap.probe_resp, new); if (old) @@ -926,10 +926,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, new->tail_len = new_tail_len; if (csa) { - new->csa_current_counter = csa->count; - memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon, + new->cntdwn_current_counter = csa->count; + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); } /* copy in head */ @@ -3186,9 +3186,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, break; if ((params->n_counter_offsets_beacon > - IEEE80211_MAX_CSA_COUNTERS_NUM) || + IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > - IEEE80211_MAX_CSA_COUNTERS_NUM)) + IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) return -EINVAL; csa.counter_offsets_beacon = params->counter_offsets_beacon; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 53632c2f5217..c0963969a465 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -145,9 +145,9 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, *pos++ = csa_settings->block_tx ? 1 : 0; *pos++ = ieee80211_frequency_to_channel( csa_settings->chandef.chan->center_freq); - presp->csa_counter_offsets[0] = (pos - presp->head); + presp->cntdwn_counter_offsets[0] = (pos - presp->head); *pos++ = csa_settings->count; - presp->csa_current_counter = csa_settings->count; + presp->cntdwn_current_counter = csa_settings->count; } /* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0b1eaec6649f..6bf879660a93 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -259,15 +259,15 @@ struct beacon_data { u8 *head, *tail; int head_len, tail_len; struct ieee80211_meshconf_ie *meshconf; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; - u8 csa_current_counter; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; + u8 cntdwn_current_counter; struct rcu_head rcu_head; }; struct probe_resp { struct rcu_head rcu_head; int len; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; u8 data[]; }; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b4a2efe8e83a..523380aed92e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1168,7 +1168,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; } - local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; + local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CNTDWN_COUNTERS_NUM; /* * We use the number of queues for feature tests (QoS, HT) internally diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 7ecd801a943b..ce5825d6f1d1 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -672,7 +672,7 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh) * @hdr: 802.11 frame header * @fc: frame control field * @meshda: destination address in the mesh - * @meshsa: source address address in the mesh. Same as TA, as frame is + * @meshsa: source address in the mesh. Same as TA, as frame is * locally originated. * * Return the length of the 802.11 (does not include a mesh control header) @@ -864,8 +864,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = 0x0; *pos++ = ieee80211_frequency_to_channel( csa->settings.chandef.chan->center_freq); - bcn->csa_current_counter = csa->settings.count; - bcn->csa_counter_offsets[0] = hdr_len + 6; + bcn->cntdwn_current_counter = csa->settings.count; + bcn->cntdwn_counter_offsets[0] = hdr_len + 6; *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f470d1a7ce9b..1ac7b8c374c9 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -916,7 +916,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, if (beacon) for (i = 0; i < params->n_csa_offsets; i++) data[params->csa_offsets[i]] = - beacon->csa_current_counter; + beacon->cntdwn_current_counter; rcu_read_unlock(); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index dca01d7e6e3e..d2136007e2eb 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4538,14 +4538,14 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, return 0; } -static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, - struct beacon_data *beacon) +static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon) { struct probe_resp *resp; u8 *beacon_data; size_t beacon_data_len; int i; - u8 count = beacon->csa_current_counter; + u8 count = beacon->cntdwn_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -4565,36 +4565,36 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, } rcu_read_lock(); - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) { + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) { resp = rcu_dereference(sdata->u.ap.probe_resp); - if (beacon->csa_counter_offsets[i]) { - if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >= + if (beacon->cntdwn_counter_offsets[i]) { + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >= beacon_data_len)) { rcu_read_unlock(); return; } - beacon_data[beacon->csa_counter_offsets[i]] = count; + beacon_data[beacon->cntdwn_counter_offsets[i]] = count; } if (sdata->vif.type == NL80211_IFTYPE_AP && resp) - resp->data[resp->csa_counter_offsets[i]] = count; + resp->data[resp->cntdwn_counter_offsets[i]] = count; } rcu_read_unlock(); } -static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon) +static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon) { - beacon->csa_current_counter--; + beacon->cntdwn_current_counter--; /* the counter should never reach 0 */ - WARN_ON_ONCE(!beacon->csa_current_counter); + WARN_ON_ONCE(!beacon->cntdwn_current_counter); - return beacon->csa_current_counter; + return beacon->cntdwn_current_counter; } -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4612,15 +4612,15 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) if (!beacon) goto unlock; - count = __ieee80211_csa_update_counter(beacon); + count = __ieee80211_beacon_update_cntdwn(beacon); unlock: rcu_read_unlock(); return count; } -EXPORT_SYMBOL(ieee80211_csa_update_counter); +EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn); -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4637,15 +4637,15 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) if (!beacon) goto unlock; - if (counter < beacon->csa_current_counter) - beacon->csa_current_counter = counter; + if (counter < beacon->cntdwn_current_counter) + beacon->cntdwn_current_counter = counter; unlock: rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_csa_set_counter); +EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn); -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4688,20 +4688,21 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) goto out; } - if (!beacon->csa_counter_offsets[0]) + if (!beacon->cntdwn_counter_offsets[0]) goto out; - if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len)) + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len)) goto out; - if (beacon_data[beacon->csa_counter_offsets[0]] == 1) + if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1) ret = true; + out: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(ieee80211_csa_is_complete); +EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete); static int ieee80211_beacon_protect(struct sk_buff *skb, struct ieee80211_local *local, @@ -4761,11 +4762,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, beacon = rcu_dereference(ap->beacon); if (beacon) { - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + ieee80211_beacon_update_cntdwn(vif); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } /* @@ -4809,11 +4810,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + @@ -4833,16 +4834,16 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) /* TODO: For mesh csa_counter is in TU, so * decrementing it by one isn't correct, but * for now we leave it consistent with overall * mac80211's behavior. */ - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } if (ifmsh->sync_ops) @@ -4874,13 +4875,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (offs && beacon) { int i; - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) { - u16 csa_off = beacon->csa_counter_offsets[i]; + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) { + u16 csa_off = beacon->cntdwn_counter_offsets[i]; if (!csa_off) continue; - offs->csa_counter_offs[i] = csa_off_base + csa_off; + offs->cntdwn_counter_offs[i] = csa_off_base + csa_off; } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1aad411a0e46..e6216c4f308c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -24,8 +24,6 @@ #include "protocol.h" #include "mib.h" -#define MPTCP_SAME_STATE TCP_MAX_STATES - #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d07de2c0fbc7..38aaeadec13d 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -600,9 +600,8 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, - " nlbl_domain=%s res=%u", - entry->domain ? entry->domain : "(default)", - ret_val == 0 ? 1 : 0); + " nlbl_domain=%s res=1", + entry->domain ? entry->domain : "(default)"); audit_log_end(audit_buf); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b5f30d7d30d0..5cee1d0eaebe 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -848,7 +848,7 @@ retry: * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) @@ -867,7 +867,7 @@ EXPORT_SYMBOL(__netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) @@ -883,7 +883,7 @@ EXPORT_SYMBOL(netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in all user namespaces. + * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { @@ -898,7 +898,7 @@ EXPORT_SYMBOL(netlink_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap over the network namespace of + * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1eb65a7a27fd..3a718e327515 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -222,7 +222,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) family->mcgrp_offset = first_id; - /* if still initializing, can't and don't need to to realloc bitmaps */ + /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index 46c11c9c212a..5c9e7530865f 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -51,6 +51,9 @@ static int add_policy(struct nl_policy_dump **statep, if (!state) return -ENOMEM; + memset(&state->policies[state->n_alloc], 0, + flex_array_size(state, policies, n_alloc - state->n_alloc)); + state->policies[state->n_alloc].policy = policy; state->policies[state->n_alloc].maxtype = maxtype; state->n_alloc = n_alloc; @@ -261,7 +264,8 @@ send_attribute: else type = NL_ATTR_TYPE_BINARY; - if (pt->validation_type != NLA_VALIDATE_NONE) { + if (pt->validation_type == NLA_VALIDATE_RANGE || + pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG) { struct netlink_range_validation range; nla_get_range_unsigned(pt, &range); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2611657f40ca..855f2c155956 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -9,7 +9,6 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/openvswitch.h> -#include <linux/netfilter_ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> @@ -742,7 +741,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int ovs_vport_output(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); struct vport *vport = data->vport; @@ -848,13 +848,9 @@ static void ovs_fragment(struct net *net, struct vport *vport, ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (key->eth.type == htons(ETH_P_IPV6)) { - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); unsigned long orig_dst; struct rt6_info ovs_rt; - if (!v6ops) - goto err; - prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); memset(&ovs_rt, 0, sizeof(ovs_rt)); @@ -866,7 +862,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(net, skb->sk, skb, ovs_vport_output); + ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", @@ -925,7 +921,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.mru = OVS_CB(skb)->mru; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6e47ef7ef036..bf701b7a394b 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -182,7 +182,7 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) head = vport_hash_bucket(dp, port_no); hlist_for_each_entry_rcu(vport, head, dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -254,7 +254,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) error = ovs_execute_actions(dp, skb, sf_acts, key); if (unlikely(error)) net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", - ovs_dp_name(dp), error); + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; @@ -302,7 +302,7 @@ err: static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, - uint32_t cutlen) + uint32_t cutlen) { unsigned int gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; @@ -1080,11 +1080,12 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, - const struct nlattr *a, - const struct sw_flow_key *key, - const struct sw_flow_mask *mask, - bool log) +static noinline_for_stack +struct sw_flow_actions *get_flow_actions(struct net *net, + const struct nlattr *a, + const struct sw_flow_key *key, + const struct sw_flow_mask *mask, + bool log) { struct sw_flow_actions *acts; struct sw_flow_key masked_key; @@ -1383,7 +1384,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_flow_genl_family, reply, info); } else { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, + PTR_ERR(reply)); } } @@ -1513,7 +1515,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, - flags, cmd); + flags, cmd); if (!ovs_header) goto error; @@ -1572,11 +1574,13 @@ static struct datapath *lookup_datapath(struct net *net, return dp ? dp : ERR_PTR(-ENODEV); } -static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info) +static void ovs_dp_reset_user_features(struct