diff options
218 files changed, 5175 insertions, 1607 deletions
@@ -2208,6 +2208,12 @@ N: Christopher Li E: sparse@chrisli.org D: Sparse maintainer 2009 - 2018 +N: Shaohua Li +D: Worked on many parts of the kernel, from core x86, ACPI, PCI, KVM, MM, +D: and much more. He was the maintainer of MD from 2016 to 2018. Shaohua +D: passed away late 2018, he will be greatly missed. +W: https://www.spinics.net/lists/raid/msg61993.html + N: Stephan Linz E: linz@mazet.de E: Stephan.Linz@gmx.de diff --git a/Documentation/admin-guide/reporting-bugs.rst b/Documentation/admin-guide/reporting-bugs.rst index 4650edb8840a..49ac8dc3594d 100644 --- a/Documentation/admin-guide/reporting-bugs.rst +++ b/Documentation/admin-guide/reporting-bugs.rst @@ -67,7 +67,7 @@ If you can't figure out which subsystem caused the issue, you should file a bug in kernel.org bugzilla and send email to linux-kernel@vger.kernel.org, referencing the bugzilla URL. (For more information on the linux-kernel mailing list see -http://www.tux.org/lkml/). +http://vger.kernel.org/lkml/). Tips for reporting bugs diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 3431337ee4e6..cdd24943fbcc 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -291,12 +291,6 @@ Block Devices .. kernel-doc:: block/blk-lib.c :export: -.. kernel-doc:: block/blk-tag.c - :export: - -.. kernel-doc:: block/blk-tag.c - :internal: - .. kernel-doc:: block/blk-integrity.c :export: diff --git a/Documentation/devicetree/bindings/eeprom/at24.txt b/Documentation/devicetree/bindings/eeprom/at24.txt index aededdbc262b..f9a7c984274c 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.txt +++ b/Documentation/devicetree/bindings/eeprom/at24.txt @@ -27,6 +27,7 @@ Required properties: "atmel,24c256", "atmel,24c512", "atmel,24c1024", + "atmel,24c2048", If <manufacturer> is not "atmel", then a fallback must be used with the same <model> and "atmel" as manufacturer. diff --git a/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.txt new file mode 100644 index 000000000000..adf4f000ea3d --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.txt @@ -0,0 +1,23 @@ +STM32 Hardware Spinlock Device Binding +------------------------------------- + +Required properties : +- compatible : should be "st,stm32-hwspinlock". +- reg : the register address of hwspinlock. +- #hwlock-cells : hwlock users only use the hwlock id to represent a specific + hwlock, so the number of cells should be <1> here. +- clock-names : Must contain "hsem". +- clocks : Must contain a phandle entry for the clock in clock-names, see the + common clock bindings. + +Please look at the generic hwlock binding for usage information for consumers, +"Documentation/devicetree/bindings/hwlock/hwlock.txt" + +Example of hwlock provider: + hwspinlock@4c000000 { + compatible = "st,stm32-hwspinlock"; + #hwlock-cells = <1>; + reg = <0x4c000000 0x400>; + clocks = <&rcc HSEM>; + clock-names = "hsem"; + }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-at91.txt b/Documentation/devicetree/bindings/i2c/i2c-at91.txt index ef973a0343c7..b7cec17c3daf 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-at91.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-at91.txt @@ -33,7 +33,7 @@ i2c0: i2c@fff84000 { clock-frequency = <400000>; 24c512@50 { - compatible = "24c512"; + compatible = "atmel,24c512"; reg = <0x50>; pagesize = <128>; } diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt index 1e98c6b3a721..8b1e49cdce3f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-ltc4306.txt @@ -43,7 +43,7 @@ Example: reg = <0>; eeprom@50 { - compatible = "at,24c02"; + compatible = "atmel,24c02"; reg = <0x50>; }; }; @@ -54,7 +54,7 @@ Example: reg = <1>; eeprom@50 { - compatible = "at,24c02"; + compatible = "atmel,24c02"; reg = <0x50>; }; }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt index ccf6c86ed076..30ac6a60f041 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt @@ -54,7 +54,7 @@ Example: reg = <2>; eeprom@54 { - compatible = "at,24c08"; + compatible = "atmel,24c08"; reg = <0x54>; }; }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-owl.txt b/Documentation/devicetree/bindings/i2c/i2c-owl.txt index b743fe444e9f..54c05dbdb2e4 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-owl.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-owl.txt @@ -2,7 +2,9 @@ Actions Semiconductor Owl I2C controller Required properties: -- compatible : Should be "actions,s900-i2c". +- compatible : Should be one of the following: + - "actions,s700-i2c" for S700 SoC + - "actions,s900-i2c" for S900 SoC - reg : Offset and length of the register set for the device. - #address-cells : Should be 1. - #size-cells : Should be 0. diff --git a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt index 30c0485b167b..3ee5e8f6ee01 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-rcar.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-rcar.txt @@ -7,6 +7,7 @@ Required properties: "renesas,i2c-r8a7745" if the device is a part of a R8A7745 SoC. "renesas,i2c-r8a77470" if the device is a part of a R8A77470 SoC. "renesas,i2c-r8a774a1" if the device is a part of a R8A774A1 SoC. + "renesas,i2c-r8a774c0" if the device is a part of a R8A774C0 SoC. "renesas,i2c-r8a7778" if the device is a part of a R8A7778 SoC. "renesas,i2c-r8a7779" if the device is a part of a R8A7779 SoC. "renesas,i2c-r8a7790" if the device is a part of a R8A7790 SoC. diff --git a/Documentation/devicetree/bindings/i2c/i2c-sh_mobile.txt b/Documentation/devicetree/bindings/i2c/i2c-sh_mobile.txt index d81b62643655..202602e6e837 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-sh_mobile.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-sh_mobile.txt @@ -8,6 +8,7 @@ Required properties: - "renesas,iic-r8a7744" (RZ/G1N) - "renesas,iic-r8a7745" (RZ/G1E) - "renesas,iic-r8a774a1" (RZ/G2M) + - "renesas,iic-r8a774c0" (RZ/G2E) - "renesas,iic-r8a7790" (R-Car H2) - "renesas,iic-r8a7791" (R-Car M2-W) - "renesas,iic-r8a7792" (R-Car V2H) @@ -16,6 +17,7 @@ Required properties: - "renesas,iic-r8a7795" (R-Car H3) - "renesas,iic-r8a7796" (R-Car M3-W) - "renesas,iic-r8a77965" (R-Car M3-N) + - "renesas,iic-r8a77990" (R-Car E3) - "renesas,iic-sh73a0" (SH-Mobile AG5) - "renesas,rcar-gen2-iic" (generic R-Car Gen2 or RZ/G1 compatible device) @@ -28,7 +30,13 @@ Required properties: the platform first followed by the generic R-Car version. - renesas,rmobile-iic must always follow. + When compatible with "renesas,rmobile-iic" it should + be the last compatibility string listed. + + The r8a77990 (R-Car E3) and r8a774c0 (RZ/G2E) + controllers are not considered compatible with + "renesas,rcar-gen3-iic" or "renesas,rmobile-iic" + due to the absence of automatic transmission registers. - reg : address start and address range size of device - interrupts : interrupt of device diff --git a/Documentation/devicetree/bindings/i2c/i2c-stm32.txt b/Documentation/devicetree/bindings/i2c/i2c-stm32.txt index 3b5489966634..69240e189b01 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-stm32.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-stm32.txt @@ -26,6 +26,11 @@ Optional properties : - i2c-scl-falling-time-ns : Only for STM32F7, I2C SCL Falling time for the board (default: 10) I2C Timings are derived from these 2 values +- st,syscfg-fmp: Only for STM32F7, use to set Fast Mode Plus bit within SYSCFG + whether Fast Mode Plus speed is selected by slave. + 1st cell : phandle to syscfg + 2nd cell : register offset within SYSCFG + 3rd cell : register bitmask for FMP bit Example : @@ -53,4 +58,5 @@ Example : clocks = <&rcc 1 CLK_I2C1>; pinctrl-0 = <&i2c1_sda_pin>, <&i2c1_scl_pin>; pinctrl-names = "default"; + st,syscfg-fmp = <&syscfg 0x4 0x1>; }; diff --git a/Documentation/devicetree/bindings/i2c/nxp,pca9541.txt b/Documentation/devicetree/bindings/i2c/nxp,pca9541.txt index 0fbbc6970ec5..42bfc09c8918 100644 --- a/Documentation/devicetree/bindings/i2c/nxp,pca9541.txt +++ b/Documentation/devicetree/bindings/i2c/nxp,pca9541.txt @@ -22,7 +22,7 @@ Example: #size-cells = <0>; eeprom@54 { - compatible = "at,24c08"; + compatible = "atmel,24c08"; reg = <0x54>; }; }; diff --git a/Documentation/devicetree/bindings/pci/amlogic,meson-pcie.txt b/Documentation/devicetree/bindings/pci/amlogic,meson-pcie.txt new file mode 100644 index 000000000000..12b18f82d441 --- /dev/null +++ b/Documentation/devicetree/bindings/pci/amlogic,meson-pcie.txt @@ -0,0 +1,70 @@ +Amlogic Meson AXG DWC PCIE SoC controller + +Amlogic Meson PCIe host controller is based on the Synopsys DesignWare PCI core. +It shares common functions with the PCIe DesignWare core driver and +inherits common properties defined in +Documentation/devicetree/bindings/pci/designware-pci.txt. + +Additional properties are described here: + +Required properties: +- compatible: + should contain "amlogic,axg-pcie" to identify the core. +- reg: + should contain the configuration address space. +- reg-names: Must be + - "elbi" External local bus interface registers + - "cfg" Meson specific registers + - "phy" Meson PCIE PHY registers + - "config" PCIe configuration space +- reset-gpios: The GPIO to generate PCIe PERST# assert and deassert signal. +- clocks: Must contain an entry for each entry in clock-names. +- clock-names: Must include the following entries: + - "pclk" PCIe GEN 100M PLL clock + - "port" PCIe_x(A or B) RC clock gate + - "general" PCIe Phy clock + - "mipi" PCIe_x(A or B) 100M ref clock gate +- resets: phandle to the reset lines. +- reset-names: must contain "phy" "port" and "apb" + - "phy" Share PHY reset + - "port" Port A or B reset + - "apb" Share APB reset +- device_type: + should be "pci". As specified in designware-pcie.txt + + +Example configuration: + + pcie: pcie@f9800000 { + compatible = "amlogic,axg-pcie", "snps,dw-pcie"; + reg = <0x0 0xf9800000 0x0 0x400000 + 0x0 0xff646000 0x0 0x2000 + 0x0 0xff644000 0x0 0x2000 + 0x0 0xf9f00000 0x0 0x100000>; + reg-names = "elbi", "cfg", "phy", "config"; + reset-gpios = <&gpio GPIOX_19 GPIO_ACTIVE_HIGH>; + interrupts = <GIC_SPI 177 IRQ_TYPE_EDGE_RISING>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SPI 179 IRQ_TYPE_EDGE_RISING>; + bus-range = <0x0 0xff>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x82000000 0 0 0x0 0xf9c00000 0 0x00300000>; + + clocks = <&clkc CLKID_USB + &clkc CLKID_MIPI_ENABLE + &clkc CLKID_PCIE_A + &clkc CLKID_PCIE_CML_EN0>; + clock-names = "general", + "mipi", + "pclk", + "port"; + resets = <&reset RESET_PCIE_PHY>, + <&reset RESET_PCIE_A>, + <&reset RESET_PCIE_APB>; + reset-names = "phy", + "port", + "apb"; + }; diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt index f37494d5a7be..d514c1f2365f 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt @@ -41,7 +41,9 @@ Optional properties: Additional required properties for imx6sx-pcie: - clock names: Must include the following additional entries: - "pcie_inbound_axi" -- power-domains: Must be set to a phandle pointing to the PCIE_PHY power domain +- power-domains: Must be set to phandles pointing to the DISPLAY and + PCIE_PHY power domains +- power-domain-names: Must be "pcie", "pcie_phy" Additional required properties for imx7d-pcie: - power-domains: Must be set to a phandle pointing to PCIE_PHY power domain diff --git a/Documentation/devicetree/bindings/pci/mediatek-pcie.txt b/Documentation/devicetree/bindings/pci/mediatek-pcie.txt index 20227a875ac8..92437a366e5f 100644 --- a/Documentation/devicetree/bindings/pci/mediatek-pcie.txt +++ b/Documentation/devicetree/bindings/pci/mediatek-pcie.txt @@ -65,7 +65,6 @@ Required properties: explanation. - ranges: Sub-ranges distributed from the PCIe controller node. An empty property is sufficient. -- num-lanes: Number of lanes to use for this port. Examples for MT7623: @@ -118,7 +117,6 @@ Examples for MT7623: interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 193 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; }; pcie@1,0 { @@ -129,7 +127,6 @@ Examples for MT7623: interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 194 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; }; pcie@2,0 { @@ -140,7 +137,6 @@ Examples for MT7623: interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 195 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; }; }; @@ -172,7 +168,6 @@ Examples for MT2712: #size-cells = <2>; #interrupt-cells = <1>; ranges; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc0 0>, <0 0 0 2 &pcie_intc0 1>, @@ -191,7 +186,6 @@ Examples for MT2712: #size-cells = <2>; #interrupt-cells = <1>; ranges; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc1 0>, <0 0 0 2 &pcie_intc1 1>, @@ -245,7 +239,6 @@ Examples for MT7622: #size-cells = <2>; #interrupt-cells = <1>; ranges; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc0 0>, <0 0 0 2 &pcie_intc0 1>, @@ -264,7 +257,6 @@ Examples for MT7622: #size-cells = <2>; #interrupt-cells = <1>; ranges; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc1 0>, <0 0 0 2 &pcie_intc1 1>, diff --git a/Documentation/devicetree/bindings/pci/uniphier-pcie.txt b/Documentation/devicetree/bindings/pci/uniphier-pcie.txt new file mode 100644 index 000000000000..1fa2c5906d4d --- /dev/null +++ b/Documentation/devicetree/bindings/pci/uniphier-pcie.txt @@ -0,0 +1,81 @@ +Socionext UniPhier PCIe host controller bindings + +This describes the devicetree bindings for PCIe host controller implemented +on Socionext UniPhier SoCs. + +UniPhier PCIe host controller is based on the Synopsys DesignWare PCI core. +It shares common functions with the PCIe DesignWare core driver and inherits +common properties defined in +Documentation/devicetree/bindings/pci/designware-pcie.txt. + +Required properties: +- compatible: Should be "socionext,uniphier-pcie". +- reg: Specifies offset and length of the register set for the device. + According to the reg-names, appropriate register sets are required. +- reg-names: Must include the following entries: + "dbi" - controller configuration registers + "link" - SoC-specific glue layer registers + "config" - PCIe configuration space +- clocks: A phandle to the clock gate for PCIe glue layer including + the host controller. +- resets: A phandle to the reset line for PCIe glue layer including + the host controller. +- interrupts: A list of interrupt specifiers. According to the + interrupt-names, appropriate interrupts are required. +- interrupt-names: Must include the following entries: + "dma" - DMA interrupt + "msi" - MSI interrupt + +Optional properties: +- phys: A phandle to generic PCIe PHY. According to the phy-names, appropriate + phys are required. +- phy-names: Must be "pcie-phy". + +Required sub-node: +- legacy-interrupt-controller: Specifies interrupt controller for legacy PCI + interrupts. + +Required properties for legacy-interrupt-controller: +- interrupt-controller: identifies the node as an interrupt controller. +- #interrupt-cells: specifies the number of cells needed to encode an + interrupt source. The value must be 1. +- interrupt-parent: Phandle to the parent interrupt controller. +- interrupts: An interrupt specifier for legacy interrupt. + +Example: + + pcie: pcie@66000000 { + compatible = "socionext,uniphier-pcie", "snps,dw-pcie"; + status = "disabled"; + reg-names = "dbi", "link", "config"; + reg = <0x66000000 0x1000>, <0x66010000 0x10000>, + <0x2fff0000 0x10000>; + #address-cells = <3>; + #size-cells = <2>; + clocks = <&sys_clk 24>; + resets = <&sys_rst 24>; + num-lanes = <1>; + num-viewport = <1>; + bus-range = <0x0 0xff>; + device_type = "pci"; + ranges = + /* downstream I/O */ + <0x81000000 0 0x00000000 0x2ffe0000 0 0x00010000 + /* non-prefetchable memory */ + 0x82000000 0 0x00000000 0x20000000 0 0x0ffe0000>; + #interrupt-cells = <1>; + interrupt-names = "dma", "msi"; + interrupts = <0 224 4>, <0 225 4>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, /* INTA */ + <0 0 0 2 &pcie_intc 1>, /* INTB */ + <0 0 0 3 &pcie_intc 2>, /* INTC */ + <0 0 0 4 &pcie_intc 3>; /* INTD */ + + pcie_intc: legacy-interrupt-controller { + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = <0 226 4>; + }; + }; diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst index 4c577fa7bef9..6d85b5a2598d 100644 --- a/Documentation/driver-api/pci/p2pdma.rst +++ b/Documentation/driver-api/pci/p2pdma.rst @@ -49,7 +49,7 @@ For example, in the NVMe Target Copy Offload implementation: in that it exposes any CMB (Controller Memory Buffer) as a P2P memory resource (provider), it accepts P2P memory pages as buffers in requests to be used directly (client) and it can also make use of the CMB as - submission queue entries (orchastrator). + submission queue entries (orchestrator). * The RDMA driver is a client in this arrangement so that an RNIC can DMA directly to the memory exposed by the NVMe device. * The NVMe Target driver (nvmet) can orchestrate the data from the RNIC @@ -111,7 +111,7 @@ that's compatible with all clients using :c:func:`pci_p2pmem_find()`. If more than one provider is supported, the one nearest to all the clients will be chosen first. If more than one provider is an equal distance away, the one returned will be chosen at random (it is not an arbitrary but -truely random). This function returns the PCI device to use for the provider +truly random). This function returns the PCI device to use for the provider with a reference taken and therefore when it's no longer needed it should be returned with pci_dev_put(). diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index 841c99529d27..b277cafce71e 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -250,7 +250,6 @@ DMA dmaenginem_async_device_register() dmam_alloc_coherent() dmam_alloc_attrs() - dmam_declare_coherent_memory() dmam_free_coherent() dmam_pool_create() dmam_pool_destroy() diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index bc393e0a22b8..6d2c0d340dea 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -75,7 +75,7 @@ exposure of uninitialized data through mmap. These filesystems may be used for inspiration: - ext2: see Documentation/filesystems/ext2.txt -- ext4: see Documentation/filesystems/ext4/ext4.rst +- ext4: see Documentation/filesystems/ext4/ - xfs: see Documentation/filesystems/xfs.txt diff --git a/Documentation/filesystems/ext2.txt b/Documentation/filesystems/ext2.txt index a45c9fc0747b..a19973a4dd1e 100644 --- a/Documentation/filesystems/ext2.txt +++ b/Documentation/filesystems/ext2.txt @@ -358,7 +358,7 @@ and are copied into the filesystem. If a transaction is incomplete at the time of the crash, then there is no guarantee of consistency for the blocks in that transaction so they are discarded (which means any filesystem changes they represent are also lost). -Check Documentation/filesystems/ext4/ext4.rst if you want to read more about +Check Documentation/filesystems/ext4/ if you want to read more about ext4 and journaling. References diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index cfbc18f0d9c9..3a7b60521b94 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -132,47 +132,28 @@ designed for this purpose be used, such as scrypt, PBKDF2, or Argon2. Per-file keys ------------- -Master keys are not used to encrypt file contents or names directly. -Instead, a unique key is derived for each encrypted file, including -each regular file, directory, and symbolic link. This has several -advantages: - -- In cryptosystems, the same key material should never be used for - different purposes. Using the master key as both an XTS key for - contents encryption and as a CTS-CBC key for filenames encryption - would violate this rule. -- Per-file keys simplify the choice of IVs (Initialization Vectors) - for contents encryption. Without per-file keys, to ensure IV - uniqueness both the inode and logical block number would need to be - encoded in the IVs. This would make it impossible to renumber - inodes, which e.g. ``resize2fs`` can do when resizing an ext4 - filesystem. With per-file keys, it is sufficient to encode just the - logical block number in the IVs. -- Per-file keys strengthen the encryption of filenames, where IVs are - reused out of necessity. With a unique key per directory, IV reuse - is limited to within a single directory. -- Per-file keys allow individual files to be securely erased simply by - securely erasing their keys. (Not yet implemented.) - -A KDF (Key Derivation Function) is used to derive per-file keys from -the master key. This is done instead of wrapping a randomly-generated -key for each file because it reduces the size of the encryption xattr, -which for some filesystems makes the xattr more likely to fit in-line -in the filesystem's inode table. With a KDF, only a 16-byte nonce is -required --- long enough to make key reuse extremely unlikely. A -wrapped key, on the other hand, would need to be up to 64 bytes --- -the length of an AES-256-XTS key. Furthermore, currently there is no -requirement to support unlocking a file with multiple alternative -master keys or to support rotating master keys. Instead, the master -keys may be wrapped in userspace, e.g. as done by the `fscrypt -<https://github.com/google/fscrypt>`_ tool. - -The current KDF encrypts the master key using the 16-byte nonce as an -AES-128-ECB key. The output is used as the derived key. If the -output is longer than needed, then it is truncated to the needed -length. Truncation is the norm for directories and symlinks, since -those use the CTS-CBC encryption mode which requires a key half as -long as that required by the XTS encryption mode. +Since each master key can protect many files, it is necessary to +"tweak" the encryption of each file so that the same plaintext in two +files doesn't map to the same ciphertext, or vice versa. In most +cases, fscrypt does this by deriving per-file keys. When a new +encrypted inode (regular file, directory, or symlink) is created, +fscrypt randomly generates a 16-byte nonce and stores it in the +inode's encryption xattr. Then, it uses a KDF (Key Derivation +Function) to derive the file's key from the master key and nonce. + +The Adiantum encryption mode (see `Encryption modes and usage`_) is +special, since it accepts longer IVs and is suitable for both contents +and filenames encryption. For it, a "direct key" option is offered +where the file's nonce is included in the IVs and the master key is +used for encryption directly. This improves performance; however, +users must not use the same master key for any other encryption mode. + +Below, the KDF and design considerations are described in more detail. + +The current KDF works by encrypting the master key with AES-128-ECB, +using the file's nonce as the AES key. The output is used as the +derived key. If the output is longer than needed, then it is +truncated to the needed length. Note: this KDF meets the primary security requirement, which is to produce unique derived keys that preserve the entropy of the master @@ -181,6 +162,20 @@ However, it is nonstandard and has some problems such as being reversible, so it is generally considered to be a mistake! It may be replaced with HKDF or another more standard KDF in the future. +Key derivation was chosen over key wrapping because wrapped keys would +require larger xattrs which would be less likely to fit in-line in the +filesystem's inode table, and there didn't appear to be any +significant advantages to key wrapping. In particular, currently +there is no requirement to support unlocking a file with multiple +alternative master keys or to support rotating master keys. Instead, +the master keys may be wrapped in userspace, e.g. as is done by the +`fscrypt <https://github.com/google/fscrypt>`_ tool. + +Including the inode number in the IVs was considered. However, it was +rejected as it would have prevented ext4 filesystems from being +resized, and by itself still wouldn't have been sufficient to prevent +the same key from being directly reused for both XTS and CTS-CBC. + Encryption modes and usage ========================== @@ -191,54 +186,80 @@ Currently, the following pairs of encryption modes are supported: - AES-256-XTS for contents and AES-256-CTS-CBC for filenames - AES-128-CBC for contents and AES-128-CTS-CBC for filenames +- Adiantum for both contents and filenames + +If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair. -It is strongly recommended to use AES-256-XTS for contents encryption. AES-128-CBC was added only for low-powered embedded devices with crypto accelerators such as CAAM or CESA that do not support XTS. +Adiantum is a (primarily) stream cipher-based mode that is fast even +on CPUs without dedicated crypto instructions. It's also a true +wide-block mode, unlike XTS. It can also eliminate the need to derive +per-file keys. However, it depends on the security of two primitives, +XChaCha12 and AES-256, rather than just one. See the paper +"Adiantum: length-preserving encryption for entry-level processors" +(https://eprint.iacr.org/2018/720.pdf) for more details. To use +Adiantum, CONFIG_CRYPTO_ADIANTUM must be enabled. Also, fast +implementations of ChaCha and NHPoly1305 should be enabled, e.g. +CONFIG_CRYPTO_CHACHA20_NEON and CONFIG_CRYPTO_NHPOLY1305_NEON for ARM. + New encryption modes can be added relatively easily, without changes to individual filesystems. However, authenticated encryption (AE) modes are not currently supported because of the difficulty of dealing with ciphertext expansion. +Contents encryption +------------------- + For file contents, each filesystem block is encrypted independently. Currently, only the case where the filesystem block size is equal to -the system's page size (usually 4096 bytes) is supported. With the -XTS mode of operation (recommended), the logical block number within -the file is used as the IV. With the CBC mode of operation (not -recommended), ESSIV is used; specifically, the IV for CBC is the -logical block number encrypted with AES-256, where the AES-256 key is -the SHA-256 hash of the inode's data encryption key. - -For filenames, the full filename is encrypted at once. Because of the -requirements to retain support for efficient directory lookups and -filenames of up to 255 bytes, a constant initialization vector (IV) is -used. However, each encrypted directory uses a unique key, which -limits IV reuse to within a single directory. Note that IV reuse in -the context of CTS-CBC encryption means that when the original -filenames share a common prefix at least as long as the cipher block -size (16 bytes for AES), the corresponding encrypted filenames will -also share a common prefix. This is undesirable; it may be fixed in -the future by switching to an encryption mode that is a strong -pseudorandom permutation on arbitrary-length messages, e.g. the HEH -(Hash-Encrypt-Hash) mode. - -Since filenames are encrypted with the CTS-CBC mode of operation, the -plaintext and ciphertext filenames need not be multiples of the AES -block size, i.e. 16 bytes. However, the minimum size that can be -encrypted is 16 bytes, so shorter filenames are NUL-padded to 16 bytes -before being encrypted. In addition, to reduce leakage of filename -lengths via their ciphertexts, all filenames are NUL-padded to the -next 4, 8, 16, or 32-byte boundary (configurable). 32 is recommended -since this provides the best confidentiality, at the cost of making -directory entries consume slightly more space. Note that since NUL -(``\0``) is not otherwise a valid character in filenames, the padding -will never produce duplicate plaintexts. +the system's page size (usually 4096 bytes) is supported. + +Each block's IV is set to the logical block number within the file as +a little endian number, except that: + +- With CBC mode encryption, ESSIV is also used. Specifically, each IV + is encrypted with AES-256 where the AES-256 key is the SHA-256 hash + of the file's data encryption key. + +- In the "direct key" configuration (FS_POLICY_FLAG_DIRECT_KEY set in + the fscrypt_policy), the file's nonce is also appended to the IV. + Currently this is only allowed with the Adiantum encryption mode. + +Filenames encryption +-------------------- + +For filenames, each full filename is encrypted at once. Because of +the requirements to retain support for efficient directory lookups and +filenames of up to 255 bytes, the same IV is used for every filename +in a directory. + +However, each encrypted directory still uses a unique key; or +alternatively (for the "direct key" configuration) has the file's +nonce included in the IVs. Thus, IV reuse is limited to within a +single directory. + +With CTS-CBC, the IV reuse means that when the plaintext filenames +share a common prefix at least as long as the cipher block size (16 +bytes for AES), the corresponding encrypted filenames will also share +a common prefix. This is undesirable. Adiantum does not have this +weakness, as it is a wide-block encryption mode. + +All supported filenames encryption modes accept any plaintext length +>= 16 bytes; cipher block alignment is not required. However, +filenames shorter than 16 bytes are NUL-padded to 16 bytes before +being encrypted. In addition, to reduce leakage of filename lengths +via their ciphertexts, all filenames are NUL-padded to the next 4, 8, +16, or 32-byte boundary (configurable). 32 is recommended since this +provides the best confidentiality, at the cost of making directory +entries consume slightly more space. Note that since NUL (``\0``) is +not otherwise a valid character in filenames, the padding will never +produce duplicate plaintexts. Symbolic link targets are considered a type of filename and are -encrypted in the same way as filenames in directory entries. Each -symlink also uses a unique key; hence, the hardcoded IV is not a -problem for symlinks. +encrypted in the same way as filenames in directory entries, except +that IV reuse is not a problem as each symlink has its own inode. User API ======== @@ -272,9 +293,13 @@ This structure must be initialized as follows: and FS_ENCRYPTION_MODE_AES_256_CTS (4) for ``filenames_encryption_mode``. -- ``flags`` must be set to a value from ``<linux/fs.h>`` which +- ``flags`` must contain a value from ``<linux/fs.h>`` which identifies the amount of NUL-padding to use when encrypting filenames. If unsure, use FS_POLICY_FLAGS_PAD_32 (0x3). + In addition, if the chosen encryption modes are both + FS_ENCRYPTION_MODE_ADIANTUM, this can contain + FS_POLICY_FLAG_DIRECT_KEY to specify that the master key should be + used directly, without key derivation. - ``master_key_descriptor`` specifies how to find the master key in the keyring; see `Adding keys`_. It is up to userspace to choose a diff --git a/Documentation/hid/uhid.txt b/Documentation/hid/uhid.txt index c8656dd029a9..958fff945304 100644 --- a/Documentation/hid/uhid.txt +++ b/Documentation/hid/uhid.txt @@ -160,7 +160,7 @@ them but you should handle them according to your needs. UHID_OUTPUT: This is sent if the HID device driver wants to send raw data to the I/O device on the interrupt channel. You should read the payload and forward it to - the device. The payload is of type "struct uhid_data_req". + the device. The payload is of type "struct uhid_output_req". This may be received even though you haven't received UHID_OPEN, yet. UHID_GET_REPORT: diff --git a/Documentation/input/event-codes.rst b/Documentation/input/event-codes.rst index a8c0873beb95..b24b5343f5eb 100644 --- a/Documentation/input/event-codes.rst +++ b/Documentation/input/event-codes.rst @@ -190,7 +190,26 @@ A few EV_REL codes have special meanings: * REL_WHEEL, REL_HWHEEL: - These codes are used for vertical and horizontal scroll wheels, - respectively. + respectively. The value is the number of detents moved on the wheel, the + physical size of which varies by device. For high-resolution wheels + this may be an approximation based on the high-resolution scroll events, + see REL_WHEEL_HI_RES. These event codes are legacy codes and + REL_WHEEL_HI_RES and REL_HWHEEL_HI_RES should be preferred where + available. + +* REL_WHEEL_HI_RES, REL_HWHEEL_HI_RES: + + - High-resolution scroll wheel data. The accumulated value 120 represents + movement by one detent. For devices that do not provide high-resolution + scrolling, the value is always a multiple of 120. For devices with + high-resolution scrolling, the value may be a fraction of 120. + + If a vertical scroll wheel supports high-resolution scrolling, this code + will be emitted in addition to REL_WHEEL or REL_HWHEEL. The REL_WHEEL + and REL_HWHEEL may be an approximation based on the high-resolution + scroll events. There is no guarantee that the high-resolution data + is a multiple of 120 at the time of an emulated REL_WHEEL or REL_HWHEEL + event. EV_ABS ------ diff --git a/MAINTAINERS b/MAINTAINERS index 39e75bbefc3d..32d444476a90 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3674,11 +3674,20 @@ F: drivers/input/touchscreen/chipone_icn8505.c CHROME HARDWARE PLATFORM SUPPORT M: Benson Leung <bleung@chromium.org> -M: Olof Johansson <olof@lixom.net> +M: Enric Balletbo i Serra <enric.balletbo@collabora.com> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/bleung/chrome-platform.git F: drivers/platform/chrome/ +CHROMEOS EC SUBDRIVERS +M: Benson Leung <bleung@chromium.org> +M: Enric Balletbo i Serra <enric.balletbo@collabora.com> +R: Guenter Roeck <groeck@chromium.org> +S: Maintained +N: cros_ec +N: cros-ec +F: drivers/power/supply/cros_usbpd-charger.c + CIRRUS LOGIC AUDIO CODEC DRIVERS M: Brian Austin <brian.austin@cirrus.com> M: Paul Handrigan <Paul.Handrigan@cirrus.com> @@ -5710,7 +5719,7 @@ W: http://ext4.wiki.kernel.org Q: http://patchwork.ozlabs.org/project/linux-ext4/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git S: Maintained -F: Documentation/filesystems/ext4/ext4.rst +F: Documentation/filesystems/ext4/ F: fs/ext4/ Extended Verification Module (EVM) @@ -11750,6 +11759,7 @@ F: include/uapi/linux/pci* F: lib/pci* F: arch/x86/pci/ F: arch/x86/kernel/quirks.c +F: arch/x86/kernel/early-quirks.c PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> @@ -11759,6 +11769,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git/ S: Supported F: drivers/pci/controller/ +PCIE DRIVER FOR AMLOGIC MESON +M: Yue Wang <yue.wang@Amlogic.com> +L: linux-pci@vger.kernel.org +L: linux-amlogic@lists.infradead.org +S: Maintained +F: drivers/pci/controller/dwc/pci-meson.c + PCIE DRIVER FOR AXIS ARTPEC M: Jesper Nilsson <jesper.nilsson@axis.com> L: linux-arm-kernel@axis.com @@ -11791,7 +11808,6 @@ F: Documentation/devicetree/bindings/pci/kirin-pcie.txt F: drivers/pci/controller/dwc/pcie-kirin.c PCIE DRIVER FOR HISILICON STB -M: Jianguo Sun <sunjianguo1@huawei.com> M: Shawn Guo <shawn.guo@linaro.org> L: linux-pci@vger.kernel.org S: Maintained @@ -11828,6 +11844,13 @@ S: Maintained F: Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt F: drivers/pci/controller/pci-v3-semi.c +PCIE DRIVER FOR SOCIONEXT UNIPHIER +M: Kunihiko Hayashi <hayashi.kunihiko@socionext.com> +L: linux-pci@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pci/uniphier-pcie.txt +F: drivers/pci/controller/dwc/pcie-uniphier.c + PCIE DRIVER FOR ST SPEAR13XX M: Pratyush Anand <pratyush.anand@gmail.com> L: linux-pci@vger.kernel.org diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h index e69c4e13c328..cf4ac791a592 100644 --- a/arch/alpha/include/asm/uaccess.h +++ b/arch/alpha/include/asm/uaccess.h @@ -30,11 +30,13 @@ * Address valid if: * - "addr" doesn't have any high-bits set * - AND "size" doesn't have any high-bits set - * - AND "addr+size" doesn't have any high-bits set + * - AND "addr+size-(size != 0)" doesn't have any high-bits set * - OR we are in kernel mode. */ -#define __access_ok(addr, size) \ - ((get_fs().seg & (addr | size | (addr+size))) == 0) +#define __access_ok(addr, size) ({ \ + unsigned long __ao_a = (addr), __ao_b = (size); \ + unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b; \ + (get_fs().seg & (__ao_a | __ao_b | __ao_end)) == 0; }) #define access_ok(addr, size) \ ({ \ diff --git a/arch/arm/boot/dts/mt7623.dtsi b/arch/arm/boot/dts/mt7623.dtsi index d01bdee6f2f3..98f115966391 100644 --- a/arch/arm/boot/dts/mt7623.dtsi +++ b/arch/arm/boot/dts/mt7623.dtsi @@ -850,7 +850,6 @@ interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 193 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; status = "disabled"; }; @@ -862,7 +861,6 @@ interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 194 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; status = "disabled"; }; @@ -874,7 +872,6 @@ interrupt-map-mask = <0 0 0 0>; interrupt-map = <0 0 0 0 &sysirq GIC_SPI 195 IRQ_TYPE_LEVEL_LOW>; ranges; - num-lanes = <1>; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 14a1028ca3a6..8fc4aa77f012 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -802,7 +802,6 @@ ranges; status = "disabled"; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc0 0>, <0 0 0 2 &pcie_intc0 1>, @@ -823,7 +822,6 @@ ranges; status = "disabled"; - num-lanes = <1>; interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc1 0>, <0 0 0 2 &pcie_intc1 1>, diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 6df622fb406d..a966d7bfac57 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -649,6 +649,9 @@ int pcibios_add_device(struct pci_dev *pdev) struct resource *res; int i; + if (pdev->is_physfn) + pdev->no_vf_scan = 1; + pdev->dev.groups = zpci_attr_groups; pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h index deebbfab5342..5fe751ad7582 100644 --- a/arch/sh/include/asm/uaccess.h +++ b/arch/sh/include/asm/uaccess.h @@ -16,8 +16,11 @@ * sum := addr + size; carry? --> flag = true; * if (sum >= addr_limit) flag = true; */ -#define __access_ok(addr, size) \ - (__addr_ok((addr) + (size))) +#define __access_ok(addr, size) ({ \ + unsigned long __ao_a = (addr), __ao_b = (size); \ + unsigned long __ao_end = __ao_a + __ao_b - !!__ao_b; \ + __ao_end >= __ao_a && __addr_ok(__ao_end); }) + #define access_ok(addr, size) \ (__chk_user_ptr(addr), \ __access_ok((unsigned long __force)(addr), (size))) diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index e0ff3ac8c127..2c0aa34af69c 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -256,7 +256,15 @@ static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, int npages; int i; - if (dma_addr == DMA_MAPPING_ERROR || + if (WARN_ON_ONCE(dma_addr == DMA_MAPPING_ERROR)) + return; + + /* + * This driver will not always use a GART mapping, but might have + * created a direct mapping instead. If that is the case there is + * nothing to unmap here. + */ + if (dma_addr < iommu_bus_base || dma_addr >= iommu_bus_base + iommu_size) return; diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c index 526536c81ddc..ca1e8e6dccc8 100644 --- a/arch/x86/pci/broadcom_bus.c +++ b/arch/x86/pci/broadcom_bus.c @@ -50,8 +50,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func) word1 = read_pci_config_16(bus, slot, func, 0xc0); word2 = read_pci_config_16(bus, slot, func, 0xc2); if (word1 != word2) { - res.start = (word1 << 16) | 0x0000; - res.end = (word2 << 16) | 0xffff; + res.start = ((resource_size_t) word1 << 16) | 0x0000; + res.end = ((resource_size_t) word2 << 16) | 0xffff; res.flags = IORESOURCE_MEM; update_res(info, res.start, res.end, res.flags, 0); } diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 0ff27e2d98c4..26937ba28f78 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -181,7 +181,7 @@ static void vdc_blk_queue_start(struct vdc_port *port) * allocated a disk. */ if (port->disk && vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50) - blk_mq_start_hw_queues(port->disk->queue); + blk_mq_start_stopped_hw_queues(port->disk->queue, true); } static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for) diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig index 145974f9662b..4199849e3758 100644 --- a/drivers/firewire/Kconfig +++ b/drivers/firewire/Kconfig @@ -1,5 +1,4 @@ menu "IEEE 1394 (FireWire) support" - depends on HAS_DMA depends on PCI || COMPILE_TEST # firewire-core does not depend on PCI but is # not useful without PCI controller driver diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index cf4e190c0a72..1c49b8266d69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1428,6 +1428,9 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data, if (IS_ERR(fence)) return PTR_ERR(fence); + if (!fence) + fence = dma_fence_get_stub(); + switch (info->in.what) { case AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ: r = drm_syncobj_create(&syncobj, 0, fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index b60afeade50a..8a078f4ae73d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3476,14 +3476,16 @@ static void amdgpu_device_lock_adev(struct amdgpu_device *adev) mutex_lock(&adev->lock_reset); atomic_inc(&adev->gpu_reset_counter); adev->in_gpu_reset = 1; - /* Block kfd */ - amdgpu_amdkfd_pre_reset(adev); + /* Block kfd: SRIOV would do it separately */ + if (!amdgpu_sriov_vf(adev)) + amdgpu_amdkfd_pre_reset(adev); } static void amdgpu_device_unlock_adev(struct amdgpu_device *adev) { - /*unlock kfd */ - amdgpu_amdkfd_post_reset(adev); + /*unlock kfd: SRIOV would do it separately */ + if (!amdgpu_sriov_vf(adev)) + amdgpu_amdkfd_post_reset(adev); amdgpu_vf_error_trans_all(adev); adev->in_gpu_reset = 0; mutex_unlock(&adev->lock_reset); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 9c77eaa45982..c806f984bcc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -865,6 +865,7 @@ static const struct pci_device_id pciidlist[] = { /* VEGAM */ {0x1002, 0x694C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM}, {0x1002, 0x694E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM}, + {0x1002, 0x694F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGAM}, /* Vega 10 */ {0x1002, 0x6860, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x6861, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index e0af44fd6a0c..0a17fb1af204 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -32,6 +32,9 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); + struct amdgpu_task_info ti; + + memset(&ti, 0, sizeof(struct amdgpu_task_info)); if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", @@ -39,9 +42,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) return; } + amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n", job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), ring->fence_drv.sync_seq); + DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", + ti.process_name, ti.tgid, ti.task_name, ti.pid); if (amdgpu_device_should_recover_gpu(ring->adev)) amdgpu_device_gpu_recover(ring->adev, job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index fd271f9746a2..728e15e5d68a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -912,7 +912,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo) struct ttm_operation_ctx ctx = { false, false }; int r, i; - if (!bo->pin_count) { + if (WARN_ON_ONCE(!bo->pin_count)) { dev_warn(adev->dev, "%p unpin not necessary\n", bo); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 6759d898b3ab..8fab0d637ee5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -155,14 +155,6 @@ psp_cmd_submit_buf(struct psp_context *psp, return ret; } -bool psp_support_vmr_ring(struct psp_context *psp) -{ - if (amdgpu_sriov_vf(psp->adev) && psp->sos_fw_version > 0x80045) - return true; - else - return false; -} - static void psp_prep_tmr_cmd_buf(struct psp_context *psp, struct psp_gfx_cmd_resp *cmd, uint64_t tmr_mc, uint32_t size) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 10decf70c9aa..3ee573b4016e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -83,12 +83,13 @@ struct psp_funcs enum AMDGPU_UCODE_ID ucode_type); bool (*smu_reload_quirk)(struct psp_context *psp); int (*mode1_reset)(struct psp_context *psp); - uint64_t (*xgmi_get_node_id)(struct psp_context *psp); - uint64_t (*xgmi_get_hive_id)(struct psp_context *psp); + int (*xgmi_get_node_id)(struct psp_context *psp, uint64_t *node_id); + int (*xgmi_get_hive_id)(struct psp_context *psp, uint64_t *hive_id); int (*xgmi_get_topology_info)(struct psp_context *psp, int number_devices, struct psp_xgmi_topology_info *topology); int (*xgmi_set_topology_info)(struct psp_context *psp, int number_devices, struct psp_xgmi_topology_info *topology); + bool (*support_vmr_ring)(struct psp_context *psp); }; struct psp_xgmi_context { @@ -192,12 +193,14 @@ struct psp_xgmi_topology_info { ((psp)->funcs->bootloader_load_sos ? (psp)->funcs->bootloader_load_sos((psp)) : 0) #define psp_smu_reload_quirk(psp) \ ((psp)->funcs->smu_reload_quirk ? (psp)->funcs->smu_reload_quirk((psp)) : false) +#define psp_support_vmr_ring(psp) \ + ((psp)->funcs->support_vmr_ring ? (psp)->funcs->support_vmr_ring((psp)) : false) #define psp_mode1_reset(psp) \ ((psp)->funcs->mode1_reset ? (psp)->funcs->mode1_reset((psp)) : false) -#define psp_xgmi_get_node_id(psp) \ - ((psp)->funcs->xgmi_get_node_id ? (psp)->funcs->xgmi_get_node_id((psp)) : 0) -#define psp_xgmi_get_hive_id(psp) \ - ((psp)->funcs->xgmi_get_hive_id ? (psp)->funcs->xgmi_get_hive_id((psp)) : 0) +#define psp_xgmi_get_node_id(psp, node_id) \ + ((psp)->funcs->xgmi_get_node_id ? (psp)->funcs->xgmi_get_node_id((psp), (node_id)) : -EINVAL) +#define psp_xgmi_get_hive_id(psp, hive_id) \ + ((psp)->funcs->xgmi_get_hive_id ? (psp)->funcs->xgmi_get_hive_id((psp), (hive_id)) : -EINVAL) #define psp_xgmi_get_topology_info(psp, num_device, topology) \ ((psp)->funcs->xgmi_get_topology_info ? \ (psp)->funcs->xgmi_get_topology_info((psp), (num_device), (topology)) : -EINVAL) @@ -217,8 +220,6 @@ extern const struct amdgpu_ip_block_version psp_v10_0_ip_block; int psp_gpu_reset(struct amdgpu_device *adev); int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id); -bool psp_support_vmr_ring(struct psp_context *psp); - extern const struct amdgpu_ip_block_version psp_v11_0_ip_block; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 0beb01fef83f..d87e828a084b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -29,7 +29,7 @@ #include <drm/drm_print.h> /* max