diff options
1041 files changed, 44023 insertions, 7183 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index efc7aa7a0670..533ff5c68970 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4846,3 +4846,8 @@ xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] + + xhci-hcd.quirks [USB,KNL] + A hex value specifying bitmask with supplemental xhci + host controller quirks. Meaning of each bit can be + consulted in header drivers/usb/host/xhci.h. diff --git a/Documentation/device-mapper/writecache.txt b/Documentation/device-mapper/writecache.txt index 4424fa2c67d7..01532b3008ae 100644 --- a/Documentation/device-mapper/writecache.txt +++ b/Documentation/device-mapper/writecache.txt @@ -15,6 +15,8 @@ Constructor parameters: size) 5. the number of optional parameters (the parameters with an argument count as two) + start_sector n (default: 0) + offset from the start of cache device in 512-byte sectors high_watermark n (default: 50) start writeback when the number of used blocks reach this watermark diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt index bdadc3da9556..6970f30a3770 100644 --- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt +++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt @@ -66,7 +66,7 @@ Required root node properties: - "insignal,arndale-octa" - for Exynos5420-based Insignal Arndale Octa board. - "insignal,origen" - for Exynos4210-based Insignal Origen board. - - "insignal,origen4412 - for Exynos4412-based Insignal Origen board. + - "insignal,origen4412" - for Exynos4412-based Insignal Origen board. Optional nodes: diff --git a/Documentation/devicetree/bindings/display/msm/dpu.txt b/Documentation/devicetree/bindings/display/msm/dpu.txt new file mode 100644 index 000000000000..ad2e8830324e --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/dpu.txt @@ -0,0 +1,131 @@ +Qualcomm Technologies, Inc. DPU KMS + +Description: + +Device tree bindings for MSM Mobile Display Subsytem(MDSS) that encapsulates +sub-blocks like DPU display controller, DSI and DP interfaces etc. +The DPU display controller is found in SDM845 SoC. + +MDSS: +Required properties: +- compatible: "qcom,sdm845-mdss" +- reg: physical base address and length of contoller's registers. +- reg-names: register region names. The following region is required: + * "mdss" +- power-domains: a power domain consumer specifier according to + Documentation/devicetree/bindings/power/power_domain.txt +- clocks: list of clock specifiers for clocks needed by the device. +- clock-names: device clock names, must be in same order as clocks property. + The following clocks are required: + * "iface" + * "bus" + * "core" +- interrupts: interrupt signal from MDSS. +- interrupt-controller: identifies the node as an interrupt controller. +- #interrupt-cells: specifies the number of cells needed to encode an interrupt + source, should be 1. +- iommus: phandle of iommu device node. +- #address-cells: number of address cells for the MDSS children. Should be 1. +- #size-cells: Should be 1. +- ranges: parent bus address space is the same as the child bus address space. + +Optional properties: +- assigned-clocks: list of clock specifiers for clocks needing rate assignment +- assigned-clock-rates: list of clock frequencies sorted in the same order as + the assigned-clocks property. + +MDP: +Required properties: +- compatible: "qcom,sdm845-dpu" +- reg: physical base address and length of controller's registers. +- reg-names : register region names. The following region is required: + * "mdp" + * "vbif" +- clocks: list of clock specifiers for clocks needed by the device. +- clock-names: device clock names, must be in same order as clocks property. + The following clocks are required. + * "bus" + * "iface" + * "core" + * "vsync" +- interrupts: interrupt line from DPU to MDSS. +- ports: contains the list of output ports from DPU device. These ports connect + to interfaces that are external to the DPU hardware, such as DSI, DP etc. + + Each output port contains an endpoint that describes how it is connected to an + external interface. These are described by the standard properties documented + here: + Documentation/devicetree/bindings/graph.txt + Documentation/devicetree/bindings/media/video-interfaces.txt + + Port 0 -> DPU_INTF1 (DSI1) + Port 1 -> DPU_INTF2 (DSI2) + +Optional properties: +- assigned-clocks: list of clock specifiers for clocks needing rate assignment +- assigned-clock-rates: list