sk_buff *skb, + struct genl_info *info) { struct datapath *dp; - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, + info->attrs); if (IS_ERR(dp)) return; @@ -2075,7 +2079,7 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2093,10 +2097,11 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) int i; dp->max_headroom = new_headroom; - for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); + } } static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) @@ -2551,7 +2556,8 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > + sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index e2235849a57e..87c286ad660e 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -111,12 +111,16 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); if (flow->sf_acts) - ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); + ovs_nla_free_flow_actions((struct sw_flow_actions __force *) + flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); + } + kmem_cache_free(flow_cache, flow); } @@ -164,7 +168,6 @@ static struct table_instance *table_instance_alloc(int new_size) ti->n_buckets = new_size; ti->node_ver = 0; - ti->keep_flows = false; get_random_bytes(&ti->hash_seed, sizeof(u32)); return ti; @@ -192,7 +195,7 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma) * zero based counter we store the value at reset, and subtract it * later when processing. */ - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { ma->masks_usage_zero_cntr[i] = 0; for_each_possible_cpu(cpu) { @@ -273,7 +276,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, if (ma_count >= ma->max) { err = tbl_mask_array_realloc(tbl, ma->max + - MASK_ARRAY_SIZE_MIN); + MASK_ARRAY_SIZE_MIN); if (err) return err; @@ -288,7 +291,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, BUG_ON(ovsl_dereference(ma->masks[ma_count])); rcu_assign_pointer(ma->masks[ma_count], new); - WRITE_ONCE(ma->count, ma_count +1); + WRITE_ONCE(ma->count, ma_count + 1); return 0; } @@ -309,10 +312,10 @@ static void tbl_mask_array_del_mask(struct flow_table *tbl, return; found: - WRITE_ONCE(ma->count, ma_count -1); + WRITE_ONCE(ma->count, ma_count - 1); - rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]); - RCU_INIT_POINTER(ma->masks[ma_count -1], NULL); + rcu_assign_pointer(ma->masks[i], ma->masks[ma_count - 1]); + RCU_INIT_POINTER(ma->masks[ma_count - 1], NULL); kfree_rcu(mask, rcu); @@ -448,26 +451,23 @@ free_mask_cache: static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) { - struct table_instance *ti = container_of(rcu, struct table_instance, rcu); + struct table_instance *ti; + ti = container_of(rcu, struct table_instance, rcu); __table_instance_destroy(ti); } static void table_instance_flow_free(struct flow_table *table, - struct table_instance *ti, - struct table_instance *ufid_ti, - struct sw_flow *flow, - bool count) + struct table_instance *ti, + struct table_instance *ufid_ti, + struct sw_flow *flow) { hlist_del_rcu(&flow->flow_table.node[ti->node_ver]); - if (count) - table->count--; + table->count--; if (ovs_identifier_is_ufid(&flow->id)) { hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); - - if (count) - table->ufid_count--; + table->ufid_count--; } flow_mask_remove(table, flow->mask); @@ -480,22 +480,25 @@ void table_instance_flow_flush(struct flow_table *table, { int i; - if (ti->keep_flows) - return; - for (i = 0; i < ti->n_buckets; i++) { - struct sw_flow *flow; struct hlist_head *head = &ti->buckets[i]; struct hlist_node *n; + struct sw_flow *flow; hlist_for_each_entry_safe(flow, n, head, flow_table.node[ti->node_ver]) { table_instance_flow_free(table, ti, ufid_ti, - flow, false); + flow); ovs_flow_free(flow, true); } } + + if (WARN_ON(table->count != 0 || + table->ufid_count != 0)) { + table->count = 0; + table->ufid_count = 0; + } } static void table_instance_destroy(struct table_instance *ti, @@ -596,8 +599,6 @@ static void flow_table_copy_flows(struct table_instance *old, lockdep_ovsl_is_held()) table_instance_insert(new, flow); } - - old->keep_flows = true; } static struct table_instance *table_instance_rehash(struct table_instance *ti, @@ -632,8 +633,6 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table) rcu_assign_pointer(flow_table->ti, new_ti); rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti); flow_table->last_rehash = jiffies; - flow_table->count = 0; - flow_table->ufid_count = 0; table_instance_flow_flush(flow_table, old_ti, old_ufid_ti); table_instance_destroy(old_ti, old_ufid_ti); @@ -661,7 +660,7 @@ static int flow_key_start(const struct sw_flow_key *key) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), - sizeof(long)); + sizeof(long)); } static bool cmp_key(const struct sw_flow_key *key1, @@ -673,7 +672,7 @@ static bool cmp_key(const struct sw_flow_key *key1, long diffs = 0; int i; - for (i = key_start; i < key_end; i += sizeof(long)) + for (i = key_start; i < key_end; i += sizeof(long)) diffs |= *cp1++ ^ *cp2++; return diffs == 0; @@ -713,7 +712,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, (*n_mask_hit)++; hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -897,7 +896,8 @@ static bool ovs_flow_cmp_ufid(const struct sw_flow *flow, return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len); } -bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match) +bool ovs_flow_cmp(const struct sw_flow *flow, + const struct sw_flow_match *match) { if (ovs_identifier_is_ufid(&flow->id)) return flow_cmp_masked_key(flow, match->key, &match->range); @@ -916,7 +916,7 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; @@ -950,7 +950,7 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti); BUG_ON(table->count == 0); - table_instance_flow_free(table, ti, ufid_ti, flow, true); + table_instance_flow_free(table, ti, ufid_ti, flow); } static struct sw_flow_mask *mask_alloc(void) @@ -1107,7 +1107,7 @@ void ovs_flow_masks_rebalance(struct flow_table *table) if (!masks_and_count) return; - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { struct sw_flow_mask *mask; unsigned int start; int cpu; diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 6e7d4ac59353..d8fb7a3a3dfd 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -53,7 +53,6 @@ struct table_instance { struct rcu_head rcu; int node_ver; u32 hash_seed; - bool keep_flows; }; struct flow_table { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 0d44c5c013fa..82d801f063b7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -98,7 +98,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -118,7 +118,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) * vport_free(). */ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, - const struct vport_parms *parms) + const struct vport_parms *parms) { struct vport *vport; size_t alloc_size; @@ -397,7 +397,8 @@ int ovs_vport_get_upcall_portids(const struct vport *vport, * * Returns the portid of the target socket. Must be called with rcu_read_lock. */ -u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) +u32 ovs_vport_find_upcall_portid(const struct vport *vport, + struct sk_buff *skb) { struct vport_portids *ids; u32 ids_index; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index db25a0dc0f57..47f9128ecb8f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -704,7 +704,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = ip_defrag(net, skb, user); local_bh_enable(); if (err && err != -EINPROGRESS) - goto out_free; + return err; if (!err) { *defrag = true; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 8d735461fa19..fdb69d46276d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1351,7 +1351,7 @@ static void sctp_select_active_and_retran_path(struct sctp_association *asoc) } /* We did not find anything useful for a possible retransmission - * path; either primary path that we found is the the same as + * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) @@ -1537,7 +1537,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored + * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 9e289c770574..589868d96e3f 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -445,7 +445,7 @@ struct sctp_shared_key *sctp_auth_get_shkey( } /* - * Initialize all the possible digest transforms that we can use. Right now + * Initialize all the possible digest transforms that we can use. Right * now, the supported digests are SHA1 and SHA256. We do this here once * because of the restrictiong that transforms may only be allocated in * user context. This forces us to pre-allocated all possible transforms @@ -810,7 +810,7 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, } /* Set a new shared key on either endpoint or association. If the - * the key with a same ID already exists, replace the key (remove the + * key with a same ID already exists, replace the key (remove the * old key and add a new one). */ int sctp_auth_set_key(struct sctp_endpoint *ep, diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 701c5a4e441d..53e5ed79f63f 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -505,7 +505,7 @@ int sctp_in_scope(struct net *net, const union sctp_addr *addr, return 0; /* * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index ab6a997e222f..fd4f8243cc35 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -179,7 +179,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, __func__, asoc, max_data); } - /* If the the peer requested that we authenticate DATA chunks + /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d19db22262fd..25833238fe93 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -372,7 +372,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * Level 3 - private addresses. * Level 4 - global addresses * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * @@ -1483,10 +1483,10 @@ static __init int sctp_init(void) num_entries = (1UL << order) * PAGE_SIZE / sizeof(struct sctp_bind_hashbucket); - /* And finish by rounding it down to the nearest power of two - * this wastes some memory of course, but its needed because + /* And finish by rounding it down to the nearest power of two. + * This wastes some memory of course, but it's needed because * the hash function operates based on the assumption that - * that the number of entries is a power of two + * the number of entries is a power of two. */ sctp_port_hashsize = rounddown_pow_of_two(num_entries); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 47910470e532..467bd77b6986 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1235,7 +1235,7 @@ nodata: /* Create an Operation Error chunk of a fixed size, specifically, * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. - * This is a helper function to allocate an error chunk for for those + * This is a helper function to allocate an error chunk for those * invalid parameter codes in which we may not want to report all the * errors, if the incoming chunk is large. If it can't fit in a single * packet, we ignore it. @@ -1780,7 +1780,7 @@ no_hmac: * for init collision case of lost COOKIE ACK. * If skb has been timestamped, then use the stamp, otherwise * use current time. This introduces a small possibility that - * that a cookie may be considered expired, but his would only slow + * a cookie may be considered expired, but this would only slow * down the new association establishment instead of every packet. */ if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) @@ -2319,7 +2319,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* This implementation defaults to making the first transport * added as the primary transport. The source address seems to - * be a a better choice than any of the embedded addresses. + * be a better choice than any of the embedded addresses. */ if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index bda2536dd740..6dc95dcc0ff4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, int ret; if (outcnt <= stream->outcnt) - return 0; + goto out; ret = genradix_prealloc(&stream->out, outcnt, gfp); if (ret) return ret; +out: stream->outcnt = outcnt; return 0; } @@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int ret; if (incnt <= stream->incnt) - return 0; + goto out; ret = genradix_prealloc(&stream->in, incnt, gfp); if (ret) return ret; +out: stream->incnt = incnt; return 0; } diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 1c6c640607c5..407fed46931b 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -740,7 +740,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq) /* Helper function to gather skbs that have possibly become - * ordered by an an incoming chunk. + * ordered by an incoming chunk. */ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index e1f64f4ba236..da9ba6d1679b 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_connection *conn = &smc->conn; - struct smcd_diag_dmbinfo dinfo = { - .linkid = *((u32 *)conn->lgr->id), - .peer_gid = conn->lgr->peer_gid, - .my_gid = conn->lgr->smcd->local_gid, - .token = conn->rmb_desc->token, - .peer_token = conn->peer_token - }; + struct smcd_diag_dmbinfo dinfo; + + memset(&dinfo, 0, sizeof(dinfo)); + + dinfo.linkid = *((u32 *)conn->lgr->id); + dinfo.peer_gid = conn->lgr->peer_gid; + dinfo.my_gid = conn->lgr->smcd->local_gid; + dinfo.token = conn->rmb_desc->token; + dinfo.peer_token = conn->peer_token; if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) goto errout; diff --git a/net/socket.c