number of rings */ -#define AMDGPU_MAX_RINGS 21 +#define AMDGPU_MAX_RINGS 23 #define AMDGPU_MAX_GFX_RINGS 1 #define AMDGPU_MAX_COMPUTE_RINGS 8 #define AMDGPU_MAX_VCE_RINGS 3 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index e2e42e3fbcf3..ecf6f96df2ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -262,7 +262,7 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev, ring = &adev->vcn.ring_dec; WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, - RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2)); + RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF); SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); @@ -322,7 +322,7 @@ static int amdgpu_vcn_pause_dpg_mode(struct amdgpu_device *adev, ring = &adev->vcn.ring_dec; WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, - RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2)); + RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF); SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); @@ -396,16 +396,26 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { struct dpg_pause_state new_state; + unsigned int fences = 0; + unsigned int i; - if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) + for (i = 0; i < adev->vcn.num_enc_rings; ++i) { + fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]); + } + if (fences) new_state.fw_based = VCN_DPG_STATE__PAUSE; else - new_state.fw_based = adev->vcn.pause_state.fw_based; + new_state.fw_based = VCN_DPG_STATE__UNPAUSE; - if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) + if (amdgpu_fence_count_emitted(&adev->vcn.ring_jpeg)) new_state.jpeg = VCN_DPG_STATE__PAUSE; else - new_state.jpeg = adev->vcn.pause_state.jpeg; + new_state.jpeg = VCN_DPG_STATE__UNPAUSE; + + if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) + new_state.fw_based = VCN_DPG_STATE__PAUSE; + else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) + new_state.jpeg = VCN_DPG_STATE__PAUSE; amdgpu_vcn_pause_dpg_mode(adev, &new_state); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 0b263a9857c6..8a8bc60cb6b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -97,8 +97,19 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev) if (!adev->gmc.xgmi.supported) return 0; - adev->gmc.xgmi.node_id = psp_xgmi_get_node_id(&adev->psp); - adev->gmc.xgmi.hive_id = psp_xgmi_get_hive_id(&adev->psp); + ret = psp_xgmi_get_node_id(&adev->psp, &adev->gmc.xgmi.node_id); + if (ret) { + dev_err(adev->dev, + "XGMI: Failed to get node id\n"); + return ret; + } + + ret = psp_xgmi_get_hive_id(&adev->psp, &adev->gmc.xgmi.hive_id); + if (ret) { + dev_err(adev->dev, + "XGMI: Failed to get hive id\n"); + return ret; + } mutex_lock(&xgmi_mutex); hive = amdgpu_get_xgmi_hive(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index ce150de723c9..bacdaef77b6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -718,37 +718,46 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev) } } -static int gmc_v9_0_late_init(void *handle) +static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev) { - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* - * The latest engine allocation on gfx9 is: - * Engine 0, 1: idle - * Engine 2, 3: firmware - * Engine 4~13: amdgpu ring, subject to change when ring number changes - * Engine 14~15: idle - * Engine 16: kfd tlb invalidation - * Engine 17: Gart flushes - */ - unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 }; + struct amdgpu_ring *ring; + unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] = + {GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP}; unsigned i; - int r; + unsigned vmhub, inv_eng; - if (!gmc_v9_0_keep_stolen_memory(adev)) - amdgpu_bo_late_init(adev); + for (i = 0; i < adev->num_rings; ++i) { + ring = adev->rings[i]; + vmhub = ring->funcs->vmhub; + + inv_eng = ffs(vm_inv_engs[vmhub]); + if (!inv_eng) { + dev_err(adev->dev, "no VM inv eng for ring %s\n", + ring->name); + return -EINVAL; + } - for(i = 0; i < adev->num_rings; ++i) { - struct amdgpu_ring *ring = adev->rings[i]; - unsigned vmhub = ring->funcs->vmhub; + ring->vm_inv_eng = inv_eng - 1; + change_bit(inv_eng - 1, (unsigned long *)(&vm_inv_engs[vmhub])); - ring->vm_inv_eng = vm_inv_eng[vmhub]++; dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n", ring->name, ring->vm_inv_eng, ring->funcs->vmhub); } - /* Engine 16 is used for KFD and 17 for GART flushes */ - for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i) - BUG_ON(vm_inv_eng[i] > 16); + return 0; +} + +static int gmc_v9_0_late_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + if (!gmc_v9_0_keep_stolen_memory(adev)) + amdgpu_bo_late_init(adev); + + r = gmc_v9_0_allocate_vm_inv_eng(adev); + if (r) + return r; if (adev->asic_type == CHIP_VEGA10 && !amdgpu_sriov_vf(adev)) { r = gmc_v9_0_ecc_available(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h index b030ca5ea107..5c8deac65580 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h @@ -24,6 +24,16 @@ #ifndef __GMC_V9_0_H__ #define __GMC_V9_0_H__ + /* + * The latest engine allocation on gfx9 is: + * Engine 2, 3: firmware + * Engine 0, 1, 4~16: amdgpu ring, + * subject to change when ring number changes + * Engine 17: Gart flushes + */ +#define GFXHUB_FREE_VM_INV_ENGS_BITMAP 0x1FFF3 +#define MMHUB_FREE_VM_INV_ENGS_BITMAP 0x1FFF3 + extern const struct amd_ip_funcs gmc_v9_0_ip_funcs; extern const struct amdgpu_ip_block_version gmc_v9_0_ip_block; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index 6f9c54978cc1..accdedd63c98 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -32,6 +32,7 @@ #define smnCPM_CONTROL 0x11180460 #define smnPCIE_CNTL2 0x11180070 #define smnPCIE_CONFIG_CNTL 0x11180044 +#define smnPCIE_CI_CNTL 0x11180080 static u32 nbio_v6_1_get_rev_id(struct amdgpu_device *adev) { @@ -270,6 +271,12 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_PCIE(smnPCIE_CONFIG_CNTL, data); + + def = data = RREG32_PCIE(smnPCIE_CI_CNTL); + data = REG_SET_FIELD(data, PCIE_CI_CNTL, CI_SLV_ORDERING_DIS, 1); + + if (def != data) + WREG32_PCIE(smnPCIE_CI_CNTL, data); } const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index f8cee95d61cc..4cd31a276dcd 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -31,6 +31,7 @@ #define smnCPM_CONTROL 0x11180460 #define smnPCIE_CNTL2 0x11180070 +#define smnPCIE_CI_CNTL 0x11180080 static u32 nbio_v7_4_get_rev_id(struct amdgpu_device *adev) { @@ -222,7 +223,13 @@ static void nbio_v7_4_detect_hw_virt(struct amdgpu_device *adev) static void nbio_v7_4_init_registers(struct amdgpu_device *adev) { + uint32_t def, data; + + def = data = RREG32_PCIE(smnPCIE_CI_CNTL); + data = REG_SET_FIELD(data, PCIE_CI_CNTL, CI_SLV_ORDERING_DIS, 1); + if (def != data) + WREG32_PCIE(smnPCIE_CI_CNTL, data); } const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 6c9a1b748ca7..0c6e7f9b143f 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -34,6 +34,7 @@ #include "nbio/nbio_7_4_offset.h" MODULE_FIRMWARE("amdgpu/vega20_sos.bin"); +MODULE_FIRMWARE("amdgpu/vega20_asd.bin"); MODULE_FIRMWARE("amdgpu/vega20_ta.bin"); /* address block */ @@ -100,6 +101,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) char fw_name[30]; int err = 0; const struct psp_firmware_header_v1_0 *sos_hdr; + const struct psp_firmware_header_v1_0 *asd_hdr; const struct ta_firmware_header_v1_0 *ta_hdr; DRM_DEBUG("\n"); @@ -132,14 +134,30 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) adev->psp.sos_start_addr = (uint8_t *)adev->psp.sys_start_addr + le32_to_cpu(sos_hdr->sos_offset_bytes); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_asd.bin", chip_name); + err = request_firmware(&adev->psp.asd_fw, fw_name, adev->dev); + if (err) + goto out1; + + err = amdgpu_ucode_validate(adev->psp.asd_fw); + if (err) + goto out1; + + asd_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.asd_fw->data; + adev->psp.asd_fw_version = le32_to_cpu(asd_hdr->header.ucode_version); + adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->ucode_feature_version); + adev->psp.asd_ucode_size = le32_to_cpu(asd_hdr->header.ucode_size_bytes); + adev->psp.asd_start_addr = (uint8_t *)asd_hdr + + le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); if (err) - goto out; + goto out2; err = amdgpu_ucode_validate(adev->psp.ta_fw); if (err) - goto out; + goto out2; ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); @@ -148,14 +166,18 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); return 0; + +out2: + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; +out1: + release_firmware(adev->psp.asd_fw); + adev->psp.asd_fw = NULL; out: - if (err) { - dev_err(adev->dev, - "psp v11.0: Failed to load firmware \"%s\"\n", - fw_name); - release_firmware(adev->psp.sos_fw); - adev->psp.sos_fw = NULL; - } + dev_err(adev->dev, + "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); + release_firmware(adev->psp.sos_fw); + adev->psp.sos_fw = NULL; return err; } @@ -291,6 +313,13 @@ static int psp_v11_0_ring_init(struct psp_context *psp, return 0; } +static bool psp_v11_0_support_vmr_ring(struct psp_context *psp) +{ + if (amdgpu_sriov_vf(psp->adev) && psp->sos_fw_version > 0x80045) + return true; + return false; +} + static int psp_v11_0_ring_create(struct psp_context *psp, enum psp_ring_type ring_type) { @@ -299,7 +328,7 @@ static int psp_v11_0_ring_create(struct psp_context *psp, struct psp_ring *ring = &psp->km_ring; struct amdgpu_device *adev = psp->adev; - if (psp_support_vmr_ring(psp)) { + if (psp_v11_0_support_vmr_ring(psp)) { /* Write low address of the ring to C2PMSG_102 */ psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr); WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg); @@ -351,7 +380,7 @@ static int psp_v11_0_ring_stop(struct psp_context *psp, struct amdgpu_device *adev = psp->adev; /* Write the ring destroy command*/ - if (psp_support_vmr_ring(psp)) + if (psp_v11_0_support_vmr_ring(psp)) WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING); else @@ -362,7 +391,7 @@ static int psp_v11_0_ring_stop(struct psp_context *psp, mdelay(20); /* Wait for response flag (bit 31) */ - if (psp_support_vmr_ring(psp)) + if (psp_v11_0_support_vmr_ring(psp)) ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101), 0x80000000, 0x80000000, false); else @@ -406,7 +435,7 @@ static int psp_v11_0_cmd_submit(struct psp_context *psp, uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4; /* KM (GPCOM) prepare write pointer */ - if (psp_support_vmr_ring(psp)) + if (psp_v11_0_support_vmr_ring(psp)) psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102); else psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67); @@ -438,7 +467,7 @@ static int psp_v11_0_cmd_submit(struct psp_context *psp, /* Update the write Pointer in DWORDs */ psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw; - if (psp_support_vmr_ring(psp)) { + if (psp_v11_0_support_vmr_ring(psp)) { WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg); WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD); } else @@ -680,7 +709,7 @@ static int psp_v11_0_xgmi_set_topology_info(struct psp_context *psp, return psp_xgmi_invoke(psp, TA_COMMAND_XGMI__SET_TOPOLOGY_INFO); } -static u64 psp_v11_0_xgmi_get_hive_id(struct psp_context *psp) +static int psp_v11_0_xgmi_get_hive_id(struct psp_context *psp, uint64_t *hive_id) { struct ta_xgmi_shared_memory *xgmi_cmd; int ret; @@ -693,12 +722,14 @@ static u64 psp_v11_0_xgmi_get_hive_id(struct psp_context *psp) /* Invoke xgmi ta to get hive id */ ret = psp_xgmi_invoke(psp, xgmi_cmd->cmd_id); if (ret) - return 0; - else - return xgmi_cmd->xgmi_out_message.get_hive_id.hive_id; + return ret; + + *hive_id = xgmi_cmd->xgmi_out_message.get_hive_id.hive_id; + + return 0; } -static u64 psp_v11_0_xgmi_get_node_id(struct psp_context *psp) +static int psp_v11_0_xgmi_get_node_id(struct psp_context *psp, uint64_t *node_id) { struct ta_xgmi_shared_memory *xgmi_cmd; int ret; @@ -711,9 +742,11 @@ static u64 psp_v11_0_xgmi_get_node_id(struct psp_context *psp) /* Invoke xgmi ta to get the node id */ ret = psp_xgmi_invoke(psp, xgmi_cmd->cmd_id); if (ret) - return 0; - else - return xgmi_cmd->xgmi_out_message.get_node_id.node_id; + return ret; + + *node_id = xgmi_cmd->xgmi_out_message.get_node_id.node_id; + + return 0; } static const struct psp_funcs psp_v11_0_funcs = { @@ -732,6 +765,7 @@ static const struct psp_funcs psp_v11_0_funcs = { .xgmi_set_topology_info = psp_v11_0_xgmi_set_topology_info, .xgmi_get_hive_id = psp_v11_0_xgmi_get_hive_id, .xgmi_get_node_id = psp_v11_0_xgmi_get_node_id, + .support_vmr_ring = psp_v11_0_support_vmr_ring, }; void psp_v11_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index 7357fd56e614..79694ff16969 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -240,8 +240,11 @@ static int psp_v3_1_bootloader_load_sos(struct psp_context *psp) * are already been loaded. */ sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); - if (sol_reg) + if (sol_reg) { + psp->sos_fw_version = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58); + printk("sos fw version = 0x%x.\n", psp->sos_fw_version); return 0; + } /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */ ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35), diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 4b6d3e5c821f..fd0bfe140ee0 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1458,8 +1458,7 @@ static bool sdma_v4_0_fw_support_paging_queue(struct amdgpu_device *adev) /*return fw_version >= 31;*/ return false; case CHIP_VEGA20: - /*return fw_version >= 115;*/ - return false; + return fw_version >= 123; default: return false; } @@ -1706,13 +1705,15 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, amdgpu_fence_process(&adev->sdma.instance[instance].ring); break; case 1: - /* XXX compute */ + if (adev->asic_type == CHIP_VEGA20) + amdgpu_fence_process(&adev->sdma.instance[instance].page); break; case 2: /* XXX compute */ break; case 3: - amdgpu_fence_process(&adev->sdma.instance[instance].page); + if (adev->asic_type != CHIP_VEGA20) + amdgpu_fence_process(&adev->sdma.instance[instance].page); break; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h index 958b10a57073..49c262540940 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h @@ -49,14 +49,19 @@ #define SOC15_WAIT_ON_RREG(ip, inst, reg, expected_value, mask, ret) \ do { \ + uint32_t old_ = 0; \ uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \ uint32_t loop = adev->usec_timeout; \ while ((tmp_ & (mask)) != (expected_value)) { \ - udelay(2); \ + if (old_ != tmp_) { \ + loop = adev->usec_timeout; \ + old_ = tmp_; \ + } else \ + udelay(1); \ tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \ loop--; \ if (!loop) { \ - DRM_ERROR("Register(%d) [%s] failed to reach value 0x%08x != 0x%08x\n", \ + DRM_WARN("Register(%d) [%s] failed to reach value 0x%08x != 0x%08x\n", \ inst, #reg, (unsigned)expected_value, (unsigned)(tmp_ & (mask))); \ ret = -ETIMEDOUT; \ break; \ diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 089645e78f98..aef924026a28 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -435,7 +435,7 @@ static int uvd_v7_0_sw_init(void *handle) continue; if (!amdgpu_sriov_vf(adev)) { ring = &adev->uvd.inst[j].ring; - sprintf(ring->name, "uvd<%d>", j); + sprintf(ring->name, "uvd_%d", ring->me); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0); if (r) return r; @@ -443,7 +443,7 @@ static int uvd_v7_0_sw_init(void *handle) for (i = 0; i < adev->uvd.num_enc_rings; ++i) { ring = &adev->uvd.inst[j].ring_enc[i]; - sprintf(ring->name, "uvd_enc%d<%d>", i, j); + sprintf(ring->name, "uvd_enc_%d.%d", ring->me, i); if (amdgpu_sriov_vf(adev)) { ring->use_doorbell = true; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 4f8352044563..89bb2fef90eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -214,7 +214,8 @@ static int vcn_v1_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring = &adev->vcn.ring_dec; - if (RREG32_SOC15(VCN, 0, mmUVD_STATUS)) + if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) || + RREG32_SOC15(VCN, 0, mmUVD_STATUS)) vcn_v1_0_set_powergating_state(adev, AMD_PG_STATE_GATE); ring->sched.ready = false; @@ -1087,7 +1088,8 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev) WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0, ~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK); - /* initialize wptr */ + /* initialize JPEG wptr */ + ring = &adev->vcn.ring_jpeg; ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR); /* copy patch commands to the jpeg ring */ @@ -1159,21 +1161,29 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev) { int ret_code = 0; + uint32_t tmp; /* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); - if (!ret_code) { - int tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF; - /* wait for read ptr to be equal to write ptr */ - SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code); + /* wait for read ptr to be equal to write ptr */ + tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR); + SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF, ret_code); - SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, - UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF, - UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); - } + tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2); + SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code); + + tmp = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR); + SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code); + + tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF; + SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code); + + SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, + UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF, + UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code); /* disable dynamic power gating mode */ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), 0, diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index ff2906c215fa..77e367459101 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -87,9 +87,9 @@ static u32 vi_pcie_rreg(struct amdgpu_device *adev, u32 reg) u32 r; spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(mmPCIE_INDEX, reg); - (void)RREG32(mmPCIE_INDEX); - r = RREG32(mmPCIE_DATA); + WREG32_NO_KIQ(mmPCIE_INDEX, reg); + (void)RREG32_NO_KIQ(mmPCIE_INDEX); + r = RREG32_NO_KIQ(mmPCIE_DATA); spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); return r; } @@ -99,10 +99,10 @@ static void vi_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v) unsigned long flags; spin_lock_irqsave(&adev->pcie_idx_lock, flags); - WREG32(mmPCIE_INDEX, reg); - (void)RREG32(mmPCIE_INDEX); - WREG32(mmPCIE_DATA, v); - (void)RREG32(mmPCIE_DATA); + WREG32_NO_KIQ(mmPCIE_INDEX, reg); + (void)RREG32_NO_KIQ(mmPCIE_INDEX); + WREG32_NO_KIQ(mmPCIE_DATA, v); + (void)RREG32_NO_KIQ(mmPCIE_DATA); spin_unlock_irqrestore(&adev->pcie_idx_lock, flags); } @@ -123,8 +123,8 @@ static void vi_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v) unsigned long flags; spin_lock_irqsave(&adev->smc_idx_lock, flags); - WREG32(mmSMC_IND_INDEX_11, (reg)); - WREG32(mmSMC_IND_DATA_11, (v)); + WREG32_NO_KIQ(mmSMC_IND_INDEX_11, (reg)); + WREG32_NO_KIQ(mmSMC_IND_DATA_11, (v)); spin_unlock_irqrestore(&adev->smc_idx_lock, flags); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index be68752c3469..083bd8114db1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1623,8 +1623,8 @@ static int kfd_ioctl_import_dmabuf(struct file *filep, return -EINVAL; dmabuf = dma_buf_get(args->dmabuf_fd); - if (!dmabuf) - return -EINVAL; + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); mutex_lock(&p->mutex); 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 d01315965af0..a9a28dbc3e24 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -331,12 +331,29 @@ static void dm_crtc_high_irq(void *interrupt_params) struct common_irq_params *irq_params = interrupt_params; struct amdgpu_device *adev = irq_params->adev; struct amdgpu_crtc *acrtc; + struct dm_crtc_state *acrtc_state; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); if (acrtc) { drm_crtc_handle_vblank(&acrtc->base); amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); + + acrtc_state = to_dm_crtc_state(acrtc->base.state); + + if (acrtc_state->stream && + acrtc_state->vrr_params.supported && + acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { + mod_freesync_handle_v_update( + adev->dm.freesync_module, + acrtc_state->stream, + &acrtc_state->vrr_params); + + dc_stream_adjust_vmin_vmax( + adev->dm.dc, + acrtc_state->stream, + &acrtc_state->vrr_params.adjust); + } } } @@ -3009,7 +3026,7 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc) dc_stream_retain(state->stream); } - state->adjust = cur->adjust; + state->vrr_params = cur->vrr_params; state->vrr_infopacket = cur->vrr_infopacket; state->abm_level = cur->abm_level; state->vrr_supported = cur->vrr_supported; @@ -3628,10 +3645,20 @@ static int dm_plane_atomic_check(struct drm_plane *plane, static int dm_plane_atomic_async_check(struct drm_plane *plane, struct drm_plane_state *new_plane_state) { + struct drm_plane_state *old_plane_state = + drm_atomic_get_old_plane_state(new_plane_state->state, plane); + /* Only support async updates on cursor planes. */ if (plane->type != DRM_PLANE_TYPE_CURSOR) return -EINVAL; + /* + * DRM calls prepare_fb and cleanup_fb on new_plane_state for + * async commits so don't allow fb changes. + */ + if (old_plane_state->fb != new_plane_state->fb) + return -EINVAL; + return 0; } @@ -4445,9 +4472,11 @@ struct dc_stream_status *dc_state_get_stream_status( static void update_freesync_state_on_stream( struct amdgpu_display_manager *dm, struct dm_crtc_state *new_crtc_state, - struct dc_stream_state *new_stream) + struct dc_stream_state *new_stream, + struct dc_plane_state *surface, + u32 flip_timestamp_in_us) { - struct mod_vrr_params vrr = {0}; + struct mod_vrr_params vrr_params = new_crtc_state->vrr_params; struct dc_info_packet vrr_infopacket = {0}; struct mod_freesync_config config = new_crtc_state->freesync_config; @@ -4474,43 +4503,52 @@ static void update_freesync_state_on_stream( mod_freesync_build_vrr_params(dm->freesync_module, new_stream, - &config, &vrr); + &config, &vrr_params); + + if (surface) { + mod_freesync_handle_preflip( + dm->freesync_module, + surface, + new_stream, + flip_timestamp_in_us, + &vrr_params); + } mod_freesync_build_vrr_infopacket( dm->freesync_module, new_stream, - &vrr, + &vrr_params, PACKET_TYPE_VRR, TRANSFER_FUNC_UNKNOWN, &vrr_infopacket); new_crtc_state->freesync_timing_changed = - (memcmp(&new_crtc_state->adjust, - &vrr.adjust, - sizeof(vrr.adjust)) != 0); + (memcmp(&new_crtc_state->vrr_params.adjust, + &vrr_params.adjust, + sizeof(vrr_params.adjust)) != 0); new_crtc_state->freesync_vrr_info_changed = (memcmp(&new_crtc_state->vrr_infopacket, &vrr_infopacket, sizeof(vrr_infopacket)) != 0); - new_crtc_state->adjust = vrr.adjust; + new_crtc_state->vrr_params = vrr_params; new_crtc_state->vrr_infopacket = vrr_infopacket; - new_stream->adjust = new_crtc_state->adjust; + new_stream->adjust = new_crtc_state->vrr_params.adjust; new_stream->vrr_infopacket = vrr_infopacket; if (new_crtc_state->freesync_vrr_info_changed) DRM_DEBUG_KMS("VRR packet update: crtc=%u enabled=%d state=%d", new_crtc_state->base.crtc->base.id, (int)new_crtc_state->base.vrr_enabled, - (int)vrr.state); + (int)vrr_params.state); if (new_crtc_state->freesync_timing_changed) DRM_DEBUG_KMS("VRR timing update: crtc=%u min=%u max=%u\n", new_crtc_state->base.crtc->base.id, - vrr.adjust.v_total_min, - vrr.adjust.v_total_max); + vrr_params.adjust.v_total_min, + vrr_params.adjust.v_total_max); } /* @@ -4524,6 +4562,7 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, struct dc_state *state) { unsigned long flags; + uint64_t timestamp_ns; uint32_t target_vblank; int r, vpos, hpos; struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); @@ -4537,6 +4576,7 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, struct dc_stream_update stream_update = {0}; struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state); struct dc_stream_status *stream_status; + struct dc_plane_state *surface; /* Prepare wait for target vblank early - before the fence-waits */ @@ -4586,6 +4626,9 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, addr.address.grph.addr.high_part = upper_32_bits(afb->address); addr.flip_immediate = async_flip; + timestamp_ns = ktime_get_ns(); + addr.flip_timestamp_in_us = div_u64(timestamp_ns, 1000); + if (acrtc->base.state->event) prepare_flip_isr(acrtc); @@ -4599,8 +4642,10 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, return; } - surface_updates->surface = stream_status->plane_states[0]; - if (!surface_updates->surface) { + surface = stream_status->plane_states[0]; + surface_updates->surface = surface; + + if (!surface) { DRM_ERROR("No surface for CRTC: id=%d\n", acrtc->crtc_id); return; @@ -4611,7 +4656,9 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, update_freesync_state_on_stream( &adev->dm, acrtc_state, - acrtc_state->stream); + acrtc_state->stream, + surface, + addr.flip_timestamp_in_us); if (acrtc_state->freesync_timing_changed) stream_update.adjust = @@ -4622,7 +4669,16 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc, &acrtc_state->stream->vrr_infopacket; } + /* Update surface timing information. */ + surface->time.time_elapsed_in_us[surface->time.index] = + addr.flip_timestamp_in_us - surface->time.prev_update_time_in_us; + surface->time.prev_update_time_in_us = addr.flip_timestamp_in_us; + surface->time.index++; + if (surface->time.index >= DC_PLANE_UPDATE_TIMES_MAX) + surface->time.index = 0; + mutex_lock(&adev->dm.dc_lock); + dc_commit_updates_for_stream(adev->dm.dc, surface_updates, 1, @@ -5314,6 +5370,7 @@ static void get_freesync_config_for_crtc( config.max_refresh_in_uhz = aconnector->max_vfreq * 1000000; config.vsif_supported = true; + config.btr = true; } new_crtc_state->freesync_config = config; @@ -5324,8 +5381,8 @@ static void reset_freesync_config_for_crtc( { new_crtc_state->vrr_supported = false; - memset(&new_crtc_state->adjust, 0, - sizeof(new_crtc_state->adjust)); + memset(&new_crtc_state->vrr_params, 0, + sizeof(new_crtc_state->vrr_params)); memset(&new_crtc_state->vrr_infopacket, 0, sizeof(new_crtc_state->vrr_infopacket)); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 25bb91ee80ba..fbd161ddc3f4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -268,7 +268,7 @@ struct dm_crtc_state { bool vrr_supported; struct mod_freesync_config freesync_config; - struct dc_crtc_timing_adjust adjust; + struct mod_vrr_params vrr_params; struct dc_info_packet vrr_infopacket; int abm_level; 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 751bb614fc0e..c513ab6f3843 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -638,6 +638,7 @@ static enum bp_result get_ss_info_v4_1( { enum bp_result result = BP_RESULT_OK; struct atom_display_controller_info_v4_1 *disp_cntl_tbl = NULL; + struct atom_smu_info_v3_3 *smu_info = NULL; if (!ss_info) return BP_RESULT_BADINPUT; @@ -650,6 +651,7 @@ static enum bp_result get_ss_info_v4_1( if (!disp_cntl_tbl) return BP_RESULT_BADBIOSTABLE; + ss_info->type.STEP_AND_DELAY_INFO = false; ss_info->spread_percentage_divider = 1000; /* BIOS no longer uses target clock. Always enable for now */ @@ -688,6 +690,19 @@ static enum bp_result get_ss_info_v4_1( */ result = BP_RESULT_UNSUPPORTED; break; + case AS_SIGNAL_TYPE_XGMI: + smu_info = GET_IMAGE(struct atom_smu_info_v3_3, + DATA_TABLES(smu_info)); + if (!smu_info) + return BP_RESULT_BADBIOSTABLE; + + ss_info->spread_spectrum_percentage = + smu_info->waflclk_ss_percentage; + ss_info->spread_spectrum_range = + smu_info->gpuclk_ss_rate_10hz * 10; + if (smu_info->waflclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE) + ss_info->type.CENTER_MODE = true; + break; default: result = BP_RESULT_UNSUPPORTED; } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c index 65b006ad372e..8196f3bb10c7 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c @@ -67,6 +67,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2( return true; #endif case DCE_VERSION_12_0: + case DCE_VERSION_12_1: *h = dal_cmd_tbl_helper_dce112_get_table2(); return true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d9c57984394b..5fd52094d459 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -151,10 +151,6 @@ static bool create_links( return false; } - if (connectors_num == 0 && num_virtual_links == 0) { - dm_error("DC: Number of connectors is zero!\n"); - } - dm_output_to_console( "DC: %s: connectors_num: physical:%d, virtual:%d\n", __func__, @@ -1471,7 +1467,8 @@ static void commit_planes_do_stream_update(struct dc *dc, if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) || stream_update->vrr_infopacket || - stream_update->vsc_infopacket) { + stream_update->vsc_infopacket || + stream_update->vsp_infopacket) { resource_build_info_frame(pipe_ctx); dc->hwss.update_info_frame(pipe_ctx); } @@ -1573,9 +1570,6 @@ static void commit_planes_for_stream(struct dc *dc, } } - if (update_type == UPDATE_TYPE_FULL) - context_timing_trace(dc, &context->res_ctx); - // Update Type FAST, Surface updates if (update_type == UPDATE_TYPE_FAST) { /* Lock the top pipe while updating plane addrs, since freesync requires 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 4dc5846de5c4..52deacf39841 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -215,6 +215,9 @@ bool dc_link_detect_sink(struct dc_link *link, enum dc_connection_type *type) return true; } + if (link->connector_signal == SIGNAL_TYPE_EDP) + link->dc->hwss.edp_wait_for_hpd_ready(link, true); + /* todo: may need to lock gpio access */ hpd_pin = get_hpd_gpio(link->ctx->dc_bios, link->link_id, link->ctx->gpio_service); if (hpd_pin == NULL) @@ -339,7 +342,7 @@ bool dc_link_is_dp_sink_present(struct dc_link *link) { enum gpio_result gpio_result; uint32_t clock_pin = 0; - + uint8_t retry = 0; struct ddc *ddc; enum connector_id connector_id = @@ -368,11 +371,22 @@ bool dc_link_is_dp_sink_present(struct dc_link *link) return present; } - /* Read GPIO: DP sink is present if both clock and data pins are zero */ - /* [anaumov] in DAL2, there was no check for GPIO failure */ - - gpio_result = dal_gpio_get_value(ddc->pin_clock, &clock_pin); - ASSERT(gpio_result == GPIO_RESULT_OK); + /* + * Read GPIO: DP sink is present if both clock and data pins are zero + * + * [W/A] plug-unplug DP cable, sometimes customer board has + * one short pulse on clk_pin(1V, < 1ms). DP will be config to HDMI/DVI + * then monitor can't br light up. Add retry 3 times + * But in real passive dongle, it need additional 3ms to detect + */ + do { + gpio_result = dal_gpio_get_value(ddc->pin_clock, &clock_pin); + ASSERT(gpio_result == GPIO_RESULT_OK); + if (clock_pin) + udelay(1000); + else + break; + } while (retry++ < 3); present = (gpio_result == GPIO_RESULT_OK) && !clock_pin; @@ -703,12 +717,26 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) if (memcmp(&link->dpcd_caps, &prev_dpcd_caps, sizeof(struct dpcd_caps))) same_dpcd = false; } - /* Active dongle downstream unplug */ + /* Active dongle plug in without display or downstream unplug*/ if (link->type == dc_connection_active_dongle && link->dpcd_caps.sink_count. bits.SINK_COUNT == 0) { - if (prev_sink != NULL) + if (prev_sink != NULL) { + /* Downstream unplug */ dc_sink_release(prev_sink); + } else { + /* Empty dongle plug in */ + for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) { + int fail_count = 0; + + dp_verify_link_cap(link, + &link->reported_link_cap, + &fail_count); + + if (fail_count == 0) + break; + } + } return true; } @@ -2622,11 +2650,11 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option) { struct dc *core_dc = pipe_ctx->stream->ctx->dc; + core_dc->hwss.blank_stream(pipe_ctx); + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); - core_dc->hwss.blank_stream(pipe_ctx); - core_dc->hwss.disable_stream(pipe_ctx, option); disable_link(pipe_ctx->stream->sink->link, pipe_ctx->stream->signal); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 849a3a3032f7..0caacb60b02f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1089,6 +1089,121 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link) return max_link_cap; } +static enum dc_status read_hpd_rx_irq_data( + struct dc_link *link, + union hpd_irq_data *irq_data) +{ + static enum dc_status retval; + + /* The HW reads 16 bytes from 200h on HPD, + * but if we get an AUX_DEFER, the HW cannot retry + * and this causes the CTS tests 4.3.2.1 - 3.2.4 to + * fail, so we now explicitly read 6 bytes which is + * the req from the above mentioned test cases. + * + * For DP 1.4 we need to read those from 2002h range. + */ + if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) + retval = core_link_read_dpcd( + link, + DP_SINK_COUNT, + irq_data->raw, + sizeof(union hpd_irq_data)); + else { + /* Read 14 bytes in a single read and then copy only the required fields. + * This is more efficient than doing it in two separate AUX reads. */ + + uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1]; + + retval = core_link_read_dpcd( + link, + DP_SINK_COUNT_ESI, + tmp, + sizeof(tmp)); + + if (retval != DC_OK) + return retval; + + irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI]; + irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI]; + irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI]; + } + + return retval; +} + +static bool hpd_rx_irq_check_link_loss_status( + struct dc_link *link, + union hpd_irq_data *hpd_irq_dpcd_data) +{ + uint8_t irq_reg_rx_power_state = 0; + enum dc_status dpcd_result = DC_ERROR_UNEXPECTED; + union lane_status lane_status; + uint32_t lane; + bool sink_status_changed; + bool return_code; + + sink_status_changed = false; + return_code = false; + + if (link->cur_link_settings.lane_count == 0) + return return_code; + + /*1. Check that Link Status changed, before re-training.*/ + + /*parse lane status*/ + for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) { + /* check status of lanes 0,1 + * changed DpcdAddress_Lane01Status (0x202) + */ + lane_status.raw = get_nibble_at_index( + &hpd_irq_dpcd_data->bytes.lane01_status.raw, + lane); + + if (!lane_status.bits.CHANNEL_EQ_DONE_0 || + !lane_status.bits.CR_DONE_0 || + !lane_status.bits.SYMBOL_LOCKED_0) { + /* if one of the channel equalization, clock + * recovery or symbol lock is dropped + * consider it as (link has been + * dropped) dp sink status has changed + */ + sink_status_changed = true; + break; + } + } + + /* Check interlane align.*/ + if (sink_status_changed || + !hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) { + + DC_LOG_HW_HPD_IRQ("%s: Link Status changed.\n", __func__); + + return_code = true; + + /*2. Check that we can handle interrupt: Not in FS DOS, + * Not in "Display Timeout" state, Link is trained. + */ + dpcd_result = core_link_read_dpcd(link, + DP_SET_POWER, + &irq_reg_rx_power_state, + sizeof(irq_reg_rx_power_state)); + + if (dpcd_result != DC_OK) { + DC_LOG_HW_HPD_IRQ("%s: DPCD read failed to obtain power state.\n", + __func__); + } else { + if (irq_reg_rx_power_state != DP_SET_POWER_D0) + return_code = false; + } + } + + return return_code; +} + bool dp_verify_link_cap( struct dc_link *link, struct dc_link_settings *known_limit_link_setting, @@ -1104,12 +1219,14 @@ bool dp_verify_link_cap( struct clock_source *dp_cs; enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL; enum link_training_result status; + union hpd_irq_data irq_data; if (link->dc->debug.skip_detection_link_training) { link->verified_link_cap = *known_limit_link_setting; return true; } + memset(&irq_data, 0, sizeof(irq_data)); success = false; skip_link_training = false; @@ -1168,9 +1285,15 @@ bool dp_verify_link_cap( (*fail_count)++; } - if (success) + if (success) { link->verified_link_cap = *cur; - + udelay(1000); + if (read_hpd_rx_irq_data(link, &irq_data) == DC_OK) + if (hpd_rx_irq_check_link_loss_status( + link, + &irq_data)) + (*fail_count)++; + } /* always disable the link before trying another * setting or before returning we'll enable it later * based on the actual mode we're driving @@ -1572,122 +1695,6 @@ void decide_link_settings(struct dc_stream_state *stream, } /*************************Short Pulse IRQ***************************/ - -static bool hpd_rx_irq_check_link_loss_status( - struct dc_link *link, - union hpd_irq_data *hpd_irq_dpcd_data) -{ - uint8_t irq_reg_rx_power_state = 0; - enum dc_status dpcd_result = DC_ERROR_UNEXPECTED; - union lane_status lane_status; - uint32_t lane; - bool sink_status_changed; - bool return_code; - - sink_status_changed = false; - return_code = false; - - if (link->cur_link_settings.lane_count == 0) - return return_code; - - /*1. Check that Link Status changed, before re-training.*/ - - /*parse lane status*/ - for (lane = 0; lane < link->cur_link_settings.lane_count; lane++) { - /* check status of lanes 0,1 - * changed DpcdAddress_Lane01Status (0x202) - */ - lane_status.raw = get_nibble_at_index( - &hpd_irq_dpcd_data->bytes.lane01_status.raw, - lane); - - if (!lane_status.bits.CHANNEL_EQ_DONE_0 || - !lane_status.bits.CR_DONE_0 || - !lane_status.bits.SYMBOL_LOCKED_0) { - /* if one of the channel equalization, clock - * recovery or symbol lock is dropped - * consider it as (link has been - * dropped) dp sink status has changed - */ - sink_status_changed = true; - break; - } - } - - /* Check interlane align.*/ - if (sink_status_changed || - !hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) { - - DC_LOG_HW_HPD_IRQ("%s: Link Status changed.\n", __func__); - - return_code = true; - - /*2. Check that we can handle interrupt: Not in FS DOS, - * Not in "Display Timeout" state, Link is trained. - */ - dpcd_result = core_link_read_dpcd(link, - DP_SET_POWER, - &irq_reg_rx_power_state, - sizeof(irq_reg_rx_power_state)); - - if (dpcd_result != DC_OK) { - DC_LOG_HW_HPD_IRQ("%s: DPCD read failed to obtain power state.\n", - __func__); - } else { - if (irq_reg_rx_power_state != DP_SET_POWER_D0) - return_code = false; - } - } - - return return_code; -} - -static enum dc_status read_hpd_rx_irq_data( - struct dc_link *link, - union hpd_irq_data *irq_data) -{ - static enum dc_status retval; - - /* The HW reads 16 bytes from 200h on HPD, - * but if we get an AUX_DEFER, the HW cannot retry - * and this causes the CTS tests 4.3.2.1 - 3.2.4 to - * fail, so we now explicitly read 6 bytes which is - * the req from the above mentioned test cases. - * - * For DP 1.4 we need to read those from 2002h range. - */ - if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_14) - retval = core_link_read_dpcd( - link, - DP_SINK_COUNT, - irq_data->raw, - sizeof(union hpd_irq_data)); - else { - /* Read 14 bytes in a single read and then copy only the required fields. - * This is more efficient than doing it in two separate AUX reads. */ - - uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1]; - - retval = core_link_read_dpcd( - link, - DP_SINK_COUNT_ESI, - tmp, - sizeof(tmp)); - - if (retval != DC_OK) - return retval; - - irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI]; - irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI]; - irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI]; - irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI]; - irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI]; - irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI]; - } - - return retval; -} - static bool allow_hpd_rx_irq(const struct dc_link *link) { /* @@ -2240,7 +2247,8 @@ static void get_active_converter_info( translate_dpcd_max_bpc( hdmi_color_caps.bits.MAX_BITS_PER_COLOR_COMPONENT); - link->dpcd_caps.dongle_caps.extendedCapValid = true; + if (link->dpcd_caps.dongle_caps.dp_hdmi_max_pixel_clk != 0) + link->dpcd_caps.dongle_caps.extendedCapValid = true; } break; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index 82cd1d6e6e59..0065ec7d5330 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -96,6 +96,7 @@ void dp_enable_link_phy( link_settings, clock_source); } + link->cur_link_settings = *link_settings; dp_receiver_power_ctrl(link, true); } @@ -307,6 +308,7 @@ void dp_retrain_link_dp_test(struct dc_link *link, link->link_enc, link_setting, pipes[i].clock_source->id); + link->cur_link_settings = *link_setting; dp_receiver_power_ctrl(link, true); @@ -316,7 +318,6 @@ void dp_retrain_link_dp_test(struct dc_link *link, skip_video_pattern, LINK_TRAINING_ATTEMPTS); - link->cur_link_settings = *link_setting; link->dc->hwss.enable_stream(&pipes[i]); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index c347afd1030f..76137df74a53 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -83,7 +83,10 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id) dc_version = DCE_VERSION_11_22; break; case FAMILY_AI: - dc_version = DCE_VERSION_12_0; + if (ASICREV_IS_VEGA20_P(asic_id.hw_internal_rev)) + dc_version = DCE_VERSION_12_1; + else + dc_version = DCE_VERSION_12_0; break; #if defined(CONFIG_DRM_AMD_DC_DCN1_0) case FAMILY_RV: @@ -136,6 +139,7 @@ struct resource_pool *dc_create_resource_pool( num_virtual_links, dc); break; case DCE_VERSION_12_0: + case DCE_VERSION_12_1: res_pool = dce120_create_resource_pool( num_virtual_links, dc); break; diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c index fcfd50b5dba0..4842d2378bbf 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c @@ -234,14 +234,14 @@ uint32_t generic_reg_wait(const struct dc_context *ctx, if (field_value == condition_value) { if (i * delay_between_poll_us > 1000 && !IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) - dm_output_to_console("REG_WAIT taking a while: %dms in %s line:%d\n", + DC_LOG_DC("REG_WAIT taking a while: %dms in %s line:%d\n", delay_between_poll_us * i / 1000, func_name, line); return reg_val; } } - dm_error("REG_WAIT timeout %dus * %d tries - %s line:%d\n", + DC_LOG_WARNING("REG_WAIT timeout %dus * %d tries - %s line:%d\n", delay_between_poll_us, time_out_num_tries, func_name, line); diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 9ddfe4c6938b..e72fce4eca65 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -192,7 +192,6 @@ enum surface_pixel_format { /*swaped & float*/ SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F, /*grow graphics here if necessary */ - SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888, SURFACE_PIXEL_FORMAT_VIDEO_BEGIN, SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr = SURFACE_PIXEL_FORMAT_VIDEO_BEGIN, @@ -200,6 +199,7 @@ enum surface_pixel_format { SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr, SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb, SURFACE_PIXEL_FORMAT_SUBSAMPLE_END, + SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888, SURFACE_PIXEL_FORMAT_INVALID /*grow 444 video here if necessary */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index bd22f51813bf..afd287f08bc9 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -676,6 +676,11 @@ static void dce112_update_clocks(struct clk_mgr *clk_mgr, { struct dce_clk_mgr *clk_mgr_dce = TO_DCE_CLK_MGR(clk_mgr); struct dm_pp_power_level_change_request level_change_req; + int unpatched_disp_clk = context->bw.dce.dispclk_khz; + + /*TODO: W/A for dal3 linux, investigate why this works */ + if (!clk_mgr_dce->dfs_bypass_active) + context->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100; level_change_req.power_level = dce_get_required_clocks_state(clk_mgr, context); /* get max clock state from PPLIB */ @@ -690,6 +695,8 @@ static void dce112_update_clocks(struct clk_mgr *clk_mgr, clk_mgr->clks.dispclk_khz = context->bw.dce.dispclk_khz; } dce11_pplib_apply_display_requirements(clk_mgr->ctx->dc, context); + + context->bw.dce.dispclk_khz = unpatched_disp_clk; } static void dce12_update_clocks(struct clk_mgr *clk_mgr, 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 6349ba7bec7c..4bf24758217f 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 @@ -1267,10 +1267,19 @@ static void program_scaler(const struct dc *dc, pipe_ctx->plane_res.scl_data.lb_params.depth, &pipe_ctx->stream->bit_depth_params); - if (pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color) + if (pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color) { + /* + * The way 420 is packed, 2 channels carry Y component, 1 channel + * alternate between Cb and Cr, so both channels need the pixel + * value for Y + */ + if (pipe_ctx->stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) + color.color_r_cr = color.color_g_y; + pipe_ctx->stream_res.tg->funcs->set_overscan_blank_color( pipe_ctx->stream_res.tg, &color); + } pipe_ctx->plane_res.xfm->funcs->transform_set_scaler(pipe_ctx->plane_res.xfm, &pipe_ctx->plane_res.scl_data); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 0bd33a713836..91e015e14355 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2159,6 +2159,15 @@ static void dcn10_blank_pixel_data( color_space = stream->output_color_space; color_space_to_black_color(dc, color_space, &black_color); + /* + * The way 420 is packed, 2 channels carry Y component, 1 channel + * alternate between Cb and Cr, so both channels need the pixel + * value for Y + */ + if (stream->timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) + black_color.color_r_cr = black_color.color_g_y; + + if (stream_res->tg->funcs->set_blank_color) stream_res->tg->funcs->set_blank_color( stream_res->tg, @@ -2348,7 +2357,8 @@ static void dcn10_apply_ctx_for_surface( struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; /* Skip inactive pipes and ones already updated */ - if (!pipe_ctx->stream || pipe_ctx->stream == stream) + if (!pipe_ctx->stream || pipe_ctx->stream == stream + || !pipe_ctx->plane_state) continue; pipe_ctx->stream_res.tg->funcs->lock(pipe_ctx->stream_res.tg); @@ -2362,7 +2372,8 @@ static void dcn10_apply_ctx_for_surface( for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; - if (!pipe_ctx->stream || pipe_ctx->stream == stream) + if (!pipe_ctx->stream || pipe_ctx->stream == stream + || !pipe_ctx->plane_state) continue; dcn10_pipe_control_lock(dc, pipe_ctx, false); diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c index a683f4102e65..c2028c4744a6 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c @@ -79,6 +79,7 @@ bool dal_hw_factory_init( dal_hw_factory_dce110_init(factory); return true; case DCE_VERSION_12_0: + case DCE_VERSION_12_1: dal_hw_factory_dce120_init(factory); return true; #if defined(CONFIG_DRM_AMD_DC_DCN1_0) diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c index 096f45628630..236ca28784a9 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c @@ -76,6 +76,7 @@ bool dal_hw_translate_init( dal_hw_translate_dce110_init(translate); return true; case DCE_VERSION_12_0: + case DCE_VERSION_12_1: dal_hw_translate_dce120_init(translate); return true; #if defined(CONFIG_DRM_AMD_DC_DCN1_0) diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c index e56093f26eed..1ad6e49102ff 100644 --- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c +++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c @@ -90,6 +90,7 @@ struct i2caux *dal_i2caux_create( case DCE_VERSION_10_0: return dal_i2caux_dce100_create(ctx); case DCE_VERSION_12_0: + case DCE_VERSION_12_1: return dal_i2caux_dce120_create(ctx); #if defined(CONFIG_DRM_AMD_DC_DCN1_0) case DCN_VERSION_1_0: 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 f8dbfa5b89f2..7fd78a696800 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -41,6 +41,7 @@ enum as_signal_type { AS_SIGNAL_TYPE_LVDS, AS_SIGNAL_TYPE_DISPLAY_PORT, AS_SIGNAL_TYPE_GPU_PLL, + AS_SIGNAL_TYPE_XGMI, AS_SIGNAL_TYPE_UNKNOWN }; diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h index 89627133e188..f5bd869d4320 100644 --- a/drivers/gpu/drm/amd/display/include/dal_types.h +++ b/drivers/gpu/drm/amd/display/include/dal_types.h @@ -42,6 +42,7 @@ enum dce_version { DCE_VERSION_11_2, DCE_VERSION_11_22, DCE_VERSION_12_0, + DCE_VERSION_12_1, DCE_VERSION_MAX, DCN_VERSION_1_0, #if defined(CONFIG_DRM_AMD_DC_DCN1_01) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 2e99ecf4ab76..26154f9b2178 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -49,6 +49,10 @@ #include "soc15_common.h" #include "smuio/smuio_9_0_offset.h" #include "smuio/smuio_9_0_sh_mask.h" +#include "nbio/nbio_7_4_sh_mask.h" + +#define smnPCIE_LC_SPEED_CNTL 0x11140290 +#define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288 static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) { @@ -2282,6 +2286,18 @@ static int vega20_force_clock_level(struct pp_hwmgr *hwmgr, break; case PP_PCIE: + soft_min_level = mask ? (ffs(mask) - 1) : 0; + soft_max_level = mask ? (fls(mask) - 1) : 0; + if (soft_min_level >= NUM_LINK_LEVELS || + soft_max_level >= NUM_LINK_LEVELS) + return -EINVAL; + + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetMinLinkDpmByIndex, soft_min_level); + PP_ASSERT_WITH_CODE(!ret, + "Failed to set min link dpm level!", + return ret); + break; default: @@ -2758,9 +2774,14 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, data->od8_settings.od8_settings_array; OverDriveTable_t *od_table = &(data->smc_state_table.overdrive_table); + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; + PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable; + struct amdgpu_device *adev = hwmgr->adev; struct pp_clock_levels_with_latency clocks; int i, now, size = 0; int ret = 0; + uint32_t gen_speed, lane_width; switch (type) { case PP_SCLK: @@ -2798,6 +2819,28 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, break; case PP_PCIE: + gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & + PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) + >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT; + lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) & + PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK) + >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT; + for (i = 0; i < NUM_LINK_LEVELS; i++) + size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, + (pptable->PcieGenSpeed[i] == 0) ? "2.5GT/s," : + (pptable->PcieGenSpeed[i] == 1) ? "5.0GT/s," : + (pptable->PcieGenSpeed[i] == 2) ? "8.0GT/s," : + (pptable->PcieGenSpeed[i] == 3) ? "16.0GT/s," : "", + (pptable->PcieLaneCount[i] == 1) ? "x1" : + (pptable->PcieLaneCount[i] == 2) ? "x2" : + (pptable->PcieLaneCount[i] == 3) ? "x4" : + (pptable->PcieLaneCount[i] == 4) ? "x8" : + (pptable->PcieLaneCount[i] == 5) ? "x12" : + (pptable->PcieLaneCount[i] == 6) ? "x16" : "", + pptable->LclkFreq[i], + (gen_speed == pptable->PcieGenSpeed[i]) && + (lane_width == pptable->PcieLaneCount[i]) ? + "*" : ""); break; case OD_SCLK: diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c index 60bd7d708e35..4985384e51f6 100644 --- a/drivers/gpu/drm/drm_atomic_state_helper.c +++ b/drivers/gpu/drm/drm_atomic_state_helper.c @@ -241,6 +241,7 @@ void __drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane, state->fence = NULL; state->commit = NULL; + state->fb_damage_clips = NULL; } EXPORT_SYMBOL(__drm_atomic_helper_plane_duplicate_state); @@ -285,6 +286,8 @@ void __drm_atomic_helper_plane_destroy_state(struct drm_plane_state *state) if (state->commit) drm_crtc_commit_put(state->commit); + + drm_property_blob_put(state->fb_damage_clips); } EXPORT_SYMBOL(__drm_atomic_helper_plane_destroy_state); diff --git a/drivers/gpu/drm/drm_damage_helper.c b/drivers/gpu/drm/drm_damage_helper.c index d2a1c7372f36..31032407254d 100644 --- a/drivers/gpu/drm/drm_damage_helper.c +++ b/drivers/gpu/drm/drm_damage_helper.c @@ -178,7 +178,7 @@ int drm_atomic_helper_dirtyfb(struct drm_framebuffer *fb, state = drm_atomic_state_alloc(fb->dev); if (!state) { ret = -ENOMEM; - goto out; + goto out_drop_locks; } state->acquire_ctx = &ctx; @@ -238,6 +238,7 @@ out: kfree(rects); drm_atomic_state_put(state); +out_drop_locks: drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 77edbfcb0f75..77ae634eb11c 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1900,11 +1900,11 @@ static struct cmd_info cmd_info[] = { {"MI_URB_CLEAR", OP_MI_URB_CLEAR, F_LEN_VAR, R_RCS, D_ALL, 0, 8, NULL}, - {"ME_SEMAPHORE_SIGNAL", OP_MI_SEMAPHORE_SIGNAL, F_LEN_VAR, R_ALL, + {"MI_SEMAPHORE_SIGNAL", OP_MI_SEMAPHORE_SIGNAL, F_LEN_VAR, R_ALL, D_BDW_PLUS, 0, 8, NULL}, - {"ME_SEMAPHORE_WAIT", OP_MI_SEMAPHORE_WAIT, F_LEN_VAR, R_ALL, D_BDW_PLUS, - ADDR_FIX_1(2), 8, cmd_handler_mi_semaphore_wait}, + {"MI_SEMAPHORE_WAIT", OP_MI_SEMAPHORE_WAIT, F_LEN_VAR, R_ALL, + D_BDW_PLUS, ADDR_FIX_1(2), 8, cmd_handler_mi_semaphore_wait}, {"MI_STORE_DATA_IMM", OP_MI_STORE_DATA_IMM, F_LEN_VAR, R_ALL, D_BDW_PLUS, ADDR_FIX_1(1), 10, cmd_handler_mi_store_data_imm}, diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 6ef5a7fc70df..733a2a0d0c30 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -437,7 +437,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv) ret = intel_gvt_debugfs_init(gvt); if (ret) - gvt_err("debugfs registeration failed, go on.