of clock frequencies sorted in the same order as + the assigned-clocks property. + +Example: + + mdss: mdss@ae00000 { + compatible = "qcom,sdm845-mdss"; + reg = <0xae00000 0x1000>; + reg-names = "mdss"; + + power-domains = <&clock_dispcc 0>; + + clocks = <&gcc GCC_DISP_AHB_CLK>, <&gcc GCC_DISP_AXI_CLK>, + <&clock_dispcc DISP_CC_MDSS_MDP_CLK>; + clock-names = "iface", "bus", "core"; + + assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>; + assigned-clock-rates = <300000000>; + + interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <1>; + + iommus = <&apps_iommu 0>; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0xae00000 0xb2008>; + + mdss_mdp: mdp@ae01000 { + compatible = "qcom,sdm845-dpu"; + reg = <0 0x1000 0x8f000>, <0 0xb0000 0x2008>; + reg-names = "mdp", "vbif"; + + clocks = <&clock_dispcc DISP_CC_MDSS_AHB_CLK>, + <&clock_dispcc DISP_CC_MDSS_AXI_CLK>, + <&clock_dispcc DISP_CC_MDSS_MDP_CLK>, + <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>; + clock-names = "iface", "bus", "core", "vsync"; + + assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>, + <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>; + assigned-clock-rates = <0 0 300000000 19200000>; + + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dpu_intf1_out: endpoint { + remote-endpoint = <&dsi0_in>; + }; + }; + + port@1 { + reg = <1>; + dpu_intf2_out: endpoint { + remote-endpoint = <&dsi1_in>; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index 518e9cdf0d4b..d22237a88eae 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -121,6 +121,20 @@ Required properties: Optional properties: - qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY regulator is wanted. +- qcom,mdss-mdp-transfer-time-us: Specifies the dsi transfer time for command mode + panels in microseconds. Driver uses this number to adjust + the clock rate according to the expected transfer time. + Increasing this value would slow down the mdp processing + and can result in slower performance. + Decreasing this value can speed up the mdp processing, + but this can also impact power consumption. + As a rule this time should not be higher than the time + that would be expected with the processing at the + dsi link rate since anyways this would be the maximum + transfer time that could be achieved. + If ping pong split is enabled, this time should not be higher + than two times the dsi link rate time. + If the property is not specified, then the default value is 14000 us. [1] Documentation/devicetree/bindings/clock/clock-bindings.txt [2] Documentation/devicetree/bindings/graph.txt @@ -171,6 +185,8 @@ Example: qcom,master-dsi; qcom,sync-dual-dsi; + qcom,mdss-mdp-transfer-time-us = <12000>; + pinctrl-names = "default", "sleep"; pinctrl-0 = <&dsi_active>; pinctrl-1 = <&dsi_suspend>; diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt index 6fddb4f4f71a..3055d5c2c04e 100644 --- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt +++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt @@ -36,7 +36,7 @@ Optional nodes: - port/ports: to describe a connection to an external encoder. The binding follows Documentation/devicetree/bindings/graph.txt and - suppors a single port with a single endpoint. + supports a single port with a single endpoint. - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting diff --git a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt index 20fc72d9e61e..45a61b462287 100644 --- a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt +++ b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt @@ -1,7 +1,7 @@ Nintendo Wii (Hollywood) GPIO controller Required properties: -- compatible: "nintendo,hollywood-gpio +- compatible: "nintendo,hollywood-gpio" - reg: Physical base address and length of the controller's registers. - gpio-controller: Marks the device node as a GPIO controller. - #gpio-cells: Should be <2>. The first cell is the pin number and the diff --git a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt index 121d9b7c79a2..1063c30d53f7 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt +++ b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt @@ -32,7 +32,7 @@ i2c@00000000 { reg = <0x6c>; interrupt-parent = <&gpx1>; interrupts = <2 IRQ_TYPE_LEVEL_LOW>; - vdd-supply = <&ldo15_reg>"; + vdd-supply = <&ldo15_reg>; vid-supply = <&ldo18_reg>; reset-gpios = <&gpx1 5 0>; touchscreen-size-x = <1080>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt index 1099fe0788fa..f246ccbf8838 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt @@ -15,7 +15,7 @@ Required properties: include "nvidia,tegra30-ictlr". - reg : Specifies base physical address and size of the registers. Each controller must be described separately (Tegra20 has 4 of them, - whereas Tegra30 and later have 5" + whereas Tegra30 and later have 5). - 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 3. diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt index 136bd612bd83..6a36bf66d932 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt @@ -12,7 +12,7 @@ Required properties: specifier, shall be 2 - interrupts: interrupts references to primary interrupt controller (only needed for exti controller with multiple exti under - same parent interrupt: st,stm32-exti and st,stm32h7-exti") + same parent interrupt: st,stm32-exti and st,stm32h7-exti) Example: diff --git a/Documentation/devicetree/bindings/mips/brcm/soc.txt b/Documentation/devicetree/bindings/mips/brcm/soc.txt index 356c29789cf5..3a66d3c483e1 100644 --- a/Documentation/devicetree/bindings/mips/brcm/soc.txt +++ b/Documentation/devicetree/bindings/mips/brcm/soc.txt @@ -152,7 +152,7 @@ Required properties: - compatible : should contain one of: "brcm,bcm7425-timers" "brcm,bcm7429-timers" - "brcm,bcm7435-timers and + "brcm,bcm7435-timers" and "brcm,brcmstb-timers" - reg : the timers register range - interrupts : the interrupt line for this timer block diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index df873d1f3b7c..f8c33890bc29 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -238,7 +238,7 @@ PROPERTIES Must include one of the following: - "fsl,fman-dtsec" for dTSEC MAC - "fsl,fman-xgec" for XGEC MAC - - "fsl,fman-memac for mEMAC MAC + - "fsl,fman-memac" for mEMAC MAC - cell-index Usage: required diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt index 9b387f861aed..7dec508987c7 100644 --- a/Documentation/devicetree/bindings/power/power_domain.txt +++ b/Documentation/devicetree/bindings/power/power_domain.txt @@ -133,7 +133,7 @@ located inside a PM domain with index 0 of a power controller represented by a node with the label "power". In the second example the consumer device are partitioned across two PM domains, the first with index 0 and the second with index 1, of a power controller that -is represented by a node with the label "power. +is represented by a node with the label "power". Optional properties: - required-opps: This contains phandle to an OPP node in another device's OPP diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt index ca69f5e3040c..ae326f263597 100644 --- a/Documentation/devicetree/bindings/regulator/tps65090.txt +++ b/Documentation/devicetree/bindings/regulator/tps65090.txt @@ -16,7 +16,7 @@ Required properties: Optional properties: - ti,enable-ext-control: This is applicable for DCDC1, DCDC2 and DCDC3. If DCDCs are externally controlled then this property should be there. -- "dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3. +- dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3. If DCDCs are externally controlled and if it is from GPIO then GPIO number should be provided. If it is externally controlled and no GPIO entry then driver will just configure this rails as external control diff --git a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt index a21658f18fe6..3661e6153a92 100644 --- a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt +++ b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt @@ -15,7 +15,7 @@ Please refer to reset.txt in this directory for common reset controller binding usage. Required properties: -- compatible: Should be st,stih407-softreset"; +- compatible: Should be "st,stih407-softreset"; - #reset-cells: 1, see below example: diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt index d330c73de9a2..68b7d6207e3d 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt @@ -39,7 +39,7 @@ Required properties: Optional property: - clock-frequency: Desired I2C bus clock frequency in Hz. - When missing default to 400000Hz. + When missing default to 100000Hz. Child nodes should conform to I2C bus binding as described in i2c.txt. diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt index 6a4aadc4ce06..84b28dbe9f15 100644 --- a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt +++ b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt @@ -30,7 +30,7 @@ Required properties: Board