b/net/socket.c index dbbe8ea7d395..e84a8e281b4c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2628,9 +2628,11 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; + if (msg->msg_control || msg->msg_controllen) { + /* disallow ancillary data reqs unless cmsg is plain data */ + if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) + return -EINVAL; + } return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 999eee1ed61c..6c86e2a7d942 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -108,8 +108,10 @@ proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp, left -= (s - tmpbuf); if (left && !isspace(*s)) return -EINVAL; - while (left && isspace(*s)) - left--, s++; + while (left && isspace(*s)) { + left--; + s++; + } } else left = 0; *(unsigned int *) table->data = value; diff --git a/net/tipc/core.c b/net/tipc/core.c index 4f6dc74adf45..37d8695548cf 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -109,6 +109,11 @@ static void __net_exit tipc_exit_net(struct net *net) { tipc_detach_loopback(net); tipc_net_stop(net); + + /* Make sure the tipc_net_finalize_work stopped + * before releasing the resources. + */ + flush_scheduled_work(); tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 001bcb0f2480..c38babaa4e57 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -757,10 +757,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err) switch (err) { case 0: this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]); + rcu_read_lock(); if (likely(test_bit(0, &b->up))) b->media->send_msg(net, skb, b, &tx_ctx->dst); else kfree_skb(skb); + rcu_read_unlock(); break; case -EINPROGRESS: return; diff --git a/net/tipc/link.c b/net/tipc/link.c index b7362556da95..a2989f22ebb6 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -216,11 +216,6 @@ enum { #define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) -/* - * Interval between NACKs when packets arrive out of order - */ -#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) - /* Link FSM states: */ enum { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 2679e97e0389..fd5bfaab8661 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -52,7 +52,6 @@ #define NAGLE_START_MAX 1024 #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */ -#define TIPC_FWD_MSG 1 #define TIPC_MAX_PORT 0xffffffff #define TIPC_MIN_PORT 1 #define TIPC_ACK_RATE 4 /* ACK at 1/4 of of rcv window size */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 53f0de0676b7..911d13cd2e67 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -660,6 +660,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; u8 node_id[NODE_ID_LEN] = {0,}; + struct net_device *dev; int rmcast = 0; ub = kzalloc(sizeof(*ub), GFP_ATOMIC); @@ -714,8 +715,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, rcu_assign_pointer(ub->bearer, b); tipc_udp_media_addr_set(&b->addr, &local); if (local.proto == htons(ETH_P_IP)) { - struct net_device *dev; - dev = __ip_dev_find(net, local.ipv4.s_addr, false); if (!dev) { err = -ENODEV; @@ -738,9 +737,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { - struct net_device *dev; - - dev = ipv6_dev_find(net, &local.ipv6); + dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL; + dev = ipv6_dev_find(net, &local.ipv6, dev); if (!dev) { err = -ENODEV; goto err; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index bbc52b088d29..002b0859fed5 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -330,12 +330,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_ctx_free(sk, ctx); } -static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, - int __user *optlen) +static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, + int __user *optlen, int tx) { int rc = 0; struct tls_context *ctx = tls_get_ctx(sk); struct tls_crypto_info *crypto_info; + struct cipher_context *cctx; int len; if (get_user(len, optlen)) @@ -352,7 +353,13 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send.info; + if (tx) { + crypto_info = &ctx->crypto_send.info; + cctx = &ctx->tx; + } else { + crypto_info = &ctx->crypto_recv.info; + cctx = &ctx->rx; + } if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -379,9 +386,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); - memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -403,9 +410,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_256->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, TLS_CIPHER_AES_GCM_256_IV_SIZE); - memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -429,7 +436,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, switch (optname) { case TLS_TX: - rc = do_tls_getsockopt_tx(sk, optval, optlen); + case TLS_RX: + rc = do_tls_getsockopt_conf(sk, optval, optlen, + optname == TLS_TX); break; default: rc = -ENOPROTOOPT; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 90f0f82cd9ca..e97a4f0c32a3 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -957,7 +957,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, if (!ht_cap->ht_supported && chandef->chan->band != NL80211_BAND_6GHZ) return false; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_20_NOHT: prohibited_flags |= IEEE80211_CHAN_NO_20MHZ; width = 20; @@ -983,7 +983,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, if (chandef->chan->band != NL80211_BAND_6GHZ && cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) return false; - /* fall through */ + fallthrough; case NL80211_CHAN_WIDTH_80: prohibited_flags |= IEEE80211_CHAN_NO_80MHZ; width = 80; diff --git a/net/wireless/core.h b/net/wireless/core.h index 67b0389fca4d..2ebc2a66680d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -466,8 +466,8 @@ extern struct work_struct cfg80211_disconnect_work; * * Checks if chandef is usable and we can/need start CAC on such channel. * - * Return: Return true if all channels available and at least - * one channel require CAC (NL80211_DFS_USABLE) + * Return: true if all channels available and at least + * one channel requires CAC (NL80211_DFS_USABLE) */ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index a6c61a2e6569..db7333e20dd7 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -941,7 +941,7 @@ void cfg80211_cac_event(struct net_device *netdev, sizeof(struct cfg80211_chan_def)); queue_work(cfg80211_wq, &rdev->propagate_cac_done_wk); cfg80211_sched_dfs_chan_update(rdev); - /* fall through */ + fallthrough; case NL80211_RADAR_CAC_ABORTED: wdev->cac_started = false; break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e45b95446ea0..201d029687cc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -336,6 +336,13 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { .len = NL80211_MAX_SUPP_HT_RATES }, [NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)), [NL80211_TXRATE_GI] = { .type = NLA_U8 }, + [NL80211_TXRATE_HE] = NLA_POLICY_EXACT_LEN(sizeof(struct nl80211_txrate_he)), + [NL80211_TXRATE_HE_GI] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_GI_0_8, + NL80211_RATE_INFO_HE_GI_3_2), + [NL80211_TXRATE_HE_LTF] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_4XLTF), }; static const struct nla_policy @@ -539,7 +546,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, - [NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, }, + + /* need to include at least Auth Transaction and Status Code */ + [NL80211_ATTR_AUTH_DATA] = NLA_POLICY_MIN_LEN(4), + [NL80211_ATTR_VHT_CAPABILITY] = NLA_POLICY_EXACT_LEN_WARN(NL80211_VHT_CAPABILITY_LEN), [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = NLA_POLICY_MAX(NLA_U8, 127), @@ -561,23 +571,30 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, - [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = + NLA_POLICY_MAX(NLA_U16, NL80211_CRIT_PROTO_MAX_DURATION), [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, [NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG }, [NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED }, - [NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY }, - [NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_BEACON] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_PRESP] = { .type = NLA_BINARY }, + [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = NLA_POLICY_MIN_LEN(2), + /* + * The value of the Length field of the Supported Operating + * Classes element is between 2 and 253. + */ + [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = + NLA_POLICY_RANGE(NLA_BINARY, 2, 253), [NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG }, [NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 }, [NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, - [NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY, - .len = IEEE80211_QOS_MAP_LEN_MAX }, + [NL80211_ATTR_QOS_MAP] = NLA_POLICY_RANGE(NLA_BINARY, + IEEE80211_QOS_MAP_LEN_MIN, + IEEE80211_QOS_MAP_LEN_MAX), [NL80211_ATTR_MAC_HINT] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, @@ -625,15 +642,17 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = FILS_ERP_MAX_RRK_LEN }, [NL80211_ATTR_FILS_CACHE_ID] = NLA_POLICY_EXACT_LEN_WARN(2), [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, + [NL80211_ATTR_PMKR0_NAME] = NLA_POLICY_EXACT_LEN(WLAN_PMK_NAME_LEN), [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, - [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, - .len = NL80211_HE_MAX_CAPABILITY_LEN }, - + [NL80211_ATTR_HE_CAPABILITY] = + NLA_POLICY_RANGE(NLA_BINARY, + NL80211_HE_MIN_CAPABILITY_LEN, + NL80211_HE_MAX_CAPABILITY_LEN), [NL80211_ATTR_FTM_RESPONDER] = NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), @@ -736,7 +755,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { .type = NLA_BINARY, .len = NL80211_KCK_EXT_LEN }, - [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN_WARN(NL80211_REPLAY_CTR_LEN), + [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN(NL80211_REPLAY_CTR_LEN), [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, }; @@ -776,7 +795,8 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { /* policy for NAN function attributes */ static const struct nla_policy nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = { - [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_TYPE] = + NLA_POLICY_MAX(NLA_U8, NL80211_NAN_FUNC_MAX_TYPE), [NL80211_NAN_FUNC_SERVICE_ID] = { .len = NL80211_NAN_FUNC_SERVICE_ID_LEN }, [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 }, @@ -2105,7 +2125,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 1: if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES, sizeof(u32) * rdev->wiphy.n_cipher_suites, @@ -2152,7 +2172,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 2: if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES, rdev->wiphy.interface_modes)) @@ -2160,7 +2180,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 3: nl_bands = nla_nest_start_noflag(msg, NL80211_ATTR_WIPHY_BANDS); @@ -2187,7 +2207,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->chan_start++; if (state->split) break; - /* fall through */ + fallthrough; default: /* add frequencies */ nl_freqs = nla_nest_start_noflag(msg, @@ -2242,7 +2262,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 4: nl_cmds = nla_nest_start_noflag(msg, NL80211_ATTR_SUPPORTED_COMMANDS); @@ -2271,7 +2291,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 5: if (rdev->ops->remain_on_channel && (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) && @@ -2289,7 +2309,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 6: #ifdef CONFIG_PM if (nl80211_send_wowlan(msg, rdev, state->split)) @@ -2300,7 +2320,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, #else state->split_start++; #endif - /* fall through */ + fallthrough; case 7: if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES, rdev->wiphy.software_iftypes)) @@ -2313,7 +2333,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, state->split_start++; if (state->split) break; - /* fall through */ + fallthrough; case 8: if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) && nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME, @@ -4417,21 +4437,106 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband, return true; } +static u16 he_mcs_map_to_mcs_mask(u8 he_mcs_map) +{ + switch (he_mcs_map) { + case IEEE80211_HE_MCS_NOT_SUPPORTED: + return 0; + case IEEE80211_HE_MCS_SUPPORT_0_7: + return 0x00FF; + case IEEE80211_HE_MCS_SUPPORT_0_9: + return 0x03FF; + case IEEE80211_HE_MCS_SUPPORT_0_11: + return 0xFFF; + default: + break; + } + return 0; +} + +static void he_build_mcs_mask(u16 he_mcs_map, + u16 he_mcs_mask[NL80211_HE_NSS_MAX]) +{ + u8 nss; + + for (nss = 0; nss < NL80211_HE_NSS_MAX; nss++) { + he_mcs_mask[nss] = he_mcs_map_to_mcs_mask(he_mcs_map & 0x03); + he_mcs_map >>= 2; + } +} + +static u16 he_get_txmcsmap(struct genl_info *info, + const struct ieee80211_sta_he_cap *he_cap) +{ + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + __le16 tx_mcs; + + switch (wdev->chandef.width) { + case NL80211_CHAN_WIDTH_80P80: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80; + break; + case NL80211_CHAN_WIDTH_160: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_160; + break; + default: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80; + break; + } + return le16_to_cpu(tx_mcs); +} + +static bool he_set_mcs_mask(struct genl_info *info, + struct wireless_dev *wdev, + struct ieee80211_supported_band *sband, + struct nl80211_txrate_he *txrate, + u16 mcs[NL80211_HE_NSS_MAX]) +{ + const struct ieee80211_sta_he_cap *he_cap; + u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {}; + u16 tx_mcs_map = 0; + u8 i; + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + return false; + + memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX); + + tx_mcs_map = he_get_txmcsmap(info, he_cap); + + /* Build he_mcs_mask from HE capabilities */ + he_build_mcs_mask(tx_mcs_map, tx_mcs_mask); + + for (i = 0; i < NL80211_HE_NSS_MAX; i++) { + if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i]) + mcs[i] = txrate->mcs[i]; + else + return false; + } + + return true; +} + static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, struct nlattr *attrs[], enum nl80211_attrs attr, - struct cfg80211_bitrate_mask *mask) + struct cfg80211_bitrate_mask *mask, + struct net_device *dev) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int rem, i; struct nlattr *tx_rates; struct ieee80211_supported_band *sband; - u16 vht_tx_mcs_map; + u16 vht_tx_mcs_map, he_tx_mcs_map; memset(mask, 0, sizeof(*mask)); /* Default to all rates enabled */ for (i = 0; i < NUM_NL80211_BANDS; i++) { + const struct ieee80211_sta_he_cap *he_cap; + sband = rdev->wiphy.bands[i]; if (!sband) @@ -4447,6 +4552,16 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + continue; + + he_tx_mcs_map = he_get_txmcsmap(info, he_cap); + he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs); + + mask->control[i].he_gi = 0xFF; + mask->control[i].he_ltf = 0xFF; } /* if no rates are given set it back to the defaults */ @@ -4502,13 +4617,25 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].gi > NL80211_TXRATE_FORCE_LGI) return -EINVAL; } + if (tb[NL80211_TXRATE_HE] && + !he_set_mcs_mask(info, wdev, sband, + nla_data(tb[NL80211_TXRATE_HE]), + mask->control[band].he_mcs)) + return -EINVAL; + if (tb[NL80211_TXRATE_HE_GI]) + mask->control[band].he_gi = + nla_get_u8(tb[NL80211_TXRATE_HE_GI]); + if (tb[NL80211_TXRATE_HE_LTF]) + mask->control[band].he_ltf = + nla_get_u8(tb[NL80211_TXRATE_HE_LTF]); if (mask->control[band].legacy == 0) { - /* don't allow empty legacy rates if HT or VHT + /* don't allow empty legacy rates if HT, VHT or HE * are not even supported. */ if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported || - rdev->wiphy.bands[band]->vht_cap.vht_supported)) + rdev->wiphy.bands[band]->vht_cap.vht_supported || + ieee80211_get_he_iftype_cap(sband, wdev->iftype))) return -EINVAL; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) @@ -4519,6 +4646,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].vht_mcs[i]) goto out; + for (i = 0; i < NL80211_HE_NSS_MAX; i++) + if (mask->control[band].he_mcs[i]) + goto out; + /* legacy and mcs rates may not be both empty */ return -EINVAL; } @@ -4829,8 +4960,9 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, return false; return true; case NL80211_CMD_START_AP: - /* SAE not supported yet */ - if (auth_type == NL80211_AUTHTYPE_SAE) + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP) && + auth_type == NL80211_AUTHTYPE_SAE) return false; /* FILS not supported yet */ if (auth_type == NL80211_AUTHTYPE_FILS_SK || @@ -4894,8 +5026,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); params.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid_len == 0 || - params.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid_len == 0) return -EINVAL; } @@ -4964,7 +5095,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - ¶ms.beacon_rate); + ¶ms.beacon_rate, + dev); if (err) return err; @@ -5205,7 +5337,7 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr) break; default: WARN_ON(1); - /* fall through */ + fallthrough; case RATE_INFO_BW_20: rate_flg = 0; break; @@ -5835,11 +5967,9 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]); /* * Need to include at least one (first channel, number of - * channels) tuple for each subband, and must have proper - * tuples for the rest of the data as well. + * channels) tuple for each subband (checked in policy), + * and must have proper tuples for the rest of the data as well. */ - if (params->supported_channels_len < 2) - return -EINVAL; if (params->supported_channels_len % 2) return -EINVAL; } @@ -5849,13 +5979,6 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); params->supported_oper_classes_len = nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); - /* - * The value of the Length field of the Supported Operating - * Classes element is between 2 and 253. - */ - if (params->supported_oper_classes_len < 2 || - params->supported_oper_classes_len > 253) - return -EINVAL; } return 0; } @@ -5878,9 +6001,6 @@ static int nl80211_set_station_tdls(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params->he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } err = nl80211_parse_sta_channel_info(info, params); @@ -6139,10 +6259,6 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params.he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - /* max len is validated in nla policy */ - if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) @@ -8414,23 +8530,14 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } if (ssid) { - if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { - err = -EINVAL; - goto out_free; - } memcpy(request->match_sets[i].ssid.ssid, nla_data(ssid), nla_len(ssid)); request->match_sets[i].ssid.ssid_len = nla_len(ssid); } - if (bssid) { - if (nla_len(bssid) != ETH_ALEN) { - err = -EINVAL; - goto out_free; - } + if (bssid) memcpy(request->match_sets[i].bssid, nla_data(bssid), ETH_ALEN); - } /* special attribute - old implementation w/a */ request->match_sets[i].rssi_thold = default_match_rssi; @@ -8785,10 +8892,10 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]) + if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]) return -EINVAL; - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8799,7 +8906,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_beacon = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_beacon; i++) { @@ -8812,8 +8919,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) { - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8824,7 +8931,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_presp = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_presp; i++) { @@ -9307,9 +9414,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EINVAL; auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]); auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]); - /* need to include at least Auth Transaction and Status Code */ - if (auth_data_len < 4) - return -EINVAL; } local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; @@ -9449,7 +9553,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (info->attrs[NL80211_ATTR_SAE_PASSWORD]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_SAE_OFFLOAD)) + NL80211_EXT_FEATURE_SAE_OFFLOAD) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP)) return -EINVAL; settings->sae_pwd = nla_data(info->attrs[NL80211_ATTR_SAE_PASSWORD]); @@ -10796,7 +10902,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, return -EOPNOTSUPP; err = nl80211_parse_tx_bitrate_mask(info, info->attrs, - NL80211_ATTR_TX_RATES, &mask); + NL80211_ATTR_TX_RATES, &mask, + dev); if (err) return err; @@ -11404,7 +11511,8 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - &setup.beacon_rate); + &setup.beacon_rate, + dev); if (err) return err; @@ -12356,8 +12464,6 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] || !tb[NL80211_REKEY_DATA_KCK]) return -EINVAL; - if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) - return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN && !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KEK_EXT_LEN)) @@ -12682,8 +12788,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb, func->cookie = cfg80211_assign_cookie(rdev); - if (!tb[NL80211_NAN_FUNC_TYPE] || - nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]) > NL80211_NAN_FUNC_MAX_TYPE) { + if (!tb[NL80211_NAN_FUNC_TYPE]) { err = -EINVAL; goto out; } @@ -13173,9 +13278,6 @@ static int nl80211_crit_protocol_start(struct sk_buff *skb, duration = nla_get_u16(info->attrs[NL80211_ATTR_MAX_CRIT_PROT_DURATION]); - if (duration > NL80211_CRIT_PROTO_MAX_DURATION) - return -ERANGE; - ret = rdev_crit_proto_start(rdev, wdev, proto, duration); if (!ret) rdev->crit_proto_nlportid = info->snd_portid; @@ -13560,8 +13662,7 @@ static int nl80211_set_qos_map(struct sk_buff *skb, pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]); len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]); - if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN || - len > IEEE80211_QOS_MAP_LEN_MAX) + if (len % 2) return -EINVAL; qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL); @@ -13829,17 +13930,9 @@ static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info) goto out; } - if (info->attrs[NL80211_ATTR_PMKR0_NAME]) { - int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]); - - if (r0_name_len != WLAN_PMK_NAME_LEN) { - ret = -EINVAL; - goto out; - } - + if (info->attrs[NL80211_ATTR_PMKR0_NAME]) pmk_conf.pmk_r0_name = nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]); - } ret = rdev_set_pmk(rdev, dev, &pmk_conf); out: @@ -13898,8 +13991,7 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_SSID]) { params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid.ssid_len == 0) return -EINVAL; memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), @@ -14200,7 +14292,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) { attr = NL80211_TID_CONFIG_ATTR_TX_RATE; err = nl80211_parse_tx_bitrate_mask(info, attrs, attr, - &tid_conf->txrate_mask); + &tid_conf->txrate_mask, dev); if (err) return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 35b8847a2f6d..dcd3d39a5372 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1594,7 +1594,7 @@ freq_reg_info_regd(u32 center_freq, /* * We only need to know if one frequency rule was - * was in center_freq's band, that's enough, so lets + * in center_freq's band, that's enough, so let's * not overwrite it once found */ if (!band_rule_found) @@ -1691,57 +1691,18 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd return bw_flags; } -/* - * Note that right now we assume the desired channel bandwidth - * is always 20 MHz for each individual channel (HT40 uses 20 MHz - * per channel, the primary and the extension channel). - */ -static void handle_channel(struct wiphy *wiphy, - enum nl80211_reg_initiator initiator, - struct ieee80211_channel *chan) +static void handle_channel_single_rule(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *reg_rule) { - u32 flags, bw_flags = 0; - const struct ieee80211_reg_rule *reg_rule = NULL; + u32 bw_flags = 0; const struct ieee80211_power_rule *power_rule = NULL; - struct wiphy *request_wiphy = NULL; - struct regulatory_request *lr = get_last_request(); const struct ieee80211_regdomain *regd; - request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); - - flags = chan->orig_flags; - - reg_rule = freq_reg_info(wiphy, ieee80211_channel_to_khz(chan)); - if (IS_ERR(reg_rule)) { - /* - * We will disable all channels that do not match our - * received regulatory rule unless the hint is coming - * from a Country IE and the Country IE had no information - * about a band. The IEEE 802.11 spec allows for an AP - * to send only a subset of the regulatory rules allowed, - * so an AP in the US that only supports 2.4 GHz may only send - * a country IE with information for the 2.4 GHz band - * while 5 GHz is still supported. - */ - if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - PTR_ERR(reg_rule) == -ERANGE) - return; - - if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && - request_wiphy && request_wiphy == wiphy && - request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - pr_debug("Disabling freq %d.%03d MHz for good\n", - chan->center_freq, chan->freq_offset); - chan->orig_flags |= IEEE80211_CHAN_DISABLED; - chan->flags = chan->orig_flags; - } else { - pr_debug("Disabling freq %d.