\n"); + gvt_err("debugfs registration failed, go on.\n"); gvt_dbg_core("gvt device initialization is done\n"); dev_priv->gvt = gvt; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 31f6cdbe5c42..b4ab1dad0143 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -159,6 +159,10 @@ struct intel_vgpu_submission { struct kmem_cache *workloads; atomic_t running_workload_num; struct i915_gem_context *shadow_ctx; + union { + u64 i915_context_pml4; + u64 i915_context_pdps[GEN8_3LVL_PDPES]; + }; DECLARE_BITMAP(shadow_ctx_desc_updated, I915_NUM_ENGINES); DECLARE_BITMAP(tlb_handle_pending, I915_NUM_ENGINES); void *ring_scan_buffer[I915_NUM_ENGINES]; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index aa280bb07125..b5475c91e2ef 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -475,6 +475,7 @@ static i915_reg_t force_nonpriv_white_list[] = { _MMIO(0x7704), _MMIO(0x7708), _MMIO(0x770c), + _MMIO(0x83a8), _MMIO(0xb110), GEN8_L3SQCREG4,//_MMIO(0xb118) _MMIO(0xe100), diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index 5daa23ae566b..6b9d1354ff29 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -126,7 +126,7 @@ static const char * const irq_name[INTEL_GVT_EVENT_MAX] = { [FDI_RX_INTERRUPTS_TRANSCODER_C] = "FDI RX Interrupts Combined C", [AUDIO_CP_CHANGE_TRANSCODER_C] = "Audio CP Change Transcoder C", [AUDIO_CP_REQUEST_TRANSCODER_C] = "Audio CP Request Transcoder C", - [ERR_AND_DBG] = "South Error and Debug Interupts Combined", + [ERR_AND_DBG] = "South Error and Debug Interrupts Combined", [GMBUS] = "Gmbus", [SDVO_B_HOTPLUG] = "SDVO B hotplug", [CRT_HOTPLUG] = "CRT Hotplug", diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index b8fbe3fabea3..1ad8c5e1455d 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1079,6 +1079,21 @@ err: return ret; } +static void +i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s) +{ + struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt; + int i; + + if (i915_vm_is_48bit(&i915_ppgtt->vm)) + px_dma(&i915_ppgtt->pml4) = s->i915_context_pml4; + else { + for (i = 0; i < GEN8_3LVL_PDPES; i++) + px_dma(i915_ppgtt->pdp.page_directory[i]) = + s->i915_context_pdps[i]; + } +} + /** * intel_vgpu_clean_submission - free submission-related resource for vGPU * @vgpu: a vGPU @@ -1091,6 +1106,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu) struct intel_vgpu_submission *s = &vgpu->submission; intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); + i915_context_ppgtt_root_restore(s); i915_gem_context_put(s->shadow_ctx); kmem_cache_destroy(s->workloads); } @@ -1116,6 +1132,21 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu, s->ops->reset(vgpu, engine_mask); } +static void +i915_context_ppgtt_root_save(struct intel_vgpu_submission *s) +{ + struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt; + int i; + + if (i915_vm_is_48bit(&i915_ppgtt->vm)) + s->i915_context_pml4 = px_dma(&i915_ppgtt->pml4); + else { + for (i = 0; i < GEN8_3LVL_PDPES; i++) + s->i915_context_pdps[i] = + px_dma(i915_ppgtt->pdp.page_directory[i]); + } +} + /** * intel_vgpu_setup_submission - setup submission-related resource for vGPU * @vgpu: a vGPU @@ -1138,6 +1169,8 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) if (IS_ERR(s->shadow_ctx)) return PTR_ERR(s->shadow_ctx); + i915_context_ppgtt_root_save(s); + bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES); s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload", diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index 4b75ad40dd80..432c440223bb 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -4,7 +4,8 @@ config DRM_NOUVEAU select FW_LOADER select DRM_KMS_HELPER select DRM_TTM - select FB_BACKLIGHT if DRM_NOUVEAU_BACKLIGHT + select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT + select BACKLIGHT_LCD_SUPPORT if DRM_NOUVEAU_BACKLIGHT select ACPI_VIDEO if ACPI && X86 && BACKLIGHT_CLASS_DEVICE && INPUT select X86_PLATFORM_DEVICES if ACPI && X86 select ACPI_WMI if ACPI && X86 diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index d87935bf8e30..0ec08394e17a 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -77,38 +77,39 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place, return 0; } -static void ttm_mem_type_debug(struct ttm_bo_device *bdev, int mem_type) +static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p, + int mem_type) { struct ttm_mem_type_manager *man = &bdev->man[mem_type]; - struct drm_printer p = drm_debug_printer(TTM_PFX); - pr_err(" has_type: %d\n", man->has_type); - pr_err(" use_type: %d\n", man->use_type); - pr_err(" flags: 0x%08X\n", man->flags); - pr_err(" gpu_offset: 0x%08llX\n", man->gpu_offset); - pr_err(" size: %llu\n", man->size); - pr_err(" available_caching: 0x%08X\n", man->available_caching); - pr_err(" default_caching: 0x%08X\n", man->default_caching); + drm_printf(p, " has_type: %d\n", man->has_type); + drm_printf(p, " use_type: %d\n", man->use_type); + drm_printf(p, " flags: 0x%08X\n", man->flags); + drm_printf(p, " gpu_offset: 0x%08llX\n", man->gpu_offset); + drm_printf(p, " size: %llu\n", man->size); + drm_printf(p, " available_caching: 0x%08X\n", man->available_caching); + drm_printf(p, " default_caching: 0x%08X\n", man->default_caching); if (mem_type != TTM_PL_SYSTEM) - (*man->func->debug)(man, &p); + (*man->func->debug)(man, p); } static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, struct ttm_placement *placement) { + struct drm_printer p = drm_debug_printer(TTM_PFX); int i, ret, mem_type; - pr_err("No space for %p (%lu pages, %luK, %luM)\n", - bo, bo->mem.num_pages, bo->mem.size >> 10, - bo->mem.size >> 20); + drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n", + bo, bo->mem.num_pages, bo->mem.size >> 10, + bo->mem.size >> 20); for (i = 0; i < placement->num_placement; i++) { ret = ttm_mem_type_from_place(&placement->placement[i], &mem_type); if (ret) return; - pr_err(" placement[%d]=0x%08X (%d)\n", - i, placement->placement[i].flags, mem_type); - ttm_mem_type_debug(bo->bdev, mem_type); + drm_printf(&p, " placement[%d]=0x%08X (%d)\n", + i, placement->placement[i].flags, mem_type); + ttm_mem_type_debug(bo->bdev, &p, mem_type); } } diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index a1fa2fc8c9b5..951bb17ae8b2 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -70,6 +70,7 @@ MODULE_DESCRIPTION("Asus HID Keyboard and TouchPad"); #define QUIRK_T100_KEYBOARD BIT(6) #define QUIRK_T100CHI BIT(7) #define QUIRK_G752_KEYBOARD BIT(8) +#define QUIRK_T101HA_DOCK BIT(9) #define I2C_KEYBOARD_QUIRKS (QUIRK_FIX_NOTEBOOK_REPORT | \ QUIRK_NO_INIT_REPORTS | \ @@ -241,6 +242,18 @@ static int asus_report_input(struct asus_drvdata *drvdat, u8 *data, int size) return 1; } +static int asus_event(struct hid_device *hdev, struct hid_field *field, + struct hid_usage *usage, __s32 value) +{ + if ((usage->hid & HID_USAGE_PAGE) == 0xff310000 && + (usage->hid & HID_USAGE) != 0x00 && !usage->type) { + hid_warn(hdev, "Unmapped Asus vendor usagepage code 0x%02x\n", + usage->hid & HID_USAGE); + } + + return 0; +} + static int asus_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { @@ -510,6 +523,7 @@ static int asus_input_mapping(struct hid_device *hdev, case 0x20: asus_map_key_clear(KEY_BRIGHTNESSUP); break; case 0x35: asus_map_key_clear(KEY_DISPLAY_OFF); break; case 0x6c: asus_map_key_clear(KEY_SLEEP); break; + case 0x7c: asus_map_key_clear(KEY_MICMUTE); break; case 0x82: asus_map_key_clear(KEY_CAMERA); break; case 0x88: asus_map_key_clear(KEY_RFKILL); break; case 0xb5: asus_map_key_clear(KEY_CALC); break; @@ -528,6 +542,9 @@ static int asus_input_mapping(struct hid_device *hdev, /* Fn+Space Power4Gear Hybrid */ case 0x5c: asus_map_key_clear(KEY_PROG3); break; + /* Fn+F5 "fan" symbol on FX503VD */ + case 0x99: asus_map_key_clear(KEY_PROG4); break; + default: /* ASUS lazily declares 256 usages, ignore the rest, * as some make the keyboard appear as a pointer device. */ @@ -683,6 +700,11 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) return ret; } + /* use hid-multitouch for T101HA touchpad */ + if (id->driver_data & QUIRK_T101HA_DOCK && + hdev->collection->usage == HID_GD_MOUSE) + return -ENODEV; + ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "Asus hw start failed: %d\n", ret); @@ -806,11 +828,16 @@ static const struct hid_device_id asus_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD3), QUIRK_G752_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD), + QUIRK_USE_KBD_BACKLIGHT }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100TA_KEYBOARD), QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100TAF_KEYBOARD), QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_T101HA_KEYBOARD), QUIRK_T101HA_DOCK }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_ASUS_AK1D) }, { HID_USB_DEVICE(USB_VENDOR_ID_TURBOX, USB_DEVICE_ID_ASUS_MD_5110) }, { HID_USB_DEVICE(USB_VENDOR_ID_JESS, USB_DEVICE_ID_ASUS_MD_5112) }, @@ -832,6 +859,7 @@ static struct hid_driver asus_driver = { #ifdef CONFIG_PM .reset_resume = asus_reset_resume, #endif + .event = asus_event, .raw_event = asus_raw_event }; module_hid_driver(asus_driver); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 5bec9244c45b..f41d5fe51abe 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -172,6 +172,8 @@ static int open_collection(struct hid_parser *parser, unsigned type) collection->type = type; collection->usage = usage; collection->level = parser->collection_stack_ptr - 1; + collection->parent = parser->active_collection; + parser->active_collection = collection; if (type == HID_COLLECTION_APPLICATION) parser->device->maxapplication++; @@ -190,6 +192,8 @@ static int close_collection(struct hid_parser *parser) return -EINVAL; } parser->collection_stack_ptr--; + if (parser->active_collection) + parser->active_collection = parser->active_collection->parent; return 0; } @@ -290,6 +294,7 @@ static int hid_add_field(struct hid_parser *parser, unsigned report_type, unsign field->usage[i].collection_index = parser->local.collection_index[j]; field->usage[i].usage_index = i; + field->usage[i].resolution_multiplier = 1; } field->maxusage = usages; @@ -943,6 +948,167 @@ struct hid_report *hid_validate_values(struct hid_device *hid, } EXPORT_SYMBOL_GPL(hid_validate_values); +static int hid_calculate_multiplier(struct hid_device *hid, + struct hid_field *multiplier) +{ + int m; + __s32 v = *multiplier->value; + __s32 lmin = multiplier->logical_minimum; + __s32 lmax = multiplier->logical_maximum; + __s32 pmin = multiplier->physical_minimum; + __s32 pmax = multiplier->physical_maximum; + + /* + * "Because OS implementations will generally divide the control's + * reported count by the Effective Resolution Multiplier, designers + * should take care not to establish a potential Effective + * Resolution Multiplier of zero." + * HID Usage Table, v1.12, Section 4.3.1, p31 + */ + if (lmax - lmin == 0) + return 1; + /* + * Handling the unit exponent is left as an exercise to whoever + * finds a device where that exponent is not 0. + */ + m = ((v - lmin)/(lmax - lmin) * (pmax - pmin) + pmin); + if (unlikely(multiplier->unit_exponent != 0)) { + hid_warn(hid, + "unsupported Resolution Multiplier unit exponent %d\n", + multiplier->unit_exponent); + } + + /* There are no devices with an effective multiplier > 255 */ + if (unlikely(m == 0 || m > 255 || m < -255)) { + hid_warn(hid, "unsupported Resolution Multiplier %d\n", m); + m = 1; + } + + return m; +} + +static void hid_apply_multiplier_to_field(struct hid_device *hid, + struct hid_field *field, + struct hid_collection *multiplier_collection, + int effective_multiplier) +{ + struct hid_collection *collection; + struct hid_usage *usage; + int i; + + /* + * If multiplier_collection is NULL, the multiplier applies + * to all fields in the report. + * Otherwise, it is the Logical Collection the multiplier applies to + * but our field may be in a subcollection of that collection. + */ + for (i = 0; i < field->maxusage; i++) { + usage = &field->usage[i]; + + collection = &hid->collection[usage->collection_index]; + while (collection && collection != multiplier_collection) + collection = collection->parent; + + if (collection || multiplier_collection == NULL) + usage->resolution_multiplier = effective_multiplier; + + } +} + +static void hid_apply_multiplier(struct hid_device *hid, + struct hid_field *multiplier) +{ + struct hid_report_enum *rep_enum; + struct hid_report *rep; + struct hid_field *field; + struct hid_collection *multiplier_collection; + int effective_multiplier; + int i; + + /* + * "The Resolution Multiplier control must be contained in the same + * Logical Collection as the control(s) to which it is to be applied. + * If no Resolution Multiplier is defined, then the Resolution + * Multiplier defaults to 1. If more than one control exists in a + * Logical Collection, the Resolution Multiplier is associated with + * all controls in the collection. If no Logical Collection is + * defined, the Resolution Multiplier is associated with all + * controls in the report." + * HID Usage Table, v1.12, Section 4.3.1, p30 + * + * Thus, search from the current collection upwards until we find a + * logical collection. Then search all fields for that same parent + * collection. Those are the fields the multiplier applies to. + * + * If we have more than one multiplier, it will overwrite the + * applicable fields later. + */ + multiplier_collection = &hid->collection[multiplier->usage->collection_index]; + while (multiplier_collection && + multiplier_collection->type != HID_COLLECTION_LOGICAL) + multiplier_collection = multiplier_collection->parent; + + effective_multiplier = hid_calculate_multiplier(hid, multiplier); + + rep_enum = &hid->report_enum[HID_INPUT_REPORT]; + list_for_each_entry(rep, &rep_enum->report_list, list) { + for (i = 0; i < rep->maxfield; i++) { + field = rep->field[i]; + hid_apply_multiplier_to_field(hid, field, + multiplier_collection, + effective_multiplier); + } + } +} + +/* + * hid_setup_resolution_multiplier - set up all resolution multipliers + * + * @device: hid device + * + * Search for all Resolution Multiplier Feature Reports and apply their + * value to all matching Input items. This only updates the internal struct + * fields. + * + * The Resolution Multiplier is applied by the hardware. If the multiplier + * is anything other than 1, the hardware will send pre-multiplied events + * so that the same physical interaction generates an accumulated + * accumulated_value = value * * multiplier + * This may be achieved by sending + * - "value * multiplier" for each event, or + * - "value" but "multiplier" times as frequently, or + * - a combination of the above + * The only guarantee is that the same physical interaction always generates + * an accumulated 'value * multiplier'. + * + * This function must be called before any event processing and after + * any SetRequest to the Resolution Multiplier. + */ +void hid_setup_resolution_multiplier(struct hid_device *hid) +{ + struct hid_report_enum *rep_enum; + struct hid_report *rep; + struct hid_usage *usage; + int i, j; + + rep_enum = &hid->report_enum[HID_FEATURE_REPORT]; + list_for_each_entry(rep, &rep_enum->report_list, list) { + for (i = 0; i < rep->maxfield; i++) { + /* Ignore if report count is out of bounds. */ + if (rep->field[i]->report_count < 1) + continue; + + for (j = 0; j < rep->field[i]->maxusage; j++) { + usage = &rep->field[i]->usage[j]; + if (usage->hid == HID_GD_RESOLUTION_MULTIPLIER) + hid_apply_multiplier(hid, + rep->field[i]); + } + } + } +} +EXPORT_SYMBOL_GPL(hid_setup_resolution_multiplier); + /** * hid_open_report - open a driver-specific device report * @@ -1039,9 +1205,17 @@ int hid_open_report(struct hid_device *device) hid_err(device, "unbalanced delimiter at end of report description\n"); goto err; } + + /* + * fetch initial values in case the device's + * default multiplier isn't the recommended 1 + */ + hid_setup_resolution_multiplier(device); + kfree(parser->collection_stack); vfree(parser); device->status |= HID_STAT_PARSED; + return 0; } } diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c index 3f0916b64c60..e0bb7b34f3a4 100644 --- a/drivers/hid/hid-cougar.c +++ b/drivers/hid/hid-cougar.c @@ -326,6 +326,8 @@ module_param_cb(g6_is_space, &cougar_g6_is_space_ops, &g6_is_space, 0644); static struct hid_device_id cougar_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR, USB_DEVICE_ID_COUGAR_500K_GAMING_KEYBOARD) }, + { HID_USB_DEVICE(USB_VENDOR_ID_SOLID_YEAR, + USB_DEVICE_ID_COUGAR_700K_GAMING_KEYBOARD) }, {} }; MODULE_DEVICE_TABLE(hid, cougar_id_table); diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index b48100236df8..c530476edba6 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1072,11 +1072,6 @@ static int hid_debug_rdesc_show(struct seq_file *f, void *p) return 0; } -static int hid_debug_rdesc_open(struct inode *inode, struct file *file) -{ - return single_open(file, hid_debug_rdesc_show, inode->i_private); -} - static int hid_debug_events_open(struct inode *inode, struct file *file) { int err = 0; @@ -1211,12 +1206,7 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) return 0; } -static const struct file_operations hid_debug_rdesc_fops = { - .open = hid_debug_rdesc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(hid_debug_rdesc); static const struct file_operations hid_debug_events_fops = { .owner = THIS_MODULE, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 27519eb8ee63..518fa76414f5 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -187,12 +187,14 @@ #define USB_DEVICE_ID_ASUSTEK_T100TA_KEYBOARD 0x17e0 #define USB_DEVICE_ID_ASUSTEK_T100TAF_KEYBOARD 0x1807 #define USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD 0x8502 +#define USB_DEVICE_ID_ASUSTEK_T101HA_KEYBOARD 0x183d #define USB_DEVICE_ID_ASUSTEK_T304_KEYBOARD 0x184a #define USB_DEVICE_ID_ASUSTEK_I2C_KEYBOARD 0x8585 #define USB_DEVICE_ID_ASUSTEK_I2C_TOUCHPAD 0x0101 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD1 0x1854 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2 0x1837 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD3 0x1822 +#define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869 #define USB_VENDOR_ID_ATEN 0x0557 #define USB_DEVICE_ID_ATEN_UC100KM 0x2004 @@ -1025,6 +1027,7 @@ #define USB_VENDOR_ID_SOLID_YEAR 0x060b #define USB_DEVICE_ID_COUGAR_500K_GAMING_KEYBOARD 0x500a +#define USB_DEVICE_ID_COUGAR_700K_GAMING_KEYBOARD 0x700a #define USB_VENDOR_ID_SOUNDGRAPH 0x15c2 #define USB_DEVICE_ID_SOUNDGRAPH_IMON_FIRST 0x0034 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index d6fab5798487..59a5608b8dc0 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -712,7 +712,15 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel map_abs_clear(usage->hid & 0xf); break; - case HID_GD_SLIDER: case HID_GD_DIAL: case HID_GD_WHEEL: + case HID_GD_WHEEL: + if (field->flags & HID_MAIN_ITEM_RELATIVE) { + set_bit(REL_WHEEL, input->relbit); + map_rel(REL_WHEEL_HI_RES); + } else { + map_abs(usage->hid & 0xf); + } + break; + case HID_GD_SLIDER: case HID_GD_DIAL: if (field->flags & HID_MAIN_ITEM_RELATIVE) map_rel(usage->hid & 0xf); else @@ -1012,7 +1020,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x22f: map_key_clear(KEY_ZOOMRESET); break; case 0x233: map_key_clear(KEY_SCROLLUP); break; case 0x234: map_key_clear(KEY_SCROLLDOWN); break; - case 0x238: map_rel(REL_HWHEEL); break; + case 0x238: /* AC Pan */ + set_bit(REL_HWHEEL, input->relbit); + map_rel(REL_HWHEEL_HI_RES); + break; case 0x23d: map_key_clear(KEY_EDIT); break; case 0x25f: map_key_clear(KEY_CANCEL); break; case 0x269: map_key_clear(KEY_INSERT); break; @@ -1200,6 +1211,38 @@ ignore: } +static void hidinput_handle_scroll(struct hid_usage *usage, + struct input_dev *input, + __s32 value) +{ + int code; + int hi_res, lo_res; + + if (value == 0) + return; + + if (usage->code == REL_WHEEL_HI_RES) + code = REL_WHEEL; + else + code = REL_HWHEEL; + + /* + * Windows reports one wheel click as value 120. Where a high-res + * scroll wheel is present, a fraction of 120 is reported instead. + * Our REL_WHEEL_HI_RES axis does the same because all HW must + * adhere to the 120 expectation. + */ + hi_res = value * 120/usage->resolution_multiplier; + + usage->wheel_accumulated += hi_res; + lo_res = usage->wheel_accumulated/120; + if (lo_res) + usage->wheel_accumulated -= lo_res * 120; + + input_event(input, EV_REL, code, lo_res); + input_event(input, EV_REL, usage->code, hi_res); +} + void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { struct input_dev *input; @@ -1262,6 +1305,12 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct if ((usage->type == EV_KEY) && (usage->code == 0)) /* Key 0 is "unassigned", not KEY_UNKNOWN */ return; + if ((usage->type == EV_REL) && (usage->code == REL_WHEEL_HI_RES || + usage->code == REL_HWHEEL_HI_RES)) { + hidinput_handle_scroll(usage, input, value); + return; + } + if ((usage->type == EV_ABS) && (field->flags & HID_MAIN_ITEM_RELATIVE) && (usage->code == ABS_VOLUME)) { int count = abs(value); @@ -1489,6 +1538,58 @@ static void hidinput_close(struct input_dev *dev) hid_hw_close(hid); } +static void hidinput_change_resolution_multipliers(struct hid_device *hid) +{ + struct hid_report_enum *rep_enum; + struct hid_report *rep; + struct hid_usage *usage; + int i, j; + + rep_enum = &hid->report_enum[HID_FEATURE_REPORT]; + list_for_each_entry(rep, &rep_enum->report_list, list) { + bool update_needed = false; + + if (rep->maxfield == 0) + continue; + + /* + * If we have more than one feature within this report we + * need to fill in the bits from the others before we can + * overwrite the ones for the Resolution Multiplier. + */ + if (rep->maxfield > 1) { + hid_hw_request(hid, rep, HID_REQ_GET_REPORT); + hid_hw_wait(hid); + } + + for (i = 0; i < rep->maxfield; i++) { + __s32 logical_max = rep->field[i]->logical_maximum; + + /* There is no good reason for a Resolution + * Multiplier to have a count other than 1. + * Ignore that case. + */ + if (rep->field[i]->report_count != 1) + continue; + + for (j = 0; j < rep->field[i]->maxusage; j++) { + usage = &rep->field[i]->usage[j]; + + if (usage->hid != HID_GD_RESOLUTION_MULTIPLIER) + continue; + + *rep->field[i]->value = logical_max; + update_needed = true; + } + } + if (update_needed) + hid_hw_request(hid, rep, HID_REQ_SET_REPORT); + } + + /* refresh our structs */ + hid_setup_resolution_multiplier(hid); +} + static void report_features(struct hid_device *hid) { struct hid_driver *drv = hid->driver; @@ -1782,6 +1883,8 @@ int hidinput_connect(struct hid_device *hid, unsigned int force) } } + hidinput_change_resolution_multipliers(hid); + list_for_each_entry_safe(hidinput, next, &hid->inputs, list) { if (drv->input_configured && drv->input_configured(hid, hidinput)) @@ -1840,4 +1943,3 @@ void hidinput_disconnect(struct hid_device *hid) cancel_work_sync(&hid->led_work); } EXPORT_SYMBOL_GPL(hidinput_disconnect); - diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 643b6eb54442..eacc76d2ab96 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -743,7 +743,9 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev) data_pointer->led_mute.brightness_get = lenovo_led_brightness_get_tpkbd; data_pointer->led_mute.brightness_set = lenovo_led_brightness_set_tpkbd; data_pointer->led_mute.dev = dev; - led_classdev_register(dev, &data_pointer->led_mute); + ret = led_classdev_register(dev, &data_pointer->led_mute); + if (ret < 0) + goto err; data_pointer->led_micmute.name = name_micmute; data_pointer->led_micmute.brightness_get = @@ -751,7 +753,11 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev) data_pointer->led_micmute.brightness_set = lenovo_led_brightness_set_tpkbd; data_pointer->led_micmute.dev = dev; - led_classdev_register(dev, &data_pointer->led_micmute); + ret = led_classdev_register(dev, &data_pointer->led_micmute); + if (ret < 0) { + led_classdev_unregister(&data_pointer->led_mute); + goto err; + } lenovo_features_set_tpkbd(hdev); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 19cc980eebce..15ed6177a7a3 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/clock.h> #include <linux/kfifo.h> #include <linux/input/mt.h> #include <linux/workqueue.h> @@ -64,6 +65,14 @@ MODULE_PARM_DESC(disable_tap_to_click, #define HIDPP_QUIRK_NO_HIDINPUT BIT(23) #define HIDPP_QUIRK_FORCE_OUTPUT_REPORTS BIT(24) #define HIDPP_QUIRK_UNIFYING BIT(25) +#define HIDPP_QUIRK_HI_RES_SCROLL_1P0 BIT(26) +#define HIDPP_QUIRK_HI_RES_SCROLL_X2120 BIT(27) +#define HIDPP_QUIRK_HI_RES_SCROLL_X2121 BIT(28) + +/* Convenience constant to check for any high-res support. */ +#define HIDPP_QUIRK_HI_RES_SCROLL (HIDPP_QUIRK_HI_RES_SCROLL_1P0 | \ + HIDPP_QUIRK_HI_RES_SCROLL_X2120 | \ + HIDPP_QUIRK_HI_RES_SCROLL_X2121) #define HIDPP_QUIRK_DELAYED_INIT HIDPP_QUIRK_NO_HIDINPUT @@ -128,6 +137,25 @@ struct hidpp_battery { bool online; }; +/** + * struct hidpp_scroll_counter - Utility class for processing high-resolution + * scroll events. + * @dev: the input device for which events should be reported. + * @wheel_multiplier: the scalar multiplier to be applied to each wheel event + * @remainder: counts the number of high-resolution units moved since the last + * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should + * only be used by class methods. + * @direction: direction of last movement (1 or -1) + * @last_time: last event time, used to reset remainder after inactivity + */ +struct hidpp_scroll_counter { + struct input_dev *dev; + int wheel_multiplier; + int remainder; + int direction; + unsigned long long last_time; +}; + struct hidpp_device { struct hid_device *hid_dev; struct mutex send_mutex; @@ -149,6 +177,7 @@ struct hidpp_device { unsigned long capabilities; struct hidpp_battery battery; + struct hidpp_scroll_counter vertical_wheel_counter; }; /* HID++ 1.0 error codes */ @@ -391,6 +420,67 @@ static void hidpp_prefix_name(char **name, int name_length) *name = new_name; } +/** + * hidpp_scroll_counter_handle_scroll() - Send high- and low-resolution scroll + * events given a high-resolution wheel + * movement. + * @counter: a hid_scroll_counter struct describing the wheel. + * @hi_res_value: the movement of the wheel, in the mouse's high-resolution + * units. + * + * Given a high-resolution movement, this function converts the movement into + * fractions of 120 and emits high-resolution scroll events for the input + * device. It also uses the multiplier from &struct hid_scroll_counter to + * emit low-resolution scroll events when appropriate for + * backwards-compatibility with userspace input libraries. + */ +static void hidpp_scroll_counter_handle_scroll(struct hidpp_scroll_counter *counter, + int hi_res_value) +{ + int low_res_value, remainder, direction; + unsigned long long now, previous; + + hi_res_value = hi_res_value * 120/counter->wheel_multiplier; + input_report_rel(counter->dev, REL_WHEEL_HI_RES, hi_res_value); + + remainder = counter->remainder; + direction = hi_res_value > 0 ? 1 : -1; + + now = sched_clock(); + previous = counter->last_time; + counter->last_time = now; + /* + * Reset the remainder after a period of inactivity or when the + * direction changes. This prevents the REL_WHEEL emulation point + * from sliding for devices that don't always provide the same + * number of movements per detent. + */ + if (now - previous > 1000000000 || direction != counter->direction) + remainder = 0; + + counter->direction = direction; + remainder += hi_res_value; + + /* Some wheels will rest 7/8ths of a detent from the previous detent + * after slow movement, so we want the threshold for low-res events to + * be in the middle between two detents (e.g. after 4/8ths) as + * opposed to on the detents themselves (8/8ths). + */ + if (abs(remainder) >= 60) { + /* Add (or subtract) 1 because we want to trigger when the wheel + * is half-way to the next detent (i.e. scroll 1 detent after a + * 1/2 detent movement, 2 detents after a 1 1/2 detent movement, + * etc.). + */ + low_res_value = remainder / 120; + if (low_res_value == 0) + low_res_value = (hi_res_value > 0 ? 1 : -1); + input_report_rel(counter->dev, REL_WHEEL, low_res_value); + remainder -= low_res_value * 120; + } + counter->remainder = remainder; +} + /* -------------------------------------------------------------------------- */ /* HIDP++ 1.0 commands */ /* -------------------------------------------------------------------------- */ @@ -400,32 +490,53 @@ static void hidpp_prefix_name(char **name, int name_length) #define HIDPP_SET_LONG_REGISTER 0x82 #define HIDPP_GET_LONG_REGISTER 0x83 -#define HIDPP_REG_GENERAL 0x00 - -static int hidpp10_enable_battery_reporting(struct hidpp_device *hidpp_dev) +/** + * hidpp10_set_register_bit() - Sets a single bit in a HID++ 1.0 register. + * @hidpp_dev: the device to set the register on. + * @register_address: the address of the register to modify. + * @byte: the byte of the register to modify. Should be less than 3. + * Return: 0 if successful, otherwise a negative error code. + */ +static int hidpp10_set_register_bit(struct hidpp_device *hidpp_dev, + u8 register_address, u8 byte, u8 bit) { struct hidpp_report response; int ret; u8 params[3] = { 0 }; ret = hidpp_send_rap_command_sync(hidpp_dev, - REPORT_ID_HIDPP_SHORT, - HIDPP_GET_REGISTER, - HIDPP_REG_GENERAL, - NULL, 0, &response); + REPORT_ID_HIDPP_SHORT, + HIDPP_GET_REGISTER, + register_address, + NULL, 0, &response); if (ret) return ret; memcpy(params, response.rap.params, 3); - /* Set the battery bit */ - params[0] |= BIT(4); + params[byte] |= BIT(bit); return hidpp_send_rap_command_sync(hidpp_dev, - REPORT_ID_HIDPP_SHORT, - HIDPP_SET_REGISTER, - HIDPP_REG_GENERAL, - params, 3, &response); + REPORT_ID_HIDPP_SHORT, + HIDPP_SET_REGISTER, + register_address, + params, 3, &response); +} + + +#define HIDPP_REG_GENERAL 0x00 + +static int hidpp10_enable_battery_reporting(struct hidpp_device *hidpp_dev) +{ + return hidpp10_set_register_bit(hidpp_dev, HIDPP_REG_GENERAL, 0, 4); +} + +#define HIDPP_REG_FEATURES 0x01 + +/* On HID++ 1.0 devices, high-res scroll was called "scrolling acceleration". */ +static int hidpp10_enable_scrolling_acceleration(struct hidpp_device *hidpp_dev) +{ + return hidpp10_set_register_bit(hidpp_dev, HIDPP_REG_FEATURES, 0, 6); } #define HIDPP_REG_BATTERY_STATUS 0x07 @@ -1137,6 +1248,99 @@ static int hidpp_battery_get_property(struct power_supply *psy, } /* -------------------------------------------------------------------------- */ +/* 0x2120: Hi-resolution scrolling */ +/* -------------------------------------------------------------------------- */ + +#define HIDPP_PAGE_HI_RESOLUTION_SCROLLING 0x2120 + +#define CMD_HI_RESOLUTION_SCROLLING_SET_HIGHRES_SCROLLING_MODE 0x10 + +static int hidpp_hrs_set_highres_scrolling_mode(struct hidpp_device *hidpp, + bool enabled, u8 *multiplier) +{ + u8 feature_index; + u8 feature_type; + int ret; + u8 params[1]; + struct hidpp_report response; + + ret = hidpp_root_get_feature(hidpp, + HIDPP_PAGE_HI_RESOLUTION_SCROLLING, + &feature_index, + &feature_type); + if (ret) + return ret; + + params[0] = enabled ? BIT(0) : 0; + ret = hidpp_send_fap_command_sync(hidpp, feature_index, + CMD_HI_RESOLUTION_SCROLLING_SET_HIGHRES_SCROLLING_MODE, + params, sizeof(params), &response); + if (ret) + return ret; + *multiplier = response.fap.params[1]; + return 0; +} + +/* -------------------------------------------------------------------------- */ +/* 0x2121: HiRes Wheel */ +/* -------------------------------------------------------------------------- */ + +#define HIDPP_PAGE_HIRES_WHEEL 0x2121 + +#define CMD_HIRES_WHEEL_GET_WHEEL_CAPABILITY 0x00 +#define CMD_HIRES_WHEEL_SET_WHEEL_MODE 0x20 + +static int hidpp_hrw_get_wheel_capability(struct hidpp_device *hidpp, + u8 *multiplier) +{ + u8 feature_index; + u8 feature_type; + int ret; + struct hidpp_report response; + + ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_HIRES_WHEEL, + &feature_index, &feature_type); + if (ret) + goto return_default; + + ret = hidpp_send_fap_command_sync(hidpp, feature_index, + CMD_HIRES_WHEEL_GET_WHEEL_CAPABILITY, + NULL, 0, &response); + if (ret) + goto return_default; + + *multiplier = response.fap.params[0]; + return 0; +return_default: + hid_warn(hidpp->hid_dev, + "Couldn't get wheel multiplier (error %d)\n", ret); + return ret; +} + +static int hidpp_hrw_set_wheel_mode(struct hidpp_device *hidpp, bool invert, + bool high_resolution, bool use_hidpp) +{ + u8 feature_index; + u8 feature_type; + int ret; + u8 params[1]; + struct hidpp_report response; + + ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_HIRES_WHEEL, + &feature_index, &feature_type); + if (ret) + return ret; + + params[0] = (invert ? BIT(2) : 0) | + (high_resolution ? BIT(1) : 0) | + (use_hidpp ? BIT(0) : 0); + + return hidpp_send_fap_command_sync(hidpp, feature_index, + CMD_HIRES_WHEEL_SET_WHEEL_MODE, + params, sizeof(params), &response); +} + +/* -------------------------------------------------------------------------- */ /* 0x4301: Solar Keyboard */ /* -------------------------------------------------------------------------- */ @@ -1465,7 +1669,7 @@ struct hidpp_ff_work_data { u8 size; }; -static const signed short hiddpp_ff_effects[] = { +static const signed short hidpp_ff_effects[] = { FF_CONSTANT, FF_PERIODIC, FF_SINE, @@ -1480,7 +1684,7 @@ static const signed short hiddpp_ff_effects[] = { -1 }; -static const signed short hiddpp_ff_effects_v2[] = { +static const signed short hidpp_ff_effects_v2[] = { FF_RAMP, FF_FRICTION, FF_INERTIA, @@ -1873,11 +2077,11 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) version = bcdDevice & 255; /* Set supported force feedback capabilities */ - for (j = 0; hiddpp_ff_effects[j] >= 0; j++) - set_bit(hiddpp_ff_effects[j], dev->ffbit); + for (j = 0; hidpp_ff_effects[j] >= 0; j++) + set_bit(hidpp_ff_effects[j], dev->ffbit); if (version > 1) - for (j = 0; hiddpp_ff_effects_v2[j] >= 0; j++) - set_bit(hiddpp_ff_effects_v2[j], dev->ffbit); + for (j = 0; hidpp_ff_effects_v2[j] >= 0; j++) + set_bit(hidpp_ff_effects_v2[j], dev->ffbit); /* Read number of slots available in device */ error = hidpp_send_fap_command_sync(hidpp, feature_index, @@ -2387,10 +2591,15 @@ static int m560_raw_event(struct hid_device *hdev, u8 *data, int size) input_report_key(mydata->input, BTN_RIGHT, !!(data[1] & M560_MOUSE_BTN_RIGHT)); - if (data[1] & M560_MOUSE_BTN_WHEEL_LEFT) + if (data[1] & M560_MOUSE_BTN_WHEEL_LEFT) { input_report_rel(mydata->input, REL_HWHEEL, -1); - else if (data[1] & M560_MOUSE_BTN_WHEEL_RIGHT) + input_report_rel(mydata->input, REL_HWHEEL_HI_RES, + -120); + } else if (data[1] & M560_MOUSE_BTN_WHEEL_RIGHT) { input_report_rel(mydata->input, REL_HWHEEL, 1); + input_report_rel(mydata->input, REL_HWHEEL_HI_RES, + 120); + } v = hid_snto32(hid_field_extract(hdev, data+3, 0, 12), 12); input_report_rel(mydata->input, REL_X, v); @@ -2399,7 +2608,8 @@ static int m560_raw_event(struct hid_device *hdev, u8 *data, int size) input_report_rel(mydata->input, REL_Y, v); v = hid_snto32(data[6], 8); - input_report_rel(mydata->input, REL_WHEEL, v); + hidpp_scroll_counter_handle_scroll( + &hidpp->vertical_wheel_counter, v); input_sync(mydata->input); } @@ -2426,6 +2636,8 @@ static void m560_populate_input(struct hidpp_device *hidpp, __set_bit(REL_Y, mydata->input->relbit); __set_bit(REL_WHEEL, mydata->input->relbit); __set_bit(REL_HWHEEL, mydata->input->relbit); + __set_bit(REL_WHEEL_HI_RES, mydata->input->relbit); + __set_bit(REL_HWHEEL_HI_RES, mydata->input->relbit); } static int m560_input_mapping(struct hid_device *hdev, struct hid_input *hi, @@ -2528,6 +2740,37 @@ static int g920_get_config(struct hidpp_device *hidpp) } /* -------------------------------------------------------------------------- */ +/* High-resolution scroll wheels */ +/* -------------------------------------------------------------------------- */ + +static int hi_res_scroll_enable(struct hidpp_device *hidpp) +{ + int ret; + u8 multiplier = 1; + + if (hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL_X2121) { + ret = hidpp_hrw_set_wheel_mode(hidpp, false, true, false); + if (ret == 0) + ret = hidpp_hrw_get_wheel_capability(hidpp, &multiplier); + } else if (hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL_X2120) { + ret = hidpp_hrs_set_highres_scrolling_mode(hidpp, true, + &multiplier); + } else /* if (hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL_1P0) */ { + ret = hidpp10_enable_scrolling_acceleration(hidpp); + multiplier = 8; + } + if (ret) + return ret; + + if (multiplier == 0) + multiplier = 1; + + hidpp->vertical_wheel_counter.wheel_multiplier = multiplier; + hid_info(hidpp->hid_dev, "multiplier = %d\n", multiplier); + return 0; +} + +/* -------------------------------------------------------------------------- */ /* Generic HID++ devices */ /* -------------------------------------------------------------------------- */ @@ -2572,6 +2815,9 @@ static void hidpp_populate_input(struct hidpp_device *hidpp, wtp_populate_input(hidpp, input, origin_is_hid_core); else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560) m560_populate_input(hidpp, input, origin_is_hid_core); + + if (hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL) + hidpp->vertical_wheel_counter.dev = input; } static int hidpp_input_configured(struct hid_device *hdev, @@ -2690,6 +2936,27 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report, return 0; } +static int hidpp_event(struct hid_device *hdev, struct hid_field *field, + struct hid_usage *usage, __s32 value) +{ + /* This function will only be called for scroll events, due to the + * restriction imposed in hidpp_usages. + */ + struct hidpp_device *hidpp = hid_get_drvdata(hdev); + struct hidpp_scroll_counter *counter = &hidpp->vertical_wheel_counter; + /* A scroll event may occur before the multiplier has been retrieved or + * the input device set, or high-res scroll enabling may fail. In such + * cases we must return early (falling back to default behaviour) to + * avoid a crash in hidpp_scroll_counter_handle_scroll. + */ + if (!(hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL) || value == 0 + || counter->dev == NULL || counter->wheel_multiplier == 0) + return 0; + + hidpp_scroll_counter_handle_scroll(counter, value); + return 1; +} + static int hidpp_initialize_battery(struct hidpp_device *hidpp) { static atomic_t battery_no = ATOMIC_INIT(0); @@ -2901,6 +3168,9 @@ static void hidpp_connect_event(struct hidpp_device *hidpp) if (hidpp->battery.ps) power_supply_changed(hidpp->battery.ps); + if (hidpp->quirks & HIDPP_QUIRK_HI_RES_SCROLL) + hi_res_scroll_enable(hidpp); + if (!