%03d MHz\n", - chan->center_freq, chan->freq_offset); - chan->flags |= IEEE80211_CHAN_DISABLED; - } - return; - } - regd = reg_get_regdomain(wiphy); power_rule = ®_rule->power_rule; @@ -1803,6 +1764,204 @@ static void handle_channel(struct wiphy *wiphy, chan->max_power = chan->max_reg_power; } +static void handle_channel_adjacent_rules(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *rrule1, + const struct ieee80211_reg_rule *rrule2, + struct ieee80211_freq_range *comb_range) +{ + u32 bw_flags1 = 0; + u32 bw_flags2 = 0; + const struct ieee80211_power_rule *power_rule1 = NULL; + const struct ieee80211_power_rule *power_rule2 = NULL; + const struct ieee80211_regdomain *regd; + + regd = reg_get_regdomain(wiphy); + + power_rule1 = &rrule1->power_rule; + power_rule2 = &rrule2->power_rule; + bw_flags1 = reg_rule_to_chan_bw_flags(regd, rrule1, chan); + bw_flags2 = reg_rule_to_chan_bw_flags(regd, rrule2, chan); + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + /* This guarantees the driver's requested regulatory domain + * will always be used as a base for further regulatory + * settings + */ + chan->flags = + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags) | + bw_flags1 | + bw_flags2; + chan->orig_flags = chan->flags; + chan->max_antenna_gain = + min_t(int, MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain)); + chan->orig_mag = chan->max_antenna_gain; + chan->max_reg_power = + min_t(int, MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + chan->max_power = chan->max_reg_power; + chan->orig_mpwr = chan->max_reg_power; + + if (chan->flags & IEEE80211_CHAN_RADAR) { + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + } + + return; + } + + chan->dfs_state = NL80211_DFS_USABLE; + chan->dfs_state_entered = jiffies; + + chan->beacon_found = false; + chan->flags = flags | bw_flags1 | bw_flags2 | + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags); + + /* reg_rule_to_chan_bw_flags may forbids 10 and forbids 20 MHz + * (otherwise no adj. rule case), recheck therefore + */ + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(10))) + chan->flags &= ~IEEE80211_CHAN_NO_10MHZ; + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(20))) + chan->flags &= ~IEEE80211_CHAN_NO_20MHZ; + + chan->max_antenna_gain = + min_t(int, chan->orig_mag, + min_t(int, + MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain))); + chan->max_reg_power = min_t(int, + MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + + if (chan->flags & IEEE80211_CHAN_RADAR) { + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + else + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + } + + if (chan->orig_mpwr) { + /* Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER + * will always follow the passed country IE power settings. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER) + chan->max_power = chan->max_reg_power; + else + chan->max_power = min(chan->orig_mpwr, + chan->max_reg_power); + } else { + chan->max_power = chan->max_reg_power; + } +} + +/* Note that right now we assume the desired channel bandwidth + * is always 20 MHz for each individual channel (HT40 uses 20 MHz + * per channel, the primary and the extension channel). + */ +static void handle_channel(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan) +{ + const u32 orig_chan_freq = ieee80211_channel_to_khz(chan); + struct regulatory_request *lr = get_last_request(); + struct wiphy *request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); + const struct ieee80211_reg_rule *rrule = NULL; + const struct ieee80211_reg_rule *rrule1 = NULL; + const struct ieee80211_reg_rule *rrule2 = NULL; + + u32 flags = chan->orig_flags; + + rrule = freq_reg_info(wiphy, orig_chan_freq); + if (IS_ERR(rrule)) { + /* check for adjacent match, therefore get rules for + * chan - 20 MHz and chan + 20 MHz and test + * if reg rules are adjacent + */ + rrule1 = freq_reg_info(wiphy, + orig_chan_freq - MHZ_TO_KHZ(20)); + rrule2 = freq_reg_info(wiphy, + orig_chan_freq + MHZ_TO_KHZ(20)); + if (!IS_ERR(rrule1) && !IS_ERR(rrule2)) { + struct ieee80211_freq_range comb_range; + + if (rrule1->freq_range.end_freq_khz != + rrule2->freq_range.start_freq_khz) + goto disable_chan; + + comb_range.start_freq_khz = + rrule1->freq_range.start_freq_khz; + comb_range.end_freq_khz = + rrule2->freq_range.end_freq_khz; + comb_range.max_bandwidth_khz = + min_t(u32, + rrule1->freq_range.max_bandwidth_khz, + rrule2->freq_range.max_bandwidth_khz); + + if (!cfg80211_does_bw_fit_range(&comb_range, + orig_chan_freq, + MHZ_TO_KHZ(20))) + goto disable_chan; + + handle_channel_adjacent_rules(wiphy, initiator, chan, + flags, lr, request_wiphy, + rrule1, rrule2, + &comb_range); + return; + } + +disable_chan: + /* We will disable all channels that do not match our + * received regulatory rule unless the hint is coming + * from a Country IE and the Country IE had no information + * about a band. The IEEE 802.11 spec allows for an AP + * to send only a subset of the regulatory rules allowed, + * so an AP in the US that only supports 2.4 GHz may only send + * a country IE with information for the 2.4 GHz band + * while 5 GHz is still supported. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + PTR_ERR(rrule) == -ERANGE) + return; + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + pr_debug("Disabling freq %d.%03d MHz for good\n", + chan->center_freq, chan->freq_offset); + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; + } else { + pr_debug("Disabling freq %d.%03d MHz\n", + chan->center_freq, chan->freq_offset); + chan->flags |= IEEE80211_CHAN_DISABLED; + } + return; + } + + handle_channel_single_rule(wiphy, initiator, chan, flags, lr, + request_wiphy, rrule); +} + static void handle_band(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, struct ieee80211_supported_band *sband) @@ -3167,7 +3326,7 @@ static void restore_custom_reg_settings(struct wiphy *wiphy) * - send a user regulatory hint if applicable * * Device drivers that send a regulatory hint for a specific country - * keep their own regulatory domain on wiphy->regd so that does does + * keep their own regulatory domain on wiphy->regd so that does * not need to be remembered. */ static void restore_regulatory_settings(bool reset_user, bool cached) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e67a74488bbe..84fc8ab16dd2 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -55,7 +55,7 @@ * * Also note that the hidden_beacon_bss pointer is only relevant * if the driver uses something other than the IEs, e.g. private - * data stored stored in the BSS struct, since the beacon IEs are + * data stored in the BSS struct, since the beacon IEs are * also linked into the probe response struct. */ @@ -1433,7 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, switch (ftype) { case CFG80211_BSS_FTYPE_BEACON: ies->from_beacon = true; - /* fall through */ + fallthrough; case CFG80211_BSS_FTYPE_UNKNOWN: rcu_assign_pointer(tmp.pub.beacon_ies, ies); break; @@ -1488,7 +1488,7 @@ static const struct element ielen - (mbssid_end - ie)); /* - * If is is not the last subelement in current MBSSID IE or there isn't + * If it is not the last subelement in current MBSSID IE or there isn't * a next MBSSID IE - profile is complete. */ if ((sub_elem->data + sub_elem->datalen < mbssid_end - 1) || diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 985f3c23f054..38df713f2e2e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -24,7 +24,7 @@ /* * Software SME in cfg80211, using auth/assoc/deauth calls to the - * driver. This is is for implementing nl80211's connect/disconnect + * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ @@ -205,7 +205,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; - /* fall through */ + fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, @@ -215,7 +215,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); - /* fall through */ + fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); diff --git a/net/wireless/util.c b/net/wireless/util.c index dfad1c0f57ad..7c5d5365a5eb 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -198,7 +198,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; - /* fall through */ + fallthrough; default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; @@ -1008,7 +1008,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_STATION: if (dev->ieee80211_ptr->use_4addr) break; - /* fall through */ + fallthrough; case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index aa918d7ff6bd..78f2927ead7f 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -497,7 +497,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, /* * We only need to store WEP keys, since they're the only keys that - * can be be set before a connection is established and persist after + * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || @@ -1334,7 +1334,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sig + 110; break; } - /* fall through */ + fallthrough; case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; @@ -1343,7 +1343,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sinfo.signal; break; } - /* fall through */ + fallthrough; default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 62c275685b75..95e4cdb94fe9 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -66,7 +66,6 @@ KBUILD_CFLAGS += -Wnested-externs KBUILD_CFLAGS += -Wshadow KBUILD_CFLAGS += $(call cc-option, -Wlogical-op) KBUILD_CFLAGS += -Wmissing-field-initializers -KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) @@ -87,6 +86,7 @@ KBUILD_CFLAGS += -Wpacked KBUILD_CFLAGS += -Wpadded KBUILD_CFLAGS += -Wpointer-arith KBUILD_CFLAGS += -Wredundant-decls +KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wswitch-default KBUILD_CFLAGS += $(call cc-option, -Wpacked-bitfield-compat) diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c index b071bf476fea..3bc48c726c41 100644 --- a/scripts/extract-cert.c +++ b/scripts/extract-cert.c @@ -71,7 +71,7 @@ static void drain_openssl_errors(void) static const char *key_pass; static BIO *wb; static char *cert_dst; -int kbuild_verbose; +static int kbuild_verbose; static void write_cert(X509 *x509) { diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c index 7a85c4e21175..057c6cabad1d 100644 --- a/scripts/genksyms/keywords.c +++ b/scripts/genksyms/keywords.c @@ -25,9 +25,9 @@ static struct resword { { "__int128_t", BUILTIN_INT_KEYW }, { "__uint128_t", BUILTIN_INT_KEYW }, - // According to rth, c99 defines "_Bool", __restrict", __restrict__", "restrict". KAO + // According to rth, c99 defines "_Bool", "__restrict", "__restrict__", "restrict". KAO { "_Bool", BOOL_KEYW }, - { "_restrict", RESTRICT_KEYW }, + { "__restrict", RESTRICT_KEYW }, { "__restrict__", RESTRICT_KEYW }, { "restrict", RESTRICT_KEYW }, { "asm", ASM_KEYW }, diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index bc390df49f1f..8638785328a7 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -885,7 +885,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowName(bool))); connect(parent(), SIGNAL(showNameChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showName); headerPopup->addAction(action); @@ -894,7 +894,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowRange(bool))); connect(parent(), SIGNAL(showRangeChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showRange); headerPopup->addAction(action); @@ -903,7 +903,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowData(bool))); connect(parent(), SIGNAL(showDataChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showData); headerPopup->addAction(action); } @@ -1012,6 +1012,16 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name) configSettings->endGroup(); connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings())); } + + contextMenu = createStandardContextMenu(); + QAction *action = new QAction("Show Debug Info", contextMenu); + + action->setCheckable(true); + connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); + connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setChecked(bool))); + action->setChecked(showDebug()); + contextMenu->addSeparator(); + contextMenu->addAction(action); } void ConfigInfoView::saveSettings(void) @@ -1066,80 +1076,80 @@ void ConfigInfoView::symbolInfo(void) void ConfigInfoView::menuInfo(void) { struct symbol* sym; - QString head, debug, help; + QString info; + QTextStream stream(&info); sym = _menu->sym; if (sym) { if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big>"; if (sym->name) { - head += " ("; + stream << " ("; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += ")"; + stream << "</a>"; + stream << ")"; } } else if (sym->name) { - head += "<big><b>"; + stream << "<big><b>"; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += "</b></big>"; + stream << "</a>"; + stream << "</b></big>"; } - head += "<br><br>"; + stream << "<br><br>"; if (showDebug()) - debug = debug_info(sym); + stream << debug_info(sym); - struct gstr help_gstr = str_new(); - menu_get_ext_help(_menu, &help_gstr); - help = print_filter(str_get(&help_gstr)); - str_free(&help_gstr); } else if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big><br><br>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big><br><br>"; if (showDebug()) { if (_menu->prompt->visible.expr) { - debug += " dep: "; - expr_print(_menu->prompt->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br><br>"; + stream << " dep: "; + expr_print(_menu->prompt->visible.expr, + expr_print_help, &stream, E_NONE); + stream << "<br><br>"; } } } if (showDebug()) - debug += QString().sprintf("defined at %s:%d<br><br>", _menu->file->name, _menu->lineno); + stream << "defined at " << _menu->file->name << ":" + << _menu->lineno << "<br><br>"; - setText(head + debug + help); + setText(info); } QString ConfigInfoView::debug_info(struct symbol *sym) { QString debug; + QTextStream stream(&debug); - debug += "type: "; - debug += print_filter(sym_type_name(sym->type)); + stream << "type: "; + stream << print_filter(sym_type_name(sym->type)); if (sym_is_choice(sym)) - debug += " (choice)"; + stream << " (choice)"; debug += "<br>"; if (sym->rev_dep.expr) { - debug += "reverse dep: "; - expr_print(sym->rev_dep.