(hidpp->quirks & HIDPP_QUIRK_NO_HIDINPUT) || hidpp->delayed_input) /* if the input nodes are already created, we can stop now */ return; @@ -3086,35 +3356,63 @@ static void hidpp_remove(struct hid_device *hdev) mutex_destroy(&hidpp->send_mutex); } +#define LDJ_DEVICE(product) \ + HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, \ + USB_VENDOR_ID_LOGITECH, (product)) + static const struct hid_device_id hidpp_devices[] = { { /* wireless touchpad */ - HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, 0x4011), + LDJ_DEVICE(0x4011), .driver_data = HIDPP_QUIRK_CLASS_WTP | HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS }, { /* wireless touchpad T650 */ - HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, 0x4101), + LDJ_DEVICE(0x4101), .driver_data = HIDPP_QUIRK_CLASS_WTP | HIDPP_QUIRK_DELAYED_INIT }, { /* wireless touchpad T651 */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_T651), .driver_data = HIDPP_QUIRK_CLASS_WTP }, + { /* Mouse Logitech Anywhere MX */ + LDJ_DEVICE(0x1017), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_1P0 }, + { /* Mouse Logitech Cube */ + LDJ_DEVICE(0x4010), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2120 }, + { /* Mouse Logitech M335 */ + LDJ_DEVICE(0x4050), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech M515 */ + LDJ_DEVICE(0x4007), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2120 }, { /* Mouse logitech M560 */ - HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, 0x402d), - .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_CLASS_M560 }, + LDJ_DEVICE(0x402d), + .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_CLASS_M560 + | HIDPP_QUIRK_HI_RES_SCROLL_X2120 }, + { /* Mouse Logitech M705 (firmware RQM17) */ + LDJ_DEVICE(0x101b), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_1P0 }, + { /* Mouse Logitech M705 (firmware RQM67) */ + LDJ_DEVICE(0x406d), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech M720 */ + LDJ_DEVICE(0x405e), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech MX Anywhere 2 */ + LDJ_DEVICE(0x404a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0xb013), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0xb018), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0xb01f), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech MX Anywhere 2S */ + LDJ_DEVICE(0x406a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech MX Master */ + LDJ_DEVICE(0x4041), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0x4060), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { LDJ_DEVICE(0x4071), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech MX Master 2S */ + LDJ_DEVICE(0x4069), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 }, + { /* Mouse Logitech Performance MX */ + LDJ_DEVICE(0x101a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_1P0 }, { /* Keyboard logitech K400 */ - HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, 0x4024), + LDJ_DEVICE(0x4024), .driver_data = HIDPP_QUIRK_CLASS_K400 }, { /* Solar Keyboard Logitech K750 */ - HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, 0x4002), + LDJ_DEVICE(0x4002), .driver_data = HIDPP_QUIRK_CLASS_K750 }, - { HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, - USB_VENDOR_ID_LOGITECH, HID_ANY_ID)}, + { LDJ_DEVICE(HID_ANY_ID) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, @@ -3123,12 +3421,19 @@ static const struct hid_device_id hidpp_devices[] = { MODULE_DEVICE_TABLE(hid, hidpp_devices); +static const struct hid_usage_id hidpp_usages[] = { + { HID_GD_WHEEL, EV_REL, REL_WHEEL_HI_RES }, + { HID_ANY_ID - 1, HID_ANY_ID - 1, HID_ANY_ID - 1} +}; + static struct hid_driver hidpp_driver = { .name = "logitech-hidpp-device", .id_table = hidpp_devices, .probe = hidpp_probe, .remove = hidpp_remove, .raw_event = hidpp_raw_event, + .usage_table = hidpp_usages, + .event = hidpp_event, .input_configured = hidpp_input_configured, .input_mapping = hidpp_input_mapping, .input_mapped = hidpp_input_mapped, diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 4a44e48e08b2..9fc51eff1079 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -107,8 +107,6 @@ out: /* * The first byte of the report buffer is expected to be a report number. - * - * This function is to be called with the minors_lock mutex held. */ static ssize_t hidraw_send_report(struct file *file, const char __user *buffer, size_t count, unsigned char report_type) { @@ -117,6 +115,8 @@ static ssize_t hidraw_send_report(struct file *file, const char __user *buffer, __u8 *buf; int ret = 0; + lockdep_assert_held(&minors_lock); + if (!hidraw_table[minor] || !hidraw_table[minor]->exist) { ret = -ENODEV; goto out; @@ -181,8 +181,6 @@ static ssize_t hidraw_write(struct file *file, const char __user *buffer, size_t * of buffer is the report number to request, or 0x0 if the defice does not * use numbered reports. The report_type parameter can be HID_FEATURE_REPORT * or HID_INPUT_REPORT. - * - * This function is to be called with the minors_lock mutex held. */ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t count, unsigned char report_type) { @@ -192,6 +190,8 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t int ret = 0, len; unsigned char report_number; + lockdep_assert_held(&minors_lock); + if (!hidraw_table[minor] || !hidraw_table[minor]->exist) { ret = -ENODEV; goto out; diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index 89f2976f9c53..fd1b6eea6d2f 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -346,6 +346,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { }, .driver_data = (void *)&sipodev_desc }, + { + .ident = "Odys Winbook 13", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AXDIA International GmbH"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "WINBOOK 13"), + }, + .driver_data = (void *)&sipodev_desc + }, { } /* Terminate list */ }; diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 8793cc49f855..a6e1ee744f4d 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -117,6 +117,7 @@ static int ish_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int ret; struct ish_hw *hw; + unsigned long irq_flag = 0; struct ishtp_device *ishtp; struct device *dev = &pdev->dev; @@ -156,8 +157,12 @@ static int ish_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3; /* request and enable interrupt */ + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (!pdev->msi_enabled && !pdev->msix_enabled) + irq_flag = IRQF_SHARED; + ret = devm_request_irq(dev, pdev->irq, ish_irq_handler, - IRQF_SHARED, KBUILD_MODNAME, ishtp); + irq_flag, KBUILD_MODNAME, ishtp); if (ret) { dev_err(dev, "ISH: request IRQ %d failed\n", pdev->irq); return ret; diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c index cd23903ddcf1..e918d78e541c 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid.c @@ -222,7 +222,7 @@ int ishtp_hid_probe(unsigned int cur_hid_dev, err_hid_device: kfree(hid_data); err_hid_data: - kfree(hid); + hid_destroy_device(hid); return rv; } diff --git a/drivers/hwspinlock/Kconfig b/drivers/hwspinlock/Kconfig index e895d29500ee..7869c67e5b6b 100644 --- a/drivers/hwspinlock/Kconfig +++ b/drivers/hwspinlock/Kconfig @@ -49,6 +49,15 @@ config HWSPINLOCK_SPRD If unsure, say N. +config HWSPINLOCK_STM32 + tristate "STM32 Hardware Spinlock device" + depends on MACH_STM32MP157 + depends on HWSPINLOCK + help + Say y here to support the STM32 Hardware Spinlock device. + + If unsure, say N. + config HSEM_U8500 tristate "STE Hardware Semaphore functionality" depends on HWSPINLOCK diff --git a/drivers/hwspinlock/Makefile b/drivers/hwspinlock/Makefile index b87c01a506a4..ed053e3f02be 100644 --- a/drivers/hwspinlock/Makefile +++ b/drivers/hwspinlock/Makefile @@ -8,4 +8,5 @@ obj-$(CONFIG_HWSPINLOCK_OMAP) += omap_hwspinlock.o obj-$(CONFIG_HWSPINLOCK_QCOM) += qcom_hwspinlock.o obj-$(CONFIG_HWSPINLOCK_SIRF) += sirf_hwspinlock.o obj-$(CONFIG_HWSPINLOCK_SPRD) += sprd_hwspinlock.o +obj-$(CONFIG_HWSPINLOCK_STM32) += stm32_hwspinlock.o obj-$(CONFIG_HSEM_U8500) += u8500_hsem.o diff --git a/drivers/hwspinlock/stm32_hwspinlock.c b/drivers/hwspinlock/stm32_hwspinlock.c new file mode 100644 index 000000000000..441839288893 --- /dev/null +++ b/drivers/hwspinlock/stm32_hwspinlock.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) STMicroelectronics SA 2018 + * Author: Benjamin Gaignard <benjamin.gaignard@st.com> for STMicroelectronics. + */ + +#include <linux/clk.h> +#include <linux/hwspinlock.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "hwspinlock_internal.h" + +#define STM32_MUTEX_COREID BIT(8) +#define STM32_MUTEX_LOCK_BIT BIT(31) +#define STM32_MUTEX_NUM_LOCKS 32 + +struct stm32_hwspinlock { + struct clk *clk; + struct hwspinlock_device bank; +}; + +static int stm32_hwspinlock_trylock(struct hwspinlock *lock) +{ + void __iomem *lock_addr = lock->priv; + u32 status; + + writel(STM32_MUTEX_LOCK_BIT | STM32_MUTEX_COREID, lock_addr); + status = readl(lock_addr); + + return status == (STM32_MUTEX_LOCK_BIT | STM32_MUTEX_COREID); +} + +static void stm32_hwspinlock_unlock(struct hwspinlock *lock) +{ + void __iomem *lock_addr = lock->priv; + + writel(STM32_MUTEX_COREID, lock_addr); +} + +static const struct hwspinlock_ops stm32_hwspinlock_ops = { + .trylock = stm32_hwspinlock_trylock, + .unlock = stm32_hwspinlock_unlock, +}; + +static int stm32_hwspinlock_probe(struct platform_device *pdev) +{ + struct stm32_hwspinlock *hw; + void __iomem *io_base; + struct resource *res; + size_t array_size; + int i, ret; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + io_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(io_base)) + return PTR_ERR(io_base); + + array_size = STM32_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock); + hw = devm_kzalloc(&pdev->dev, sizeof(*hw) + array_size, GFP_KERNEL); + if (!hw) + return -ENOMEM; + + hw->clk = devm_clk_get(&pdev->dev, "hsem"); + if (IS_ERR(hw->clk)) + return PTR_ERR(hw->clk); + + for (i = 0; i < STM32_MUTEX_NUM_LOCKS; i++) + hw->bank.lock[i].priv = io_base + i * sizeof(u32); + + platform_set_drvdata(pdev, hw); + pm_runtime_enable(&pdev->dev); + + ret = hwspin_lock_register(&hw->bank, &pdev->dev, &stm32_hwspinlock_ops, + 0, STM32_MUTEX_NUM_LOCKS); + + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static int stm32_hwspinlock_remove(struct platform_device *pdev) +{ + struct stm32_hwspinlock *hw = platform_get_drvdata(pdev); + int ret; + + ret = hwspin_lock_unregister(&hw->bank); + if (ret) + dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret); + + pm_runtime_disable(&pdev->dev); + + return 0; +} + +static int __maybe_unused stm32_hwspinlock_runtime_suspend(struct device *dev) +{ + struct stm32_hwspinlock *hw = dev_get_drvdata(dev); + + clk_disable_unprepare(hw->clk); + + return 0; +} + +static int __maybe_unused stm32_hwspinlock_runtime_resume(struct device *dev) +{ + struct stm32_hwspinlock *hw = dev_get_drvdata(dev); + + clk_prepare_enable(hw->clk); + + return 0; +} + +static const struct dev_pm_ops stm32_hwspinlock_pm_ops = { + SET_RUNTIME_PM_OPS(stm32_hwspinlock_runtime_suspend, + stm32_hwspinlock_runtime_resume, + NULL) +}; + +static const struct of_device_id stm32_hwpinlock_ids[] = { + { .compatible = "st,stm32-hwspinlock", }, + {}, +}; +MODULE_DEVICE_TABLE(of, stm32_hwpinlock_ids); + +static struct platform_driver stm32_hwspinlock_driver = { + .probe = stm32_hwspinlock_probe, + .remove = stm32_hwspinlock_remove, + .driver = { + .name = "stm32_hwspinlock", + .of_match_table = stm32_hwpinlock_ids, + .pm = &stm32_hwspinlock_pm_ops, + }, +}; + +static int __init stm32_hwspinlock_init(void) +{ + return platform_driver_register(&stm32_hwspinlock_driver); +} +/* board init code might need to reserve hwspinlocks for predefined purposes */ +postcore_initcall(stm32_hwspinlock_init); + +static void __exit stm32_hwspinlock_exit(void) +{ + platform_driver_unregister(&stm32_hwspinlock_driver); +} +module_exit(stm32_hwspinlock_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Hardware spinlock driver for STM32 SoCs"); +MODULE_AUTHOR("Benjamin Gaignard <benjamin.gaignard@st.com>"); diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c index 51d34959709b..bf564391091f 100644 --- a/drivers/i2c/busses/i2c-axxia.c +++ b/drivers/i2c/busses/i2c-axxia.c @@ -12,6 +12,7 @@ */ #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/delay.h> #include <linux/err.h> #include <linux/i2c.h> #include <linux/init.h> @@ -25,6 +26,7 @@ #define I2C_XFER_TIMEOUT (msecs_to_jiffies(250)) #define I2C_STOP_TIMEOUT (msecs_to_jiffies(100)) #define FIFO_SIZE 8 +#define SEQ_LEN 2 #define GLOBAL_CONTROL 0x00 #define GLOBAL_MST_EN BIT(0) @@ -51,6 +53,7 @@ #define CMD_BUSY (1<<3) #define CMD_MANUAL (0x00 | CMD_BUSY) #define CMD_AUTO (0x01 | CMD_BUSY) +#define CMD_SEQUENCE (0x02 | CMD_BUSY) #define MST_RX_XFER 0x2c #define MST_TX_XFER 0x30 #define MST_ADDR_1 0x34 @@ -87,7 +90,9 @@ * axxia_i2c_dev - I2C device context * @base: pointer to register struct * @msg: pointer to current message - * @msg_xfrd: number of bytes transferred in msg + * @msg_r: pointer to current read message (sequence transfer) + * @msg_xfrd: number of bytes transferred in tx_fifo + * @msg_xfrd_r: number of bytes transferred in rx_fifo * @msg_err: error code for completed message * @msg_complete: xfer completion object * @dev: device reference @@ -98,7 +103,9 @@ struct axxia_i2c_dev { void __iomem *base; struct i2c_msg *msg; + struct i2c_msg *msg_r; size_t msg_xfrd; + size_t msg_xfrd_r; int msg_err; struct completion msg_complete; struct device *dev; @@ -227,14 +234,14 @@ static int i2c_m_recv_len(const struct i2c_msg *msg) */ static int axxia_i2c_empty_rx_fifo(struct axxia_i2c_dev *idev) { - struct i2c_msg *msg = idev->msg; + struct i2c_msg *msg = idev->msg_r; size_t rx_fifo_avail = readl(idev->base + MST_RX_FIFO); - int bytes_to_transfer = min(rx_fifo_avail, msg->len - idev->msg_xfrd); + int bytes_to_transfer = min(rx_fifo_avail, msg->len - idev->msg_xfrd_r); while (bytes_to_transfer-- > 0) { int c = readl(idev->base + MST_DATA); - if (idev->msg_xfrd == 0 && i2c_m_recv_len(msg)) { + if (idev->msg_xfrd_r == 0 && i2c_m_recv_len(msg)) { /* * Check length byte for SMBus block read */ @@ -247,7 +254,7 @@ static int axxia_i2c_empty_rx_fifo(struct axxia_i2c_dev *idev) msg->len = 1 + c; writel(msg->len, idev->base + MST_RX_XFER); } - msg->buf[idev->msg_xfrd++] = c; + msg->buf[idev->msg_xfrd_r++] = c; } return 0; @@ -287,7 +294,7 @@ static irqreturn_t axxia_i2c_isr(int irq, void *_dev) } /* RX FIFO needs service? */ - if (i2c_m_rd(idev->msg) && (status & MST_STATUS_RFL)) + if (i2c_m_rd(idev->msg_r) && (status & MST_STATUS_RFL)) axxia_i2c_empty_rx_fifo(idev); /* TX FIFO needs service? */ @@ -296,22 +303,7 @@ static irqreturn_t axxia_i2c_isr(int irq, void *_dev) i2c_int_disable(idev, MST_STATUS_TFL); } - if (status & MST_STATUS_SCC) { - /* Stop completed */ - i2c_int_disable(idev, ~MST_STATUS_TSS); - complete(&idev->msg_complete); - } else if (status & MST_STATUS_SNS) { - /* Transfer done */ - i2c_int_disable(idev, ~MST_STATUS_TSS); - if (i2c_m_rd(idev->msg) && idev->msg_xfrd < idev->msg->len) - axxia_i2c_empty_rx_fifo(idev); - complete(&idev->msg_complete); - } else if (status & MST_STATUS_TSS) { - /* Transfer timeout */ - idev->msg_err = -ETIMEDOUT; - i2c_int_disable(idev, ~MST_STATUS_TSS); - complete(&idev->msg_complete); - } else if (unlikely(status & MST_STATUS_ERR)) { + if (unlikely(status & MST_STATUS_ERR)) { /* Transfer error */ i2c_int_disable(idev, ~0); if (status & MST_STATUS_AL) @@ -328,6 +320,24 @@ static irqreturn_t axxia_i2c_isr(int irq, void *_dev) readl(idev->base + MST_TX_BYTES_XFRD), readl(idev->base + MST_TX_XFER)); complete(&idev->msg_complete); + } else if (status & MST_STATUS_SCC) { + /* Stop completed */ + i2c_int_disable(idev, ~MST_STATUS_TSS); + complete(&idev->msg_complete); + } else if (status & MST_STATUS_SNS) { + /* Transfer done */ + i2c_int_disable(idev, ~MST_STATUS_TSS); + if (i2c_m_rd(idev->msg_r) && idev->msg_xfrd_r < idev->msg_r->len) + axxia_i2c_empty_rx_fifo(idev); + complete(&idev->msg_complete); + } else if (status & MST_STATUS_SS) { + /* Auto/Sequence transfer done */ + complete(&idev->msg_complete); + } else if (status & MST_STATUS_TSS) { + /* Transfer timeout */ + idev->msg_err = -ETIMEDOUT; + i2c_int_disable(idev, ~MST_STATUS_TSS); + complete(&idev->msg_complete); } out: @@ -337,17 +347,9 @@ out: return IRQ_HANDLED; } -static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg) +static void axxia_i2c_set_addr(struct axxia_i2c_dev *idev, struct i2c_msg *msg) { - u32 int_mask = MST_STATUS_ERR | MST_STATUS_SNS; - u32 rx_xfer, tx_xfer; u32 addr_1, addr_2; - unsigned long time_left; - unsigned int wt_value; - - idev->msg = msg; - idev->msg_xfrd = 0; - reinit_completion(&idev->msg_complete); if (i2c_m_ten(msg)) { /* 10-bit address @@ -367,6 +369,90 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg) addr_2 = 0; } + writel(addr_1, idev->base + MST_ADDR_1); + writel(addr_2, idev->base + MST_ADDR_2); +} + +/* The NAK interrupt will be sent _before_ issuing STOP command + * so the controller might still be busy processing it. No + * interrupt will be sent at the end so we have to poll for it + */ +static int axxia_i2c_handle_seq_nak(struct axxia_i2c_dev *idev) +{ + unsigned long timeout = jiffies + I2C_XFER_TIMEOUT; + + do { + if ((readl(idev->base + MST_COMMAND) & CMD_BUSY) == 0) + return 0; + usleep_range(1, 100); + } while (time_before(jiffies, timeout)); + + return -ETIMEDOUT; +} + +static int axxia_i2c_xfer_seq(struct axxia_i2c_dev *idev, struct i2c_msg msgs[]) +{ + u32 int_mask = MST_STATUS_ERR | MST_STATUS_SS | MST_STATUS_RFL; + u32 rlen = i2c_m_recv_len(&msgs[1]) ? I2C_SMBUS_BLOCK_MAX : msgs[1].len; + unsigned long time_left; + + axxia_i2c_set_addr(idev, &msgs[0]); + + writel(msgs[0].len, idev->base + MST_TX_XFER); + writel(rlen, idev->base + MST_RX_XFER); + + idev->msg = &msgs[0]; + idev->msg_r = &msgs[1]; + idev->msg_xfrd = 0; + idev->msg_xfrd_r = 0; + axxia_i2c_fill_tx_fifo(idev); + + writel(CMD_SEQUENCE, idev->base + MST_COMMAND); + + reinit_completion(&idev->msg_complete); + i2c_int_enable(idev, int_mask); + + time_left = wait_for_completion_timeout(&idev->msg_complete, + I2C_XFER_TIMEOUT); + + i2c_int_disable(idev, int_mask); + + axxia_i2c_empty_rx_fifo(idev); + + if (idev->msg_err == -ENXIO) { + if (axxia_i2c_handle_seq_nak(idev)) + axxia_i2c_init(idev); + } else if (readl(idev->base + MST_COMMAND) & CMD_BUSY) { + dev_warn(idev->dev, "busy after xfer\n"); + } + + if (time_left == 0) { + idev->msg_err = -ETIMEDOUT; + i2c_recover_bus(&idev->adapter); + axxia_i2c_init(idev); + } + + if (unlikely(idev->msg_err) && idev->msg_err != -ENXIO) + axxia_i2c_init(idev); + + return idev->msg_err; +} + +static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg) +{ + u32 int_mask = MST_STATUS_ERR | MST_STATUS_SNS; + u32 rx_xfer, tx_xfer; + unsigned long time_left; + unsigned int wt_value; + + idev->msg = msg; + idev->msg_r = msg; + idev->msg_xfrd = 0; + idev->msg_xfrd_r = 0; + reinit_completion(&idev->msg_complete); + + axxia_i2c_set_addr(idev, msg); + if (i2c_m_rd(msg)) { /* I2C read transfer */ rx_xfer = i2c_m_recv_len(msg) ? I2C_SMBUS_BLOCK_MAX : msg->len; @@ -379,8 +465,6 @@ static int axxia_i2c_xfer_msg(struct axxia_i2c_dev *idev, struct i2c_msg *msg) writel(rx_xfer, idev->base + MST_RX_XFER); writel(tx_xfer, idev->base + MST_TX_XFER); - writel(addr_1, idev->base + MST_ADDR_1); - writel(addr_2, idev->base + MST_ADDR_2); if (i2c_m_rd(msg)) int_mask |= MST_STATUS_RFL; @@ -445,6 +529,18 @@ static int axxia_i2c_stop(struct axxia_i2c_dev *idev) return 0; } +/* This function checks if the msgs[] array contains messages compatible with + * Sequence mode of operation. This mode assumes there will be exactly one + * write of non-zero length followed by exactly one read of non-zero length, + * both targeted at the same client device. + */ +static bool axxia_i2c_sequence_ok(struct i2c_msg msgs[], int num) +{ + return num == SEQ_LEN && !i2c_m_rd(&msgs[0]) && i2c_m_rd(&msgs[1]) && + msgs[0].len > 0 && msgs[0].len <= FIFO_SIZE && + msgs[1].len > 0 && msgs[0].addr == msgs[1].addr; +} + static int axxia_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) { @@ -453,6 +549,12 @@ axxia_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) int ret = 0; idev->msg_err = 0; + + if (axxia_i2c_sequence_ok(msgs, num)) { + ret = axxia_i2c_xfer_seq(idev, msgs); + return ret ? : SEQ_LEN; + } + i2c_int_enable(idev, MST_STATUS_TSS); for (i = 0; ret == 0 && i < num; ++i) diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index 44deae78913e..ec6e69aa3a8e 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * BCM2835 master mode driver - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <linux/clk.h> diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c index eb76b76f4754..82bcd9a78759 100644 --- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c +++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c @@ -1,13 +1,7 @@ -/* - * Copyright (C) 2013 Google, Inc - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * Expose an I2C passthrough to the ChromeOS EC. - */ +// SPDX-License-Identifier: GPL-2.0+ +// Expose an I2C passthrough to the ChromeOS EC. +// +// Copyright (C) 2013 Google, Inc. #include <linux/module.h> #include <linux/i2c.h> diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c index 6f6e1dfe7cce..d78023d42a35 100644 --- a/drivers/i2c/busses/i2c-ibm_iic.c +++ b/drivers/i2c/busses/i2c-ibm_iic.c @@ -437,7 +437,7 @@ static int iic_wait_for_tc(struct ibm_iic_private* dev){ break; } - if (unlikely(signal_pending(current))){ + if (signal_pending(current)){ DBG("%d: poll interrupted\n", dev->idx); ret = -ERESTARTSYS; break; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index c406700789e1..fa9ad53845d9 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1090,7 +1090,8 @@ static int i2c_imx_probe(struct platform_device *pdev) /* Get I2C clock */ i2c_imx->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(i2c_imx->clk)) { - dev_err(&pdev->dev, "can't get I2C clock\n"); + if (PTR_ERR(i2c_imx->clk) != -EPROBE_DEFER) + dev_err(&pdev->dev, "can't get I2C clock\n"); return PTR_ERR(i2c_imx->clk); } diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 0d1c3ec8cb40..02d23edb2fb1 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -75,6 +75,7 @@ /* PCI DIDs for the Intel SMBus Message Transport (SMT) Devices */ #define PCI_DEVICE_ID_INTEL_S1200_SMT0 0x0c59 #define PCI_DEVICE_ID_INTEL_S1200_SMT1 0x0c5a +#define PCI_DEVICE_ID_INTEL_CDF_SMT 0x18ac #define PCI_DEVICE_ID_INTEL_DNV_SMT 0x19ac #define PCI_DEVICE_ID_INTEL_AVOTON_SMT 0x1f15 @@ -181,6 +182,7 @@ struct ismt_priv { static const struct pci_device_id ismt_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT0) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT1) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AVOTON_SMT) }, { 0, } diff --git a/drivers/i2c/busses/i2c-owl.c b/drivers/i2c/busses/i2c-owl.c index 96b4572e6d9c..b6b5a495118b 100644 --- a/drivers/i2c/busses/i2c-owl.c +++ b/drivers/i2c/busses/i2c-owl.c @@ -475,6 +475,7 @@ disable_clk: } static const struct of_device_id owl_i2c_of_match[] = { + { .compatible = "actions,s700-i2c" }, { .compatible = "actions,s900-i2c" }, { /* sentinel */ } }; diff --git a/drivers/i2c/busses/i2c-powermac.c b/drivers/i2c/busses/i2c-powermac.c index f6f4ed8afc93..281113c28314 100644 --- a/drivers/i2c/busses/i2c-powermac.c +++ b/drivers/i2c/busses/i2c-powermac.c @@ -229,9 +229,9 @@ static u32 i2c_powermac_get_addr(struct i2c_adapter *adap, return (be32_to_cpup(prop) & 0xff) >> 1; /* Now handle some devices with missing "reg" properties */ - if (!strcmp(node->name, "cereal")) + if (of_node_name_eq(node, "cereal")) return 0x60; - else if (!strcmp(node->name, "deq")) + else if (of_node_name_eq(node, "deq")) return 0x34; dev_warn(&adap->dev, "No i2c address for %pOF\n", node); @@ -304,7 +304,7 @@ static bool i2c_powermac_get_type(struct i2c_adapter *adap, } /* Now look for known workarounds */ - if (!strcmp(node->name, "deq")) { + if (of_node_name_eq(node, "deq")) { /* Apple uses address 0x34 for TAS3001 and 0x35 for TAS3004 */ if (addr == 0x34) { snprintf(type, type_size, "MAC,tas3001"); @@ -331,7 +331,7 @@ static void i2c_powermac_register_devices(struct i2c_adapter *adap, * case we skip this function completely as the device-tree will * not contain anything useful. */ - if (!strcmp(adap->dev.of_node->name, "via-pmu")) + if (of_node_name_eq(adap->dev.of_node, "via-pmu")) return; for_each_child_of_node(adap->dev.of_node, node) { diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index a7a7a9c3bc7c..a64f2ff3cb49 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -800,6 +800,7 @@ static const struct sh_mobile_dt_config r8a7740_dt_config = { static const struct of_device_id sh_mobile_i2c_dt_ids[] = { { .compatible = "renesas,iic-r8a73a4", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7740", .data = &r8a7740_dt_config }, + { .compatible = "renesas,iic-r8a774c0", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7790", .data = &v2_freq_calc_dt_config }, { .compatible = "renesas,iic-r8a7791", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7792", .data = &fast_clock_dt_config }, @@ -808,6 +809,7 @@ static const struct of_device_id sh_mobile_i2c_dt_ids[] = { { .compatible = "renesas,rcar-gen2-iic", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-r8a7795", .data = &fast_clock_dt_config }, { .compatible = "renesas,rcar-gen3-iic", .data = &fast_clock_dt_config }, + { .compatible = "renesas,iic-r8a77990", .data = &fast_clock_dt_config }, { .compatible = "renesas,iic-sh73a0", .data = &fast_clock_dt_config }, { .compatible = "renesas,rmobile-iic", .data = &default_dt_config }, {}, diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 62d023e737d9..13e1213561d4 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -21,12 +21,16 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/pinctrl/consumer.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> #include <linux/reset.h> #include <linux/slab.h> @@ -163,6 +167,8 @@ #define STM32F7_SCLH_MAX BIT(8) #define STM32F7_SCLL_MAX BIT(8) +#define STM32F7_AUTOSUSPEND_DELAY (HZ / 100) + /** * struct stm32f7_i2c_spec - private i2c specification timing * @rate: I2C bus speed (Hz) @@ -276,6 +282,7 @@ struct stm32f7_i2c_msg { * slave) * @dma: dma data * @use_dma: boolean to know if dma is used in the current transfer + * @regmap: holds SYSCFG phandle for Fast Mode Plus bits */ struct stm32f7_i2c_dev { struct i2c_adapter adap; @@ -296,6 +303,7 @@ struct stm32f7_i2c_dev { bool master_mode; struct stm32_i2c_dma *dma; bool use_dma; + struct regmap *regmap; }; /** @@ -1545,15 +1553,13 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap, i2c_dev->msg_id = 0; f7_msg->smbus = false; - ret = clk_enable(i2c_dev->clk); - if (ret) { - dev_err(i2c_dev->dev, "Failed to enable clock\n"); + ret = pm_runtime_get_sync(i2c_dev->dev); + if (ret < 0) return ret; - } ret = stm32f7_i2c_wait_free_bus(i2c_dev); if (ret) - goto clk_free; + goto pm_free; stm32f7_i2c_xfer_msg(i2c_dev, msgs); @@ -1569,8 +1575,9 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap, ret = -ETIMEDOUT; } -clk_free: - clk_disable(i2c_dev->clk); +pm_free: + pm_runtime_mark_last_busy(i2c_dev->dev); + pm_runtime_put_autosuspend(i2c_dev->dev); return (ret < 0) ? ret : num; } @@ -1592,39 +1599,37 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, f7_msg->read_write = read_write; f7_msg->smbus = true; - ret = clk_enable(i2c_dev->clk); - if (ret) { - dev_err(i2c_dev->dev, "Failed to enable clock\n"); + ret = pm_runtime_get_sync(dev); + if (ret < 0) return ret; - } ret = stm32f7_i2c_wait_free_bus(i2c_dev); if (ret) - goto clk_free; + goto pm_free; ret = stm32f7_i2c_smbus_xfer_msg(i2c_dev, flags, command, data); if (ret) - goto clk_free; + goto pm_free; timeout = wait_for_completion_timeout(&i2c_dev->complete, i2c_dev->adap.timeout); ret = f7_msg->result; if (ret) - goto clk_free; + goto pm_free; if (!timeout) { dev_dbg(dev, "Access to slave 0x%x timed out\n", f7_msg->addr); if (i2c_dev->use_dma) dmaengine_terminate_all(dma->chan_using); ret = -ETIMEDOUT; - goto clk_free; + goto pm_free; } /* Check PEC */ if ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && read_write) { ret = stm32f7_i2c_smbus_check_pec(i2c_dev); if (ret) - goto clk_free; + goto pm_free; } if (read_write && size != I2C_SMBUS_QUICK) { @@ -1649,8 +1654,9 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, } } -clk_free: - clk_disable(i2c_dev->clk); +pm_free: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); return ret; } @@ -1676,13 +1682,9 @@ static int stm32f7_i2c_reg_slave(struct i2c_client *slave) if (ret) return ret; - if (!(stm32f7_i2c_is_slave_registered(i2c_dev))) { - ret = clk_enable(i2c_dev->clk); - if (ret) { - dev_err(dev, "Failed to enable clock\n"); - return ret; - } - } + ret = pm_runtime_get_sync(dev); + if (ret < 0) + return ret; if (id == 0) { /* Configure Own Address 1 */ @@ -1703,7 +1705,7 @@ static int stm32f7_i2c_reg_slave(struct i2c_client *slave) oar2 &= ~STM32F7_I2C_OAR2_MASK; if (slave->flags & I2C_CLIENT_TEN) { ret = -EOPNOTSUPP; - goto exit; + goto pm_free; } oar2 |= STM32F7_I2C_OAR2_OA2_7(slave->addr); @@ -1712,7 +1714,7 @@ static int stm32f7_i2c_reg_slave(struct i2c_client *slave) writel_relaxed(oar2, i2c_dev->base + STM32F7_I2C_OAR2); } else { ret = -ENODEV; - goto exit; + goto pm_free; } /* Enable ACK */ @@ -1723,11 +1725,10 @@ static int stm32f7_i2c_reg_slave(struct i2c_client *slave) STM32F7_I2C_CR1_PE; stm32f7_i2c_set_bits(base + STM32F7_I2C_CR1, mask); - return 0; - -exit: - if (!(stm32f7_i2c_is_slave_registered(i2c_dev))) - clk_disable(i2c_dev->clk); + ret = 0; +pm_free: + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); return ret; } @@ -1745,6 +1746,10 @@ static int stm32f7_i2c_unreg_slave(struct i2c_client *slave) WARN_ON(!i2c_dev->slave[id]); + ret = pm_runtime_get_sync(i2c_dev->dev); + if (ret < 0) + return ret; + if (id == 0) { mask = STM32F7_I2C_OAR1_OA1EN; stm32f7_i2c_clr_bits(base + STM32F7_I2C_OAR1, mask); @@ -1755,14 +1760,39 @@ static int stm32f7_i2c_unreg_slave(struct i2c_client *slave) i2c_dev->slave[id] = NULL; - if (!(stm32f7_i2c_is_slave_registered(i2c_dev))) { + if (!(stm32f7_i2c_is_slave_registered(i2c_dev))) stm32f7_i2c_disable_irq(i2c_dev, STM32F7_I2C_ALL_IRQ_MASK); - clk_disable(i2c_dev->clk); - } + + pm_runtime_mark_last_busy(i2c_dev->dev); + pm_runtime_put_autosuspend(i2c_dev->dev); return 0; } +static int stm32f7_i2c_setup_fm_plus_bits(struct platform_device *pdev, + struct stm32f7_i2c_dev *i2c_dev) +{ + struct device_node *np = pdev->dev.of_node; + int ret; + u32 reg, mask; + + i2c_dev->regmap = syscon_regmap_lookup_by_phandle(np, "st,syscfg-fmp"); + if (IS_ERR(i2c_dev->regmap)) { + /* Optional */ + return 0; + } + + ret = of_property_read_u32_index(np, "st,syscfg-fmp", 1, ®); + if (ret) + return ret; + + ret = of_property_read_u32_index(np, "st,syscfg-fmp", 2, &mask); + if (ret) + return ret; + + return regmap_update_bits(i2c_dev->regmap, reg, mask, mask); +} + static u32 stm32f7_i2c_func(struct i2c_adapter *adap) { return I2C_FUNC_I2C | I2C_FUNC_10BIT_ADDR | I2C_FUNC_SLAVE | @@ -1819,6 +1849,7 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Error: Missing controller clock\n"); return PTR_ERR(i2c_dev->clk); } + ret = clk_prepare_enable(i2c_dev->clk); if (ret) { dev_err(&pdev->dev, "Failed to prepare_enable clock\n"); @@ -1828,12 +1859,16 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) i2c_dev->speed = STM32_I2C_SPEED_STANDARD; ret = device_property_read_u32(&pdev->dev, "clock-frequency", &clk_rate); - if (!ret && clk_rate >= 1000000) + if (!ret && clk_rate >= 1000000) { i2c_dev->speed = STM32_I2C_SPEED_FAST_PLUS; - else if (!ret && clk_rate >= 400000) + ret = stm32f7_i2c_setup_fm_plus_bits(pdev, i2c_dev); + if (ret) + goto clk_free; + } else if (!ret && clk_rate >= 400000) { i2c_dev->speed = STM32_I2C_SPEED_FAST; - else if (!ret && clk_rate >= 100000) + } else if (!ret && clk_rate >= 100000) { i2c_dev->speed = STM32_I2C_SPEED_STANDARD; + } rst = devm_reset_control_get(&pdev->dev, NULL); if (IS_ERR(rst)) { @@ -1888,8 +1923,6 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) if (ret) goto clk_free; - stm32f7_i2c_hw_config(i2c_dev); - adap = &i2c_dev->adap; i2c_set_adapdata(adap, i2c_dev); snprintf(adap->name, sizeof(adap->name), "STM32F7 I2C(%pa)", @@ -1908,18 +1941,35 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) STM32F7_I2C_TXDR, STM32F7_I2C_RXDR); - ret = i2c_add_adapter(adap); - if (ret) - goto clk_free; - platform_set_drvdata(pdev, i2c_dev); - clk_disable(i2c_dev->clk); + pm_runtime_set_autosuspend_delay(i2c_dev->dev, + STM32F7_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(i2c_dev->dev); + pm_runtime_set_active(i2c_dev->dev); + pm_runtime_enable(i2c_dev->dev); + + pm_runtime_get_noresume(&pdev->dev); + + stm32f7_i2c_hw_config(i2c_dev); + + ret = i2c_add_adapter(adap); + if (ret) + goto pm_disable; dev_info(i2c_dev->dev, "STM32F7 I2C-%d bus adapter\n", adap->nr); + pm_runtime_mark_last_busy(i2c_dev->dev); + pm_runtime_put_autosuspend(i2c_dev->dev); + return 0; +pm_disable: + pm_runtime_put_noidle(i2c_dev->dev); + pm_runtime_disable(i2c_dev->dev); + pm_runtime_set_suspended(i2c_dev->dev); + pm_runtime_dont_use_autosuspend(i2c_dev->dev); + clk_free: clk_disable_unprepare(i2c_dev->clk); @@ -1936,11 +1986,50 @@ static int stm32f7_i2c_remove(struct platform_device *pdev) } i2c_del_adapter(&i2c_dev->adap); + pm_runtime_get_sync(i2c_dev->dev); - clk_unprepare(i2c_dev->clk); + clk_disable_unprepare(i2c_dev->clk); + + pm_runtime_put_noidle(i2c_dev->dev); + pm_runtime_disable(i2c_dev->dev); + pm_runtime_set_suspended(i2c_dev->dev); + pm_runtime_dont_use_autosuspend(i2c_dev->dev); + + return 0; +} + +#ifdef CONFIG_PM +static int stm32f7_i2c_runtime_suspend(struct device *dev) +{ + struct stm32f7_i2c_dev *i2c_dev = dev_get_drvdata(dev); + + if (!stm32f7_i2c_is_slave_registered(i2c_dev)) + clk_disable_unprepare(i2c_dev->clk); + + return 0; +} + +static int stm32f7_i2c_runtime_resume(struct device *dev) +{ + struct stm32f7_i2c_dev *i2c_dev = dev_get_drvdata(dev); + int ret; + + if (!stm32f7_i2c_is_slave_registered(i2c_dev)) { + ret = clk_prepare_enable(i2c_dev->clk); + if (ret) { + dev_err(dev, "failed to prepare_enable clock\n"); + return ret; + } + } return 0; } +#endif + +static const struct dev_pm_ops stm32f7_i2c_pm_ops = { + SET_RUNTIME_PM_OPS(stm32f7_i2c_runtime_suspend, + stm32f7_i2c_runtime_resume, NULL) +}; static const struct of_device_id stm32f7_i2c_match[] = { { .compatible = "st,stm32f7-i2c", .data = &stm32f7_setup}, @@ -1952,6 +2041,7 @@ static struct platform_driver stm32f7_i2c_driver = { .driver = { .name = "stm32f7-i2c", .of_match_table = stm32f7_i2c_match, + .pm = &stm32f7_i2c_pm_ops, }, .probe = stm32f7_i2c_probe, .remove = stm32f7_i2c_remove, diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 437294ea2f0a..e417ebf7628c 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/i2c/busses/i2c-tegra.c * * Copyright (C) 2010 Google, Inc. * Author: Colin Cross <ccross@android.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include <linux/kernel.h> @@ -145,8 +136,8 @@ enum msg_end_type { * @has_continue_xfer_support: Continue transfer supports. * @has_per_pkt_xfer_complete_irq: Has enable/disable capability for transfer * complete interrupt per packet basis. - * @has_single_clk_source: The i2c controller has single clock source. Tegra30 - * and earlier Socs has two clock sources i.e. div-clk and + * @has_single_clk_source: The I2C controller has single clock source. Tegra30 + * and earlier SoCs have two clock sources i.e. div-clk and * fast-clk. * @has_config_load_reg: Has the config load register to load the new * configuration. @@ -154,8 +145,17 @@ enum msg_end_type { * @clk_divisor_std_fast_mode: Clock divisor in standard/fast mode. It is * applicable if there is no fast clock source i.e. single clock * source. + * @clk_divisor_fast_plus_mode: Clock divisor in fast mode plus. It is + * applicable if there is no fast clock source (i.e. single + * clock source). + * @has_multi_master_mode: The I2C controller supports running in single-master + * or multi-master mode. + * @has_slcg_override_reg: The I2C controller supports a register that + * overrides the second level clock gating. + * @has_mst_fifo: The I2C controller contains the new MST FIFO interface that + * provides additional features and allows for longer messages to + * be transferred in one go. */ - struct tegra_i2c_hw_feature { bool has_continue_xfer_support; bool has_per_pkt_xfer_complete_irq; @@ -170,22 +170,27 @@ struct tegra_i2c_hw_feature { }; /** - * struct tegra_i2c_dev - per device i2c context + * struct tegra_i2c_dev - per device I2C context * @dev: device reference for power management - * @hw: Tegra i2c hw feature. - * @adapter: core i2c layer adapter information - * @div_clk: clock reference for div clock of i2c controller. - * @fast_clk: clock reference for fast clock of i2c controller. + * @hw: Tegra I2C HW feature + * @adapter: core I2C layer adapter information + * @div_clk: clock reference for div clock of I2C controller + * @fast_clk: clock reference for fast clock of I2C controller + * @rst: reset control for the I2C controller * @base: ioremapped registers cookie - * @cont_id: i2c controller id, used for for packet header - * @irq: irq number of transfer complete interrupt - * @is_dvc: identifies the DVC i2c controller, has a different register layout + * @cont_id: I2C controller ID, used for packet header + * @irq: IRQ number of transfer complete interrupt + * @irq_disabled: used to track whether or not the interrupt is enabled + * @is_dvc: identifies the DVC I2C controller, has a different register layout * @msg_complete: transfer completion notifier * @msg_err: error code for completed message * @msg_buf: pointer to current message data * @msg_buf_remaining: size of unsent data in the message buffer * @msg_read: identifies read transfers - * @bus_clk_rate: current i2c bus clock rate + * @bus_clk_rate: current I2C bus clock rate + * @clk_divisor_non_hs_mode: clock divider for non-high-speed modes + * @is_multimaster_mode: track if I2C controller is in multi-master mode + * @xfer_lock: lock to serialize transfer submission and processing */ struct tegra_i2c_dev { struct device *dev; @@ -608,11 +613,10 @@ static irqreturn_t tegra_i2c_isr(int irq, void *dev_id) u32 status; const u32 status_err = I2C_INT_NO_ACK | I2C_INT_ARBITRATION_LOST; struct tegra_i2c_dev *i2c_dev = dev_id; - unsigned long flags; status = i2c_readl(i2c_dev, I2C_INT_STATUS); - spin_lock_irqsave(&i2c_dev->xfer_lock, flags); + spin_lock(&i2c_dev->xfer_lock); if (status == 0) { dev_warn(i2c_dev->dev, "irq status 0 %08x %08x %08x\n", i2c_readl(i2c_dev, I2C_PACKET_TRANSFER_STATUS), @@ -670,7 +674,7 @@ err: complete(&i2c_dev->msg_complete); done: - spin_unlock_irqrestore(&i2c_dev->xfer_lock, flags); + spin_unlock(&i2c_dev->xfer_lock); return IRQ_HANDLED; } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 47ab34ee1a9d..8872453e26c0 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1232,6 +1232,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) } while (0) SET_DEVICE_OP(dev_ops, add_gid); + SET_DEVICE_OP(dev_ops, advise_mr); SET_DEVICE_OP(dev_ops, alloc_dm); SET_DEVICE_OP(dev_ops, alloc_fmr); SET_DEVICE_OP(dev_ops, alloc_hw_stats); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index be03b5738f71..efa0f2949dc7 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -780,9 +780,8 @@ int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids) req.cos0 = cpu_to_le16(cids[0]); req.cos1 = cpu_to_le16(cids[1]); - bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, - 0); - return 0; + return bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, + NULL, 0); } int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 1bd8c1b1dba1..fd6ea1f75085 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -73,8 +73,7 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING /* Wait until all page fault handlers using the mr complete. */ - if (mr->umem && mr->umem->is_odp) - synchronize_srcu(&dev->mr_srcu); + synchronize_srcu(&dev->mr_srcu); #endif return err; @@ -238,9 +237,6 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) { struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_cache_ent *ent = &cache->ent[c]; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - bool odp_mkey_exist = false; -#endif struct mlx5_ib_mr *tmp_mr; struct mlx5_ib_mr *mr; LIST_HEAD(del_list); @@ -253,10 +249,6 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) break; } mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list); -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (mr->umem && mr->umem->is_odp) - odp_mkey_exist = true; -#endif list_move(&mr->list, &del_list); ent->cur--; ent->size--; @@ -265,8 +257,7 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) } #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (odp_mkey_exist) - synchronize_srcu(&dev->mr_srcu); + synchronize_srcu(&dev->mr_srcu); #endif list_for_each_entry_safe(mr, tmp_mr, &del_list, list) { @@ -581,7 +572,6 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) { struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_cache_ent *ent = &cache->ent[c]; - bool odp_mkey_exist = false; struct mlx5_ib_mr *tmp_mr; struct mlx5_ib_mr *mr; LIST_HEAD(del_list); @@ -594,8 +584,6 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) break; } mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list); - if (mr->umem && mr->umem->is_odp) - odp_mkey_exist = true; list_move(&mr->list, &del_list); ent->cur--; ent->size--; @@ -604,8 +592,7 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) } #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - if (odp_mkey_exist) - synchronize_srcu(&dev->mr_srcu); + synchronize_srcu(&dev->mr_srcu); #endif list_for_each_entry_safe(mr, tmp_mr, &del_list, list) { diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 9c94c1b9ec35..dd2ae640bc84 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -837,7 +837,8 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, goto err_umem; } - uid = (attr->qp_type != IB_QPT_XRC_TGT) ? to_mpd(pd)->uid : 0; + uid = (attr->qp_type != IB_QPT_XRC_TGT && + attr->qp_type != IB_QPT_XRC_INI) ? to_mpd(pd)->uid : 0; MLX5_SET(create_qp_in, *in, uid, uid); pas = (__be64 *)MLX5_ADDR_OF(create_qp_in, *in, pas); if (ubuffer->umem) diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 505fa3648762..93b16237b767 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -492,6 +492,8 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) int i; qp = idr_find(&dev->qpidr.idr, conn_param->qpn); + if (unlikely(!qp)) + return -EINVAL; laddr = (struct sockaddr_in *)&cm_id->m_local_addr; raddr = (struct sockaddr_in *)&cm_id->m_remote_addr; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 6d35570092d6..78fa777c87b1 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -669,7 +669,6 @@ static void __ipoib_reap_ah(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; - LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); diff --git a/drivers/md/md.c b/drivers/md/md.c index 9a0a1e0934d5..fd4af4de03b4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2147,14 +2147,12 @@ EXPORT_SYMBOL(md_integrity_register); */ int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { - struct blk_integrity *bi_rdev; struct blk_integrity *bi_mddev; char name[BDEVNAME_SIZE]; if (!mddev->gendisk) return 0; - bi_rdev = bdev_get_integrity(rdev->bdev); bi_mddev = blk_get_integrity(mddev->gendisk); if (!bi_mddev) /* nothing to do */ @@ -5693,14 +5691,10 @@ int md_run(struct mddev *mddev) return 0; abort: - if (mddev->flush_bio_pool) { - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - } - if (mddev->flush_pool){ - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - } + mempool_destroy(mddev->flush_bio_pool); + mddev->flush_bio_pool = NULL; + mempool_destroy(mddev->flush_pool); + mddev->flush_pool = NULL; return err; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b98e746e7fc4..abb5d382f64d 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1124,6 +1124,29 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) kfree(plug); } +/* + * 1. Register the new request and wait if the reconstruction thread has put + * up a bar for new requests. Continue immediately if no resync is active + * currently. + * 2. If IO spans the reshape position. Need to wait for reshape to pass. + */ +static void regular_request_wait(struct mddev *mddev, struct r10conf *conf, + struct bio *bio, sector_t sectors) +{ + wait_barrier(conf); + while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + bio->bi_iter.bi_sector < conf->reshape_progress && + bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { + raid10_log(conf->mddev, "wait reshape"); + allow_barrier(conf); + wait_event(conf->wait_barrier, + conf->reshape_progress <= bio->bi_iter.bi_sector || + conf->reshape_progress >= bio->bi_iter.bi_sector + + sectors); + wait_barrier(conf); + } +} + static void raid10_read_request(struct mddev *mddev, struct bio *bio, struct r10bio *r10_bio) { @@ -1132,7 +1155,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, const int op = bio_op(bio); const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); int max_sectors; - sector_t sectors; struct md_rdev *rdev; char b[BDEVNAME_SIZE]; int slot = r10_bio->read_slot; @@ -1166,30 +1188,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, } rcu_read_unlock(); } - /* - * Register the new request and wait if the reconstruction - * thread has put up a bar for new requests. - * Continue immediately if no resync is active currently. - */ - wait_barrier(conf); - - sectors = r10_bio->sectors; - while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && - bio->bi_iter.bi_sector < conf->reshape_progress && - bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { - /* - * IO spans the reshape position. Need to wait for reshape to - * pass - */ - raid10_log(conf->mddev, "wait reshape"); - allow_barrier(conf); - wait_event(conf->wait_barrier, - conf->reshape_progress <= bio->bi_iter.bi_sector || - conf->reshape_progress >= bio->bi_iter.bi_sector + - sectors); - wait_barrier(conf); - } + regular_request_wait(mddev, conf, bio, r10_bio->sectors); rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, struct bio *split = bio_split(bio, max_sectors, gfp, &conf->bio_split); bio_chain(split, bio); + allow_barrier(conf); generic_make_request(bio); + wait_barrier(conf); bio = split; r10_bio->master_bio = bio; r10_bio->sectors = max_sectors; @@ -1332,30 +1334,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, finish_wait(&conf->wait_barrier, &w); } - /* - * Register the new request and wait if the reconstruction - * thread has put up a bar for new requests. - * Continue immediately if no resync is active currently. - */ - wait_barrier(conf); - sectors = r10_bio->sectors; - while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && - bio->bi_iter.bi_sector < conf->reshape_progress && - bio->bi_iter.bi_sector + sectors > conf->reshape_progress) { - /* - * IO spans the reshape position. Need to wait for reshape to - * pass - */ - raid10_log(conf->mddev, "wait reshape"); - allow_barrier(conf); - wait_event(conf->wait_barrier, - conf->reshape_progress <= bio->bi_iter.bi_sector || - conf->reshape_progress >= bio->bi_iter.bi_sector + - sectors); - wait_barrier(conf); - } - + regular_request_wait(mddev, conf, bio, sectors); if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && @@ -1514,7 +1494,9 @@ retry_write: struct bio *split = bio_split(bio, r10_bio->sectors, GFP_NOIO, &conf->bio_split); bio_chain(split, bio); + allow_barrier(conf); generic_make_request(bio); + wait_barrier(conf); bio = split; r10_bio->master_bio = bio; } diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index fe7a1d27a017..a846faefa210 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -13,7 +13,7 @@ config EEPROM_AT24 ones like at24c64, 24lc02 or fm24c04: 24c00, 24c01, 24c02, spd (readonly 24c02), 24c04, 24c08, - 24c16, 24c32, 24c64, 24c128, 24c256, 24c512, 24c1024 + 24c16, 24c32, 24c64, 24c128, 24c256, 24c512, 24c1024, 24c2048 Unless you like data loss puzzles, always be sure that any chip you configure as a 24c32 (32 kbit) or larger is NOT really a diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 636ed7149793..ddfcf4ade7bf 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -156,6 +156,7 @@ AT24_CHIP_DATA(at24_data_24c128, 131072 / 8, AT24_FLAG_ADDR16); AT24_CHIP_DATA(at24_data_24c256, 262144 / 8, AT24_FLAG_ADDR16); AT24_CHIP_DATA(at24_data_24c512, 524288 / 8, AT24_FLAG_ADDR16); AT24_CHIP_DATA(at24_data_24c1024, 1048576 / 8, AT24_FLAG_ADDR16); +AT24_CHIP_DATA(at24_data_24c2048, 2097152 / 8, AT24_FLAG_ADDR16); /* identical to 24c08 ? */ AT24_CHIP_DATA(at24_data_INT3499, 8192 / 8, 0); @@ -182,6 +183,7 @@ static const struct i2c_device_id at24_ids[] = { { "24c256", (kernel_ulong_t)&at24_data_24c256 }, { "24c512", (kernel_ulong_t)&at24_data_24c512 }, { "24c1024", (kernel_ulong_t)&at24_data_24c1024 }, + { "24c2048", (kernel_ulong_t)&at24_data_24c2048 }, { "at24", 0 }, { /* END OF LIST */ } }; @@ -210,6 +212,7 @@ static const struct of_device_id at24_of_match[] = { { .compatible = "atmel,24c256", .data = &at24_data_24c256 }, { .compatible = "atmel,24c512", .data = &at24_data_24c512 }, { .compatible = "atmel,24c1024", .data = &at24_data_24c1024 }, + { .compatible = "atmel,24c2048", .data = &at24_data_24c2048 }, { /* END OF LIST */ }, }; MODULE_DEVICE_TABLE(of, at24_of_match); diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 31ec770b433d..4310c7a4212e 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -103,9 +103,9 @@ config PCI_PF_STUB depends on PCI_IOV help Say Y or M here if you want to enable support for devices that - require SR-IOV support, while at the same time the PF itself is - not providing any actual services on the host itself such as - storage or networking. + require SR-IOV support, while at the same time the PF (Physical + Function) itself is not providing any actual services on the + host itself such as storage or networking. When in doubt, say N. diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 91b0194240a5..548c58223868 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -89,8 +89,8 @@ config PCI_EXYNOS select PCIE_DW_HOST config PCI_IMX6 - bool "Freescale i.MX6 PCIe controller" - depends on SOC_IMX6Q || (ARM && COMPILE_TEST) + bool "Freescale i.MX6/7 PCIe controller" + depends on SOC_IMX6Q || SOC_IMX7D || (ARM && COMPILE_TEST) depends on PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST @@ -193,4 +193,24 @@ config PCIE_HISI_STB help Say Y here if you want PCIe controller support on HiSilicon STB SoCs +config PCI_MESON + bool "MESON PCIe controller" + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want to enable PCI controller support on Amlogic + SoCs. The PCI controller on Amlogic is based on DesignWare hardware + and therefore the driver re-uses the DesignWare core functions to + implement the driver. + +config PCIE_UNIPHIER + bool "Socionext UniPhier PCIe controllers" + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support on UniPhier SoCs. + This driver supports LD20 and PXs3 SoCs. + endmenu diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile index fcf91eacfc63..7bcdcdf5024e 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -14,6 +14,8 @@ obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o +obj-$(CONFIG_PCI_MESON) += pci-meson.o +obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o # The following drivers are for devices that use the generic ACPI # pci_root.c driver but don't support standard ECAM config access. diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 88af6bff945f..52e47dac028f 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -27,6 +27,8 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/reset.