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "reverse dep: "; + expr_print(sym->rev_dep.expr, expr_print_help, &stream, E_NONE); + stream << "<br>"; } for (struct property *prop = sym->prop; prop; prop = prop->next) { switch (prop->type) { case P_PROMPT: case P_MENU: - debug += QString().sprintf("prompt: <a href=\"m%s\">", sym->name); - debug += print_filter(prop->text); - debug += "</a><br>"; + stream << "prompt: <a href=\"m" << sym->name << "\">"; + stream << print_filter(prop->text); + stream << "</a><br>"; break; case P_DEFAULT: case P_SELECT: @@ -1147,30 +1157,33 @@ QString ConfigInfoView::debug_info(struct symbol *sym) case P_COMMENT: case P_IMPLY: case P_SYMBOL: - debug += prop_get_type_name(prop->type); - debug += ": "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << prop_get_type_name(prop->type); + stream << ": "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; break; case P_CHOICE: if (sym_is_choice(sym)) { - debug += "choice: "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "choice: "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } break; default: - debug += "unknown property: "; - debug += prop_get_type_name(prop->type); - debug += "<br>"; + stream << "unknown property: "; + stream << prop_get_type_name(prop->type); + stream << "<br>"; } if (prop->visible.expr) { - debug += " dep: "; - expr_print(prop->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << " dep: "; + expr_print(prop->visible.expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } } - debug += "<br>"; + stream << "<br>"; return debug; } @@ -1208,15 +1221,15 @@ QString ConfigInfoView::print_filter(const QString &str) void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char *str) { - QString* text = reinterpret_cast<QString*>(data); - QString str2 = print_filter(str); + QTextStream *stream = reinterpret_cast<QTextStream *>(data); if (sym && sym->name && !(sym->flags & SYMBOL_CONST)) { - *text += QString().sprintf("<a href=\"s%s\">", sym->name); - *text += str2; - *text += "</a>"; - } else - *text += str2; + *stream << "<a href=\"s" << sym->name << "\">"; + *stream << print_filter(str); + *stream << "</a>"; + } else { + *stream << print_filter(str); + } } void ConfigInfoView::clicked(const QUrl &url) @@ -1228,7 +1241,6 @@ void ConfigInfoView::clicked(const QUrl &url) struct menu *m = NULL; if (count < 1) { - qInfo() << "Clicked link is empty"; delete[] data; return; } @@ -1241,7 +1253,6 @@ void ConfigInfoView::clicked(const QUrl &url) strcat(data, "$"); result = sym_re_search(data); if (!result) { - qInfo() << "Clicked symbol is invalid:" << data; delete[] data; return; } @@ -1268,23 +1279,10 @@ void ConfigInfoView::clicked(const QUrl &url) delete data; } -QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos) -{ - QMenu* popup = Parent::createStandardContextMenu(pos); - QAction* action = new QAction("Show Debug Info", popup); - - action->setCheckable(true); - connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); - connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool))); - action->setChecked(showDebug()); - popup->addSeparator(); - popup->addAction(action); - return popup; -} - -void ConfigInfoView::contextMenuEvent(QContextMenuEvent *e) +void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event) { - Parent::contextMenuEvent(e); + contextMenu->popup(event->globalPos()); + event->accept(); } ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent) diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index 461df6419f15..f97376a8123f 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -30,7 +30,7 @@ public: }; enum colIdx { - promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx, colNr + promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx }; enum listMode { singleMode, menuMode, symbolMode, fullMode, listMode @@ -215,6 +215,7 @@ public: class ConfigInfoView : public QTextBrowser { Q_OBJECT typedef class QTextBrowser Parent; + QMenu *contextMenu; public: ConfigInfoView(QWidget* parent, const char *name = 0); bool showDebug(void) const { return _showDebug; } @@ -235,8 +236,7 @@ protected: QString debug_info(struct symbol *sym); static QString print_filter(const QString &str); static void expr_print_help(void *data, struct symbol *sym, const char *str); - QMenu *createStandardContextMenu(const QPoint & pos); - void contextMenuEvent(QContextMenuEvent *e); + void contextMenuEvent(QContextMenuEvent *event); struct symbol *sym; struct menu *_menu; diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 09ddab5f5cae..9766f6af8743 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -46,6 +46,18 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev, INIT_LIST_HEAD(&bus->hlink_list); init_waitqueue_head(&bus->rirb_wq); bus->irq = -1; + + /* + * Default value of '8' is as per the HD audio specification (Rev 1.0a). + * Following relation is used to derive STRIPE control value. + * For sample rate <= 48K: + * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } + * For sample rate > 48K: + * { ((num_channels * bits_per_sample * rate/48000) / + * number of SDOs) >= 8 } + */ + bus->sdo_limit = 8; + return 0; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 011b17cc1efa..b98449fd92f3 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -529,17 +529,6 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset) bus->chip_init = true; - /* - * Default value of '8' is as per the HD audio specification (Rev 1.0a). - * Following relation is used to derive STRIPE control value. - * For sample rate <= 48K: - * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } - * For sample rate > 48K: - * { ((num_channels * bits_per_sample * rate/48000) / - * number of SDOs) >= 8 } - */ - bus->sdo_limit = 8; - return true; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init_chip); diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c index 5363d88cc4b9..2e5a5c5279e8 100644 --- a/sound/isa/sscape.c +++ b/sound/isa/sscape.c @@ -308,7 +308,7 @@ static inline int verify_mpu401(const struct snd_mpu401 *mpu) } /* - * This is apparently the standard way to initailise an MPU-401 + * This is apparently the standard way to initialise an MPU-401 */ static inline void initialise_mpu401(const struct snd_mpu401 *mpu) { @@ -339,7 +339,7 @@ static void soundscape_free(struct snd_card *c) } /* - * Tell the SoundScape to begin a DMA tranfer using the given channel. + * Tell the SoundScape to begin a DMA transfer using the given channel. * All locking issues are left to the caller. */ static void sscape_start_dma_unsafe(unsigned io_base, enum GA_REG reg) @@ -803,7 +803,7 @@ static int mpu401_open(struct snd_mpu401 *mpu) } /* - * Initialse an MPU-401 subdevice for MIDI support on the SoundScape. + * Initialise an MPU-401 subdevice for MIDI support on the SoundScape. */ static int create_mpu401(struct snd_card *card, int devnum, unsigned long port, int irq) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7f9d35273734..a1fa983d2a94 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7694,6 +7694,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), @@ -7955,6 +7957,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"}, {.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"}, {.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"}, + {.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 55815fdaa1aa..406526e79af3 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -138,7 +138,7 @@ static int acp3x_1015_hw_params(struct snd_pcm_substream *substream, srate = params_rate(params); for_each_rtd_codec_dais(rtd, i, codec_dai) { - if (strcmp(codec_dai->component->name, "rt1015-aif")) + if (strcmp(codec_dai->name, "rt1015-aif")) continue; ret = snd_soc_dai_set_bclk_ratio(codec_dai, 64); if (ret < 0) diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index 623dfd3ea705..7b14d9a81b97 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -314,40 +314,30 @@ static int acp_pdm_dma_close(struct snd_soc_component *component, return 0; } -static int acp_pdm_dai_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) +static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) { struct pdm_stream_instance *rtd; + int ret; + bool pdm_status; unsigned int ch_mask; rtd = substream->runtime->private_data; - switch (params_channels(params)) { + ret = 0; + switch (substream->runtime->channels) { case TWO_CH: ch_mask = 0x00; break; default: return -EINVAL; } - rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); - rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + - ACP_WOV_PDM_DECIMATION_FACTOR); - return 0; -} - -static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, - int cmd, struct snd_soc_dai *dai) -{ - struct pdm_stream_instance *rtd; - int ret; - bool pdm_status; - - rtd = substream->runtime->private_data; - ret = 0; switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); + rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + + ACP_WOV_PDM_DECIMATION_FACTOR); rtd->bytescount = acp_pdm_get_byte_count(rtd, substream->stream); pdm_status = check_pdm_dma_status(rtd->acp_base); @@ -369,7 +359,6 @@ static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, } static struct snd_soc_dai_ops acp_pdm_dai_ops = { - .hw_params = acp_pdm_dai_hw_params, .trigger = acp_pdm_dai_trigger, }; diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 4428c62e25cf..3ddd822240e3 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -19,8 +19,8 @@ #define CDC_D_REVISION1 (0xf000) #define CDC_D_PERPH_SUBTYPE (0xf005) -#define CDC_D_INT_EN_SET (0x015) -#define CDC_D_INT_EN_CLR (0x016) +#define CDC_D_INT_EN_SET (0xf015) +#define CDC_D_INT_EN_CLR (0xf016) #define MBHC_SWITCH_INT BIT(7) #define MBHC_MIC_ELECTRICAL_INS_REM_DET BIT(6) #define MBHC_BUTTON_PRESS_DET BIT(5) diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index 68a3b48e6b31..3bce9a14f0f3 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -412,8 +412,12 @@ int wm8958_aif_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct wm8994 *control = dev_get_drvdata(component->dev->parent); int i; + if (control->type != WM8958) + return 0; + switch (event) { case SND_SOC_DAPM_POST_PMU: case SND_SOC_DAPM_PRE_PMU: diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 317916cb4e27..0623a2251084 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -151,7 +151,6 @@ static const struct reg_default wm8962_reg[] = { { 40, 0x0000 }, /* R40 - SPKOUTL volume */ { 41, 0x0000 }, /* R41 - SPKOUTR volume */ - { 48, 0x0000 }, /* R48 - Additional control(4) */ { 49, 0x0010 }, /* R49 - Class D Control 1 */ { 51, 0x0003 }, /* R51 - Class D Control 2 */ @@ -842,6 +841,7 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg) case WM8962_SPKOUTL_VOLUME: case WM8962_SPKOUTR_VOLUME: case WM8962_THERMAL_SHUTDOWN_STATUS: + case WM8962_ADDITIONAL_CONTROL_4: case WM8962_CLASS_D_CONTROL_1: case WM8962_CLASS_D_CONTROL_2: case WM8962_CLOCKING_4: diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index a84ae879d37e..038be667c1a6 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -43,10 +43,12 @@ #define WM8994_NUM_DRC 3 #define WM8994_NUM_EQ 3 -static struct { +struct wm8994_reg_mask { unsigned int reg; unsigned int mask; -} wm8994_vu_bits[] = { +}; + +static struct wm8994_reg_mask wm8994_vu_bits[] = { { WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU }, @@ -60,14 +62,10 @@ static struct { { WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU }, { WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU }, - { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, - { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, { WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU }, { WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU }, - { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, - { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU }, { WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU }, @@ -76,6 +74,14 @@ static struct { { WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU }, }; +/* VU bitfields for ADC2, DAC2 not available on WM1811 */ +static struct wm8994_reg_mask wm8994_adc2_dac2_vu_bits[] = { + { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, + { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, +}; + static int wm8994_drc_base[] = { WM8994_AIF1_DRC1_1, WM8994_AIF1_DRC2_1, @@ -1030,6 +1036,26 @@ static bool wm8994_check_class_w_digital(struct snd_soc_component *component) return true; } +static void wm8994_update_vu_bits(struct snd_soc_component *component) +{ + struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); + struct wm8994 *control = wm8994->wm8994; + int i; + + for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) + snd_soc_component_write(component, wm8994_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_vu_bits[i].reg)); + if (control->type == WM1811) + return; + + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_write(component, + wm8994_adc2_dac2_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_adc2_dac2_vu_bits[i].reg)); +} + static int aif_mclk_set(struct snd_soc_component *component, int aif, bool enable) { struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); @@ -1076,7 +1102,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); struct wm8994 *control = wm8994->wm8994; int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA; - int ret, i; + int ret; int dac; int adc; int val; @@ -1144,10 +1170,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -1181,7 +1204,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - int ret, i; + int ret; int dac; int adc; int val; @@ -1237,10 +1260,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -4346,6 +4366,14 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994_vu_bits[i].mask, wm8994_vu_bits[i].mask); + if (control->type != WM1811) { + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_update_bits(component, + wm8994_adc2_dac2_vu_bits[i].reg, + wm8994_adc2_dac2_vu_bits[i].mask, + wm8994_adc2_dac2_vu_bits[i].mask); + } + /* Set the low bit of the 3D stereo depth so TLV matches */ snd_soc_component_update_bits(component, WM8994_AIF1_DAC1_FILTERS_2, 1 << WM8994_AIF1DAC1_3D_GAIN_SHIFT, diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index de136c0a497d..52adedc03245 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -73,6 +73,7 @@ struct cpu_priv { * @codec_priv: CODEC private data * @cpu_priv: CPU private data * @card: ASoC card structure + * @streams: Mask of current active streams * @sample_rate: Current sample rate * @sample_format: Current sample format * @asrc_rate: ASRC sample rate used by Back-Ends @@ -89,6 +90,7 @@ struct fsl_asoc_card_priv { struct codec_priv codec_priv; struct cpu_priv cpu_priv; struct snd_soc_card card; + u8 streams; u32 sample_rate; snd_pcm_format_t sample_format; u32 asrc_rate; @@ -151,21 +153,17 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; + struct codec_priv *codec_priv = &priv->codec_priv; struct cpu_priv *cpu_priv = &priv->cpu_priv; struct device *dev = rtd->card->dev; + unsigned int pll_out; int ret; priv->sample_rate = params_rate(params); priv->sample_format = params_format(params); + priv->streams |= BIT(substream->stream); - /* - * If codec-dai is DAI Master and all configurations are already in the - * set_bias_level(), bypass the remaining settings in hw_params(). - * Note: (dai_fmt & CBM_CFM) includes CBM_CFM and CBM_CFS. - */ - if ((priv->card.set_bias_level && - priv->dai_fmt & SND_SOC_DAIFMT_CBM_CFM) || - fsl_asoc_card_is_ac97(priv)) + if (fsl_asoc_card_is_ac97(priv)) return 0; /* Specific configurations of DAIs starts from here */ @@ -174,7 +172,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->sysclk_dir[tx]); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set sysclk for cpu dai\n"); - return ret; + goto fail; } if (cpu_priv->slot_width) { @@ -182,6 +180,68 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->slot_width); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set TDM slot for cpu dai\n"); + goto fail; + } + } + + /* Specific configuration for PLL */ + if (codec_priv->pll_id && codec_priv->fll_id) { + if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) + pll_out = priv->sample_rate * 384; + else + pll_out = priv->sample_rate * 256; + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, + codec_priv->mclk_id, + codec_priv->mclk_freq, pll_out); + if (ret) { + dev_err(dev, "failed to start FLL: %d\n", ret); + goto fail; + } + + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->fll_id, + pll_out, SND_SOC_CLOCK_IN); + + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to set SYSCLK: %d\n", ret); + goto fail; + } + } + + return 0; + +fail: + priv->streams &= ~BIT(substream->stream); + return ret; +} + +static int fsl_asoc_card_hw_free(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); + struct codec_priv *codec_priv = &priv->codec_priv; + struct device *dev = rtd->card->dev; + int ret; + + priv->streams &= ~BIT(substream->stream); + + if (!priv->streams && codec_priv->pll_id && codec_priv->fll_id) { + /* Force freq to be 0 to avoid error message in codec */ + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->mclk_id, + 0, + SND_SOC_CLOCK_IN); + if (ret) { + dev_err(dev, "failed to switch away from FLL: %d\n", ret); + return ret; + } + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, 0, 0, 0); + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to stop FLL: %d\n", ret); return ret; } } @@ -191,6 +251,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, static const struct snd_soc_ops fsl_asoc_card_ops = { .hw_params = fsl_asoc_card_hw_params, + .hw_free = fsl_asoc_card_hw_free, }; static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, @@ -254,75 +315,6 @@ static struct snd_soc_dai_link fsl_asoc_card_dai[] = { }, }; -static int fsl_asoc_card_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card); - struct snd_soc_pcm_runtime *rtd; - struct snd_soc_dai *codec_dai; - struct codec_priv *codec_priv = &priv->codec_priv; - struct device *dev = card->dev; - unsigned int pll_out; - int ret; - - rtd = snd_soc_get_pcm_runtime(card, &card->dai_link[0]); - codec_dai = asoc_rtd_to_codec(rtd, 0); - if (dapm->dev != codec_dai->dev) - return 0; - - switch (level) { - case SND_SOC_BIAS_PREPARE: - if (dapm->bias_level != SND_SOC_BIAS_STANDBY) - break; - - if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) - pll_out = priv->sample_rate * 384; - else - pll_out = priv->sample_rate * 256; - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, - codec_priv->mclk_id, - codec_priv->mclk_freq, pll_out); - if (ret) { - dev_err(dev, "failed to start FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->fll_id, - pll_out, SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to set SYSCLK: %d\n", ret); - return ret; - } - break; - - case SND_SOC_BIAS_STANDBY: - if (dapm->bias_level != SND_SOC_BIAS_PREPARE) - break; - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id, - codec_priv->mclk_freq, - SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to switch away from FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, 0, 0, 0); - if (ret) { - dev_err(dev, "failed to stop FLL: %d\n", ret); - return ret; - } - break; - - default: - break; - } - - return 0; -} - static int fsl_asoc_card_audmux_init(struct device_node *np, struct fsl_asoc_card_priv *priv) { @@ -611,7 +603,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Diversify the card configurations */ if (of_device_is_compatible(np, "fsl,imx-audio-cs42888")) { codec_dai_name = "cs42888"; - priv->card.set_bias_level = NULL; priv->cpu_priv.sysclk_freq[TX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_freq[RX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT; @@ -628,26 +619,22 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) { codec_dai_name = "wm8962"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK; priv->codec_priv.fll_id = WM8962_SYSCLK_FLL; priv->codec_priv.pll_id = WM8962_FLL; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) { codec_dai_name = "wm8960-hifi"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO; priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-ac97")) { codec_dai_name = "ac97-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_AC97; priv->card.dapm_routes = audio_map_ac97; priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_ac97); } else if (of_device_is_compatible(np, "fsl,imx-audio-mqs")) { codec_dai_name = "fsl-mqs-dai"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS | SND_SOC_DAIFMT_NB_NF; @@ -657,7 +644,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_tx); } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8524")) { codec_dai_name = "wm8524-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS; priv->dai_link[1].dpcm_capture = 0; priv->dai_link[2].dpcm_capture = 0; diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c index 9e4f66b6b92b..231984882176 100644 --- a/sound/soc/fsl/mpc5200_dma.c +++ b/sound/soc/fsl/mpc5200_dma.c @@ -339,7 +339,6 @@ static int psc_dma_new(struct snd_soc_component *component, static void psc_dma_free(struct snd_soc_component *component, struct snd_pcm *pcm) { - struct snd_soc_pcm_runtime *rtd = pcm->private_data; struct snd_pcm_substream *substream; int stream; diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 49b9f18472bc..b1cac7abdc0a 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -331,7 +331,7 @@ static int sst_media_open(struct snd_pcm_substream *substream, ret_val = power_up_sst(stream); if (ret_val < 0) - return ret_val; + goto out_power_up; /* Make sure, that the period size is always even */ snd_pcm_hw_constraint_step(substream->runtime, 0, @@ -340,8 +340,9 @@ static int sst_media_open(struct snd_pcm_substream *substream, return snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); out_ops: - kfree(stream); mutex_unlock(&sst_lock); +out_power_up: + kfree(stream); return ret_val; } diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c index 2a5302f1db98..0168af849272 100644 --- a/sound/soc/qcom/qdsp6/q6afe-dai.c +++ b/sound/soc/qcom/qdsp6/q6afe-dai.c @@ -1150,206 +1150,206 @@ static int q6afe_of_xlate_dai_name(struct snd_soc_component *component, } static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = { - SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX_SD1", "Secondary MI2S Playback SD1", - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRI_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRI_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_7", NULL, - 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, SND_SOC_NOPM, 0, 0), }; static const struct snd_soc_component_driver q6afe_dai_component = { diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index eaa95b5a7b66..25d23e0266c7 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -973,6 +973,20 @@ static int msm_routing_probe(struct snd_soc_component *c) return 0; } +static unsigned int q6routing_reg_read(struct snd_soc_component *component, + unsigned int reg) +{ + /* default value */ + return 0; +} + +static int q6routing_reg_write(struct snd_soc_component *component, + unsigned int reg, unsigned int val) +{ + /* dummy */ + return 0; +} + static const struct snd_soc_component_driver msm_soc_routing_component = { .probe = msm_routing_probe, .name = DRV_NAME, @@ -981,6 +995,8 @@ static const struct snd_soc_component_driver msm_soc_routing_component = { .num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets), .dapm_routes = intercon, .num_dapm_routes = ARRAY_SIZE(intercon), + .read = q6routing_reg_read, + .write = q6routing_reg_write, }; static int q6pcm_routing_probe(struct platform_device *pdev) diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index f0b4f4bc44a4..5504b92946e3 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -406,7 +406,7 @@ static unsigned int soc_component_read_no_lock( ret = -EIO; if (ret < 0) - soc_component_ret(component, ret); + return soc_component_ret(component, ret); return val; } diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index fe7117171a0e..0cbe31e2c7e9 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -71,7 +71,7 @@ static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol, return 0; } -static int tegra186_dspk_runtime_suspend(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); @@ -83,7 +83,7 @@ static int tegra186_dspk_runtime_suspend(struct device *dev) return 0; } -static int tegra186_dspk_runtime_resume(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_resume(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c index 4894e8e6ee7f..1268046b345d 100644 --- a/sound/soc/tegra/tegra210_admaif.c +++ b/sound/soc/tegra/tegra210_admaif.c @@ -219,7 +219,7 @@ static const struct regmap_config tegra186_admaif_regmap_config = { .cache_type = REGCACHE_FLAT, }; -static int tegra_admaif_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_suspend(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); @@ -229,7 +229,7 @@ static int tegra_admaif_runtime_suspend(struct device *dev) return 0; } -static int tegra_admaif_runtime_resume(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_resume(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 5123a96fdde8..66287a7c9865 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -564,7 +564,7 @@ static const struct of_device_id tegra_ahub_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_ahub_of_match); -static int tegra_ahub_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_suspend(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); @@ -576,7 +576,7 @@ static int tegra_ahub_runtime_suspend(struct device *dev) return 0; } -static int tegra_ahub_runtime_resume(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_resume(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c index d682414ad90d..a661f40bc41c 100644 --- a/sound/soc/tegra/tegra210_dmic.c +++ b/sound/soc/tegra/tegra210_dmic.c @@ -40,7 +40,7 @@ static const struct reg_default tegra210_dmic_reg_defaults[] = { { TEGRA210_DMIC_LP_BIQUAD_1_COEF_4, 0x0 }, }; -static int tegra210_dmic_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_suspend(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); @@ -52,7 +52,7 @@ static int tegra210_dmic_runtime_suspend(struct device *dev) return 0; } -static int tegra210_dmic_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_resume(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c index 722092181583..a383bd5c51cd 100644 --- a/sound/soc/tegra/tegra210_i2s.c +++ b/sound/soc/tegra/tegra210_i2s.c @@ -164,7 +164,7 @@ static int tegra210_i2s_init(struct snd_soc_dapm_widget *w, return tegra210_i2s_sw_reset(compnt, is_playback); } -static int tegra210_i2s_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_suspend(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); @@ -176,7 +176,7 @@ static int tegra210_i2s_runtime_suspend(struct device *dev) return 0; } -static int tegra210_i2s_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_resume(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); int err; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 6b0f3a8469ef..81e987eaf063 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2371,7 +2371,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, int num_ins; struct usb_mixer_elem_info *cval; struct snd_kcontrol *kctl; - int i, err, nameid, type, len; + int i, err, nameid, type, len, val; const struct procunit_info *info; const struct procunit_value_info *valinfo; const struct usbmix_name_map *map; @@ -2474,6 +2474,12 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, break; } + err = get_cur_ctl_value(cval, cval->control << 8, &val); + if (err < 0) { + usb_mixer_elem_info_free(cval); + return -EINVAL; + } + kctl = snd_ctl_new1(&mixer_procunit_ctl, cval); if (!kctl) { usb_mixer_elem_info_free(cval); diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index d79e3ddc5690..f4fb002e3ef4 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2680,6 +2680,10 @@ YAMAHA_DEVICE(0x7010, "UB99"), .data = (const struct snd_usb_audio_quirk[]) { { .