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> #include "pcie-designware.h" @@ -59,6 +61,11 @@ struct imx6_pcie { u32 tx_swing_low; int link_gen; struct regulator *vpcie; + + /* power domain for pcie */ + struct device *pd_pcie; + /* power domain for pcie phy */ + struct device *pd_pcie_phy; }; /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */ @@ -67,6 +74,7 @@ struct imx6_pcie { #define PHY_PLL_LOCK_WAIT_USLEEP_MAX 200 /* PCIe Root Complex registers (memory-mapped) */ +#define PCIE_RC_IMX6_MSI_CAP 0x50 #define PCIE_RC_LCR 0x7c #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN1 0x1 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2 0x2 @@ -290,6 +298,43 @@ static int imx6q_pcie_abort_handler(unsigned long addr, return 1; } +static int imx6_pcie_attach_pd(struct device *dev) +{ + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct device_link *link; + + /* Do nothing when in a single power domain */ + if (dev->pm_domain) + return 0; + + imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); + if (IS_ERR(imx6_pcie->pd_pcie)) + return PTR_ERR(imx6_pcie->pd_pcie); + link = device_link_add(dev, imx6_pcie->pd_pcie, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie pd.\n"); + return -EINVAL; + } + + imx6_pcie->pd_pcie_phy = dev_pm_domain_attach_by_name(dev, "pcie_phy"); + if (IS_ERR(imx6_pcie->pd_pcie_phy)) + return PTR_ERR(imx6_pcie->pd_pcie_phy); + + device_link_add(dev, imx6_pcie->pd_pcie_phy, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE); + if (IS_ERR(link)) { + dev_err(dev, "Failed to add device_link to pcie_phy pd: %ld\n", PTR_ERR(link)); + return PTR_ERR(link); + } + + return 0; +} + static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie) { struct device *dev = imx6_pcie->pci->dev; @@ -765,8 +810,28 @@ static void imx6_pcie_ltssm_disable(struct device *dev) static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie) { - reset_control_assert(imx6_pcie->turnoff_reset); - reset_control_deassert(imx6_pcie->turnoff_reset); + struct device *dev = imx6_pcie->pci->dev; + + /* Some variants have a turnoff reset in DT */ + if (imx6_pcie->turnoff_reset) { + reset_control_assert(imx6_pcie->turnoff_reset); + reset_control_deassert(imx6_pcie->turnoff_reset); + goto pm_turnoff_sleep; + } + + /* Others poke directly at IOMUXC registers */ + switch (imx6_pcie->variant) { + case IMX6SX: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_PM_TURN_OFF, + IMX6SX_GPR12_PCIE_PM_TURN_OFF); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0); + break; + default: + dev_err(dev, "PME_Turn_Off not implemented\n"); + return; + } /* * Components with an upstream port must respond to @@ -775,6 +840,7 @@ static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie) * The standard recommends a 1-10ms timeout after which to * proceed anyway as if acks were received. */ +pm_turnoff_sleep: usleep_range(1000, 10000); } @@ -784,18 +850,31 @@ static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie) clk_disable_unprepare(imx6_pcie->pcie_phy); clk_disable_unprepare(imx6_pcie->pcie_bus); - if (imx6_pcie->variant == IMX7D) { + switch (imx6_pcie->variant) { + case IMX6SX: + clk_disable_unprepare(imx6_pcie->pcie_inbound_axi); + break; + case IMX7D: regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); + break; + default: + break; } } +static inline bool imx6_pcie_supports_suspend(struct imx6_pcie *imx6_pcie) +{ + return (imx6_pcie->variant == IMX7D || + imx6_pcie->variant == IMX6SX); +} + static int imx6_pcie_suspend_noirq(struct device *dev) { struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); - if (imx6_pcie->variant != IMX7D) + if (!imx6_pcie_supports_suspend(imx6_pcie)) return 0; imx6_pcie_pm_turnoff(imx6_pcie); @@ -811,7 +890,7 @@ static int imx6_pcie_resume_noirq(struct device *dev) struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); struct pcie_port *pp = &imx6_pcie->pci->pp; - if (imx6_pcie->variant != IMX7D) + if (!imx6_pcie_supports_suspend(imx6_pcie)) return 0; imx6_pcie_assert_core_reset(imx6_pcie); @@ -840,6 +919,7 @@ static int imx6_pcie_probe(struct platform_device *pdev) struct resource *dbi_base; struct device_node *node = dev->of_node; int ret; + u16 val; imx6_pcie = devm_kzalloc(dev, sizeof(*imx6_pcie), GFP_KERNEL); if (!imx6_pcie) @@ -977,10 +1057,22 @@ static int imx6_pcie_probe(struct platform_device *pdev) platform_set_drvdata(pdev, imx6_pcie); + ret = imx6_pcie_attach_pd(dev); + if (ret) + return ret; + ret = imx6_add_pcie_port(imx6_pcie, pdev); if (ret < 0) return ret; + if (pci_msi_enabled()) { + val = dw_pcie_readw_dbi(pci, PCIE_RC_IMX6_MSI_CAP + + PCI_MSI_FLAGS); + val |= PCI_MSI_FLAGS_ENABLE; + dw_pcie_writew_dbi(pci, PCIE_RC_IMX6_MSI_CAP + PCI_MSI_FLAGS, + val); + } + return 0; } diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c index 7aa9a82b7ebd..ce45bde29bf8 100644 --- a/drivers/pci/controller/dwc/pci-layerscape.c +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -222,12 +222,12 @@ static const struct dw_pcie_ops dw_ls_pcie_ops = { .link_up = ls_pcie_link_up, }; -static struct ls_pcie_drvdata ls1021_drvdata = { +static const struct ls_pcie_drvdata ls1021_drvdata = { .ops = &ls1021_pcie_host_ops, .dw_pcie_ops = &dw_ls1021_pcie_ops, }; -static struct ls_pcie_drvdata ls1043_drvdata = { +static const struct ls_pcie_drvdata ls1043_drvdata = { .lut_offset = 0x10000, .ltssm_shift = 24, .lut_dbg = 0x7fc, @@ -235,7 +235,7 @@ static struct ls_pcie_drvdata ls1043_drvdata = { .dw_pcie_ops = &dw_ls_pcie_ops, }; -static struct ls_pcie_drvdata ls1046_drvdata = { +static const struct ls_pcie_drvdata ls1046_drvdata = { .lut_offset = 0x80000, .ltssm_shift = 24, .lut_dbg = 0x407fc, @@ -243,7 +243,7 @@ static struct ls_pcie_drvdata ls1046_drvdata = { .dw_pcie_ops = &dw_ls_pcie_ops, }; -static struct ls_pcie_drvdata ls2080_drvdata = { +static const struct ls_pcie_drvdata ls2080_drvdata = { .lut_offset = 0x80000, .ltssm_shift = 0, .lut_dbg = 0x7fc, @@ -251,7 +251,7 @@ static struct ls_pcie_drvdata ls2080_drvdata = { .dw_pcie_ops = &dw_ls_pcie_ops, }; -static struct ls_pcie_drvdata ls2088_drvdata = { +static const struct ls_pcie_drvdata ls2088_drvdata = { .lut_offset = 0x80000, .ltssm_shift = 0, .lut_dbg = 0x407fc, diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c new file mode 100644 index 000000000000..241ebe0c4505 --- /dev/null +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -0,0 +1,592 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Amlogic MESON SoCs + * + * Copyright (c) 2018 Amlogic, inc. + * Author: Yue Wang <yue.wang@amlogic.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +#define to_meson_pcie(x) dev_get_drvdata((x)->dev) + +/* External local bus interface registers */ +#define PLR_OFFSET 0x700 +#define PCIE_PORT_LINK_CTRL_OFF (PLR_OFFSET + 0x10) +#define FAST_LINK_MODE BIT(7) +#define LINK_CAPABLE_MASK GENMASK(21, 16) +#define LINK_CAPABLE_X1 BIT(16) + +#define PCIE_GEN2_CTRL_OFF (PLR_OFFSET + 0x10c) +#define NUM_OF_LANES_MASK GENMASK(12, 8) +#define NUM_OF_LANES_X1 BIT(8) +#define DIRECT_SPEED_CHANGE BIT(17) + +#define TYPE1_HDR_OFFSET 0x0 +#define PCIE_STATUS_COMMAND (TYPE1_HDR_OFFSET + 0x04) +#define PCI_IO_EN BIT(0) +#define PCI_MEM_SPACE_EN BIT(1) +#define PCI_BUS_MASTER_EN BIT(2) + +#define PCIE_BASE_ADDR0 (TYPE1_HDR_OFFSET + 0x10) +#define PCIE_BASE_ADDR1 (TYPE1_HDR_OFFSET + 0x14) + +#define PCIE_CAP_OFFSET 0x70 +#define PCIE_DEV_CTRL_DEV_STUS (PCIE_CAP_OFFSET + 0x08) +#define PCIE_CAP_MAX_PAYLOAD_MASK GENMASK(7, 5) +#define PCIE_CAP_MAX_PAYLOAD_SIZE(x) ((x) << 5) +#define PCIE_CAP_MAX_READ_REQ_MASK GENMASK(14, 12) +#define PCIE_CAP_MAX_READ_REQ_SIZE(x) ((x) << 12) + +/* PCIe specific config registers */ +#define PCIE_CFG0 0x0 +#define APP_LTSSM_ENABLE BIT(7) + +#define PCIE_CFG_STATUS12 0x30 +#define IS_SMLH_LINK_UP(x) ((x) & (1 << 6)) +#define IS_RDLH_LINK_UP(x) ((x) & (1 << 16)) +#define IS_LTSSM_UP(x) ((((x) >> 10) & 0x1f) == 0x11) + +#define PCIE_CFG_STATUS17 0x44 +#define PM_CURRENT_STATE(x) (((x) >> 7) & 0x1) + +#define WAIT_LINKUP_TIMEOUT 4000 +#define PORT_CLK_RATE 100000000UL +#define MAX_PAYLOAD_SIZE 256 +#define MAX_READ_REQ_SIZE 256 +#define MESON_PCIE_PHY_POWERUP 0x1c +#define PCIE_RESET_DELAY 500 +#define PCIE_SHARED_RESET 1 +#define PCIE_NORMAL_RESET 0 + +enum pcie_data_rate { + PCIE_GEN1, + PCIE_GEN2, + PCIE_GEN3, + PCIE_GEN4 +}; + +struct meson_pcie_mem_res { + void __iomem *elbi_base; + void __iomem *cfg_base; + void __iomem *phy_base; +}; + +struct meson_pcie_clk_res { + struct clk *clk; + struct clk *mipi_gate; + struct clk *port_clk; + struct clk *general_clk; +}; + +struct meson_pcie_rc_reset { + struct reset_control *phy; + struct reset_control *port; + struct reset_control *apb; +}; + +struct meson_pcie { + struct dw_pcie pci; + struct meson_pcie_mem_res mem_res; + struct meson_pcie_clk_res clk_res; + struct meson_pcie_rc_reset mrst; + struct gpio_desc *reset_gpio; +}; + +static struct reset_control *meson_pcie_get_reset(struct meson_pcie *mp, + const char *id, + u32 reset_type) +{ + struct device *dev = mp->pci.dev; + struct reset_control *reset; + + if (reset_type == PCIE_SHARED_RESET) + reset = devm_reset_control_get_shared(dev, id); + else + reset = devm_reset_control_get(dev, id); + + return reset; +} + +static int meson_pcie_get_resets(struct meson_pcie *mp) +{ + struct meson_pcie_rc_reset *mrst = &mp->mrst; + + mrst->phy = meson_pcie_get_reset(mp, "phy", PCIE_SHARED_RESET); + if (IS_ERR(mrst->phy)) + return PTR_ERR(mrst->phy); + reset_control_deassert(mrst->phy); + + mrst->port = meson_pcie_get_reset(mp, "port", PCIE_NORMAL_RESET); + if (IS_ERR(mrst->port)) + return PTR_ERR(mrst->port); + reset_control_deassert(mrst->port); + + mrst->apb = meson_pcie_get_reset(mp, "apb", PCIE_SHARED_RESET); + if (IS_ERR(mrst->apb)) + return PTR_ERR(mrst->apb); + reset_control_deassert(mrst->apb); + + return 0; +} + +static void __iomem *meson_pcie_get_mem(struct platform_device *pdev, + struct meson_pcie *mp, + const char *id) +{ + struct device *dev = mp->pci.dev; + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id); + + return devm_ioremap_resource(dev, res); +} + +static void __iomem *meson_pcie_get_mem_shared(struct platform_device *pdev, + struct meson_pcie *mp, + const char *id) +{ + struct device *dev = mp->pci.dev; + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id); + if (!res) { + dev_err(dev, "No REG resource %s\n", id); + return ERR_PTR(-ENXIO); + } + + return devm_ioremap(dev, res->start, resource_size(res)); +} + +static int meson_pcie_get_mems(struct platform_device *pdev, + struct meson_pcie *mp) +{ + mp->mem_res.elbi_base = meson_pcie_get_mem(pdev, mp, "elbi"); + if (IS_ERR(mp->mem_res.elbi_base)) + return PTR_ERR(mp->mem_res.elbi_base); + + mp->mem_res.cfg_base = meson_pcie_get_mem(pdev, mp, "cfg"); + if (IS_ERR(mp->mem_res.cfg_base)) + return PTR_ERR(mp->mem_res.cfg_base); + + /* Meson SoC has two PCI controllers use same phy register*/ + mp->mem_res.phy_base = meson_pcie_get_mem_shared(pdev, mp, "phy"); + if (IS_ERR(mp->mem_res.phy_base)) + return PTR_ERR(mp->mem_res.phy_base); + + return 0; +} + +static void meson_pcie_power_on(struct meson_pcie *mp) +{ + writel(MESON_PCIE_PHY_POWERUP, mp->mem_res.phy_base); +} + +static void meson_pcie_reset(struct meson_pcie *mp) +{ + struct meson_pcie_rc_reset *mrst = &mp->mrst; + + reset_control_assert(mrst->phy); + udelay(PCIE_RESET_DELAY); + reset_control_deassert(mrst->phy); + udelay(PCIE_RESET_DELAY); + + reset_control_assert(mrst->port); + reset_control_assert(mrst->apb); + udelay(PCIE_RESET_DELAY); + reset_control_deassert(mrst->port); + reset_control_deassert(mrst->apb); + udelay(PCIE_RESET_DELAY); +} + +static inline struct clk *meson_pcie_probe_clock(struct device *dev, + const char *id, u64 rate) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get(dev, id); + if (IS_ERR(clk)) + return clk; + + if (rate) { + ret = clk_set_rate(clk, rate); + if (ret) { + dev_err(dev, "set clk rate failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + } + + ret = clk_prepare_enable(clk); + if (ret) { + dev_err(dev, "couldn't enable clk\n"); + return ERR_PTR(ret); + } + + devm_add_action_or_reset(dev, + (void (*) (void *))clk_disable_unprepare, + clk); + + return clk; +} + +static int meson_pcie_probe_clocks(struct meson_pcie *mp) +{ + struct device *dev = mp->pci.dev; + struct meson_pcie_clk_res *res = &mp->clk_res; + + res->port_clk = meson_pcie_probe_clock(dev, "port", PORT_CLK_RATE); + if (IS_ERR(res->port_clk)) + return PTR_ERR(res->port_clk); + + res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0); + if (IS_ERR(res->mipi_gate)) + return PTR_ERR(res->mipi_gate); + + res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0); + if (IS_ERR(res->general_clk)) + return PTR_ERR(res->general_clk); + + res->clk = meson_pcie_probe_clock(dev, "pcie", 0); + if (IS_ERR(res->clk)) + return PTR_ERR(res->clk); + + return 0; +} + +static inline void meson_elb_writel(struct meson_pcie *mp, u32 val, u32 reg) +{ + writel(val, mp->mem_res.elbi_base + reg); +} + +static inline u32 meson_elb_readl(struct meson_pcie *mp, u32 reg) +{ + return readl(mp->mem_res.elbi_base + reg); +} + +static inline u32 meson_cfg_readl(struct meson_pcie *mp, u32 reg) +{ + return readl(mp->mem_res.cfg_base + reg); +} + +static inline void meson_cfg_writel(struct meson_pcie *mp, u32 val, u32 reg) +{ + writel(val, mp->mem_res.cfg_base + reg); +} + +static void meson_pcie_assert_reset(struct meson_pcie *mp) +{ + gpiod_set_value_cansleep(mp->reset_gpio, 0); + udelay(500); + gpiod_set_value_cansleep(mp->reset_gpio, 1); +} + +static void meson_pcie_init_dw(struct meson_pcie *mp) +{ + u32 val; + + val = meson_cfg_readl(mp, PCIE_CFG0); + val |= APP_LTSSM_ENABLE; + meson_cfg_writel(mp, val, PCIE_CFG0); + + val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); + val &= ~LINK_CAPABLE_MASK; + meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); + + val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); + val |= LINK_CAPABLE_X1 | FAST_LINK_MODE; + meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); + + val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF); + val &= ~NUM_OF_LANES_MASK; + meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF); + + val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF); + val |= NUM_OF_LANES_X1 | DIRECT_SPEED_CHANGE; + meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF); + + meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR0); + meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR1); +} + +static int meson_size_to_payload(struct meson_pcie *mp, int size) +{ + struct device *dev = mp->pci.dev; + + /* + * dwc supports 2^(val+7) payload size, which val is 0~5 default to 1. + * So if input size is not 2^order alignment or less than 2^7 or bigger + * than 2^12, just set to default size 2^(1+7). + */ + if (!is_power_of_2(size) || size < 128 || size > 4096) { + dev_warn(dev, "payload size %d, set to default 256\n", size); + return 1; + } + + return fls(size) - 8; +} + +static void meson_set_max_payload(struct meson_pcie *mp, int size) +{ + u32 val; + int max_payload_size = meson_size_to_payload(mp, size); + + val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val &= ~PCIE_CAP_MAX_PAYLOAD_MASK; + meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + + val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val |= PCIE_CAP_MAX_PAYLOAD_SIZE(max_payload_size); + meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); +} + +static void meson_set_max_rd_req_size(struct meson_pcie *mp, int size) +{ + u32 val; + int max_rd_req_size = meson_size_to_payload(mp, size); + + val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val &= ~PCIE_CAP_MAX_READ_REQ_MASK; + meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + + val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val |= PCIE_CAP_MAX_READ_REQ_SIZE(max_rd_req_size); + meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); +} + +static inline void meson_enable_memory_space(struct meson_pcie *mp) +{ + /* Set the RC Bus Master, Memory Space and I/O Space enables */ + meson_elb_writel(mp, PCI_IO_EN | PCI_MEM_SPACE_EN | PCI_BUS_MASTER_EN, + PCIE_STATUS_COMMAND); +} + +static int meson_pcie_establish_link(struct meson_pcie *mp) +{ + struct dw_pcie *pci = &mp->pci; + struct pcie_port *pp = &pci->pp; + + meson_pcie_init_dw(mp); + meson_set_max_payload(mp, MAX_PAYLOAD_SIZE); + meson_set_max_rd_req_size(mp, MAX_READ_REQ_SIZE); + + dw_pcie_setup_rc(pp); + meson_enable_memory_space(mp); + + meson_pcie_assert_reset(mp); + + return dw_pcie_wait_for_link(pci); +} + +static void meson_pcie_enable_interrupts(struct meson_pcie *mp) +{ + if (IS_ENABLED(CONFIG_PCI_MSI)) + dw_pcie_msi_init(&mp->pci.pp); +} + +static int meson_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, + u32 *val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int ret; + + ret = dw_pcie_read(pci->dbi_base + where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + /* + * There is a bug in the MESON AXG PCIe controller whereby software + * cannot program the PCI_CLASS_DEVICE register, so we must fabricate + * the return value in the config accessors. + */ + if (where == PCI_CLASS_REVISION && size == 4) + *val = (PCI_CLASS_BRIDGE_PCI << 16) | (*val & 0xffff); + else if (where == PCI_CLASS_DEVICE && size == 2) + *val = PCI_CLASS_BRIDGE_PCI; + else if (where == PCI_CLASS_DEVICE && size == 1) + *val = PCI_CLASS_BRIDGE_PCI & 0xff; + else if (where == PCI_CLASS_DEVICE + 1 && size == 1) + *val = (PCI_CLASS_BRIDGE_PCI >> 8) & 0xff; + + return PCIBIOS_SUCCESSFUL; +} + +static int meson_pcie_wr_own_conf(struct pcie_port *pp, int where, + int size, u32 val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + return dw_pcie_write(pci->dbi_base + where, size, val); +} + +static int meson_pcie_link_up(struct dw_pcie *pci) +{ + struct meson_pcie *mp = to_meson_pcie(pci); + struct device *dev = pci->dev; + u32 speed_okay = 0; + u32 cnt = 0; + u32 state12, state17, smlh_up, ltssm_up, rdlh_up; + + do { + state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); + state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17); + smlh_up = IS_SMLH_LINK_UP(state12); + rdlh_up = IS_RDLH_LINK_UP(state12); + ltssm_up = IS_LTSSM_UP(state12); + + if (PM_CURRENT_STATE(state17) < PCIE_GEN3) + speed_okay = 1; + + if (smlh_up) + dev_dbg(dev, "smlh_link_up is on\n"); + if (rdlh_up) + dev_dbg(dev, "rdlh_link_up is on\n"); + if (ltssm_up) + dev_dbg(dev, "ltssm_up is on\n"); + if (speed_okay) + dev_dbg(dev, "speed_okay\n"); + + if (smlh_up && rdlh_up && ltssm_up && speed_okay) + return 1; + + cnt++; + + udelay(10); + } while (cnt < WAIT_LINKUP_TIMEOUT); + + dev_err(dev, "error: wait linkup timeout\n"); + return 0; +} + +static int meson_pcie_host_init(struct pcie_port *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct meson_pcie *mp = to_meson_pcie(pci); + int ret; + + ret = meson_pcie_establish_link(mp); + if (ret) + return ret; + + meson_pcie_enable_interrupts(mp); + + return 0; +} + +static const struct dw_pcie_host_ops meson_pcie_host_ops = { + .rd_own_conf = meson_pcie_rd_own_conf, + .wr_own_conf = meson_pcie_wr_own_conf, + .host_init = meson_pcie_host_init, +}; + +static int meson_add_pcie_port(struct meson_pcie *mp, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &mp->pci; + struct pcie_port *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + pp->msi_irq = platform_get_irq(pdev, 0); + if (pp->msi_irq < 0) { + dev_err(dev, "failed to get MSI IRQ\n"); + return pp->msi_irq; + } + } + + pp->ops = &meson_pcie_host_ops; + pci->dbi_base = mp->mem_res.elbi_base; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = meson_pcie_link_up, +}; + +static int meson_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct meson_pcie *mp; + int ret; + + mp = devm_kzalloc(dev, sizeof(*mp), GFP_KERNEL); + if (!mp) + return -ENOMEM; + + pci = &mp->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(mp->reset_gpio)) { + dev_err(dev, "get reset gpio failed\n"); + return PTR_ERR(mp->reset_gpio); + } + + ret = meson_pcie_get_resets(mp); + if (ret) { + dev_err(dev, "get reset resource failed, %d\n", ret); + return ret; + } + + ret = meson_pcie_get_mems(pdev, mp); + if (ret) { + dev_err(dev, "get memory resource failed, %d\n", ret); + return ret; + } + + meson_pcie_power_on(mp); + meson_pcie_reset(mp); + + ret = meson_pcie_probe_clocks(mp); + if (ret) { + dev_err(dev, "init clock resources failed, %d\n", ret); + return ret; + } + + platform_set_drvdata(pdev, mp); + + ret = meson_add_pcie_port(mp, pdev); + if (ret < 0) { + dev_err(dev, "Add PCIe port failed, %d\n", ret); + return ret; + } + + return 0; +} + +static const struct of_device_id meson_pcie_of_match[] = { + { + .compatible = "amlogic,axg-pcie", + }, + {}, +}; + +static struct platform_driver meson_pcie_driver = { + .probe = meson_pcie_probe, + .driver = { + .name = "meson-pcie", + .of_match_table = meson_pcie_of_match, + }, +}; + +builtin_platform_driver(meson_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index 0c389a30ef5d..b171b6bc15c8 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -22,6 +22,7 @@ #include <linux/resource.h> #include <linux/of_pci.h> #include <linux/of_irq.h> +#include <linux/gpio/consumer.h> #include "pcie-designware.h" @@ -29,6 +30,7 @@ struct armada8k_pcie { struct dw_pcie *pci; struct clk *clk; struct clk *clk_reg; + struct gpio_desc *reset_gpio; }; #define PCIE_VENDOR_REGS_OFFSET 0x8000 @@ -137,6 +139,12 @@ static int armada8k_pcie_host_init(struct pcie_port *pp) struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct armada8k_pcie *pcie = to_armada8k_pcie(pci); + if (pcie->reset_gpio) { + /* assert and then deassert the reset signal */ + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + msleep(100); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); + } dw_pcie_setup_rc(pp); armada8k_pcie_establish_link(pcie); @@ -249,6 +257,14 @@ static int armada8k_pcie_probe(struct platform_device *pdev) goto fail_clkreg; } + /* Get reset gpio signal and hold asserted (logically high) */ + pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->reset_gpio)) { + ret = PTR_ERR(pcie->reset_gpio); + goto fail_clkreg; + } + platform_set_drvdata(pdev, pcie); ret = armada8k_add_pcie_port(pcie, pdev); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index de8635af4cde..a543c45c7224 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -503,6 +503,10 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) dev_err(dev, "dbi_base/dbi_base2 is not populated\n"); return -EINVAL; } + if (pci->iatu_unroll_enabled && !pci->atu_base) { + dev_err(dev, "atu_base is not populated\n"); + return -EINVAL; + } ret = of_property_read_u32(np, "num-ib-windows", &ep->num_ib_windows); if (ret < 0) { diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 29a05759a294..721d60a5d9e4 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -99,9 +99,6 @@ irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) (i * MAX_MSI_IRQS_PER_CTRL) + pos); generic_handle_irq(irq); - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_STATUS + - (i * MSI_REG_CTRL_BLOCK_SIZE), - 4, 1 << pos); pos++; } } @@ -168,8 +165,8 @@ static void dw_pci_bottom_mask(struct irq_data *data) bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL; pp->irq_status[ctrl] &= ~(1 << bit); - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, - pp->irq_status[ctrl]); + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4, + ~pp->irq_status[ctrl]); } raw_spin_unlock_irqrestore(&pp->lock, flags); @@ -191,8 +188,8 @@ static void dw_pci_bottom_unmask(struct irq_data *data) bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL; pp->irq_status[ctrl] |= 1 << bit; - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4, - pp->irq_status[ctrl]); + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4, + ~pp->irq_status[ctrl]); } raw_spin_unlock_irqrestore(&pp->lock, flags); @@ -200,13 +197,22 @@ static void dw_pci_bottom_unmask(struct irq_data *data) static void dw_pci_bottom_ack(struct irq_data *d) { - struct msi_desc *msi = irq_data_get_msi_desc(d); - struct pcie_port *pp; + struct pcie_port *pp = irq_data_get_irq_chip_data(d); + unsigned int res, bit, ctrl; + unsigned long flags; + + ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; + res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; + bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; + + raw_spin_lock_irqsave(&pp->lock, flags); - pp = msi_desc_to_pci_sysdata(msi); + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_STATUS + res, 4, 1 << bit); if (pp->ops->msi_irq_ack) pp->ops->msi_irq_ack(d->hwirq, pp); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } static struct irq_chip dw_pci_msi_bottom_irq_chip = { @@ -658,10 +664,15 @@ void dw_pcie_setup_rc(struct pcie_port *pp) num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; /* Initialize IRQ Status array */ - for (ctrl = 0; ctrl < num_ctrls; ctrl++) - dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE + + for (ctrl = 0; ctrl < num_ctrls; ctrl++) { + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), + 4, ~0); + dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), - 4, &pp->irq_status[ctrl]); + 4, ~0); + pp->irq_status[ctrl] = 0; + } /* Setup RC BARs */ dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0x00000004); @@ -699,6 +710,9 @@ void dw_pcie_setup_rc(struct pcie_port *pp) dev_dbg(pci->dev, "iATU unroll: %s\n", pci->iatu_unroll_enabled ? "enabled" : "disabled"); + if (pci->iatu_unroll_enabled && !pci->atu_base) + pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET; + dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0, PCIE_ATU_TYPE_MEM, pp->mem_base, pp->mem_bus_addr, pp->mem_size); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 2153956a0b20..93ef8c31fb39 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -93,7 +93,7 @@ static u32 dw_pcie_readl_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg) { u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); - return dw_pcie_readl_dbi(pci, offset + reg); + return dw_pcie_readl_atu(pci, offset + reg); } static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg, @@ -101,7 +101,7 @@ static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg, { u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); - dw_pcie_writel_dbi(pci, offset + reg, val); + dw_pcie_writel_atu(pci, offset + reg, val); } static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, int index, @@ -187,7 +187,7 @@ static u32 dw_pcie_readl_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg) { u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index); - return dw_pcie_readl_dbi(pci, offset + reg); + return dw_pcie_readl_atu(pci, offset + reg); } static void dw_pcie_writel_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg, @@ -195,7 +195,7 @@ static void dw_pcie_writel_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg, { u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index); - dw_pcie_writel_dbi(pci, offset + reg, val); + dw_pcie_writel_atu(pci, offset + reg, val); } static int dw_pcie_prog_inbound_atu_unroll(struct dw_pcie *pci, int index, diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 0989d880ac46..9943d8c68335 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -92,12 +92,20 @@ #define PCIE_ATU_UNR_LOWER_TARGET 0x14 #define PCIE_ATU_UNR_UPPER_TARGET 0x18 +/* + * The default address offset between dbi_base and atu_base. Root controller + * drivers are not required to initialize atu_base if the offset matches this + * default; the driver core automatically derives atu_base from dbi_base using + * this offset, if atu_base not set. + */ +#define DEFAULT_DBI_ATU_OFFSET (0x3 << 20) + /* Register address builder */ -#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region) \ - ((0x3 << 20) | ((region) << 9)) +#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region) \ + ((region) << 9) -#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \ - ((0x3 << 20) | ((region) << 9) | (0x1 << 8)) +#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \ + (((region) << 9) | (0x1 << 8)) #define MAX_MSI_IRQS 256 #define MAX_MSI_IRQS_PER_CTRL 32 @@ -219,6 +227,8 @@ struct dw_pcie { struct device *dev; void __iomem *dbi_base; void __iomem *dbi_base2; + /* Used when iatu_unroll_enabled is true */ + void __iomem *atu_base; u32 num_viewport; u8 iatu_unroll_enabled; struct pcie_port pp; @@ -289,6 +299,16 @@ static inline u32 dw_pcie_readl_dbi2(struct dw_pcie *pci, u32 reg) return __dw_pcie_read_dbi(pci, pci->dbi_base2, reg, 0x4); } +static inline void dw_pcie_writel_atu(struct dw_pcie *pci, u32 reg, u32 val) +{ + __dw_pcie_write_dbi(pci, pci->atu_base, reg, 0x4, val); +} + +static inline u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 reg) +{ + return __dw_pcie_read_dbi(pci, pci->atu_base, reg, 0x4); +} + static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci) { u32 reg; diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c index 7b32e619b959..954bc2b74bbc 100644 --- a/drivers/pci/controller/dwc/pcie-histb.c +++ b/drivers/pci/controller/dwc/pcie-histb.c @@ -202,7 +202,7 @@ static int histb_pcie_host_init(struct pcie_port *pp) return 0; } -static struct dw_pcie_host_ops histb_pcie_host_ops = { +static const struct dw_pcie_host_ops histb_pcie_host_ops = { .rd_own_conf = histb_pcie_rd_own_conf, .wr_own_conf = histb_pcie_wr_own_conf, .host_init = histb_pcie_host_init, diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c new file mode 100644 index 000000000000..d5dc40289cce --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-uniphier.c @@ -0,0 +1,471 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for UniPhier SoCs + * Copyright 2018 Socionext Inc. + * Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com> + */ + +#include <linux/bitops.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +#define PCL_PINCTRL0 0x002c +#define PCL_PERST_PLDN_REGEN BIT(12) +#define PCL_PERST_NOE_REGEN BIT(11) +#define PCL_PERST_OUT_REGEN BIT(8) +#define PCL_PERST_PLDN_REGVAL BIT(4) +#define PCL_PERST_NOE_REGVAL BIT(3) +#define PCL_PERST_OUT_REGVAL BIT(0) + +#define PCL_PIPEMON 0x0044 +#define PCL_PCLK_ALIVE BIT(15) + +#define PCL_APP_READY_CTRL 0x8008 +#define PCL_APP_LTSSM_ENABLE BIT(0) + +#define PCL_APP_PM0 0x8078 +#define PCL_SYS_AUX_PWR_DET BIT(8) + +#define PCL_RCV_INT 0x8108 +#define PCL_RCV_INT_ALL_ENABLE GENMASK(20, 17) +#define PCL_CFG_BW_MGT_STATUS BIT(4) +#define PCL_CFG_LINK_AUTO_BW_STATUS BIT(3) +#define PCL_CFG_AER_RC_ERR_MSI_STATUS BIT(2) +#define PCL_CFG_PME_MSI_STATUS BIT(1) + +#define PCL_RCV_INTX 0x810c +#define PCL_RCV_INTX_ALL_ENABLE GENMASK(19, 16) +#define PCL_RCV_INTX_ALL_MASK GENMASK(11, 8) +#define PCL_RCV_INTX_MASK_SHIFT 8 +#define PCL_RCV_INTX_ALL_STATUS GENMASK(3, 0) +#define PCL_RCV_INTX_STATUS_SHIFT 0 + +#define PCL_STATUS_LINK 0x8140 +#define PCL_RDLH_LINK_UP BIT(1) +#define PCL_XMLH_LINK_UP BIT(0) + +struct uniphier_pcie_priv { + void __iomem *base; + struct dw_pcie pci; + struct clk *clk; + struct reset_control *rst; + struct phy *phy; + struct irq_domain *legacy_irq_domain; +}; + +#define to_uniphier_pcie(x) dev_get_drvdata((x)->dev) + +static void uniphier_pcie_ltssm_enable(struct uniphier_pcie_priv *priv, + bool enable) +{ + u32 val; + + val = readl(priv->base + PCL_APP_READY_CTRL); + if (enable) + val |= PCL_APP_LTSSM_ENABLE; + else + val &= ~PCL_APP_LTSSM_ENABLE; + writel(val, priv->base + PCL_APP_READY_CTRL); +} + +static void uniphier_pcie_init_rc(struct uniphier_pcie_priv *priv) +{ + u32 val; + + /* use auxiliary power detection */ + val = readl(priv->base + PCL_APP_PM0); + val |= PCL_SYS_AUX_PWR_DET; + writel(val, priv->base + PCL_APP_PM0); + + /* assert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL + | PCL_PERST_PLDN_REGVAL); + val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN + | PCL_PERST_PLDN_REGEN; + writel(val, priv->base + PCL_PINCTRL0); + + uniphier_pcie_ltssm_enable(priv, false); + + usleep_range(100000, 200000); + + /* deassert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN; + writel(val, priv->base + PCL_PINCTRL0); +} + +static int uniphier_pcie_wait_rc(struct uniphier_pcie_priv *priv) +{ + u32 status; + int ret; + + /* wait PIPE clock */ + ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status, + status & PCL_PCLK_ALIVE, 100000, 1000000); + if (ret) { + dev_err(priv->pci.dev, + "Failed to initialize controller in RC mode\n"); + return ret; + } + + return 0; +} + +static int uniphier_pcie_link_up(struct dw_pcie *pci) +{ + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + u32 val, mask; + + val = readl(priv->base + PCL_STATUS_LINK); + mask = PCL_RDLH_LINK_UP | PCL_XMLH_LINK_UP; + + return (val & mask) == mask; +} + +static int uniphier_pcie_establish_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + + if (dw_pcie_link_up(pci)) + return 0; + + uniphier_pcie_ltssm_enable(priv, true); + + return dw_pcie_wait_for_link(pci); +} + +static void uniphier_pcie_stop_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(priv, false); +} + +static void uniphier_pcie_irq_enable(struct uniphier_pcie_priv *priv) +{ + writel(PCL_RCV_INT_ALL_ENABLE, priv->base + PCL_RCV_INT); + writel(PCL_RCV_INTX_ALL_ENABLE, priv->base + PCL_RCV_INTX); +} + +static void uniphier_pcie_irq_disable(struct uniphier_pcie_priv *priv) +{ + writel(0, priv->base + PCL_RCV_INT); + writel(0, priv->base + PCL_RCV_INTX); +} + +static void uniphier_pcie_irq_ack(struct irq_data *d) +{ + struct pcie_port *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + u32 val; + + val = readl(priv->base + PCL_RCV_INTX); + val &= ~PCL_RCV_INTX_ALL_STATUS; + val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_STATUS_SHIFT); + writel(val, priv->base + PCL_RCV_INTX); +} + +static void uniphier_pcie_irq_mask(struct irq_data *d) +{ + struct pcie_port *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + u32 val; + + val = readl(priv->base + PCL_RCV_INTX); + val &= ~PCL_RCV_INTX_ALL_MASK; + val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); + writel(val, priv->base + PCL_RCV_INTX); +} + +static void uniphier_pcie_irq_unmask(struct irq_data *d) +{ + struct pcie_port *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + u32 val; + + val = readl(priv->base + PCL_RCV_INTX); + val &= ~PCL_RCV_INTX_ALL_MASK; + val &= ~BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); + writel(val, priv->base + PCL_RCV_INTX); +} + +static struct irq_chip uniphier_pcie_irq_chip = { + .name = "PCI", + .irq_ack = uniphier_pcie_irq_ack, + .irq_mask = uniphier_pcie_irq_mask, + .irq_unmask = uniphier_pcie_irq_unmask, +}; + +static int uniphier_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &uniphier_pcie_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops uniphier_intx_domain_ops = { + .map = uniphier_pcie_intx_map, +}; + +static void uniphier_pcie_irq_handler(struct irq_desc *desc) +{ + struct pcie_port *pp = irq_desc_get_handler_data(desc); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long reg; + u32 val, bit, virq; + + /* INT for debug */ + val = readl(priv->base + PCL_RCV_INT); + + if (val & PCL_CFG_BW_MGT_STATUS) + dev_dbg(pci->dev, "Link Bandwidth Management Event\n"); + if (val & PCL_CFG_LINK_AUTO_BW_STATUS) + dev_dbg(pci->dev, "Link Autonomous Bandwidth Event\n"); + if (val & PCL_CFG_AER_RC_ERR_MSI_STATUS) + dev_dbg(pci->dev, "Root Error\n"); + if (val & PCL_CFG_PME_MSI_STATUS) + dev_dbg(pci->dev, "PME Interrupt\n"); + + writel(val, priv->base + PCL_RCV_INT); + + /* INTx */ + chained_irq_enter(chip, desc); + + val = readl(priv->base + PCL_RCV_INTX); + reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val); + + for_each_set_bit(bit, ®, PCI_NUM_INTX) { + virq = irq_linear_revmap(priv->legacy_irq_domain, bit); + generic_handle_irq(virq); + } + + chained_irq_exit(chip, desc); +} + +static int uniphier_pcie_config_legacy_irq(struct pcie_port *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct device_node *np = pci->dev->of_node; + struct device_node *np_intc; + + np_intc = of_get_child_by_name(np, "legacy-interrupt-controller"); + if (!np_intc) { + dev_err(pci->dev, "Failed to get legacy-interrupt-controller node\n"); + return -EINVAL; + } + + pp->irq = irq_of_parse_and_map(np_intc, 0); + if (!pp->irq) { + dev_err(pci->dev, "Failed to get an IRQ entry in legacy-interrupt-controller\n"); + return -EINVAL; + } + + priv->legacy_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX, + &uniphier_intx_domain_ops, pp); + if (!priv->legacy_irq_domain) { + dev_err(pci->dev, "Failed to get INTx domain\n"); + return -ENODEV; + } + + irq_set_chained_handler_and_data(pp->irq, uniphier_pcie_irq_handler, + pp); + + return 0; +} + +static int uniphier_pcie_host_init(struct pcie_port *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + int ret; + + ret = uniphier_pcie_config_legacy_irq(pp); + if (ret) + return ret; + + uniphier_pcie_irq_enable(priv); + + dw_pcie_setup_rc(pp); + ret = uniphier_pcie_establish_link(pci); + if (ret) + return ret; + + if (IS_ENABLED(CONFIG_PCI_MSI)) + dw_pcie_msi_init(pp); + + return 0; +} + +static const struct dw_pcie_host_ops uniphier_pcie_host_ops = { + .host_init = uniphier_pcie_host_init, +}; + +static int uniphier_add_pcie_port(struct uniphier_pcie_priv *priv, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &priv->pci; + struct pcie_port *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + pp->ops = &uniphier_pcie_host_ops; + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + pp->msi_irq = platform_get_irq_byname(pdev, "msi"); + if (pp->msi_irq < 0) + return pp->msi_irq; + } + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "Failed to initialize host (%d)\n", ret); + return ret; + } + + return 0; +} + +static int uniphier_pcie_host_enable(struct uniphier_pcie_priv *priv) +{ + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + ret = reset_control_deassert(priv->rst); + if (ret) + goto out_clk_disable; + + uniphier_pcie_init_rc(priv); + + ret = phy_init(priv->phy); + if (ret) + goto out_rst_assert; + + ret = uniphier_pcie_wait_rc(priv); + if (ret) + goto out_phy_exit; + + return 0; + +out_phy_exit: + phy_exit(priv->phy); +out_rst_assert: + reset_control_assert(priv->rst); +out_clk_disable: + clk_disable_unprepare(priv->clk); + + return ret; +} + +static void uniphier_pcie_host_disable(struct uniphier_pcie_priv *priv) +{ + uniphier_pcie_irq_disable(priv); + phy_exit(priv->phy); + reset_control_assert(priv->rst); + clk_disable_unprepare(priv->clk); +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = uniphier_pcie_establish_link, + .stop_link = uniphier_pcie_stop_link, + .link_up = uniphier_pcie_link_up, +}; + +static int uniphier_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct uniphier_pcie_priv *priv; + struct resource *res; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->pci.dev = dev; + priv->pci.ops = &dw_pcie_ops; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + priv->pci.dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(priv->pci.dbi_base)) + return PTR_ERR(priv->pci.dbi_base); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "link"); + priv->base = devm_ioremap_resource(dev, res); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + priv->clk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->rst = devm_reset_control_get_shared(dev, NULL); + if (IS_ERR(priv->rst)) + return PTR_ERR(priv->rst); + + priv->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(priv->phy)) + return PTR_ERR(priv->phy); + + platform_set_drvdata(pdev, priv); + + ret = uniphier_pcie_host_enable(priv); + if (ret) + return ret; + + return uniphier_add_pcie_port(priv, pdev); +} + +static int uniphier_pcie_remove(struct platform_device *pdev) +{ + struct uniphier_pcie_priv *priv = platform_get_drvdata(pdev); + + uniphier_pcie_host_disable(priv); + + return 0; +} + +static const struct of_device_id uniphier_pcie_match[] = { + { .compatible = "socionext,uniphier-pcie", }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, uniphier_pcie_match); + +static struct platform_driver uniphier_pcie_driver = { + .probe = uniphier_pcie_probe, + .remove = uniphier_pcie_remove, + .driver = { + .name = "uniphier-pcie", + .of_match_table = uniphier_pcie_match, + }, +}; +builtin_platform_driver(uniphier_pcie_driver); + +MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>"); +MODULE_DESCRIPTION("UniPhier PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index d069a76cbb95..55e471c18e8d 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -161,7 +161,6 @@ struct mtk_pcie_soc { * @obff_ck: pointer to OBFF functional block operating clock * @pipe_ck: pointer to LTSSM and