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 0, .type = QUIRK_AUDIO_FIXED_ENDPOINT, .data = &(const struct audioformat) { .formats = SNDRV_PCM_FMTBIT_S24_3LE, @@ -2690,6 +2694,32 @@ YAMAHA_DEVICE(0x7010, "UB99"), .attributes = UAC_EP_CS_ATTR_SAMPLE_RATE, .endpoint = 0x01, .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x024c, + .rates = SNDRV_PCM_RATE_44100 | + SNDRV_PCM_RATE_48000, + .rate_min = 44100, + .rate_max = 48000, + .nr_rates = 2, + .rate_table = (unsigned int[]) { + 44100, 48000 + } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 2, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x0126, .rates = SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000, .rate_min = 44100, @@ -3714,8 +3744,8 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ * they pretend to be 96kHz mono as a workaround for stereo being broken * by that... * - * They also have swapped L-R channels, but that's for userspace to deal - * with. + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index e3b116325403..df7d8ec76036 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -134,6 +134,8 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) while (true) { ret = read(fd, buf, sizeof(buf)); if (ret < 0) { + if (errno == EAGAIN) + continue; err = -errno; p_err("failed to read PID iterator output: %d", err); goto out; diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 6152d1356d7b..dfa540d8a02d 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -258,6 +258,39 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) return btf_id__add(root, id, false); } +/* + * The data of compressed section should be aligned to 4 + * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld + * sets sh_addralign to 1, which makes libelf fail with + * misaligned section error during the update: + * FAILED elf_update(WRITE): invalid section alignment + * + * While waiting for ld fix, we fix the compressed sections + * sh_addralign value manualy. + */ +static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh) +{ + int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8; + + if (!(sh->sh_flags & SHF_COMPRESSED)) + return 0; + + if (sh->sh_addralign == expected) + return 0; + + pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n", + sh->sh_addralign, expected); + + sh->sh_addralign = expected; + + if (gelf_update_shdr(scn, sh) == 0) { + printf("FAILED cannot update section header: %s\n", + elf_errmsg(-1)); + return -1; + } + return 0; +} + static int elf_collect(struct object *obj) { Elf_Scn *scn = NULL; @@ -334,6 +367,9 @@ static int elf_collect(struct object *obj) obj->efile.idlist_shndx = idx; obj->efile.idlist_addr = sh.sh_addr; } + + if (compressed_section_fix(elf, scn, &sh)) + return -1; } return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a613750d5515..8dda13880957 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -776,7 +776,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1042,14 +1042,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1156,7 +1156,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0eaafd9bcfea..6c079b3c8679 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -875,7 +875,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; } else { - m_sz = max(0LL, btf__resolve_size(d->btf, m->type)); + m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; } btf_dump_printf(d, ";"); diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1bb204cee853..9a0946ddb705 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -6,7 +6,6 @@ test_lpm_map test_tag FEATURE-DUMP.libbpf fixdep -test_align test_dev_cgroup /test_progs* test_tcpbpf_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 09657d0afb5c..65d3d9aaeb31 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -32,7 +32,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ + test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \ diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 25b068591e9a..193002b14d7f 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -19,7 +19,7 @@ static int libbpf_debug_print(enum libbpf_print_level level, log_buf = va_arg(args, char *); if (!log_buf) goto out; - if (strstr(log_buf, err_str) == 0) + if (err_str && strstr(log_buf, err_str) == 0) found = true; out: printf(format, log_buf); diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh index 47edf099a17e..508a702f0021 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh @@ -207,7 +207,7 @@ __rate_test() RET=0 - devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 16 + devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 512 devlink trap group set $DEVLINK_DEV group l3_drops policer $id # Send packets at highest possible rate and make sure they are dropped @@ -220,8 +220,8 @@ __rate_test() rate=$(trap_rate_get) pct=$((100 * (rate - 1000) / 1000)) - ((-5 <= pct && pct <= 5)) - check_err $? "Expected rate 1000 pps, got $rate pps, which is $pct% off. Required accuracy is +-5%" + ((-10 <= pct && pct <= 10)) + check_err $? "Expected rate 1000 pps, got $rate pps, which is $pct% off. Required accuracy is +-10%" log_info "Expected rate 1000 pps, measured rate $rate pps" drop_rate=$(policer_drop_rate_get $id) @@ -288,35 +288,12 @@ __burst_test() RET=0 - devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 32 + devlink trap policer set $DEVLINK_DEV policer $id rate 1000 burst 512 devlink trap group set $DEVLINK_DEV group l3_drops policer $id - # Send a burst of 64 packets and make sure that about 32 are received - # and the rest are dropped by the policer - log_info "=== Tx burst size: 64, Policer burst size: 32 pps ===" - - t0_rx=$(devlink_trap_rx_packets_get blackhole_route) - t0_drop=$(devlink_trap_policer_rx_dropped_get $id) - - start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -c 64 - - t1_rx=$(devlink_trap_rx_packets_get blackhole_route) - t1_drop=$(devlink_trap_policer_rx_dropped_get $id) - - rx=$((t1_rx - t0_rx)) - pct=$((100 * (rx - 32) / 32)) - ((-20 <= pct && pct <= 20)) - check_err $? "Expected burst size of 32 packets, got $rx packets, which is $pct% off. Required accuracy is +-20%" - log_info "Expected burst size of 32 packets, measured burst size of $rx packets" - - drop=$((t1_drop - t0_drop)) - (( drop > 0 )) - check_err $? "Expected non-zero policer drops, got 0" - log_info "Measured policer drops of $drop packets" - # Send a burst of 16 packets and make sure that 16 are received # and that none are dropped by the policer - log_info "=== Tx burst size: 16, Policer burst size: 32 pps ===" + log_info "=== Tx burst size: 16, Policer burst size: 512 ===" t0_rx=$(devlink_trap_rx_packets_get blackhole_route) t0_drop=$(devlink_trap_policer_rx_dropped_get $id) diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh index 4b96561c462f..3e3e06ea5703 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -24,6 +24,13 @@ tc_police_switch_destroy() simple_if_fini $swp1 } +tc_police_addr() +{ + local num=$1; shift + + printf "2001:db8:1::%x" $num +} + tc_police_rules_create() { local count=$1; shift @@ -34,8 +41,9 @@ tc_police_rules_create() for ((i = 0; i < count; ++i)); do cat >> $TC_POLICE_BATCH_FILE <<-EOF filter add dev $swp1 ingress \ - prot ip \ - flower skip_sw \ + prot ipv6 \ + pref 1000 \ + flower skip_sw dst_ip $(tc_police_addr $i) \ action police rate 10mbit burst 100k \ conform-exceed drop/ok EOF diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 8162c58a1234..b8d14f9db5f9 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -40,11 +40,11 @@ static void guest_code(void) /* Single step test, covers 2 basic instructions and 2 emulated */ asm volatile("ss_start: " - "xor %%rax,%%rax\n\t" + "xor %%eax,%%eax\n\t" "cpuid\n\t" "movl $0x1a0,%%ecx\n\t" "rdmsr\n\t" - : : : "rax", "ecx"); + : : : "eax", "ebx", "ecx", "edx"); /* DR6.BD test */ asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax"); diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 22dc2f3d428b..b74884d52913 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -739,6 +739,36 @@ ipv6_fcnal_runtime() run_cmd "$IP nexthop replace id 81 via 172.16.1.1 dev veth1" log_test $? 2 "Nexthop replace of group entry - v6 route, v4 nexthop" + run_cmd "$IP nexthop add id 86 via 2001:db8:92::2 dev veth3" + run_cmd "$IP nexthop add id 87 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 88 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 124 group 86/87/88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop del id 88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop del id 87" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 0 "IPv6 route using a group after removing v4 gateways" + + run_cmd "$IP ro delete 2001:db8:101::1/128" + run_cmd "$IP nexthop add id 87 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop add id 88 via 172.16.1.1 dev veth1" + run_cmd "$IP nexthop replace id 124 group 86/87/88" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop replace id 88 via 2001:db8:92::2 dev veth3" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 2 "IPv6 route can not have a group with v4 and v6 gateways" + + run_cmd "$IP nexthop replace id 87 via 2001:db8:92::2 dev veth3" + run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 124" + log_test $? 0 "IPv6 route using a group after replacing v4 gateways" + $IP nexthop flush >/dev/null 2>&1 # diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index c33bfd7ba214..13db1cb50e57 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -31,7 +31,7 @@ mirror_test() local t0=$(tc_rule_stats_get $dev $pref) $MZ $vrf_name ${sip:+-A $sip} -B $dip -a own -b bc -q \ - -c 10 -d 100ms -t icmp type=8 + -c 10 -d 100msec -t icmp type=8 sleep 0.5 local t1=$(tc_rule_stats_get $dev $pref) local delta=$((t1 - t0)) diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index a61b7b3da549..00f837c9bc6c 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -123,6 +123,28 @@ void hash_zone(void *zone, unsigned int length) #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) ((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to)) + +static void *mmap_large_buffer(size_t need, size_t *allocated) +{ + void *buffer; + size_t sz; + + /* Attempt to use huge pages if possible. */ + sz = ALIGN_UP(need, map_align); + buffer = mmap(NULL, sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + + if (buffer == (void *)-1) { + sz = need; + buffer = mmap(NULL, sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buffer != (void *)-1) + fprintf(stderr, "MAP_HUGETLB attempt failed, look at /sys/kernel/mm/hugepages for optimal performance\n"); + } + *allocated = sz; + return buffer; +} + void *child_thread(void *arg) { unsigned long total_mmap = 0, total = 0; @@ -135,6 +157,7 @@ void *child_thread(void *arg) void *addr = NULL; double throughput; struct rusage ru; + size_t buffer_sz; int lu, fd; fd = (int)(unsigned long)arg; @@ -142,9 +165,9 @@ void *child_thread(void *arg) gettimeofday(&t0, NULL); fcntl(fd, F_SETFL, O_NDELAY); - buffer = malloc(chunk_size); - if (!buffer) { - perror("malloc"); + buffer = mmap_large_buffer(chunk_size, &buffer_sz); + if (buffer == (void *)-1) { + perror("mmap"); goto error; } if (zflg) { @@ -179,6 +202,10 @@ void *child_thread(void *arg) total_mmap += zc.length; if (xflg) hash_zone(addr, zc.length); + /* It is more efficient to unmap the pages right now, + * instead of doing this in next TCP_ZEROCOPY_RECEIVE. + */ + madvise(addr, zc.length, MADV_DONTNEED); total += zc.length; } if (zc.recv_skip_hint) { @@ -230,7 +257,7 @@ end: ru.ru_nvcsw); } error: - free(buffer); + munmap(buffer, buffer_sz); close(fd); if (zflg) munmap(raddr, chunk_size + map_align); @@ -347,6 +374,7 @@ int main(int argc, char *argv[]) uint64_t total = 0; char *host = NULL; int fd, c, on = 1; + size_t buffer_sz; char *buffer; int sflg = 0; int mss = 0; @@ -437,8 +465,8 @@ int main(int argc, char *argv[]) } do_accept(fdlisten); } - buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + buffer = mmap_large_buffer(chunk_size, &buffer_sz); if (buffer == (char *)-1) { perror("mmap"); exit(1); @@ -484,6 +512,6 @@ int main(int argc, char *argv[]) total += wr; } close(fd); - munmap(buffer, chunk_size); + munmap(buffer, buffer_sz); return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 737666db02de..67cd0b88a6b6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -482,7 +482,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end); + need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end, + range->flags); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) |