PHY/MAC layer operating clock * @phy: pointer to PHY control block - * @lane: lane count * @slot: port slot * @irq: GIC irq * @irq_domain: legacy INTx IRQ domain @@ -182,7 +181,6 @@ struct mtk_pcie_port { struct clk *obff_ck; struct clk *pipe_ck; struct phy *phy; - u32 lane; u32 slot; int irq; struct irq_domain *irq_domain; @@ -197,29 +195,20 @@ struct mtk_pcie_port { * @dev: pointer to PCIe device * @base: IO mapped register base * @free_ck: free-run reference clock - * @io: IO resource - * @pio: PIO resource * @mem: non-prefetchable memory resource - * @busn: bus range - * @offset: IO / Memory offset * @ports: pointer to PCIe port information * @soc: pointer to SoC-dependent operations + * @busnr: root bus number */ struct mtk_pcie { struct device *dev; void __iomem *base; struct clk *free_ck; - struct resource io; - struct resource pio; struct resource mem; - struct resource busn; - struct { - resource_size_t mem; - resource_size_t io; - } offset; struct list_head ports; const struct mtk_pcie_soc *soc; + unsigned int busnr; }; static void mtk_pcie_subsys_powerdown(struct mtk_pcie *pcie) @@ -904,12 +893,6 @@ static int mtk_pcie_parse_port(struct mtk_pcie *pcie, if (!port) return -ENOMEM; - err = of_property_read_u32(node, "num-lanes", &port->lane); - if (err) { - dev_err(dev, "missing num-lanes property\n"); - return err; - } - snprintf(name, sizeof(name), "port%d", slot); regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); port->base = devm_ioremap_resource(dev, regs); @@ -1045,55 +1028,43 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie) { struct device *dev = pcie->dev; struct device_node *node = dev->of_node, *child; - struct of_pci_range_parser parser; - struct of_pci_range range; - struct resource res; struct mtk_pcie_port *port, *tmp; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct list_head *windows = &host->windows; + struct resource_entry *win, *tmp_win; + resource_size_t io_base; int err; - if (of_pci_range_parser_init(&parser, node)) { - dev_err(dev, "missing \"ranges\" property\n"); - return -EINVAL; - } + err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, + windows, &io_base); + if (err) + return err; - for_each_of_pci_range(&parser, &range) { - err = of_pci_range_to_resource(&range, node, &res); - if (err < 0) - return err; + err = devm_request_pci_bus_resources(dev, windows); + if (err < 0) + return err; - switch (res.flags & IORESOURCE_TYPE_BITS) { + /* Get the I/O and memory ranges from DT */ + resource_list_for_each_entry_safe(win, tmp_win, windows) { + switch (resource_type(win->res)) { case IORESOURCE_IO: - pcie->offset.io = res.start - range.pci_addr; - - memcpy(&pcie->pio, &res, sizeof(res)); - pcie->pio.name = node->full_name; - - pcie->io.start = range.cpu_addr; - pcie->io.end = range.cpu_addr + range.size - 1; - pcie->io.flags = IORESOURCE_MEM; - pcie->io.name = "I/O"; - - memcpy(&res, &pcie->io, sizeof(res)); + err = devm_pci_remap_iospace(dev, win->res, io_base); + if (err) { + dev_warn(dev, "error %d: failed to map resource %pR\n", + err, win->res); + resource_list_destroy_entry(win); + } break; - case IORESOURCE_MEM: - pcie->offset.mem = res.start - range.pci_addr; - - memcpy(&pcie->mem, &res, sizeof(res)); + memcpy(&pcie->mem, win->res, sizeof(*win->res)); pcie->mem.name = "non-prefetchable"; break; + case IORESOURCE_BUS: + pcie->busnr = win->res->start; + break; } } - err = of_pci_parse_bus_range(node, &pcie->busn); - if (err < 0) { - dev_err(dev, "failed to parse bus ranges property: %d\n", err); - pcie->busn.name = node->name; - pcie->busn.start = 0; - pcie->busn.end = 0xff; - pcie->busn.flags = IORESOURCE_BUS; - } - for_each_available_child_of_node(node, child) { int slot; @@ -1125,28 +1096,6 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie) return 0; } -static int mtk_pcie_request_resources(struct mtk_pcie *pcie) -{ - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); - struct list_head *windows = &host->windows; - struct device *dev = pcie->dev; - int err; - - pci_add_resource_offset(windows, &pcie->pio, pcie->offset.io); - pci_add_resource_offset(windows, &pcie->mem, pcie->offset.mem); - pci_add_resource(windows, &pcie->busn); - - err = devm_request_pci_bus_resources(dev, windows); - if (err < 0) - return err; - - err = devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start); - if (err) - return err; - - return 0; -} - static int mtk_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1169,11 +1118,7 @@ static int mtk_pcie_probe(struct platform_device *pdev) if (err) return err; - err = mtk_pcie_request_resources(pcie); - if (err) - goto put_resources; - - host->busnr = pcie->busn.start; + host->busnr = pcie->busnr; host->dev.parent = pcie->dev; host->ops = pcie->soc->ops; host->map_irq = of_irq_parse_and_map_pci; diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 9616eca3182f..3aa115ed3a65 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -252,6 +252,27 @@ int __weak pcibios_sriov_disable(struct pci_dev *pdev) return 0; } +static int sriov_add_vfs(struct pci_dev *dev, u16 num_vfs) +{ + unsigned int i; + int rc; + + if (dev->no_vf_scan) + return 0; + + for (i = 0; i < num_vfs; i++) { + rc = pci_iov_add_virtfn(dev, i); + if (rc) + goto failed; + } + return 0; +failed: + while (i--) + pci_iov_remove_virtfn(dev, i); + + return rc; +} + static int sriov_enable(struct pci_dev *dev, int nr_virtfn) { int rc; @@ -337,21 +358,15 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) msleep(100); pci_cfg_access_unlock(dev); - for (i = 0; i < initial; i++) { - rc = pci_iov_add_virtfn(dev, i); - if (rc) - goto failed; - } + rc = sriov_add_vfs(dev, initial); + if (rc) + goto err_pcibios; kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE); iov->num_VFs = nr_virtfn; return 0; -failed: - while (i--) - pci_iov_remove_virtfn(dev, i); - err_pcibios: iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE); pci_cfg_access_lock(dev); @@ -368,17 +383,26 @@ err_pcibios: return rc; } -static void sriov_disable(struct pci_dev *dev) +static void sriov_del_vfs(struct pci_dev *dev) { - int i; struct pci_sriov *iov = dev->sriov; + int i; - if (!iov->num_VFs) + if (dev->no_vf_scan) return; for (i = 0; i < iov->num_VFs; i++) pci_iov_remove_virtfn(dev, i); +} + +static void sriov_disable(struct pci_dev *dev) +{ + struct pci_sriov *iov = dev->sriov; + + if (!iov->num_VFs) + return; + sriov_del_vfs(dev); iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE); pci_cfg_access_lock(dev); pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl); diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index a2eb25271c96..c52298d76e64 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -416,7 +416,7 @@ static int upstream_bridge_distance_warn(struct pci_dev *provider, * * Returns -1 if any of the clients are not compatible (behind the same * root port as the provider), otherwise returns a positive number where - * a lower number is the preferrable choice. (If there's one client + * a lower number is the preferable choice. (If there's one client * that's the same as the provider it will return 0, which is best choice). * * For now, "compatible" means the provider and the clients are all behind @@ -487,7 +487,7 @@ EXPORT_SYMBOL_GPL(pci_has_p2pmem); * @num_clients: number of client devices in the list * * If multiple devices are behind the same switch, the one "closest" to the - * client devices in use will be chosen first. (So if one of the providers are + * client devices in use will be chosen first. (So if one of the providers is * the same as one of the clients, that provider will be used ahead of any * other providers that are unrelated). If multiple providers are an equal * distance away, one will be chosen at random. @@ -574,7 +574,7 @@ EXPORT_SYMBOL_GPL(pci_alloc_p2pmem); * pci_free_p2pmem - free peer-to-peer DMA memory * @pdev: the device the memory was allocated from * @addr: address of the memory that was allocated - * @size: number of bytes that was allocated + * @size: number of bytes that were allocated */ void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size) { @@ -611,7 +611,7 @@ EXPORT_SYMBOL_GPL(pci_p2pmem_virt_to_bus); * @nents: the number of SG entries in the list * @length: number of bytes to allocate * - * Returns 0 on success + * Return: %NULL on error or &struct scatterlist pointer and @nents on success */ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, unsigned int *nents, u32 length) @@ -667,7 +667,7 @@ EXPORT_SYMBOL_GPL(pci_p2pmem_free_sgl); * * Published memory can be used by other PCI device drivers for * peer-2-peer DMA operations. Non-published memory is reserved for - * exlusive use of the device driver that registers the peer-to-peer + * exclusive use of the device driver that registers the peer-to-peer * memory. */ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) @@ -727,7 +727,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg); * @use_p2pdma: returns whether to enable p2pdma or not * * Parses an attribute value to decide whether to enable p2pdma. - * The value can select a PCI device (using it's full BDF device + * The value can select a PCI device (using its full BDF device * name) or a boolean (in any format strtobool() accepts). A false * value disables p2pdma, a true value expects the caller * to automatically find a compatible device and specifying a PCI device @@ -778,7 +778,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_enable_store); * whether p2pdma is enabled * @page: contents of the stored value * @p2p_dev: the selected p2p device (NULL if no device is selected) - * @use_p2pdma: whether p2pdme has been enabled + * @use_p2pdma: whether p2pdma has been enabled * * Attributes that use pci_p2pdma_enable_store() should use this function * to show the value of the attribute. diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index ea55444e6ead..79b1610a8beb 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1251,30 +1251,29 @@ static int pci_pm_runtime_suspend(struct device *dev) return 0; } - if (!pm || !pm->runtime_suspend) - return -ENOSYS; - pci_dev->state_saved = false; - error = pm->runtime_suspend(dev); - if (error) { + if (pm && pm->runtime_suspend) { + error = pm->runtime_suspend(dev); /* * -EBUSY and -EAGAIN is used to request the runtime PM core * to schedule a new suspend, so log the event only with debug * log level. */ - if (error == -EBUSY || error == -EAGAIN) + if (error == -EBUSY || error == -EAGAIN) { dev_dbg(dev, "can't suspend now (%pf returned %d)\n", pm->runtime_suspend, error); - else + return error; + } else if (error) { dev_err(dev, "can't suspend (%pf returned %d)\n", pm->runtime_suspend, error); - - return error; + return error; + } } pci_fixup_device(pci_fixup_suspend, pci_dev); - if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 + if (pm && pm->runtime_suspend + && !pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { WARN_ONCE(pci_dev->current_state != prev, "PCI PM: State of device not saved by %pF\n", @@ -1292,7 +1291,7 @@ static int pci_pm_runtime_suspend(struct device *dev) static int pci_pm_runtime_resume(struct device *dev) { - int rc; + int rc = 0; struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; @@ -1306,14 +1305,12 @@ static int pci_pm_runtime_resume(struct device *dev) if (!pci_dev->driver) return 0; - if (!pm || !pm->runtime_resume) - return -ENOSYS; - pci_fixup_device(pci_fixup_resume_early, pci_dev); pci_enable_wake(pci_dev, PCI_D0, false); pci_fixup_device(pci_fixup_resume, pci_dev); - rc = pm->runtime_resume(dev); + if (pm && pm->runtime_resume) + rc = pm->runtime_resume(dev); pci_dev->runtime_d3cold = false; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 662b7457db23..224d88634115 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -2,6 +2,8 @@ #ifndef DRIVERS_PCI_H #define DRIVERS_PCI_H +#include <linux/pci.h> + #define PCI_FIND_CAP_TTL 48 #define PCI_VSEC_ID_INTEL_TBT 0x1234 /* Thunderbolt */ diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index f78860ce884b..727e3c1ef9a4 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -53,8 +53,6 @@ struct pcie_link_state { struct pcie_link_state *root; /* pointer to the root port link */ struct pcie_link_state *parent; /* pointer to the parent Link state */ struct list_head sibling; /* node in link_list */ - struct list_head children; /* list of child link states */ - struct list_head link; /* node in parent's children list */ /* ASPM state */ u32 aspm_support:7; /* Supported ASPM state */ @@ -850,8 +848,6 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) return NULL; INIT_LIST_HEAD(&link->sibling); - INIT_LIST_HEAD(&link->children); - INIT_LIST_HEAD(&link->link); link->pdev = pdev; link->downstream = pci_function_0(pdev->subordinate); @@ -877,7 +873,6 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) link->parent = parent; link->root = link->parent->root; - list_add(&link->link, &parent->children); } list_add(&link->sibling, &link_list); @@ -1001,7 +996,6 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) /* All functions are removed, so just disable ASPM for the link */ pcie_config_aspm_link(link, 0); list_del(&link->sibling); - list_del(&link->link); /* Clock PM is for endpoint device */ free_link_state(link); diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index e495f04394d0..fbbf00b0992e 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -71,19 +71,19 @@ static inline void *get_service_data(struct pcie_device *dev) struct pcie_port_service_driver { const char *name; - int (*probe) (struct pcie_device *dev); - void (*remove) (struct pcie_device *dev); - int (*suspend) (struct pcie_device *dev); - int (*resume_noirq) (struct pcie_device *dev); - int (*resume) (struct pcie_device *dev); - int (*runtime_suspend) (struct pcie_device *dev); - int (*runtime_resume) (struct pcie_device *dev); + int (*probe)(struct pcie_device *dev); + void (*remove)(struct pcie_device *dev); + int (*suspend)(struct pcie_device *dev); + int (*resume_noirq)(struct pcie_device *dev); + int (*resume)(struct pcie_device *dev); + int (*runtime_suspend)(struct pcie_device *dev); + int (*runtime_resume)(struct pcie_device *dev); /* Device driver may resume normal operations */ void (*error_resume)(struct pci_dev *dev); /* Link Reset Capability - AER service driver specific */ - pci_ers_result_t (*reset_link) (struct pci_dev *dev); + pci_ers_result_t (*reset_link)(struct pci_dev *dev); int port_type; /* Type of the port this driver can handle */ u32 service; /* Port service this device represents */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 4700d24e5d55..b0a413f3f7ca 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -619,6 +619,30 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB, quirk_amd_nl_class); /* + * Synopsys USB 3.x host HAPS platform has a class code of + * PCI_CLASS_SERIAL_USB_XHCI, and xhci driver can claim it. However, these + * devices should use dwc3-haps driver. Change these devices' class code to + * PCI_CLASS_SERIAL_USB_DEVICE to prevent the xhci-pci driver from claiming + * them. + */ +static void quirk_synopsys_haps(struct pci_dev *pdev) +{ + u32 class = pdev->class; + + switch (pdev->device) { + case PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3: + case PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3_AXI: + case PCI_DEVICE_ID_SYNOPSYS_HAPSUSB31: + pdev->class = PCI_CLASS_SERIAL_USB_DEVICE; + pci_info(pdev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n", + class, pdev->class); + break; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, + quirk_synopsys_haps); + +/* * Let's make the southbridge information explicit instead of having to * worry about people probing the ACPI areas, for example.. (Yes, it * happens, and if you read the wrong ACPI register it will put the machine diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 54a8b30dda38..6c5536d3d42a 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -13,7 +13,7 @@ #include <linux/uaccess.h> #include <linux/poll.h> #include <linux/wait.h> - +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/nospec.h> MODULE_DESCRIPTION("Microsemi Switchtec(tm) PCIe Management Driver"); @@ -25,6 +25,11 @@ static int max_devices = 16; module_param(max_devices, int, 0644); MODULE_PARM_DESC(max_devices, "max number of switchtec device instances"); +static bool use_dma_mrpc = 1; +module_param(use_dma_mrpc, bool, 0644); +MODULE_PARM_DESC(use_dma_mrpc, + "Enable the use of the DMA MRPC feature"); + static dev_t switchtec_devt; static DEFINE_IDA(switchtec_minor_ida); @@ -113,6 +118,19 @@ static void stuser_set_state(struct switchtec_user *stuser, static void mrpc_complete_cmd(struct switchtec_dev *stdev); +static void flush_wc_buf(struct switchtec_dev *stdev) +{ + struct ntb_dbmsg_regs __iomem *mmio_dbmsg; + + /* + * odb (outbound doorbell) register is processed by low latency + * hardware and w/o side effect + */ + mmio_dbmsg = (void __iomem *)stdev->mmio_ntb + + SWITCHTEC_NTB_REG_DBMSG_OFFSET; + ioread32(&mmio_dbmsg->odb); +} + static void mrpc_cmd_submit(struct switchtec_dev *stdev) { /* requires the mrpc_mutex to already be held when called */ @@ -128,16 +146,18 @@ static void mrpc_cmd_submit(struct switchtec_dev *stdev) stuser = list_entry(stdev->mrpc_queue.next, struct switchtec_user, list); + if (stdev->dma_mrpc) { + stdev->dma_mrpc->status = SWITCHTEC_MRPC_STATUS_INPROGRESS; + memset(stdev->dma_mrpc->data, 0xFF, SWITCHTEC_MRPC_PAYLOAD_SIZE); + } + stuser_set_state(stuser, MRPC_RUNNING); stdev->mrpc_busy = 1; memcpy_toio(&stdev->mmio_mrpc->input_data, stuser->data, stuser->data_len); + flush_wc_buf(stdev); iowrite32(stuser->cmd, &stdev->mmio_mrpc->cmd); - stuser->status = ioread32(&stdev->mmio_mrpc->status); - if (stuser->status != SWITCHTEC_MRPC_STATUS_INPROGRESS) - mrpc_complete_cmd(stdev); - schedule_delayed_work(&stdev->mrpc_timeout, msecs_to_jiffies(500)); } @@ -170,7 +190,11 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) stuser = list_entry(stdev->mrpc_queue.next, struct switchtec_user, list); - stuser->status = ioread32(&stdev->mmio_mrpc->status); + if (stdev->dma_mrpc) + stuser->status = stdev->dma_mrpc->status; + else + stuser->status = ioread32(&stdev->mmio_mrpc->status); + if (stuser->status == SWITCHTEC_MRPC_STATUS_INPROGRESS) return; @@ -180,13 +204,19 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev) if (stuser->status != SWITCHTEC_MRPC_STATUS_DONE) goto out; - stuser->return_code = ioread32(&stdev->mmio_mrpc->ret_value); + if (stdev->dma_mrpc) + stuser->return_code = stdev->dma_mrpc->rtn_code; + else + stuser->return_code = ioread32(&stdev->mmio_mrpc->ret_value); if (stuser->return_code != 0) goto out; - memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data, - stuser->read_len); - + if (stdev->dma_mrpc) + memcpy(stuser->data, &stdev->dma_mrpc->data, + stuser->read_len); + else + memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data, + stuser->read_len); out: complete_all(&stuser->comp); list_del_init(&stuser->list); @@ -221,7 +251,10 @@ static void mrpc_timeout_work(struct work_struct *work) mutex_lock(&stdev->mrpc_mutex); - status = ioread32(&stdev->mmio_mrpc->status); + if (stdev->dma_mrpc) + status = stdev->dma_mrpc->status; + else + status = ioread32(&stdev->mmio_mrpc->status); if (status == SWITCHTEC_MRPC_STATUS_INPROGRESS) { schedule_delayed_work(&stdev->mrpc_timeout, msecs_to_jiffies(500)); @@ -229,7 +262,6 @@ static void mrpc_timeout_work(struct work_struct *work) } mrpc_complete_cmd(stdev); - out: mutex_unlock(&stdev->mrpc_mutex); } @@ -800,6 +832,7 @@ static int ioctl_event_ctl(struct switchtec_dev *stdev, { int ret; int nr_idxs; + unsigned int event_flags; struct switchtec_ioctl_event_ctl ctl; if (copy_from_user(&ctl, uctl, sizeof(ctl))) @@ -821,7 +854,9 @@ static int ioctl_event_ctl(struct switchtec_dev *stdev, else return -EINVAL; + event_flags = ctl.flags; for (ctl.index = 0; ctl.index < nr_idxs; ctl.index++) { + ctl.flags = event_flags; ret = event_ctl(stdev, &ctl); if (ret < 0) return ret; @@ -1017,10 +1052,24 @@ static void enable_link_state_events(struct switchtec_dev *stdev) } } +static void enable_dma_mrpc(struct switchtec_dev *stdev) +{ + writeq(stdev->dma_mrpc_dma_addr, &stdev->mmio_mrpc->dma_addr); + flush_wc_buf(stdev); + iowrite32(SWITCHTEC_DMA_MRPC_EN, &stdev->mmio_mrpc->dma_en); +} + static void stdev_release(struct device *dev) { struct switchtec_dev *stdev = to_stdev(dev); + if (stdev->dma_mrpc) { + iowrite32(0, &stdev->mmio_mrpc->dma_en); + flush_wc_buf(stdev); + writeq(0, &stdev->mmio_mrpc->dma_addr); + dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc), + stdev->dma_mrpc, stdev->dma_mrpc_dma_addr); + } kfree(stdev); } @@ -1176,10 +1225,27 @@ static irqreturn_t switchtec_event_isr(int irq, void *dev) return ret; } + +static irqreturn_t switchtec_dma_mrpc_isr(int irq, void *dev) +{ + struct switchtec_dev *stdev = dev; + irqreturn_t ret = IRQ_NONE; + + iowrite32(SWITCHTEC_EVENT_CLEAR | + SWITCHTEC_EVENT_EN_IRQ, + &stdev->mmio_part_cfg->mrpc_comp_hdr); + schedule_work(&stdev->mrpc_work); + + ret = IRQ_HANDLED; + return ret; +} + static int switchtec_init_isr(struct switchtec_dev *stdev) { int nvecs; int event_irq; + int dma_mrpc_irq; + int rc; nvecs = pci_alloc_irq_vectors(stdev->pdev, 1, 4, PCI_IRQ_MSIX | PCI_IRQ_MSI); @@ -1194,9 +1260,29 @@ static int switchtec_init_isr(struct switchtec_dev *stdev) if (event_irq < 0) return event_irq; - return devm_request_irq(&stdev->pdev->dev, event_irq, + rc = devm_request_irq(&stdev->pdev->dev, event_irq, switchtec_event_isr, 0, KBUILD_MODNAME, stdev); + + if (rc) + return rc; + + if (!stdev->dma_mrpc) + return rc; + + dma_mrpc_irq = ioread32(&stdev->mmio_mrpc->dma_vector); + if (dma_mrpc_irq < 0 || dma_mrpc_irq >= nvecs) + return -EFAULT; + + dma_mrpc_irq = pci_irq_vector(stdev->pdev, dma_mrpc_irq); + if (dma_mrpc_irq < 0) + return dma_mrpc_irq; + + rc = devm_request_irq(&stdev->pdev->dev, dma_mrpc_irq, + switchtec_dma_mrpc_isr, 0, + KBUILD_MODNAME, stdev); + + return rc; } static void init_pff(struct switchtec_dev *stdev) @@ -1232,19 +1318,38 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, struct pci_dev *pdev) { int rc; + void __iomem *map; + unsigned long res_start, res_len; rc = pcim_enable_device(pdev); if (rc) return rc; - rc = pcim_iomap_regions(pdev, 0x1, KBUILD_MODNAME); + rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); if (rc) return rc; pci_set_master(pdev); - stdev->mmio = pcim_iomap_table(pdev)[0]; - stdev->mmio_mrpc = stdev->mmio + SWITCHTEC_GAS_MRPC_OFFSET; + res_start = pci_resource_start(pdev, 0); + res_len = pci_resource_len(pdev, 0); + + if (!devm_request_mem_region(&pdev->dev, res_start, + res_len, KBUILD_MODNAME)) + return -EBUSY; + + stdev->mmio_mrpc = devm_ioremap_wc(&pdev->dev, res_start, + SWITCHTEC_GAS_TOP_CFG_OFFSET); + if (!stdev->mmio_mrpc) + return -ENOMEM; + + map = devm_ioremap(&pdev->dev, + res_start + SWITCHTEC_GAS_TOP_CFG_OFFSET, + res_len - SWITCHTEC_GAS_TOP_CFG_OFFSET); + if (!map) + return -ENOMEM; + + stdev->mmio = map - SWITCHTEC_GAS_TOP_CFG_OFFSET; stdev->mmio_sw_event = stdev->mmio + SWITCHTEC_GAS_SW_EVENT_OFFSET; stdev->mmio_sys_info = stdev->mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET; stdev->mmio_flash_info = stdev->mmio + SWITCHTEC_GAS_FLASH_INFO_OFFSET; @@ -1262,6 +1367,19 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, pci_set_drvdata(pdev, stdev); + if (!use_dma_mrpc) + return 0; + + if (ioread32(&stdev->mmio_mrpc->dma_ver) == 0) + return 0; + + stdev->dma_mrpc = dma_zalloc_coherent(&stdev->pdev->dev, + sizeof(*stdev->dma_mrpc), + &stdev->dma_mrpc_dma_addr, + GFP_KERNEL); + if (stdev->dma_mrpc == NULL) + return -ENOMEM; + return 0; } @@ -1293,6 +1411,9 @@ static int switchtec_pci_probe(struct pci_dev *pdev, &stdev->mmio_part_cfg->mrpc_comp_hdr); enable_link_state_events(stdev); + if (stdev->dma_mrpc) + enable_dma_mrpc(stdev); + rc = cdev_device_add(&stdev->cdev, &stdev->dev); if (rc) goto err_devadd; @@ -1318,7 +1439,6 @@ static void switchtec_pci_remove(struct pci_dev *pdev) cdev_device_del(&stdev->cdev, &stdev->dev); ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt)); dev_info(&stdev->dev, "unregistered.\n"); - stdev_kill(stdev); put_device(&stdev->dev); } diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index b6fd4838f60f..cc7baf0ecb3c 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -575,12 +575,13 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev) int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) { + u8 event_type; u32 host_event; int ret; if (!ec_dev->mkbp_event_supported) { ret = get_keyboard_state_event(ec_dev); - if (ret < 0) + if (ret <= 0) return ret; if (wake_event) @@ -590,15 +591,26 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) } ret = get_next_event(ec_dev); - if (ret < 0) + if (ret <= 0) return ret; if (wake_event) { + event_type = ec_dev->event_data.event_type; host_event = cros_ec_get_host_event(ec_dev); - /* Consider non-host_event as wake event */ - *wake_event = !host_event || - !!(host_event & ec_dev->host_event_wake_mask); + /* + * Sensor events need to be parsed by the sensor sub-device. + * Defer them, and don't report the wakeup here. + */ + if (event_type == EC_MKBP_EVENT_SENSOR_FIFO) + *wake_event = false; + /* Masked host-events should not count as wake events. */ + else if (host_event && + !(host_event & ec_dev->host_event_wake_mask)) + *wake_event = false; + /* Consider all other events as wake events. */ + else + *wake_event = true; } return ret; diff --git a/drivers/usb/dwc3/dwc3-haps.c b/drivers/usb/dwc3/dwc3-haps.c index c9cc33881bef..02d57d98ef9b 100644 --- a/drivers/usb/dwc3/dwc3-haps.c +++ b/drivers/usb/dwc3/dwc3-haps.c @@ -15,10 +15,6 @@ #include <linux/platform_device.h> #include <linux/property.h> -#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3 0xabcd -#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3_AXI 0xabce -#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB31 0xabcf - /** * struct dwc3_haps - Driver private structure * @dwc3: child dwc3 platform_device diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index e413f54208f4..ae7712c9687a 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -184,7 +184,7 @@ config FB_MACMODES depends on FB config FB_BACKLIGHT - bool + tristate depends on FB select BACKLIGHT_LCD_SUPPORT select BACKLIGHT_CLASS_DEVICE @@ -2037,7 +2037,8 @@ config FB_XILINX config FB_GOLDFISH tristate "Goldfish Framebuffer" - depends on FB && HAS_DMA && (GOLDFISH || COMPILE_TEST) + depends on FB + depends on GOLDFISH || COMPILE_TEST select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c index ff561073ee4e..42f909618f04 100644 --- a/drivers/video/fbdev/clps711x-fb.c +++ b/drivers/video/fbdev/clps711x-fb.c @@ -287,14 +287,17 @@ static int clps711x_fb_probe(struct platform_device *pdev) } ret = of_get_fb_videomode(disp, &cfb->mode, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + of_node_put(disp); goto out_fb_release; + } of_property_read_u32(disp, "ac-prescale", &cfb->ac_prescale); cfb->cmap_invert = of_property_read_bool(disp, "cmap-invert"); ret = of_property_read_u32(disp, "bits-per-pixel", &info->var.bits_per_pixel); + of_node_put(disp); if (ret) goto out_fb_release; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 8958ccc8b1ac..8976190b6c1f 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -3064,7 +3064,7 @@ static int fbcon_fb_unbind(int idx) for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] != idx && con2fb_map[i] != -1) { - new_idx = i; + new_idx = con2fb_map[i]; break; } } diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 861bf8081619..558ed2ed3124 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -436,7 +436,9 @@ static void fb_do_show_logo(struct fb_info *info, struct fb_image *image, image->dx += image->width + 8; } } else if (rotate == FB_ROTATE_UD) { - for (x = 0; x < num; x++) { + u32 dx = image->dx; + + for (x = 0; x < num && image->dx <= dx; x++) { info->fbops->fb_imageblit(info, image); image->dx -= image->width + 8; } @@ -448,7 +450,9 @@ static void fb_do_show_logo(struct fb_info *info, struct fb_image *image, image->dy += image->height + 8; } } else if (rotate == FB_ROTATE_CCW) { - for (x = 0; x < num; x++) { + u32 dy = image->dy; + + for (x = 0; x < num && image->dy <= dy; x++) { info->fbops->fb_imageblit(info, image); image->dy -= image->height + 8; } @@ -502,8 +506,25 @@ static int fb_show_logo_line(struct fb_info *info, int rotate, fb_set_logo(info, logo, logo_new, fb_logo.depth); } +#ifdef CONFIG_FB_LOGO_CENTER + { + int xres = info->var.xres; + int yres = info->var.yres; + + if (rotate == FB_ROTATE_CW || rotate == FB_ROTATE_CCW) { + xres = info->var.yres; + yres = info->var.xres; + } + + while (n && (n * (logo->width + 8) - 8 > xres)) + --n; + image.dx = (xres - n * (logo->width + 8) - 8) / 2; + image.dy = y ?: (yres - logo->height) / 2; + } +#else image.dx = 0; image.dy = y; +#endif image.width = logo->width; image.height = logo->height; @@ -521,7 +542,7 @@ static int fb_show_logo_line(struct fb_info *info, int rotate, info->pseudo_palette = saved_pseudo_palette; kfree(logo_new); kfree(logo_rotate); - return logo->height; + return image.dy + logo->height; } @@ -573,8 +594,8 @@ static int fb_show_extra_logos(struct fb_info *info, int y, int rotate) unsigned int i; for (i = 0; i < fb_logo_ex_num; i++) - y += fb_show_logo_line(info, rotate, - fb_logo_ex[i].logo, y, fb_logo_ex[i].n); + y = fb_show_logo_line(info, rotate, + fb_logo_ex[i].logo, y, fb_logo_ex[i].n); return y; } @@ -600,6 +621,7 @@ int fb_prepare_logo(struct fb_info *info, int rotate) { int depth = fb_get_color_depth(&info->var, &info->fix); unsigned int yres; + int height; memset(&fb_logo, 0, sizeof(struct logo_data)); @@ -661,7 +683,12 @@ int fb_prepare_logo(struct fb_info *info, int rotate) } } - return fb_prepare_extra_logos(info, fb_logo.logo->height, yres); + height = fb_logo.logo->height; +#ifdef CONFIG_FB_LOGO_CENTER + height += (yres - fb_logo.logo->height) / 2; +#endif + + return fb_prepare_extra_logos(info, height, yres); } int fb_show_logo(struct fb_info *info, int rotate) diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index e31a182b42bf..44cca39f2b51 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -60,7 +60,7 @@ struct fb_info *framebuffer_alloc(size_t size, struct device *dev) info->device = dev; info->fbcon_rotate_hint = -1; -#ifdef CONFIG_FB_BACKLIGHT +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) mutex_init(&info->bl_curve_mutex); #endif @@ -429,7 +429,7 @@ static ssize_t show_fbstate(struct device *device, return snprintf(buf, PAGE_SIZE, "%d\n", fb_info->state); } -#ifdef CONFIG_FB_BACKLIGHT +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) static ssize_t store_bl_curve(struct device *device, struct device_attribute *attr, const char *buf, size_t count) @@ -510,7 +510,7 @@ static struct device_attribute device_attrs[] = { __ATTR(stride, S_IRUGO, show_stride, NULL), __ATTR(rotate, S_IRUGO|S_IWUSR, show_rotate, store_rotate), __ATTR(state, S_IRUGO|S_IWUSR, show_fbstate, store_fbstate), -#ifdef CONFIG_FB_BACKLIGHT +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) __ATTR(bl_curve, S_IRUGO|S_IWUSR, show_bl_curve, store_bl_curve), #endif }; @@ -551,7 +551,7 @@ void fb_cleanup_device(struct fb_info *fb_info) } } -#ifdef CONFIG_FB_BACKLIGHT +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) /* This function generates a linear backlight curve * * 0: off diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index 332a56b6811f..9a5451ba4d44 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -1575,8 +1575,7 @@ static void uninstall_fb(struct fb_info *info) unregister_framebuffer(info); unmap_video_memory(info); - if (&info->cmap) - fb_dealloc_cmap(&info->cmap); + fb_dealloc_cmap(&info->cmap); mfbi->registered = 0; } diff --git a/drivers/video/fbdev/omap2/omapfb/dss/core.c b/drivers/video/fbdev/omap2/omapfb/dss/core.c index a5e58a829ea0..b4bcf3a4a647 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/core.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/core.c @@ -99,24 +99,14 @@ int dss_set_min_bus_tput(struct device *dev, unsigned long tput) } #if defined(CONFIG_FB_OMAP2_DSS_DEBUGFS) -static int dss_debug_show(struct seq_file *s, void *unused) +static int dss_show(struct seq_file *s, void *unused) { void (*func)(struct seq_file *) = s->private; func(s); return 0; } -static int dss_debug_open(struct inode *inode, struct file *file) -{ - return single_open(file, dss_debug_show, inode->i_private); -} - -static const struct file_operations dss_debug_fops = { - .open = dss_debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(dss); static struct dentry *dss_debugfs_dir; @@ -130,7 +120,7 @@ static int dss_initialize_debugfs(void) } debugfs_create_file("clk", S_IRUGO, dss_debugfs_dir, - &dss_debug_dump_clocks, &dss_debug_fops); + &dss_debug_dump_clocks, &dss_fops); return 0; } @@ -145,7 +135,7 @@ int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *)) struct dentry *d; d = debugfs_create_file(name, S_IRUGO, dss_debugfs_dir, - write, &dss_debug_fops); + write, &dss_fops); return PTR_ERR_OR_ZERO(d); } diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index e31340fad3c7..1410f476e135 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -279,7 +279,7 @@ static void set_clock_divider(struct pxa168fb_info *fbi, /* check whether divisor is too small. */ if (divider_int < 2) { - dev_warn(fbi->dev, "Warning: clock source is too slow." + dev_warn(fbi->dev, "Warning: clock source is too slow. " "Try smaller resolution\n"); divider_int = 2; } diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index bbed039617a4..d59c8a59f582 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2234,10 +2234,8 @@ static struct pxafb_mach_info *of_pxafb_of_mach_info(struct device *dev) if (!info) return ERR_PTR(-ENOMEM); ret = of_get_pxafb_mode_info(dev, info); - if (ret) { - kfree(info->modes); + if (ret) return ERR_PTR(ret); - } /* * On purpose, neither lccrX registers nor video memory size can be diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 070026a7e55a..1d034dddc556 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -1598,7 +1598,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); if (!dlfb) { dev_err(&intf->dev, "%s: failed to allocate dlfb\n", __func__); - goto error; + return -ENOMEM; } INIT_LIST_HEAD(&dlfb->deferred_free); @@ -1703,7 +1703,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, error: if (dlfb->info) { dlfb_ops_destroy(dlfb->info); - } else if (dlfb) { + } else { usb_put_dev(dlfb->udev); kfree(dlfb); } @@ -1730,12 +1730,10 @@ static void dlfb_usb_disconnect(struct usb_interface *intf) /* this function will wait for all in-flight urbs to complete */ dlfb_free_urb_list(dlfb); - if (info) { - /* remove udlfb's sysfs interfaces */ - for (i = 0; i < ARRAY_SIZE(fb_device_attrs); i++) - device_remove_file(info->dev, &fb_device_attrs[i]); - device_remove_bin_file(info->dev, &edid_attr); - } + /* remove udlfb's sysfs interfaces */ + for (i = 0; i < ARRAY_SIZE(fb_device_attrs); i++) + device_remove_file(info->dev, &fb_device_attrs[i]); + device_remove_bin_file(info->dev, &edid_attr); unregister_framebuffer(info); } diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index 440a6636d8f0..34dc8e53a1e9 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1979,7 +1979,7 @@ MODULE_PARM_DESC(noedid, module_param(vram_remap, uint, 0); MODULE_PARM_DESC(vram_remap, "Set amount of video memory to be used [MiB]"); module_param(vram_total, uint, 0); -MODULE_PARM_DESC(vram_total, "Set total amount of video memoery [MiB]"); +MODULE_PARM_DESC(vram_total, "Set total amount of video memory [MiB]"); module_param(maxclk, ushort, 0); MODULE_PARM_DESC(maxclk, "Maximum pixelclock [MHz], overrides EDID data"); module_param(maxhf, ushort, 0); diff --git a/drivers/video/logo/Kconfig b/drivers/video/logo/Kconfig index d1f6196c8b9a..1e972c4e88b1 100644 --- a/drivers/video/logo/Kconfig +++ b/drivers/video/logo/Kconfig @@ -10,6 +10,15 @@ menuconfig LOGO if LOGO +config FB_LOGO_CENTER + bool "Center the logo" + depends on FB=y + help + When this option is selected, the bootup logo is centered both + horizontally and vertically. If more than one logo is displayed + due to multiple CPUs, the collected line of logos is centered + as a whole. + config FB_LOGO_EXTRA bool depends on FB=y diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 0f46cf550907..4dc788e3bc96 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -133,15 +133,25 @@ struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) } EXPORT_SYMBOL(fscrypt_get_ctx); +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci) +{ + memset(iv, 0, ci->ci_mode->ivsize); + iv->lblk_num = cpu_to_le64(lblk_num); + + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) + memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); + + if (ci->ci_essiv_tfm != NULL) + crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw); +} + int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, u64 lblk_num, struct page *src_page, struct page *dest_page, unsigned int len, unsigned int offs, gfp_t gfp_flags) { - struct { - __le64 index; - u8 padding[FS_IV_SIZE - sizeof(__le64)]; - } iv; + union fscrypt_iv iv; struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist dst, src; @@ -151,15 +161,7 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, BUG_ON(len == 0); - BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE); - BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE); - iv.index = cpu_to_le64(lblk_num); - memset(iv.padding, 0, sizeof(iv.padding)); - - if (ci->ci_essiv_tfm != NULL) { - crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv, - (u8 *)&iv); - } + fscrypt_generate_iv(&iv, lblk_num, ci); req = skcipher_request_alloc(tfm, gfp_flags); if (!req) diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index d7a0f682ca12..7ff40a73dbec 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -40,10 +40,11 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, { struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); - struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + union fscrypt_iv iv; struct scatterlist sg; + int res; /* * Copy the filename to the output buffer for encrypting in-place and @@ -55,7 +56,7 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, memset(out + iname->len, 0, olen - iname->len); /* Initialize the IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); @@ -65,7 +66,7 @@ int fname_encrypt(struct inode *inode, const struct qstr *iname, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); sg_init_one(&sg, out, olen); - skcipher_request_set_crypt(req, &sg, &sg, olen, iv); + skcipher_request_set_crypt(req, &sg, &sg, olen, &iv); /* Do the encryption */ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); @@ -94,9 +95,10 @@ static int fname_decrypt(struct inode *inode, struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; - struct crypto_skcipher *tfm = inode->i_crypt_info->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; + struct fscrypt_info *ci = inode->i_crypt_info; + struct crypto_skcipher *tfm = ci->ci_ctfm; + union fscrypt_iv iv; + int res; /* Allocate request */ req = skcipher_request_alloc(tfm, GFP_NOFS); @@ -107,12 +109,12 @@ static int fname_decrypt(struct inode *inode, crypto_req_done, &wait); /* Initialize IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Create decryption request */ sg_init_one(&src_sg, iname->name, iname->len); sg_init_one(&dst_sg, oname->name, oname->len); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv); res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait); skcipher_request_free(req); if (res < 0) { diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 79debfc9cef9..7424f851eb5c 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -17,7 +17,6 @@ #include <crypto/hash.h> /* Encryption parameters */ -#define FS_IV_SIZE 16 #define FS_KEY_DERIVATION_NONCE_SIZE 16 /** @@ -52,16 +51,42 @@ struct fscrypt_symlink_data { } __packed; /* - * A pointer to this structure is stored in the file system's in-core - * representation of an inode. + * fscrypt_info - the "encryption key" for an inode + * + * When an encrypted file's key is made available, an instance of this struct is + * allocated and stored in ->i_crypt_info. Once created, it remains until the + * inode is evicted. */ struct fscrypt_info { + + /* The actual crypto transform used for encryption and decryption */ + struct crypto_skcipher *ci_ctfm; + + /* + * Cipher for ESSIV IV generation. Only set for CBC contents + * encryption, otherwise is NULL. + */ + struct crypto_cipher *ci_essiv_tfm; + + /* + * Encryption mode used for this inode. It corresponds to either + * ci_data_mode or ci_filename_mode, depending on the inode type. + */ + struct fscrypt_mode *ci_mode; + + /* + * If non-NULL, then this inode uses a master key directly rather than a + * derived key, and ci_ctfm will equal ci_master_key->mk_ctfm. + * Otherwise, this inode uses a derived key. + */ + struct fscrypt_master_key *ci_master_key; + + /* fields from the fscrypt_context */ u8 ci_data_mode; u8 ci_filename_mode; u8 ci_flags; - struct crypto_skcipher *ci_ctfm; - struct crypto_cipher *ci_essiv_tfm; - u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; }; typedef enum { @@ -83,6 +108,10 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode, filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) return true; + if (contents_mode == FS_ENCRYPTION_MODE_ADIANTUM && + filenames_mode == FS_ENCRYPTION_MODE_ADIANTUM) + return true; + return false; } @@ -107,6 +136,22 @@ fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...); #define fscrypt_err(sb, fmt, ...) \ fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__) +#define FSCRYPT_MAX_IV_SIZE 32 + +union fscrypt_iv { + struct { + /* logical block number within the file */ + __le64 lblk_num; + + /* per-file nonce; only set in DIRECT_KEY mode */ + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + }; + u8 raw[FSCRYPT_MAX_IV_SIZE]; +}; + +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci); + /* fname.c */ extern int fname_encrypt(struct inode *inode, const struct qstr *iname, u8 *out, unsigned int olen); @@ -115,6 +160,16 @@ extern bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 *encrypted_len_ret); /* keyinfo.c */ + +struct fscrypt_mode { + const char *friendly_name; + const char *cipher_str; + int keysize; + int ivsize; + bool logged_impl_name; + bool needs_essiv; +}; + extern void __exit fscrypt_essiv_cleanup(void); #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 7874c9bb2fc5..1e11a683f63d 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -10,15 +10,21 @@ */ #include <keys/user-type.h> +#include <linux/hashtable.h> #include <linux/scatterlist.h> #include <linux/ratelimit.h> #include <crypto/aes.h> +#include <crypto/algapi.h> #include <crypto/sha.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" static struct crypto_shash *essiv_hash_tfm; +/* Table of keys referenced by FS_POLICY_FLAG_DIRECT_KEY policies */ +static DEFINE_HASHTABLE(fscrypt_master_keys, 6); /* 6 bits = 64 buckets */ +static DEFINE_SPINLOCK(fscrypt_master_keys_lock); + /* * Key derivation function. This generates the derived key by encrypting the * master key with AES-128-ECB using the inode's nonce as the AES key. @@ -123,56 +129,37 @@ invalid: return ERR_PTR(-ENOKEY); } -/* Find the master key, then derive the inode's actual encryption key */ -static int find_and_derive_key(const struct inode *inode, - const struct fscrypt_context *ctx, - u8 *derived_key, unsigned int derived_keysize) -{ - struct key *key; - const struct fscrypt_key *payload; - int err; - - key = find_and_lock_process_key(FS_KEY_DESC_PREFIX, - ctx->master_key_descriptor, - derived_keysize, &payload); - if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) { - key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix, - ctx->master_key_descriptor, - derived_keysize, &payload); - } - if (IS_ERR(key)) - return PTR_ERR(key); - err = derive_key_aes(payload->raw, ctx, derived_key, derived_keysize); - up_read(&key->sem); - key_put(key); - return err; -} - -static struct fscrypt_mode { - const char *friendly_name; - const char *cipher_str; - int keysize; - bool logged_impl_name; -} available_modes[] = { +static struct fscrypt_mode available_modes[] = { [FS_ENCRYPTION_MODE_AES_256_XTS] = { .friendly_name = "AES-256-XTS", .cipher_str = "xts(aes)", .keysize = 64, + .ivsize = 16, }, [FS_ENCRYPTION_MODE_AES_256_CTS] = { .friendly_name = "AES-256-CTS-CBC", .cipher_str = "cts(cbc(aes))", .keysize = 32, + .ivsize = 16, }, [FS_ENCRYPTION_MODE_AES_128_CBC] = { .friendly_name = "AES-128-CBC", .cipher_str = "cbc(aes)", .keysize = 16, + .ivsize = 16, + .needs_essiv = true, }, [FS_ENCRYPTION_MODE_AES_128_CTS] = { .friendly_name = "AES-128-CTS-CBC", .cipher_str = "cts(cbc(aes))", .keysize = 16, + .ivsize = 16, + }, + [FS_ENCRYPTION_MODE_ADIANTUM] = { + .friendly_name = "Adiantum", + .cipher_str = "adiantum(xchacha12,aes)", + .keysize = 32, + .ivsize = 32, }, }; @@ -198,14 +185,196 @@ select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode) return ERR_PTR(-EINVAL); } -static void put_crypt_info(struct fscrypt_info *ci) +/* Find the master key, then derive the inode's actual encryption key */ +static int find_and_derive_key(const struct inode *inode, + const struct fscrypt_context *ctx, + u8 *derived_key, const struct fscrypt_mode *mode) { - if (!ci) + struct key *key; + const struct fscrypt_key *payload; + int err; + + key = find_and_lock_process_key(FS_KEY_DESC_PREFIX, + ctx->master_key_descriptor, + mode->keysize, &payload); + if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) { + key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix, + ctx->master_key_descriptor, + mode->keysize, &payload); + } + if (IS_ERR(key)) + return PTR_ERR(key); + + if (ctx->flags & FS_POLICY_FLAG_DIRECT_KEY) { + if (mode->ivsize < offsetofend(union fscrypt_iv, nonce)) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with %s", + mode->friendly_name); + err = -EINVAL; + } else if (ctx->contents_encryption_mode != + ctx->filenames_encryption_mode) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with different contents and filenames modes"); + err = -EINVAL; + } else { + memcpy(derived_key, payload->raw, mode->keysize); + err = 0; + } + } else { + err = derive_key_aes(payload->raw, ctx, derived_key, + mode->keysize); + } + up_read(&key->sem); + key_put(key); + return err; +} + +/* Allocate and key a symmetric cipher object for the given encryption mode */ +static struct crypto_skcipher * +allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, + const struct inode *inode) +{ + struct crypto_skcipher *tfm; + int err; + + tfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0); + if (IS_ERR(tfm)) { + fscrypt_warn(inode->i_sb, + "error allocating '%s' transform for inode %lu: %ld", + mode->cipher_str, inode->i_ino, PTR_ERR(tfm)); + return tfm; + } + if (unlikely(!mode->logged_impl_name)) { + /* + * fscrypt performance can vary greatly depending on which + * crypto algorithm implementation is used. Help people debug + * performance problems by logging the ->cra_driver_name the + * first time a mode is used. Note that multiple threads can + * race here, but it doesn't really matter. + */ + mode->logged_impl_name = true; + pr_info("fscrypt: %s using implementation \"%s\"\n", + mode->friendly_name, + crypto_skcipher_alg(tfm)->base.cra_driver_name); + } + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); + if (err) + goto err_free_tfm; + + return tfm; + +err_free_tfm: + crypto_free_skcipher(tfm); + return ERR_PTR(err); +} + +/* Master key referenced by FS_POLICY_FLAG_DIRECT_KEY policy */ +struct fscrypt_master_key { + struct hlist_node mk_node; + refcount_t mk_refcount; + const struct fscrypt_mode *mk_mode; + struct crypto_skcipher *mk_ctfm; + u8 mk_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 mk_raw[FS_MAX_KEY_SIZE]; +}; + +static void free_master_key(struct fscrypt_master_key *mk) +{ + if (mk) { + crypto_free_skcipher(mk->mk_ctfm); + kzfree(mk); + } +} + +static void put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_lock(&mk->mk_refcount, &fscrypt_master_keys_lock)) return; + hash_del(&mk->mk_node); + spin_unlock(&fscrypt_master_keys_lock); - crypto_free_skcipher(ci->ci_ctfm); - crypto_free_cipher(ci->ci_essiv_tfm); - kmem_cache_free(fscrypt_info_cachep, ci); + free_master_key(mk); +} + +/* + * Find/insert the given master key into the fscrypt_master_keys table. If + * found, it is returned with elevated refcount, and 'to_insert' is freed if + * non-NULL. If not found, 'to_insert' is inserted and returned if it's + * non-NULL; otherwise NULL is returned. + */ +static struct fscrypt_master_key * +find_or_insert_master_key(struct fscrypt_master_key *to_insert, + const u8 *raw_key, const struct fscrypt_mode *mode, + const struct fscrypt_info *ci) +{ + unsigned long hash_key; + struct fscrypt_master_key *mk; + + /* + * Careful: to avoid potentially leaking secret key bytes via timing + * information, we must key the hash table by descriptor rather than by + * raw key, and use crypto_memneq() when comparing raw keys. + */ + + BUILD_BUG_ON(sizeof(hash_key) > FS_KEY_DESCRIPTOR_SIZE); + memcpy(&hash_key, ci->ci_master_key_descriptor, sizeof(hash_key)); + + spin_lock(&fscrypt_master_keys_lock); + hash_for_each_possible(fscrypt_master_keys, mk, mk_node, hash_key) { + if (memcmp(ci->ci_master_key_descriptor, mk->mk_descriptor, + FS_KEY_DESCRIPTOR_SIZE) != 0) + continue; + if (mode != mk->mk_mode) + continue; + if (crypto_memneq(raw_key, mk->mk_raw, mode->keysize)) + continue; + /* using existing tfm with same (descriptor, mode, raw_key) */ + refcount_inc(&mk->mk_refcount); + spin_unlock(&fscrypt_master_keys_lock); + free_master_key(to_insert); + return mk; + } + if (to_insert) + hash_add(fscrypt_master_keys, &to_insert->mk_node, hash_key); + spin_unlock(&fscrypt_master_keys_lock); + return to_insert; +} + +/* Prepare to encrypt directly using the master key in the given mode */ +static struct fscrypt_master_key * +fscrypt_get_master_key(const struct fscrypt_info *ci, struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + int err; + + /* Is there already a tfm for this key? */ + mk = find_or_insert_master_key(NULL, raw_key, mode, ci); + if (mk) + return mk; + + /* Nope, allocate one. */ + mk = kzalloc(sizeof(*mk), GFP_NOFS); + if (!mk) + return ERR_PTR(-ENOMEM); + refcount_set(&mk->mk_refcount, 1); + mk->mk_mode = mode; + mk->mk_ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(mk->mk_ctfm)) { + err = PTR_ERR(mk->mk_ctfm); + mk->mk_ctfm = NULL; + goto err_free_mk; + } + memcpy(mk->mk_descriptor, ci->ci_master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(mk->mk_raw, raw_key, mode->keysize); + + return find_or_insert_master_key(mk, raw_key, mode, ci); + +err_free_mk: + free_master_key(mk); + return ERR_PTR(err); } static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) @@ -275,11 +444,67 @@ void __exit fscrypt_essiv_cleanup(void) crypto_free_shash(essiv_hash_tfm); } +/* + * Given the encryption mode and key (normally the derived key, but for + * FS_POLICY_FLAG_DIRECT_KEY mode it's the master key), set up the inode's + * symmetric cipher transform object(s). + */ +static int setup_crypto_transform(struct fscrypt_info *ci, + struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + struct crypto_skcipher *ctfm; + int err; + + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) { + mk = fscrypt_get_master_key(ci, mode, raw_key, inode); + if (IS_ERR(mk)) + return PTR_ERR(mk); + ctfm = mk->mk_ctfm; + } else { + mk = NULL; + ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(ctfm)) + return PTR_ERR(ctfm); + } + ci->ci_master_key = mk; + ci->ci_ctfm = ctfm; + + if (mode->needs_essiv) { + /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */ + WARN_ON(mode->ivsize != AES_BLOCK_SIZE); + WARN_ON(ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY); + + err = init_essiv_generator(ci, raw_key, mode->keysize); + if (err) { + fscrypt_warn(inode->i_sb, + "error initializing ESSIV generator for inode %lu: %d", + inode->i_ino, err); + return err; + } + } + return 0; +} + +static void put_crypt_info(struct fscrypt_info *ci) +{ + if (!ci) + return; + + if (ci->ci_master_key) { + put_master_key(ci->ci_master_key); + } else { + crypto_free_skcipher(ci->ci_ctfm); + crypto_free_cipher(ci->ci_essiv_tfm); + } + kmem_cache_free(fscrypt_info_cachep, ci); +} + int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; struct fscrypt_context ctx; - struct crypto_skcipher *ctfm; struct fscrypt_mode *mode; u8 *raw_key = NULL; int res; @@ -312,74 +537,42 @@ int fscrypt_get_encryption_info(struct inode *inode) if (ctx.flags & ~FS_POLICY_FLAGS_VALID) return -EINVAL; - crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS); + crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS); if (!crypt_info) return -ENOMEM; crypt_info->ci_flags = ctx.flags; crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; - crypt_info->ci_ctfm = NULL; - crypt_info->ci_essiv_tfm = NULL; - memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, - sizeof(crypt_info->ci_master_key)); + memcpy(crypt_info->ci_master_key_descriptor, ctx.master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(crypt_info->ci_nonce, ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); mode = select_encryption_mode(crypt_info, inode); if (IS_ERR(mode)) { res = PTR_ERR(mode); goto out; } + WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); + crypt_info->ci_mode = mode; /* - * This cannot be a stack buffer because it is passed to the scatterlist - * crypto API as part of key derivation. + * This cannot be a stack buffer because it may be passed to the + * scatterlist crypto API as part of key derivation. */ res = -ENOMEM; raw_key = kmalloc(mode->keysize, GFP_NOFS); if (!raw_key) goto out; - res = find_and_derive_key(inode, &ctx, raw_key, mode->keysize); + res = find_and_derive_key(inode, &ctx, raw_key, mode); if (res) goto out; - ctfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0); - if (IS_ERR(ctfm)) { - res = PTR_ERR(ctfm); - fscrypt_warn(inode->i_sb, - "error allocating '%s' transform for inode %lu: %d", - mode->cipher_str, inode->i_ino, res); - goto out; - } - if (unlikely(!mode->logged_impl_name)) { - /* - * fscrypt performance can vary greatly depending on which - * crypto algorithm implementation is used. Help people debug - * performance problems by logging the ->cra_driver_name the - * first time a mode is used. Note that multiple threads can - * race here, but it doesn't really matter. - */ - mode->logged_impl_name = true; - pr_info("fscrypt: %s using implementation \"%s\"\n", - mode->friendly_name, - crypto_skcipher_alg(ctfm)->base.cra_driver_name); - } - crypt_info->ci_ctfm = ctfm; - crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); - res = crypto_skcipher_setkey(ctfm, raw_key, mode->keysize); + res = setup_crypto_transform(crypt_info, mode, raw_key, inode); if (res) goto out; - if (S_ISREG(inode->i_mode) && - crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) { - res = init_essiv_generator(crypt_info, raw_key, mode->keysize); - if (res) { - fscrypt_warn(inode->i_sb, - "error initializing ESSIV generator for inode %lu: %d", - inode->i_ino, res); - goto out; - } - } if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index c6d431a5cce9..f490de921ce8 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -199,7 +199,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) child_ci = child->i_crypt_info; if (parent_ci && child_ci) { - return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key, + return memcmp(parent_ci->ci_master_key_descriptor, + child_ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE) == 0 && (parent_ci->ci_data_mode == child_ci->ci_data_mode) && (parent_ci->ci_filename_mode == @@ -254,7 +255,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, ctx.contents_encryption_mode = ci->ci_data_mode; ctx.filenames_encryption_mode = ci->ci_filename_mode; ctx.flags = ci->ci_flags; - memcpy(ctx.master_key_descriptor, ci->ci_master_key, + memcpy(ctx.master_key_descriptor, ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 26a7fe5c4fd3..712f00995390 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,8 +116,16 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; + if (!journal) { - ret = __generic_file_fsync(file, start, end, datasync); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL + }; + + ret = ext4_write_inode(inode, &wbc); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -125,9 +133,6 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. @@ -159,6 +164,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = err; } out: + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; trace_ext4_sync_file_exit(inode, ret); return ret; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 27373d88b5f0..56f6e1782d5f 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1890,12 +1890,12 @@ int ext4_inline_data_fiemap(struct inode *inode, physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; physical += offsetof(struct ext4_inode, i_block); - if (physical) - error = fiemap_fill_next_extent(fieinfo, start, physical, - inline_len, flags); brelse(iloc.bh); out: up_read(&EXT4_I(inode)->xattr_sem); + if (physical) + error = fiemap_fill_next_extent(fieinfo, start, physical, + inline_len, flags); return (error < 0 ? error : 0); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9affabd07682..34d7e0703cc6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2778,7 +2778,8 @@ static int ext4_writepages(struct address_space *mapping, * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ - rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits); + rsv_blocks = 1 + ext4_chunk_trans_blocks(inode, + PAGE_SIZE >> inode->i_blkbits); } /* @@ -4833,7 +4834,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, gid_t i_gid; projid_t i_projid; - if (((flags & EXT4_IGET_NORMAL) && + if ((!(flags & EXT4_IGET_SPECIAL) && (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)) || (ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d6c142d73d99..fb12d3c17c1b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4902,7 +4902,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) ext4_superblock_csum_set(sb); if (sync) lock_buffer(sbh); - if (buffer_write_io_error(sbh)) { + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 2ad5c363d7d5..cb422cbe587d 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -35,13 +35,12 @@ extern void debug_dma_map_single(struct device *dev, const void *addr, extern void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction, dma_addr_t dma_addr, - bool map_single); + int direction, dma_addr_t dma_addr); extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction, bool map_single); + size_t size, int direction); extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, int mapped_ents, int direction); @@ -95,8 +94,7 @@ static inline void debug_dma_map_single(struct device *dev, const void *addr, static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction, dma_addr_t dma_addr, - bool map_single) + int direction, dma_addr_t dma_addr) { } @@ -106,8 +104,7 @@ static inline void debug_dma_mapping_error(struct device *dev, } static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction, - bool map_single) + size_t size, int direction) { } diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index ba521d5506c9..cef2127e1d70 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -194,33 +194,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -#ifdef CONFIG_HAS_DMA -#include <asm/dma-mapping.h> -static inline const struct dma_map_ops *get_dma_ops(struct device *dev) -{ - if (dev && dev->dma_ops) - return dev->dma_ops; - return get_arch_dma_ops(dev ? dev->bus : NULL); -} - -static inline void set_dma_ops(struct device *dev, - const struct dma_map_ops *dma_ops) -{ - dev->dma_ops = dma_ops; -} -#else -/* - * Define the dma api to allow compilation of dma dependent code. - * Code that depends on the dma-mapping API needs to set 'depends on HAS_DMA' - * in its Kconfig, unless it already depends on <something> || COMPILE_TEST, - * where <something> guarantuees the availability of the dma-mapping API. - */ -static inline const struct dma_map_ops *get_dma_ops(struct device *dev) -{ - return NULL; -} -#endif - static inline bool dma_is_direct(const struct dma_map_ops *ops) { return likely(!ops); @@ -284,32 +257,41 @@ static inline void dma_direct_sync_sg_for_cpu(struct device *dev, } #endif -static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, - size_t size, - enum dma_data_direction dir, - unsigned long attrs) +#ifdef CONFIG_HAS_DMA +#include <asm/dma-mapping.h> + +static inline const struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (dev && dev->dma_ops) + return dev->dma_ops; + return get_arch_dma_ops(dev ? dev->bus : NULL); +} + +static inline void set_dma_ops(struct device *dev, + const struct dma_map_ops *dma_ops) +{ + dev->dma_ops = dma_ops; +} + +static inline dma_addr_t dma_map_page_attrs(struct device *dev, + struct page *page, size_t offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); - debug_dma_map_single(dev, ptr, size); if (dma_is_direct(ops)) - addr = dma_direct_map_page(dev, virt_to_page(ptr), - offset_in_page(ptr), size, dir, attrs); + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); else - addr = ops->map_page(dev, virt_to_page(ptr), - offset_in_page(ptr), size, dir, attrs); - debug_dma_map_page(dev, virt_to_page(ptr), - offset_in_page(ptr), size, - dir, addr, true); + addr = ops->map_page(dev, page, offset, size, dir, attrs); + debug_dma_map_page(dev, page, offset, size, dir, addr); + return addr; } -static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, - size_t size, - enum dma_data_direction dir, - unsigned long attrs) +static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -318,13 +300,7 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, dma_direct_unmap_page(dev, addr, size, dir, attrs); else if (ops->unmap_page) ops->unmap_page(dev, addr, size, dir, attrs); - debug_dma_unmap_page(dev, addr, size, dir, true); -} - -static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - return dma_unmap_single_attrs(dev, addr, size, dir, attrs); + debug_dma_unmap_page(dev, addr, size, dir); } /* @@ -363,25 +339,6 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg ops->unmap_sg(dev, sg, nents, dir, attrs); } -static inline dma_addr_t dma_map_page_attrs(struct device *dev, - struct page *page, - size_t offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - dma_addr_t addr; - - BUG_ON(!valid_dma_direction(dir)); - if (dma_is_direct(ops)) - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); - else - addr = ops->map_page(dev, page, offset, size, dir, attrs); - debug_dma_map_page(dev, page, offset, size, dir, addr, false); - - return addr; -} - static inline dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, @@ -431,13 +388,6 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, debug_dma_sync_single_for_cpu(dev, addr, size, dir); } -static inline void dma_sync_single_range_for_cpu(struct device *dev, - dma_addr_t addr, unsigned long offset, size_t size, - enum dma_data_direction dir) -{ - return dma_sync_single_for_cpu(dev, addr + offset, size, dir); -} - static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -452,13 +402,6 @@ static inline void dma_sync_single_for_device(struct device *dev, debug_dma_sync_single_for_device(dev, addr, size, dir); } -static inline void dma_sync_single_range_for_device(struct device *dev, - dma_addr_t addr, unsigned long offset, size_t size, - enum dma_data_direction dir) -{ - return dma_sync_single_for_device(dev, addr + offset, size, dir); -} - static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) @@ -488,15 +431,174 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + debug_dma_mapping_error(dev, dma_addr); + + if (dma_addr == DMA_MAPPING_ERROR) + return -ENOMEM; + return 0; +} + +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t flag, unsigned long attrs); +void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs); +void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs); +void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle); +void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction dir); +int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +int dma_supported(struct device *dev, u64 mask); +int dma_set_mask(struct device *dev, u64 mask); +int dma_set_coherent_mask(struct device *dev, u64 mask); +u64 dma_get_required_mask(struct device *dev); +#else /* CONFIG_HAS_DMA */ +static inline dma_addr_t dma_map_page_attrs(struct device *dev, + struct page *page, size_t offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} +static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ +} +static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + return 0; +} +static inline void dma_unmap_sg_attrs(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir, + unsigned long attrs) +{ +} +static inline dma_addr_t dma_map_resource(struct device *dev, + phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + return DMA_MAPPING_ERROR; +} +static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ +} +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return -ENOMEM; +} +static inline void *dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) +{ + return NULL; +} +static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ +} +static inline void *dmam_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + return NULL; +} +static inline void dmam_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ +} +static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction dir) +{ +} +static inline int dma_get_sgtable_attrs(struct device *dev, + struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, + size_t size, unsigned long attrs) +{ + return -ENXIO; +} +static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + return -ENXIO; +} +static inline int dma_supported(struct device *dev, u64 mask) +{ + return 0; +} +static inline int dma_set_mask(struct device *dev, u64 mask) +{ + return -EIO; +} +static inline int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + return -EIO; +} +static inline u64 dma_get_required_mask(struct device *dev) +{ + return 0; +} +#endif /* CONFIG_HAS_DMA */ + +static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + debug_dma_map_single(dev, ptr, size); + return dma_map_page_attrs(dev, virt_to_page(ptr), offset_in_page(ptr), + size, dir, attrs); +} + +static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + return dma_unmap_page_attrs(dev, addr, size, dir, attrs); +} + +static inline void dma_sync_single_range_for_cpu(struct device *dev, + dma_addr_t addr, unsigned long offset, size_t size, + enum dma_data_direction dir) +{ + return dma_sync_single_for_cpu(dev, addr + offset, size, dir); +} + +static inline void dma_sync_single_range_for_device(struct device *dev, + dma_addr_t addr, unsigned long offset, size_t size, + enum dma_data_direction dir) +{ + return dma_sync_single_for_device(dev, addr + offset, size, dir); +} + #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0) #define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0) #define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0) - -void dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction dir); +#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) +#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, @@ -516,25 +618,10 @@ bool dma_in_atomic_pool(void *start, size_t size); void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); bool dma_free_from_pool(void *start, size_t size); -int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); -#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) - int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs); -#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) - -void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flag, unsigned long attrs); -void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, unsigned long attrs); - static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { @@ -549,18 +636,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size, return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } -static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - debug_dma_mapping_error(dev, dma_addr); - - if (dma_addr == DMA_MAPPING_ERROR) - return -ENOMEM; - return 0; -} - -int dma_supported(struct device *dev, u64 mask); -int dma_set_mask(struct device *dev, u64 mask); -int dma_set_coherent_mask(struct device *dev, u64 mask); static inline u64 dma_get_mask(struct device *dev) { @@ -593,8 +668,6 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) return dma_set_mask_and_coherent(dev, mask); } -extern u64 dma_get_required_mask(struct device *dev); - #ifndef arch_setup_dma_ops static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, @@ -691,43 +764,12 @@ dma_mark_declared_memory_occupied(struct device *dev, } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -/* - * Managed DMA API - */ -#ifdef CONFIG_HAS_DMA -extern void *dmam_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); -extern void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle); -#else /* !CONFIG_HAS_DMA */ static inline void *dmam_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ return NULL; } -static inline void dmam_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) { } -#endif /* !CONFIG_HAS_DMA */ - -extern void *dmam_alloc_attrs(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - unsigned long attrs); -#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT -extern int dmam_declare_coherent_memory(struct device *dev, - phys_addr_t phys_addr, - dma_addr_t device_addr, size_t size, - int flags); -extern void dmam_release_declared_memory(struct device *dev); -#else /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -static inline int dmam_declare_coherent_memory(struct device *dev, - phys_addr_t phys_addr, dma_addr_t device_addr, - size_t size, gfp_t gfp) -{ - return 0; -} - -static inline void dmam_release_declared_memory(struct device *dev) + dma_addr_t *dma_handle, gfp_t gfp) { + return dmam_alloc_attrs(dev, size, dma_handle, gfp, + (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } -#endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) diff --git a/include/linux/fb.h b/include/linux/fb.h index a3cab6dc9b44..7cdd31a69719 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -485,7 +485,7 @@ struct fb_info { struct list_head modelist; /* mode list */ struct fb_videomode *mode; /* current mode */ -#ifdef CONFIG_FB_BACKLIGHT +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) /* assigned backlight device */ /* set before framebuffer registration, remove after unregister */ diff --git a/include/linux/hid.h b/include/linux/hid.h index a355d61940f2..d99287327ef2 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -219,6 +219,7 @@ struct hid_item { #define HID_GD_VBRZ 0x00010045 #define HID_GD_VNO 0x00010046 #define HID_GD_FEATURE 0x00010047 +#define HID_GD_RESOLUTION_MULTIPLIER 0x00010048 #define HID_GD_SYSTEM_CONTROL 0x00010080 #define HID_GD_UP 0x00010090 #define HID_GD_DOWN 0x00010091 @@ -232,12 +233,14 @@ struct hid_item { #define HID_DC_BATTERYSTRENGTH 0x00060020 #define HID_CP_CONSUMER_CONTROL 0x000c0001 +#define HID_CP_AC_PAN 0x000c0238 #define HID_DG_DIGITIZER 0x000d0001 #define HID_DG_PEN 0x000d0002 #define HID_DG_LIGHTPEN 0x000d0003 #define HID_DG_TOUCHSCREEN 0x000d0004 #define HID_DG_TOUCHPAD 0x000d0005 +#define HID_DG_WHITEBOARD 0x000d0006 #define HID_DG_STYLUS 0x000d0020 #define HID_DG_PUCK 0x000d0021 #define HID_DG_FINGER 0x000d0022 @@ -427,6 +430,7 @@ struct hid_local { */ struct hid_collection { + struct hid_collection *parent; unsigned type; unsigned usage; unsigned level; @@ -436,12 +440,16 @@ struct hid_usage { unsigned hid; /* hid usage code */ unsigned collection_index; /* index into collection array */ unsigned usage_index; /* index into usage array */ + __s8 resolution_multiplier;/* Effective Resolution Multiplier + (HUT v1.12, 4.3.1), default: 1 */ /* hidinput data */ + __s8 wheel_factor; /* 120/resolution_multiplier */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ __s8 hat_min; /* hat switch fun */ __s8 hat_max; /* ditto */ __s8 hat_dir; /* ditto */ + __s16 wheel_accumulated; /* hi-res wheel */ }; struct hid_input; @@ -650,6 +658,7 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; + struct hid_collection *active_collection; struct hid_device *device; unsigned int scan_flags; }; @@ -836,7 +845,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ -#define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || ((a >= 0x000d0002) && (a <= 0x000d0006))) +#define IS_INPUT_APPLICATION(a) \ + (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ + || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ + || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL) \ + || (a == HID_GD_WIRELESS_RADIO_CTLS)) /* HID core API */ @@ -892,6 +905,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, unsigned int type, unsigned int id, unsigned int field_index, unsigned int report_counts); + +void hid_setup_resolution_multiplier(struct hid_device *hid); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index e44e3ec8a9c7..de8b588c8776 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -317,7 +317,9 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev); * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. * - * Return: 0 on success or negative error code. + * Return: negative error code on errors; 0 for no data; or else number of + * bytes received (i.e., an event was retrieved successfully). Event types are + * written out to @ec_dev->event_data.event_type on success. */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); @@ -329,7 +331,7 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); * events raised and call the functions in the ec notifier. This function * is a helper to know which events are raised. * - * Return: 0 on success or negative error code. + * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h index 6c1ad160ed87..c1b25f5e386d 100644 --- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h +++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h @@ -440,6 +440,7 @@ #define IMX6SX_GPR5_DISP_MUX_DCIC1_MASK (0x1 << 1) #define IMX6SX_GPR12_PCIE_TEST_POWERDOWN BIT(30) +#define IMX6SX_GPR12_PCIE_PM_TURN_OFF BIT(16) #define IMX6SX_GPR12_PCIE_RX_EQ_MASK (0x7 << 0) #define IMX6SX_GPR12_PCIE_RX_EQ_2 (0x2 << 0) diff --git a/include/linux/pci.h b/include/linux/pci.h index 1ab78a23ae08..65f1d8c2f082 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -413,6 +413,7 @@ struct pci_dev { unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */ unsigned int is_probed:1; /* Device probing in progress */ unsigned int link_active_reporting:1;/* Device capable of reporting link active */ + unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -772,9 +773,9 @@ struct pci_driver { int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ int (*suspend_late)(struct pci_dev *dev, pm_message_t state); int (*resume_early)(struct pci_dev *dev); - int (*resume) (struct pci_dev *dev); /* Device woken up */ - void (*shutdown) (struct pci_dev *dev); - int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* On PF */ + int (*resume)(struct pci_dev *dev); /* Device woken up */ + void (*shutdown)(struct pci_dev *dev); + int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ const struct pci_error_handlers *err_handler; const struct attribute_group **groups; struct device_driver driver; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d86d5a2477fc..5eaf39dbc388 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2361,6 +2361,9 @@ #define PCI_DEVICE_ID_CENATEK_IDE 0x0001 #define PCI_VENDOR_ID_SYNOPSYS 0x16c3 +#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3 0xabcd +#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3_AXI 0xabce +#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB31 0xabcf #define PCI_VENDOR_ID_USR 0x16ec diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index ea8505204fdf..605cf46c17bd 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -35,6 +35,7 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #include <limits.h> #include <stddef.h> #include <sys/mman.h> +#include <sys/time.h> #include <sys/types.h> /* Not standard, but glibc defines it */ @@ -52,7 +53,9 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #define __init #define __exit -#define __attribute_const__ __attribute__((const)) +#ifndef __attribute_const__ +# define __attribute_const__ __attribute__((const)) +#endif #define noinline __attribute__((noinline)) #define preempt_enable() @@ -67,6 +70,9 @@ extern const char raid6_empty_zero_page[PAGE_SIZE]; #define MODULE_DESCRIPTION(desc) #define subsys_initcall(x) #define module_exit(x) + +#define IS_ENABLED(x) (x) +#define CONFIG_RAID6_PQ_BENCHMARK 1 #endif /* __KERNEL__ */ /* Routine choices */ diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index ab400af6f0ce..eee0412bdf4b 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -29,6 +29,7 @@ #define SWITCHTEC_EVENT_EN_IRQ BIT(3) #define SWITCHTEC_EVENT_FATAL BIT(4) +#define SWITCHTEC_DMA_MRPC_EN BIT(0) enum { SWITCHTEC_GAS_MRPC_OFFSET = 0x0000, SWITCHTEC_GAS_TOP_CFG_OFFSET = 0x1000, @@ -46,6 +47,10 @@ struct mrpc_regs { u32 cmd; u32 status; u32 ret_value; + u32 dma_en; + u64 dma_addr; + u32 dma_vector; + u32 dma_ver; } __packed; enum mrpc_status { @@ -342,6 +347,14 @@ struct pff_csr_regs { struct switchtec_ntb; +struct dma_mrpc_output { + u32 status; + u32 cmd_id; + u32 rtn_code; + u32 output_size; + u8 data[SWITCHTEC_MRPC_PAYLOAD_SIZE]; +}; + struct switchtec_dev { struct pci_dev *pdev; struct device dev; @@ -381,6 +394,9 @@ struct switchtec_dev { u8 link_event_count[SWITCHTEC_MAX_PFF_CSR]; struct switchtec_ntb *sndev; + + struct dma_mrpc_output *dma_mrpc; + dma_addr_t dma_mrpc_dma_addr; }; static inline struct switchtec_dev *to_stdev(struct device *dev) diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 6cd9b198b7c6..b6aac7ee1f67 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -393,11 +393,9 @@ struct fb_cursor { struct fb_image image; /* Cursor image */ }; -#ifdef CONFIG_FB_BACKLIGHT /* Settings for the generic backlight code */ #define FB_BACKLIGHT_LEVELS 128 #define FB_BACKLIGHT_MAX 0xFF -#endif #endif /* _UAPI_LINUX_FB_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 53a22e8e0408..121e82ce296b 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -223,7 +223,8 @@ struct fsxattr { #define FS_POLICY_FLAGS_PAD_16 0x02 #define FS_POLICY_FLAGS_PAD_32 0x03 #define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 +#define FS_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */ +#define FS_POLICY_FLAGS_VALID 0x07 /* Encryption algorithms */ #define FS_ENCRYPTION_MODE_INVALID 0 @@ -235,6 +236,7 @@ struct fsxattr { #define FS_ENCRYPTION_MODE_AES_128_CTS 6 #define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* Removed, do not use. */ #define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* Removed, do not use. */ +#define FS_ENCRYPTION_MODE_ADIANTUM 9 struct fscrypt_policy { __u8 version; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index ae366b87426a..7f14d4a66c28 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -716,6 +716,8 @@ * the situation described above. */ #define REL_RESERVED 0x0a +#define REL_WHEEL_HI_RES 0x0b +#define REL_HWHEEL_HI_RES 0x0c #define REL_MAX 0x0f #define REL_CNT (REL_MAX+1) diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 597d40893862..66f0fb7e9a3a 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -223,7 +223,6 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, */ return mem->flags & DMA_MEMORY_EXCLUSIVE; } -EXPORT_SYMBOL(dma_alloc_from_dev_coherent); void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle) { @@ -268,7 +267,6 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr) return __dma_release_from_coherent(mem, order, vaddr); } -EXPORT_SYMBOL(dma_release_from_dev_coherent); int dma_release_from_global_coherent(int order, void *vaddr) { diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 164706da2a73..23cf5361bcf1 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -49,7 +49,6 @@ enum { dma_debug_single, - dma_debug_page, dma_debug_sg, dma_debug_coherent, dma_debug_resource, @@ -1300,8 +1299,7 @@ void debug_dma_map_single(struct device *dev, const void *addr, EXPORT_SYMBOL(debug_dma_map_single); void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, - size_t size, int direction, dma_addr_t dma_addr, - bool map_single) + size_t size, int direction, dma_addr_t dma_addr) { struct dma_debug_entry *entry; @@ -1316,7 +1314,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, return; entry->dev = dev; - entry->type = dma_debug_page; + entry->type = dma_debug_single; entry->pfn = page_to_pfn(page); entry->offset = offset, entry->dev_addr = dma_addr; @@ -1324,9 +1322,6 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, entry->direction = direction; entry->map_err_type = MAP_ERR_NOT_CHECKED; - if (map_single) - entry->type = dma_debug_single; - check_for_stack(dev, page, offset); if (!PageHighMem(page)) { @@ -1378,10 +1373,10 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) EXPORT_SYMBOL(debug_dma_mapping_error); void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction, bool map_single) + size_t size, int direction) { struct dma_debug_entry ref = { - .type = dma_debug_page, + .type = dma_debug_single, .dev = dev, .dev_addr = addr, .size = size, @@ -1390,10 +1385,6 @@ void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, if (unlikely(dma_debug_disabled())) return; - - if (map_single) - ref.type = dma_debug_single; - check_unmap(&ref); } EXPORT_SYMBOL(debug_dma_unmap_page); @@ -1521,7 +1512,6 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, add_dma_entry(entry); } -EXPORT_SYMBOL(debug_dma_alloc_coherent); void debug_dma_free_coherent(struct device *dev, size_t size, void *virt, dma_addr_t addr) @@ -1549,7 +1539,6 @@ void debug_dma_free_coherent(struct device *dev, size_t size, check_unmap(&ref); } -EXPORT_SYMBOL(debug_dma_free_coherent); void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size, int direction, dma_addr_t dma_addr) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index d7c34d2d1ba5..a11006b6d8e8 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -46,45 +46,6 @@ static int dmam_match(struct device *dev, void *res, void *match_data) } /** - * dmam_alloc_coherent - Managed dma_alloc_coherent() - * @dev: Device to allocate coherent memory for - * @size: Size of allocation - * @dma_handle: Out argument for allocated DMA handle - * @gfp: Allocation flags - * - * Managed dma_alloc_coherent(). Memory allocated using this function - * will be automatically released on driver detach. - * - * RETURNS: - * Pointer to allocated memory on success, NULL on failure. - */ -void *dmam_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - struct dma_devres *dr; - void *vaddr; - - dr = devres_alloc(dmam_release, sizeof(*dr), gfp); - if (!dr) - return NULL; - - vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp); - if (!vaddr) { - devres_free(dr); - return NULL; - } - - dr->vaddr = vaddr; - dr->dma_handle = *dma_handle; - dr->size = size; - - devres_add(dev, dr); - - return vaddr; -} -EXPORT_SYMBOL(dmam_alloc_coherent); - -/** * dmam_free_coherent - Managed dma_free_coherent() * @dev: Device to free coherent memory for * @size: Size of allocation @@ -144,61 +105,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, } EXPORT_SYMBOL(dmam_alloc_attrs); -#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT - -static void dmam_coherent_decl_release(struct device *dev, void *res) -{ - dma_release_declared_memory(dev); -} - -/** - * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory() - * @dev: Device to declare coherent memory for - * @phys_addr: Physical address of coherent memory to be declared - * @device_addr: Device address of coherent memory to be declared - * @size: Size of coherent memory to be declared - * @flags: Flags - * - * Managed dma_declare_coherent_memory(). - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, - dma_addr_t device_addr, size_t size, int flags) -{ - void *res; - int rc; - - res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL); - if (!res) - return -ENOMEM; - - rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size, - flags); - if (!rc) - devres_add(dev, res); - else - devres_free(res); - - return rc; -} -EXPORT_SYMBOL(dmam_declare_coherent_memory); - -/** - * dmam_release_declared_memory - Managed dma_release_declared_memory(). - * @dev: Device to release declared coherent memory for - * - * Managed dmam_release_declared_memory(). - */ -void dmam_release_declared_memory(struct device *dev) -{ - WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL)); -} -EXPORT_SYMBOL(dmam_release_declared_memory); - -#endif - /* * Create scatter-list for the already allocated DMA buffer. */ diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index 18cc09fc27b9..7a723194ecbe 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -204,8 +204,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, ret = dma_alloc_from_pool(size, &page, flags); if (!ret) return NULL; - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - return ret; + goto done; } page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); @@ -215,8 +214,10 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, /* remove any dirty cache lines on the kernel alias */ arch_dma_prep_coherent(page, size); - if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) - return page; /* opaque cookie */ + if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) { + ret = page; /* opaque cookie */ + goto done; + } /* create a coherent mapping */ ret = dma_common_contiguous_remap(page, size, VM_USERMAP, @@ -227,9 +228,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, return ret; } - *dma_handle = phys_to_dma(dev, page_to_phys(page)); memset(ret, 0, size); - +done: + *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; } diff --git a/lib/Kconfig b/lib/Kconfig index 79bc2eef9c14..a9e56539bd11 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -10,6 +10,14 @@ menu "Library routines" config RAID6_PQ tristate +config RAID6_PQ_BENCHMARK + bool "Automatically choose fastest RAID6 PQ functions" + depends on RAID6_PQ + default y + help + Benchmark all available RAID6 PQ functions on init and choose the + fastest one. + config BITREVERSE tristate diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 5065b1e7e327..7e4f7a8ffa8e 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -34,64 +34,64 @@ struct raid6_calls raid6_call; EXPORT_SYMBOL_GPL(raid6_call); const struct raid6_calls * const raid6_algos[] = { -#if defined(__ia64__) - &raid6_intx16, - &raid6_intx32, -#endif #if defined(__i386__) && !defined(__arch_um__) - &raid6_mmxx1, - &raid6_mmxx2, - &raid6_sse1x1, - &raid6_sse1x2, - &raid6_sse2x1, - &raid6_sse2x2, -#ifdef CONFIG_AS_AVX2 - &raid6_avx2x1, - &raid6_avx2x2, -#endif #ifdef CONFIG_AS_AVX512 - &raid6_avx512x1, &raid6_avx512x2, + &raid6_avx512x1, #endif -#endif -#if defined(__x86_64__) && !defined(__arch_um__) - &raid6_sse2x1, - &raid6_sse2x2, - &raid6_sse2x4, #ifdef CONFIG_AS_AVX2 - &raid6_avx2x1, &raid6_avx2x2, - &raid6_avx2x4, + &raid6_avx2x1, +#endif + &raid6_sse2x2, + &raid6_sse2x1, + &raid6_sse1x2, + &raid6_sse1x1, + &raid6_mmxx2, + &raid6_mmxx1, #endif +#if defined(__x86_64__) && !defined(__arch_um__) #ifdef CONFIG_AS_AVX512 - &raid6_avx512x1, - &raid6_avx512x2, &raid6_avx512x4, + &raid6_avx512x2, + &raid6_avx512x1, #endif +#ifdef CONFIG_AS_AVX2 + &raid6_avx2x4, + &raid6_avx2x2, + &raid6_avx2x1, +#endif + &raid6_sse2x4, + &raid6_sse2x2, + &raid6_sse2x1, #endif #ifdef CONFIG_ALTIVEC - &raid6_altivec1, - &raid6_altivec2, - &raid6_altivec4, - &raid6_altivec8, - &raid6_vpermxor1, - &raid6_vpermxor2, - &raid6_vpermxor4, &raid6_vpermxor8, + &raid6_vpermxor4, + &raid6_vpermxor2, + &raid6_vpermxor1, + &raid6_altivec8, + &raid6_altivec4, + &raid6_altivec2, + &raid6_altivec1, #endif #if defined(CONFIG_S390) &raid6_s390vx8, #endif - &raid6_intx1, - &raid6_intx2, - &raid6_intx4, - &raid6_intx8, #ifdef CONFIG_KERNEL_MODE_NEON - &raid6_neonx1, - &raid6_neonx2, - &raid6_neonx4, &raid6_neonx8, + &raid6_neonx4, + &raid6_neonx2, + &raid6_neonx1, #endif +#if defined(__ia64__) + &raid6_intx32, + &raid6_intx16, +#endif + &raid6_intx8, + &raid6_intx4, + &raid6_intx2, + &raid6_intx1, NULL }; @@ -163,6 +163,11 @@ static inline const struct raid6_calls *raid6_choose_gen( if ((*algo)->valid && !(*algo)->valid()) continue; + if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) { + best = *algo; + break; + } + perf = 0; preempt_disable(); diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 79777645cac9..3ab8720aa2f8 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -34,6 +34,9 @@ endif ifeq ($(IS_X86),yes) OBJS += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o + CFLAGS += $(shell echo "pshufb %xmm0, %xmm0" | \ + gcc -c -x assembler - >&/dev/null && \ + rm ./-.o && echo -DCONFIG_AS_SSSE3=1) CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" | \ gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX2=1) diff --git a/mm/mincore.c b/mm/mincore.c index 218099b5ed31..f0f91461a9f4 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -42,72 +42,14 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, return 0; } -/* - * Later we can get more picky about what "in core" means precisely. - * For now, simply check to see if the page is in the page cache, - * and is up to date; i.e. that no page-in operation would be required - * at this time if an application were to map and access this page. - */ -static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) -{ - unsigned char present = 0; - struct page *page; - - /* - * When tmpfs swaps out a page from a file, any process mapping that - * file will not get a swp_entry_t in its pte, but rather it is like - * any other file mapping (ie. marked !present and faulted in with - * tmpfs's .fault). So swapped out tmpfs mappings are tested here. - */ -#ifdef CONFIG_SWAP - if (shmem_mapping(mapping)) { - page = find_get_entry(mapping, pgoff); - /* - * shmem/tmpfs may return swap: account for swapcache - * page too. - */ - if (xa_is_value(page)) { - swp_entry_t swp = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swp), - swp_offset(swp)); - } - } else - page = find_get_page(mapping, pgoff); -#else - page = find_get_page(mapping, pgoff); -#endif - if (page) { - present = PageUptodate(page); - put_page(page); - } - - return present; -} - -static int __mincore_unmapped_range(unsigned long addr, unsigned long end, - struct vm_area_struct *vma, unsigned char *vec) -{ - unsigned long nr = (end - addr) >> PAGE_SHIFT; - int i; - - if (vma->vm_file) { - pgoff_t pgoff; - - pgoff = linear_page_index(vma, addr); - for (i = 0; i < nr; i++, pgoff++) - vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff); - } else { - for (i = 0; i < nr; i++) - vec[i] = 0; - } - return nr; -} - static int mincore_unmapped_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { - walk->private += __mincore_unmapped_range(addr, end, - walk->vma, walk->private); + unsigned char *vec = walk->private; + unsigned long nr = (end - addr) >> PAGE_SHIFT; + + memset(vec, 0, nr); + walk->private += nr; return 0; } @@ -127,8 +69,9 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, goto out; } + /* We'll consider a THP page under construction to be there */ if (pmd_trans_unstable(pmd)) { - __mincore_unmapped_range(addr, end, vma, vec); + memset(vec, 1, nr); goto out; } @@ -137,28 +80,17 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t pte = *ptep; if (pte_none(pte)) - __mincore_unmapped_range(addr, addr + PAGE_SIZE, - vma, vec); + *vec = 0; else if (pte_present(pte)) *vec = 1; else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); - if (non_swap_entry(entry)) { - /* - * migration or hwpoison entries are always - * uptodate - */ - *vec = 1; - } else { -#ifdef CONFIG_SWAP - *vec = mincore_page(swap_address_space(entry), - swp_offset(entry)); -#else - WARN_ON(1); - *vec = 1; -#endif - } + /* + * migration or hwpoison entries are always + * uptodate + */ + *vec = !!non_swap_entry(entry); } vec++; } diff --git a/samples/hidraw/hid-example.c b/samples/hidraw/hid-example.c index 9bfd8ff6de82..37a0ffcb4d63 100644 --- a/samples/hidraw/hid-example.c +++ b/samples/hidraw/hid-example.c @@ -119,7 +119,7 @@ int main(int argc, char **argv) if (res < 0) perror("HIDIOCSFEATURE"); else - printf("ioctl HIDIOCGFEATURE returned: %d\n", res); + printf("ioctl HIDIOCSFEATURE returned: %d\n", res); /* Get Feature */ buf[0] = 0x9; /* Report Number */ diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c index 49b13553eaae..e8f1bd6b29b1 100644 --- a/samples/livepatch/livepatch-shadow-fix1.c +++ b/samples/livepatch/livepatch-shadow-fix1.c @@ -89,6 +89,11 @@ struct dummy *livepatch_fix1_dummy_alloc(void) * pointer to handle resource release. */ leak = kzalloc(sizeof(int), GFP_KERNEL); + if (!leak) { + kfree(d); + return NULL; + } + klp_shadow_alloc(d, SV_LEAK, sizeof(leak), GFP_KERNEL, shadow_leak_ctor, leak); diff --git a/samples/livepatch/livepatch-shadow-mod.c b/samples/livepatch/livepatch-shadow-mod.c index 4c54b250332d..4aa8a88d3cd6 100644 --- a/samples/livepatch/livepatch-shadow-mod.c +++ b/samples/livepatch/livepatch-shadow-mod.c @@ -118,6 +118,10 @@ noinline struct dummy *dummy_alloc(void) /* Oops, forgot to save leak! */ leak = kzalloc(sizeof(int), GFP_KERNEL); + if (!leak) { + kfree(d); + return NULL; + } pr_info("%s: dummy @ %p, expires @ %lx\n", __func__, d, d->jiffies_expire); diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index d47b8f73e2e7..5467c6bf9ceb 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -82,8 +82,8 @@ FEATURE_TESTS_EXTRA := \ cplus-demangle \ hello \ libbabeltrace \ - liberty \ - liberty-z \ + libbfd-liberty \ + libbfd-liberty-z \ libunwind-debug-frame \ libunwind-debug-frame-arm \ libunwind-debug-frame-aarch64 \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 2dbcc0d00f52..7ceb4441b627 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -17,8 +17,8 @@ FILES= \ test-libbfd.bin \ test-disassembler-four-args.bin \ test-reallocarray.bin \ - test-liberty.bin \ - test-liberty-z.bin \ + test-libbfd-liberty.bin \ + test-libbfd-liberty-z.bin \ test-cplus-demangle.bin \ test-libelf.bin \ test-libelf-getphdrnum.bin \ @@ -210,7 +210,7 @@ $(OUTPUT)test-libpython-version.bin: $(BUILD) $(OUTPUT)test-libbfd.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl + $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl $(OUTPUT)test-disassembler-four-args.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes @@ -218,10 +218,10 @@ $(OUTPUT)test-disassembler-four-args.bin: $(OUTPUT)test-reallocarray.bin: $(BUILD) -$(OUTPUT)test-liberty.bin: +$(OUTPUT)test-libbfd-liberty.bin: $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -$(OUTPUT)test-liberty-z.bin: +$(OUTPUT)test-libbfd-liberty-z.bin: $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz $(OUTPUT)test-cplus-demangle.bin: diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 240eda014b37..6ecdd1067826 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -12,7 +12,7 @@ endif # (this improves performance and avoids hard-to-debug behaviour); MAKEFLAGS += -r -CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include +override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h new file mode 100644 index 000000000000..964e87217be4 --- /dev/null +++ b/tools/include/uapi/linux/usbdevice_fs.h @@ -0,0 +1,201 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/*****************************************************************************/ + +/* + * usbdevice_fs.h -- USB device file system. + * + * Copyright (C) 2000 + * Thomas Sailer (sailer@ife.ee.ethz.ch) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * History: + * 0.1 04.01.2000 Created + */ + +/*****************************************************************************/ + +#ifndef _UAPI_LINUX_USBDEVICE_FS_H +#define _UAPI_LINUX_USBDEVICE_FS_H + +#include <linux/types.h> +#include <linux/magic.h> + +/* --------------------------------------------------------------------- */ + +/* usbdevfs ioctl codes */ + +struct usbdevfs_ctrltransfer { + __u8 bRequestType; + __u8 bRequest; + __u16 wValue; + __u16 wIndex; + __u16 wLength; + __u32 timeout; /* in milliseconds */ + void __user *data; +}; + +struct usbdevfs_bulktransfer { + unsigned int ep; + unsigned int len; + unsigned int timeout; /* in milliseconds */ + void __user *data; +}; + +struct usbdevfs_setinterface { + unsigned int interface; + unsigned int altsetting; +}; + +struct usbdevfs_disconnectsignal { + unsigned int signr; + void __user *context; +}; + +#define USBDEVFS_MAXDRIVERNAME 255 + +struct usbdevfs_getdriver { + unsigned int interface; + char driver[USBDEVFS_MAXDRIVERNAME + 1]; +}; + +struct usbdevfs_connectinfo { + unsigned int devnum; + unsigned char slow; +}; + +#define USBDEVFS_URB_SHORT_NOT_OK 0x01 +#define USBDEVFS_URB_ISO_ASAP 0x02 +#define USBDEVFS_URB_BULK_CONTINUATION 0x04 +#define USBDEVFS_URB_NO_FSBR 0x20 /* Not used */ +#define USBDEVFS_URB_ZERO_PACKET 0x40 +#define USBDEVFS_URB_NO_INTERRUPT 0x80 + +#define USBDEVFS_URB_TYPE_ISO 0 +#define USBDEVFS_URB_TYPE_INTERRUPT 1 +#define USBDEVFS_URB_TYPE_CONTROL 2 +#define USBDEVFS_URB_TYPE_BULK 3 + +struct usbdevfs_iso_packet_desc { + unsigned int length; + unsigned int actual_length; + unsigned int status; +}; + +struct usbdevfs_urb { + unsigned char type; + unsigned char endpoint; + int status; + unsigned int flags; + void __user *buffer; + int buffer_length; + int actual_length; + int start_frame; + union { + int number_of_packets; /* Only used for isoc urbs */ + unsigned int stream_id; /* Only used with bulk streams */ + }; + int error_count; + unsigned int signr; /* signal to be sent on completion, + or 0 if none should be sent. */ + void __user *usercontext; + struct usbdevfs_iso_packet_desc iso_frame_desc[0]; +}; + +/* ioctls for talking directly to drivers */ +struct usbdevfs_ioctl { + int ifno; /* interface 0..N ; negative numbers reserved */ + int ioctl_code; /* MUST encode size + direction of data so the + * macros in <asm/ioctl.h> give correct values */ + void __user *data; /* param buffer (in, or out) */ +}; + +/* You can do most things with hubs just through control messages, + * except find out what device connects to what port. */ +struct usbdevfs_hub_portinfo { + char nports; /* number of downstream ports in this hub */ + char port [127]; /* e.g. port 3 connects to device 27 */ +}; + +/* System and bus capability flags */ +#define USBDEVFS_CAP_ZERO_PACKET 0x01 +#define USBDEVFS_CAP_BULK_CONTINUATION 0x02 +#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04 +#define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08 +#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10 +#define USBDEVFS_CAP_MMAP 0x20 +#define USBDEVFS_CAP_DROP_PRIVILEGES 0x40 + +/* USBDEVFS_DISCONNECT_CLAIM flags & struct */ + +/* disconnect-and-claim if the driver matches the driver field */ +#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER 0x01 +/* disconnect-and-claim except when the driver matches the driver field */ +#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER 0x02 + +struct usbdevfs_disconnect_claim { + unsigned int interface; + unsigned int flags; + char driver[USBDEVFS_MAXDRIVERNAME + 1]; +}; + +struct usbdevfs_streams { + unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */ + unsigned int num_eps; + unsigned char eps[0]; +}; + +/* + * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in + * linux/usb/ch9.h + */ + +#define USBDEVFS_CONTROL _IOWR('U', 0, struct usbdevfs_ctrltransfer) +#define USBDEVFS_CONTROL32 _IOWR('U', 0, struct usbdevfs_ctrltransfer32) +#define USBDEVFS_BULK _IOWR('U', 2, struct usbdevfs_bulktransfer) +#define USBDEVFS_BULK32 _IOWR('U', 2, struct usbdevfs_bulktransfer32) +#define USBDEVFS_RESETEP _IOR('U', 3, unsigned int) +#define USBDEVFS_SETINTERFACE _IOR('U', 4, struct usbdevfs_setinterface) +#define USBDEVFS_SETCONFIGURATION _IOR('U', 5, unsigned int) +#define USBDEVFS_GETDRIVER _IOW('U', 8, struct usbdevfs_getdriver) +#define USBDEVFS_SUBMITURB _IOR('U', 10, struct usbdevfs_urb) +#define USBDEVFS_SUBMITURB32 _IOR('U', 10, struct usbdevfs_urb32) +#define USBDEVFS_DISCARDURB _IO('U', 11) +#define USBDEVFS_REAPURB _IOW('U', 12, void *) +#define USBDEVFS_REAPURB32 _IOW('U', 12, __u32) +#define USBDEVFS_REAPURBNDELAY _IOW('U', 13, void *) +#define USBDEVFS_REAPURBNDELAY32 _IOW('U', 13, __u32) +#define USBDEVFS_DISCSIGNAL _IOR('U', 14, struct usbdevfs_disconnectsignal) +#define USBDEVFS_DISCSIGNAL32 _IOR('U', 14, struct usbdevfs_disconnectsignal32) +#define USBDEVFS_CLAIMINTERFACE _IOR('U', 15, unsigned int) +#define USBDEVFS_RELEASEINTERFACE _IOR('U', 16, unsigned int) +#define USBDEVFS_CONNECTINFO _IOW('U', 17, struct usbdevfs_connectinfo) +#define USBDEVFS_IOCTL _IOWR('U', 18, struct usbdevfs_ioctl) +#define USBDEVFS_IOCTL32 _IOWR('U', 18, struct usbdevfs_ioctl32) +#define USBDEVFS_HUB_PORTINFO _IOR('U', 19, struct usbdevfs_hub_portinfo) +#define USBDEVFS_RESET _IO('U', 20) +#define USBDEVFS_CLEAR_HALT _IOR('U', 21, unsigned int) +#define USBDEVFS_DISCONNECT _IO('U', 22) +#define USBDEVFS_CONNECT _IO('U', 23) +#define USBDEVFS_CLAIM_PORT _IOR('U', 24, unsigned int) +#define USBDEVFS_RELEASE_PORT _IOR('U', 25, unsigned int) +#define USBDEVFS_GET_CAPABILITIES _IOR('U', 26, __u32) +#define USBDEVFS_DISCONNECT_CLAIM _IOR('U', 27, struct usbdevfs_disconnect_claim) +#define USBDEVFS_ALLOC_STREAMS _IOR('U', 28, struct usbdevfs_streams) +#define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams) +#define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32) +#define USBDEVFS_GET_SPEED _IO('U', 31) + +#endif /* _UAPI_LINUX_USBDEVICE_FS_H */ diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 07c1857c3d7a..b441c88cafa1 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -702,18 +702,20 @@ endif ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd +else + # we are on a system that requires -liberty and (maybe) -lz + # to link against -lbfd; test each case individually here # call all detections now so we get correct # status in VF output - $(call feature_check,liberty) - $(call feature_check,liberty-z) - $(call feature_check,cplus-demangle) + $(call feature_check,libbfd-liberty) + $(call feature_check,libbfd-liberty-z) - ifeq ($(feature-liberty), 1) - EXTLIBS += -liberty + ifeq ($(feature-libbfd-liberty), 1) + EXTLIBS += -lbfd -liberty else - ifeq ($(feature-liberty-z), 1) - EXTLIBS += -liberty -lz + ifeq ($(feature-libbfd-liberty-z), 1) + EXTLIBS += -lbfd -liberty -lz endif endif endif @@ -723,24 +725,24 @@ ifdef NO_DEMANGLE else ifdef HAVE_CPLUS_DEMANGLE_SUPPORT EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else - ifneq ($(feature-libbfd), 1) - ifneq ($(feature-liberty), 1) - ifneq ($(feature-liberty-z), 1) - # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT - # or any of 'bfd iberty z' trinity - ifeq ($(feature-cplus-demangle), 1) - EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT - else - msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) - CFLAGS += -DNO_DEMANGLE - endif - endif + ifeq ($(filter -liberty,$(EXTLIBS)),) + $(call feature_check,cplus-demangle) + + # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT + # or any of 'bfd iberty z' trinity + ifeq ($(feature-cplus-demangle), 1) + EXTLIBS += -liberty + else + msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) + CFLAGS += -DNO_DEMANGLE endif endif endif + + ifneq ($(filter -liberty,$(EXTLIBS)),) + CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT + endif endif ifneq ($(filter -lbfd,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index bd23e3f30895..ff29c3372ec3 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -497,6 +497,12 @@ prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh $(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl) $(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@ +usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c +usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh + +$(usbdevfs_ioctl_array): $(linux_uapi_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl) + $(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(linux_uapi_dir) > $@ + x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -624,6 +630,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(mount_flags_array) \ $(perf_ioctl_array) \ $(prctl_option_array) \ + $(usbdevfs_ioctl_array) \ $(x86_arch_prctl_code_array) \ $(rename_flags_array) \ $(arch_errno_name_array) @@ -923,6 +930,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ + $(OUTPUT)$(usbdevfs_ioctl_array) \ $(OUTPUT)$(x86_arch_prctl_code_array) \ $(OUTPUT)$(rename_flags_array) \ $(OUTPUT)$(arch_errno_name_array) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f3aa9d02a5ab..d340d2e42776 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -68,7 +68,7 @@ struct c2c_hist_entry { struct hist_entry he; }; -static char const *coalesce_default = "pid,iaddr"; +static char const *coalesce_default = "iaddr"; struct perf_c2c { struct perf_tool tool; @@ -1878,7 +1878,7 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists, return hpp_list__parse(&c2c_hists->list, output, sort); } -#define DISPLAY_LINE_LIMIT 0.0005 +#define DISPLAY_LINE_LIMIT 0.001 static bool he__display(struct hist_entry *he, struct c2c_stats *stats) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3728b50e52e2..d079f36d342d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1073,9 +1073,18 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, /* * Print final block upto sample + * + * Due to pipeline delays the LBRs might be missing a branch + * or two, which can result in very large or negative blocks + * between final branch and sample. When this happens just + * continue walking after the last TO until we hit a branch. */ start = br->entries[0].to; end = sample->ip; + if (end < start) { + /* Missing jump. Scan 128 bytes for the next branch */ + end = start + 128; + } len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (len <= 0) { @@ -1084,7 +1093,6 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, machine, thread, &x.is64bit, &x.cpumode, false); if (len <= 0) goto out; - printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip, dump_insn(&x, sample->ip, buffer, len, NULL)); if (PRINT_FIELD(SRCCODE)) @@ -1096,6 +1104,13 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, dump_insn(&x, start + off, buffer + off, len - off, &ilen)); if (ilen == 0) break; + if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) { + /* + * Hit a missing branch. Just stop. + */ + printed += fprintf(fp, "\t... not reaching sample ...\n"); + break; + } if (PRINT_FIELD(SRCCODE)) print_srccode(thread, x.cpumode, start + off); } @@ -1167,7 +1182,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, struct addr_location *al, FILE *fp) { struct perf_event_attr *attr = &evsel->attr; - size_t depth = thread_stack__depth(thread); + size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; int len = 0; @@ -1701,7 +1716,7 @@ static bool show_event(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - int depth = thread_stack__depth(thread); + int depth = thread_stack__depth(thread, sample->cpu); if (!symbol_conf.graph_function) return true; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ebde59e61133..adbf28183560 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -60,6 +60,7 @@ #include <linux/stringify.h> #include <linux/time64.h> #include <fcntl.h> +#include <sys/sysmacros.h> #include "sane_ctype.h" @@ -112,8 +113,9 @@ struct trace { } stats; unsigned int max_stack; unsigned int min_stack; - bool sort_events; + int raw_augmented_syscalls_args_size; bool raw_augmented_syscalls; + bool sort_events; bool not_ev_qualifier; bool live; bool full_time; @@ -283,12 +285,17 @@ out_delete: return -ENOENT; } -static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel) +static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel, struct perf_evsel *tp) { struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); - if (evsel->priv != NULL) { /* field, sizeof_field, offsetof_field */ - if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap)) + if (evsel->priv != NULL) { + struct tep_format_field *syscall_id = perf_evsel__field(tp, "id"); + if (syscall_id == NULL) + syscall_id = perf_evsel__field(tp, "__syscall_nr"); + if (syscall_id == NULL) + goto out_delete; + if (__tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap)) goto out_delete; return 0; @@ -974,9 +981,9 @@ struct thread_trace { char *name; } filename; struct { - int max; - char **table; - } paths; + int max; + struct file *table; + } files; struct intlist *syscall_stats; }; @@ -986,7 +993,7 @@ static struct thread_trace *thread_trace__new(void) struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace)); if (ttrace) - ttrace->paths.max = -1; + ttrace->files.max = -1; ttrace->syscall_stats = intlist__new(NULL); @@ -1030,30 +1037,48 @@ void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg, static const size_t trace__entry_str_size = 2048; -static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) +static struct file *thread_trace__files_entry(struct thread_trace *ttrace, int fd) { - struct thread_trace *ttrace = thread__priv(thread); - - if (fd > ttrace->paths.max) { - char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *)); + if (fd > ttrace->files.max) { + struct file *nfiles = realloc(ttrace->files.table, (fd + 1) * sizeof(struct file)); - if (npath == NULL) - return -1; + if (nfiles == NULL) + return NULL; - if (ttrace->paths.max != -1) { - memset(npath + ttrace->paths.max + 1, 0, - (fd - ttrace->paths.max) * sizeof(char *)); + if (ttrace->files.max != -1) { + memset(nfiles + ttrace->files.max + 1, 0, + (fd - ttrace->files.max) * sizeof(struct file)); } else { - memset(npath, 0, (fd + 1) * sizeof(char *)); + memset(nfiles, 0, (fd + 1) * sizeof(struct file)); } - ttrace->paths.table = npath; - ttrace->paths.max = fd; + ttrace->files.table = nfiles; + ttrace->files.max = fd; } - ttrace->paths.table[fd] = strdup(pathname); + return ttrace->files.table + fd; +} - return ttrace->paths.table[fd] != NULL ? 0 : -1; +struct file *thread__files_entry(struct thread *thread, int fd) +{ + return thread_trace__files_entry(thread__priv(thread), fd); +} + +static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) +{ + struct thread_trace *ttrace = thread__priv(thread); + struct file *file = thread_trace__files_entry(ttrace, fd); + + if (file != NULL) { + struct stat st; + if (stat(pathname, &st) == 0) + file->dev_maj = major(st.st_rdev); + file->pathname = strdup(pathname); + if (file->pathname) + return 0; + } + + return -1; } static int thread__read_fd_path(struct thread *thread, int fd) @@ -1093,7 +1118,7 @@ static const char *thread__fd_path(struct thread *thread, int fd, if (fd < 0) return NULL; - if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) { + if ((fd > ttrace->files.max || ttrace->files.table[fd].pathname == NULL)) { if (!trace->live) return NULL; ++trace->stats.proc_getname; @@ -1101,7 +1126,7 @@ static const char *thread__fd_path(struct thread *thread, int fd, return NULL; } - return ttrace->paths.table[fd]; + return ttrace->files.table[fd].pathname; } size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg) @@ -1140,8 +1165,8 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, size_t printed = syscall_arg__scnprintf_fd(bf, size, arg); struct thread_trace *ttrace = thread__priv(arg->thread); - if (ttrace && fd >= 0 && fd <= ttrace->paths.max) - zfree(&ttrace->paths.table[fd]); + if (ttrace && fd >= 0 && fd <= ttrace->files.max) + zfree(&ttrace->files.table[fd].pathname); return printed; } @@ -1768,16 +1793,16 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } -static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented) +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, int raw_augmented_args_size) { void *augmented_args = NULL; /* * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter - * and there we get all 6 syscall args plus the tracepoint common - * fields (sizeof(long)) and the syscall_nr (another long). So we check - * if that is the case and if so don't look after the sc->args_size, - * but always after the full raw_syscalls:sys_enter payload, which is - * fixed. + * and there we get all 6 syscall args plus the tracepoint common fields + * that gets calculated at the start and the syscall_nr (another long). + * So we check if that is the case and if so don't look after the + * sc->args_size but always after the full raw_syscalls:sys_enter payload, + * which is fixed. * * We'll revisit this later to pass s->args_size to the BPF augmenter * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it @@ -1785,7 +1810,7 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace * traffic to just what is needed for each syscall. */ - int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size; + int args_size = raw_augmented_args_size ?: sc->args_size; *augmented_args_size = sample->raw_size - args_size; if (*augmented_args_size > 0) @@ -1839,7 +1864,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); @@ -1897,7 +1922,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse goto out_put; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size); syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); fprintf(trace->output, "%s", msg); err = 0; @@ -2686,7 +2711,9 @@ static int trace__set_ev_qualifier_filter(struct trace *trace) { if (trace->syscalls.map) return trace__set_ev_qualifier_bpf_filter(trace); - return trace__set_ev_qualifier_tp_filter(trace); + if (trace->syscalls.events.sys_enter) + return trace__set_ev_qualifier_tp_filter(trace); + return 0; } static int bpf_map__set_filter_pids(struct bpf_map *map __maybe_unused, @@ -3812,13 +3839,6 @@ int cmd_trace(int argc, const char **argv) * syscall. */ if (trace.syscalls.events.augmented) { - evsel = trace.syscalls.events.augmented; - - if (perf_evsel__init_augmented_syscall_tp(evsel) || - perf_evsel__init_augmented_syscall_tp_args(evsel)) - goto out; - evsel->handler = trace__sys_enter; - evlist__for_each_entry(trace.evlist, evsel) { bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0; @@ -3827,9 +3847,41 @@ int cmd_trace(int argc, const char **argv) goto init_augmented_syscall_tp; } + if (strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_enter") == 0) { + struct perf_evsel *augmented = trace.syscalls.events.augmented; + if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) || + perf_evsel__init_augmented_syscall_tp_args(augmented)) + goto out; + augmented->handler = trace__sys_enter; + } + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { + struct syscall_tp *sc; init_augmented_syscall_tp: - perf_evsel__init_augmented_syscall_tp(evsel); + if (perf_evsel__init_augmented_syscall_tp(evsel, evsel)) + goto out; + sc = evsel->priv; + /* + * For now with BPF raw_augmented we hook into + * raw_syscalls:sys_enter and there we get all + * 6 syscall args plus the tracepoint common + * fields and the syscall_nr (another long). + * So we check if that is the case and if so + * don't look after the sc->args_size but + * always after the full raw_syscalls:sys_enter + * payload, which is fixed. + * + * We'll revisit this later to pass + * s->args_size to the BPF augmenter (now + * tools/perf/examples/bpf/augmented_raw_syscalls.c, + * so that it copies only what we need for each + * syscall, like what happens when we use + * syscalls:sys_enter_NAME, so that we reduce + * the kernel/userspace traffic to just what is + * needed for each syscall. + */ + if (trace.raw_augmented_syscalls) + trace.raw_augmented_syscalls_args_size = (6 + 1) * sizeof(long) + sc->id.offset; perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; } diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 8e811ea0cf85..6cb98f8570a2 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -14,6 +14,7 @@ include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h include/uapi/linux/stat.h +include/uapi/linux/usbdevice_fs.h include/uapi/linux/vhost.h include/uapi/sound/asound.h include/linux/bits.h diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 83c5b202e00e..139d485a6f16 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -32,6 +32,13 @@ size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, boo struct trace; struct thread; +struct file { + char *pathname; + int dev_maj; +}; + +struct file *thread__files_entry(struct thread *thread, int fd); + struct strarrays { int nr_entries; struct strarray **entries; diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c index 9efeb6a936c2..620350d41209 100644 --- a/tools/perf/trace/beauty/ioctl.c +++ b/tools/perf/trace/beauty/ioctl.c @@ -112,6 +112,17 @@ static size_t ioctl__scnprintf_perf_cmd(int nr, int dir, char *bf, size_t size) return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir); } +static size_t ioctl__scnprintf_usbdevfs_cmd(int nr, int dir, char *bf, size_t size) +{ +#include "trace/beauty/generated/ioctl/usbdevfs_ioctl_array.c" + static DEFINE_STRARRAY(usbdevfs_ioctl_cmds, ""); + + if (nr < strarray__usbdevfs_ioctl_cmds.nr_entries && strarray__usbdevfs_ioctl_cmds.entries[nr] != NULL) + return scnprintf(bf, size, "USBDEVFS_%s", strarray__usbdevfs_ioctl_cmds.entries[nr]); + + return scnprintf(bf, size, "(%c, %#x, %#x)", 'U', nr, dir); +} + static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size, bool show_prefix) { const char *prefix = "_IOC_"; @@ -157,9 +168,20 @@ static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size, boo return printed + scnprintf(bf + printed, size - printed, ", %#x, %#x, %#x)", type, nr, sz); } +#ifndef USB_DEVICE_MAJOR +#define USB_DEVICE_MAJOR 189 +#endif // USB_DEVICE_MAJOR + size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg) { unsigned long cmd = arg->val; + unsigned int fd = syscall_arg__val(arg, 0); + struct file *file = thread__files_entry(arg->thread, fd); + + if (file != NULL) { + if (file->dev_maj == USB_DEVICE_MAJOR) + return ioctl__scnprintf_usbdevfs_cmd(_IOC_NR(cmd), _IOC_DIR(cmd), bf, size); + } return ioctl__scnprintf_cmd(cmd, bf, size, arg->show_string_prefix); } diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index eb31089790e3..859a8a9db2c6 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -18,8 +18,8 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, } P_MMAP_PROT(READ); - P_MMAP_PROT(EXEC); P_MMAP_PROT(WRITE); + P_MMAP_PROT(EXEC); P_MMAP_PROT(SEM); P_MMAP_PROT(GROWSDOWN); P_MMAP_PROT(GROWSUP); diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c index 4600c28a3cfe..637722e2796b 100644 --- a/tools/perf/trace/beauty/seccomp.c +++ b/tools/perf/trace/beauty/seccomp.c @@ -9,7 +9,7 @@ static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg) { bool show_prefix = arg->show_string_prefix; - const char *prefix = "SECOMP_SET_MODE_"; + const char *prefix = "SECCOMP_SET_MODE_"; int op = arg->val; size_t printed = 0; @@ -34,7 +34,7 @@ static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size, struct syscall_arg *arg) { bool show_prefix = arg->show_string_prefix; - const char *prefix = "SECOMP_FILTER_FLAG_"; + const char *prefix = "SECCOMP_FILTER_FLAG_"; int printed = 0, flags = arg->val; #define P_FLAG(n) \ diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh new file mode 100755 index 000000000000..930b80f422e8 --- /dev/null +++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh @@ -0,0 +1,19 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ + +printf "static const char *usbdevfs_ioctl_cmds[] = {\n" +regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" +egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" +printf "#if 0\n" +printf "static const char *usbdevfs_ioctl_32_cmds[] = {\n" +regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" +egrep $regex ${header_dir}/usbdevice_fs.h | egrep 'USBDEVFS_\w+32[[:space:]]' | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" +printf "#endif\n" diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c index 10988d3de7ce..2bd8585db93c 100644 --- a/tools/perf/util/dump-insn.c +++ b/tools/perf/util/dump-insn.c @@ -13,3 +13,11 @@ const char *dump_insn(struct perf_insn *x __maybe_unused, *lenp = 0; return "?"; } + +__weak +int arch_is_branch(const unsigned char *buf __maybe_unused, + size_t len __maybe_unused, + int x86_64 __maybe_unused) +{ + return 0; +} diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h index 0e06280a8860..650125061530 100644 --- a/tools/perf/util/dump-insn.h +++ b/tools/perf/util/dump-insn.h @@ -20,4 +20,6 @@ struct perf_insn { const char *dump_insn(struct perf_insn *x, u64 ip, u8 *inbuf, int inlen, int *lenp); +int arch_is_branch(const unsigned char *buf, size_t len, int x86_64); + #endif diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 7b27d77306c2..ee6ca65f81f4 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -451,7 +451,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq, continue; intel_bts_get_branch_type(btsq, branch); if (btsq->bts->synth_opts.thread_stack) - thread_stack__event(thread, btsq->sample_flags, + thread_stack__event(thread, btsq->cpu, btsq->sample_flags, le64_to_cpu(branch->from), le64_to_cpu(branch->to), btsq->intel_pt_insn.length, @@ -523,7 +523,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp) !btsq->bts->synth_opts.thread_stack && thread && (!old_buffer || btsq->bts->sampling_mode || (btsq->bts->snapshot_mode && !buffer->consecutive))) - thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1); + thread_stack__set_trace_nr(thread, btsq->cpu, buffer->buffer_nr + 1); err = intel_bts_process_buffer(btsq, buffer, thread); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 54818828023b..1c0e289f01e6 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -180,6 +180,14 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, return 0; } +int arch_is_branch(const unsigned char *buf, size_t len, int x86_64) +{ + struct intel_pt_insn in; + if (intel_pt_get_insn(buf, len, x86_64, &in) < 0) + return -1; + return in.branch != INTEL_PT_BR_NO_BRANCH; +} + const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused, u8 *inbuf, int inlen, int *lenp) { diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 149ff361ca78..2e72373ec6df 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1174,7 +1174,7 @@ static void intel_pt_prep_sample(struct intel_pt *pt, intel_pt_prep_b_sample(pt, ptq, event, sample); if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, + thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain, pt->synth_opts.callchain_sz + 1, sample->ip, pt->kernel_start); sample->callchain = ptq->chain; @@ -1526,11 +1526,11 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) return 0; if (pt->synth_opts.callchain || pt->synth_opts.thread_stack) - thread_stack__event(ptq->thread, ptq->flags, state->from_ip, + thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip, state->to_ip, ptq->insn_len, state->trace_nr); else - thread_stack__set_trace_nr(ptq->thread, state->trace_nr); + thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr); if (pt->sample_branches) { err = intel_pt_synth_branch_sample(ptq); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 47628e85c5eb..dda0ac978b1e 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -939,7 +939,8 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, file = PyFile_FromFile(fp, "perf", "r", NULL); #else - file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1); + file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, + NULL, NULL, NULL, 0); #endif if (file == NULL) goto free_list; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 78a067777144..5456c84c7dd1 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1527,6 +1527,13 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) return machine__findnew_thread(&session->machines.host, -1, pid); } +/* + * Threads are identified by pid and tid, and the idle task has pid == tid == 0. + * So here a single thread is created for that, but actually there is a separate + * idle task per cpu, so there should be one 'struct thread' per cpu, but there + * is only 1. That causes problems for some tools, requiring workarounds. For + * example get_idle_thread() in builtin-sched.c, or thread_stack__per_cpu(). + */ int perf_session__register_idle_thread(struct perf_session *session) { struct thread *thread; diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 61a4286a74dc..d52f27f373ce 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -15,6 +15,7 @@ #include <linux/rbtree.h> #include <linux/list.h> +#include <linux/log2.h> #include <errno.h> #include "thread.h" #include "event.h" @@ -60,6 +61,7 @@ struct thread_stack_entry { * @last_time: last timestamp * @crp: call/return processor * @comm: current comm + * @arr_sz: size of array if this is the first element of an array */ struct thread_stack { struct thread_stack_entry *stack; @@ -71,8 +73,19 @@ struct thread_stack { u64 last_time; struct call_return_processor *crp; struct comm *comm; + unsigned int arr_sz; }; +/* + * Assume pid == tid == 0 identifies the idle task as defined by + * perf_session__register_idle_thread(). The idle task is really 1 task per cpu, + * and therefore requires a stack for each cpu. + */ +static inline bool thread_stack__per_cpu(struct thread *thread) +{ + return !(thread->tid || thread->pid_); +} + static int thread_stack__grow(struct thread_stack *ts) { struct thread_stack_entry *new_stack; @@ -91,19 +104,14 @@ static int thread_stack__grow(struct thread_stack *ts) return 0; } -static struct thread_stack *thread_stack__new(struct thread *thread, - struct call_return_processor *crp) +static int thread_stack__init(struct thread_stack *ts, struct thread *thread, + struct call_return_processor *crp) { - struct thread_stack *ts; - - ts = zalloc(sizeof(struct thread_stack)); - if (!ts) - return NULL; + int err; - if (thread_stack__grow(ts)) { - free(ts); - return NULL; - } + err = thread_stack__grow(ts); + if (err) + return err; if (thread->mg && thread->mg->machine) ts->kernel_start = machine__kernel_start(thread->mg->machine); @@ -111,9 +119,72 @@ static struct thread_stack *thread_stack__new(struct thread *thread, ts->kernel_start = 1ULL << 63; ts->crp = crp; + return 0; +} + +static struct thread_stack *thread_stack__new(struct thread *thread, int cpu, + struct call_return_processor *crp) +{ + struct thread_stack *ts = thread->ts, *new_ts; + unsigned int old_sz = ts ? ts->arr_sz : 0; + unsigned int new_sz = 1; + + if (thread_stack__per_cpu(thread) && cpu > 0) + new_sz = roundup_pow_of_two(cpu + 1); + + if (!ts || new_sz > old_sz) { + new_ts = calloc(new_sz, sizeof(*ts)); + if (!new_ts) + return NULL; + if (ts) + memcpy(new_ts, ts, old_sz * sizeof(*ts)); + new_ts->arr_sz = new_sz; + zfree(&thread->ts); + thread->ts = new_ts; + ts = new_ts; + } + + if (thread_stack__per_cpu(thread) && cpu > 0 && + (unsigned int)cpu < ts->arr_sz) + ts += cpu; + + if (!ts->stack && + thread_stack__init(ts, thread, crp)) + return NULL; + return ts; } +static struct thread_stack *thread__cpu_stack(struct thread *thread, int cpu) +{ + struct thread_stack *ts = thread->ts; + + if (cpu < 0) + cpu = 0; + + if (!ts || (unsigned int)cpu >= ts->arr_sz) + return NULL; + + ts += cpu; + + if (!ts->stack) + return NULL; + + return ts; +} + +static inline struct thread_stack *thread__stack(struct thread *thread, + int cpu) +{ + if (!thread) + return NULL; + + if (thread_stack__per_cpu(thread)) + return thread__cpu_stack(thread, cpu); + + return thread->ts; +} + static int thread_stack__push(struct thread_stack *ts, u64 ret_addr, bool trace_end) { @@ -226,25 +297,37 @@ static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts) int thread_stack__flush(struct thread *thread) { - if (thread->ts) - return __thread_stack__flush(thread, thread->ts); + struct thread_stack *ts = thread->ts; + unsigned int pos; + int err = 0; - return 0; + if (ts) { + for (pos = 0; pos < ts->arr_sz; pos++) { + int ret = __thread_stack__flush(thread, ts + pos); + + if (ret) + err = ret; + } + } + + return err; } -int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, +int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip, u64 to_ip, u16 insn_len, u64 trace_nr) { + struct thread_stack *ts = thread__stack(thread, cpu); + if (!thread) return -EINVAL; - if (!thread->ts) { - thread->ts = thread_stack__new(thread, NULL); - if (!thread->ts) { + if (!ts) { + ts = thread_stack__new(thread, cpu, NULL); + if (!ts) { pr_warning("Out of memory: no thread stack\n"); return -ENOMEM; } - thread->ts->trace_nr = trace_nr; + ts->trace_nr = trace_nr; } /* @@ -252,14 +335,14 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, * the stack might be completely invalid. Better to report nothing than * to report something misleading, so flush the stack. */ - if (trace_nr != thread->ts->trace_nr) { - if (thread->ts->trace_nr) - __thread_stack__flush(thread, thread->ts); - thread->ts->trace_nr = trace_nr; + if (trace_nr != ts->trace_nr) { + if (ts->trace_nr) + __thread_stack__flush(thread, ts); + ts->trace_nr = trace_nr; } /* Stop here if thread_stack__process() is in use */ - if (thread->ts->crp) + if (ts->crp) return 0; if (flags & PERF_IP_FLAG_CALL) { @@ -270,7 +353,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, ret_addr = from_ip + insn_len; if (ret_addr == to_ip) return 0; /* Zero-length calls are excluded */ - return thread_stack__push(thread->ts, ret_addr, + return thread_stack__push(ts, ret_addr, flags & PERF_IP_FLAG_TRACE_END); } else if (flags & PERF_IP_FLAG_TRACE_BEGIN) { /* @@ -280,32 +363,52 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, * address, so try to pop that. Also, do not expect a call made * when the trace ended, to return, so pop that. */ - thread_stack__pop(thread->ts, to_ip); - thread_stack__pop_trace_end(thread->ts); + thread_stack__pop(ts, to_ip); + thread_stack__pop_trace_end(ts); } else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) { - thread_stack__pop(thread->ts, to_ip); + thread_stack__pop(ts, to_ip); } return 0; } -void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr) +void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr) { - if (!thread || !thread->ts) + struct thread_stack *ts = thread__stack(thread, cpu); + + if (!ts) return; - if (trace_nr != thread->ts->trace_nr) { - if (thread->ts->trace_nr) - __thread_stack__flush(thread, thread->ts); - thread->ts->trace_nr = trace_nr; + if (trace_nr != ts->trace_nr) { + if (ts->trace_nr) + __thread_stack__flush(thread, ts); + ts->trace_nr = trace_nr; } } +static void __thread_stack__free(struct thread *thread, struct thread_stack *ts) +{ + __thread_stack__flush(thread, ts); + zfree(&ts->stack); +} + +static void thread_stack__reset(struct thread *thread, struct thread_stack *ts) +{ + unsigned int arr_sz = ts->arr_sz; + + __thread_stack__free(thread, ts); + memset(ts, 0, sizeof(*ts)); + ts->arr_sz = arr_sz; +} + void thread_stack__free(struct thread *thread) { - if (thread->ts) { - __thread_stack__flush(thread, thread->ts); - zfree(&thread->ts->stack); + struct thread_stack *ts = thread->ts; + unsigned int pos; + + if (ts) { + for (pos = 0; pos < ts->arr_sz; pos++) + __thread_stack__free(thread, ts + pos); zfree(&thread->ts); } } @@ -315,9 +418,11 @@ static inline u64 callchain_context(u64 ip, u64 kernel_start) return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL; } -void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, +void thread_stack__sample(struct thread *thread, int cpu, + struct ip_callchain *chain, size_t sz, u64 ip, u64 kernel_start) { + struct thread_stack *ts = thread__stack(thread, cpu); u64 context = callchain_context(ip, kernel_start); u64 last_context; size_t i, j; @@ -330,15 +435,15 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, chain->ips[0] = context; chain->ips[1] = ip; - if (!thread || !thread->ts) { + if (!ts) { chain->nr = 2; return; } last_context = context; - for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) { - ip = thread->ts->stack[thread->ts->cnt - j].ret_addr; + for (i = 2, j = 1; i < sz && j <= ts->cnt; i++, j++) { + ip = ts->stack[ts->cnt - j].ret_addr; context = callchain_context(ip, kernel_start); if (context != last_context) { if (i >= sz - 1) @@ -449,7 +554,7 @@ static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts, return 1; } -static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts, +static int thread_stack__bottom(struct thread_stack *ts, struct perf_sample *sample, struct addr_location *from_al, struct addr_location *to_al, u64 ref) @@ -474,7 +579,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts, if (!cp) return -ENOMEM; - return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp, + return thread_stack__push_cp(ts, ip, sample->time, ref, cp, true, false); } @@ -590,24 +695,19 @@ int thread_stack__process(struct thread *thread, struct comm *comm, struct addr_location *to_al, u64 ref, struct call_return_processor *crp) { - struct thread_stack *ts = thread->ts; + struct thread_stack *ts = thread__stack(thread, sample->cpu); int err = 0; - if (ts) { - if (!ts->crp) { - /* Supersede thread_stack__event() */ - thread_stack__free(thread); - thread->ts = thread_stack__new(thread, crp); - if (!thread->ts) - return -ENOMEM; - ts = thread->ts; - ts->comm = comm; - } - } else { - thread->ts = thread_stack__new(thread, crp); - if (!thread->ts) + if (ts && !ts->crp) { + /* Supersede thread_stack__event() */ + thread_stack__reset(thread, ts); + ts = NULL; + } + + if (!ts) { + ts = thread_stack__new(thread, sample->cpu, crp); + if (!ts) return -ENOMEM; - ts = thread->ts; ts->comm = comm; } @@ -621,8 +721,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm, /* If the stack is empty, put the current symbol on the stack */ if (!ts->cnt) { - err = thread_stack__bottom(thread, ts, sample, from_al, to_al, - ref); + err = thread_stack__bottom(ts, sample, from_al, to_al, ref); if (err) return err; } @@ -671,9 +770,11 @@ int thread_stack__process(struct thread *thread, struct comm *comm, return err; } -size_t thread_stack__depth(struct thread *thread) +size_t thread_stack__depth(struct thread *thread, int cpu) { - if (!thread->ts) + struct thread_stack *ts = thread__stack(thread, cpu); + + if (!ts) return 0; - return thread->ts->cnt; + return ts->cnt; } diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h index f97c00a8c251..1f626f4a1c40 100644 --- a/tools/perf/util/thread-stack.h +++ b/tools/perf/util/thread-stack.h @@ -80,14 +80,14 @@ struct call_return_processor { void *data; }; -int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip, +int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip, u64 to_ip, u16 insn_len, u64 trace_nr); -void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr); -void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, +void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr); +void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain, size_t sz, u64 ip, u64 kernel_start); int thread_stack__flush(struct thread *thread); void thread_stack__free(struct thread *thread); -size_t thread_stack__depth(struct thread *thread); +size_t thread_stack__depth(struct thread *thread, int cpu); struct call_return_processor * call_return_processor__new(int (*process)(struct call_return *cr, void *data), diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2ab25aa38263..1598b4fa0b11 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -9,13 +9,13 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -CFLAGS += -Wall -CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' -CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -Wall +override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' +override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) .PHONY : clean clean : diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index f4534fb8b951..ae7a0e09b722 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -9,12 +9,12 @@ ifeq ("$(origin O)", "command line") endif x86_energy_perf_policy : x86_energy_perf_policy.c -CFLAGS += -Wall -CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' +override CFLAGS += -Wall +override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) .PHONY : clean clean : diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile index 735a510230c3..89a2444c1df2 100644 --- a/tools/thermal/tmon/Makefile +++ b/tools/thermal/tmon/Makefile @@ -6,13 +6,13 @@ VERSION = 1.0 BINDIR=usr/bin WARNFLAGS=-Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int -CFLAGS+= -O1 ${WARNFLAGS} +override CFLAGS+= -O1 ${WARNFLAGS} # Add "-fstack-protector" only if toolchain supports it. -CFLAGS+= $(call cc-option,-fstack-protector) +override CFLAGS+= $(call cc-option,-fstack-protector-strong) CC?= $(CROSS_COMPILE)gcc PKG_CONFIG?= pkg-config -CFLAGS+=-D VERSION=\"$(VERSION)\" +override CFLAGS+=-D VERSION=\"$(VERSION)\" LDFLAGS+= TARGET=tmon @@ -29,7 +29,7 @@ TMON_LIBS += $(shell $(PKG_CONFIG) --libs $(STATIC) panelw ncursesw 2> /dev/null $(PKG_CONFIG) --libs $(STATIC) panel ncurses 2> /dev/null || \ echo -lpanel -lncurses) -CFLAGS += $(shell $(PKG_CONFIG) --cflags $(STATIC) panelw ncursesw 2> /dev/null || \ +override CFLAGS += $(shell $(PKG_CONFIG) --cflags $(STATIC) panelw ncursesw 2> /dev/null || \ $(PKG_CONFIG) --cflags $(STATIC) panel ncurses 2> /dev/null) OBJS = tmon.o tui.o sysfs.o pid.o |