connectors: * Headset Mic - * Secondary Mic", + * Secondary Mic * DMIC * Ext Spk diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt index aa54e49fc8a2..c7600a93ab39 100644 --- a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt +++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt @@ -35,7 +35,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio. "Digital Mic3" Audio pins and MicBias on WCD9335 Codec: - "MIC_BIAS1 + "MIC_BIAS1" "MIC_BIAS2" "MIC_BIAS3" "MIC_BIAS4" diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt index 252a05c5d976..c8c4b00ecb94 100644 --- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt @@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt +Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY +Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY Example device nodes: diff --git a/Documentation/devicetree/bindings/w1/w1-gpio.txt b/Documentation/devicetree/bindings/w1/w1-gpio.txt index 6e09c35d9f1a..37091902a021 100644 --- a/Documentation/devicetree/bindings/w1/w1-gpio.txt +++ b/Documentation/devicetree/bindings/w1/w1-gpio.txt @@ -15,7 +15,7 @@ Optional properties: Examples: - onewire@0 { + onewire { compatible = "w1-gpio"; gpios = <&gpio 126 0>, <&gpio 105 0>; }; diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst new file mode 100644 index 000000000000..757cd257e0d8 --- /dev/null +++ b/Documentation/gpu/msm-crash-dump.rst @@ -0,0 +1,96 @@ +===================== +MSM Crash Dump Format +===================== + +Following a GPU hang the MSM driver outputs debugging information via +/sys/kernel/dri/X/show or via devcoredump (/sys/class/devcoredump/dcdX/data). +This document describes how the output is formatted. + +Each entry is in the form key: value. Sections headers will not have a value +and all the contents of a section will be indented two spaces from the header. +Each section might have multiple array entries the start of which is designated +by a (-). + +Mappings +-------- + +kernel + The kernel version that generated the dump (UTS_RELEASE). + +module + The module that generated the crashdump. + +time + The kernel time at crash formated as seconds.microseconds. + +comm + Comm string for the binary that generated the fault. + +cmdline + Command line for the binary that generated the fault. + +revision + ID of the GPU that generated the crash formatted as + core.major.minor.patchlevel separated by dots. + +rbbm-status + The current value of RBBM_STATUS which shows what top level GPU + components are in use at the time of crash. + +ringbuffer + Section containing the contents of each ringbuffer. Each ringbuffer is + identified with an id number. + + id + Ringbuffer ID (0 based index). Each ringbuffer in the section + will have its own unique id. + iova + GPU address of the ringbuffer. + + last-fence + The last fence that was issued on the ringbuffer + + retired-fence + The last fence retired on the ringbuffer. + + rptr + The current read pointer (rptr) for the ringbuffer. + + wptr + The current write pointer (wptr) for the ringbuffer. + + size + Maximum size of the ringbuffer programmed in the hardware. + + data + The contents of the ring encoded as ascii85. Only the used + portions of the ring will be printed. + +bo + List of buffers from the hanging submission if available. + Each buffer object will have a uinque iova. + + iova + GPU address of the buffer object. + + size + Allocated size of the buffer object. + + data + The contents of the buffer object encoded with ascii85. Only + Trailing zeros at the end of the buffer will be skipped. + +registers + Set of registers values. Each entry is on its own line enclosed + by brackets { }. + + offset + Byte offset of the register from the start of the + GPU memory region. + + value + Hexadecimal value of the register. + +registers-hlsq + (5xx only) Register values from the HLSQ aperture. + Same format as the register section. diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt index 6c9c69ec3986..114c7ce7b58d 100644 --- a/Documentation/kbuild/kbuild.txt +++ b/Documentation/kbuild/kbuild.txt @@ -50,6 +50,11 @@ LDFLAGS_MODULE -------------------------------------------------- Additional options used for $(LD) when linking modules. +KBUILD_KCONFIG +-------------------------------------------------- +Set the top-level Kconfig file to the value of this environment +variable. The default name is "Kconfig". + KBUILD_VERBOSE -------------------------------------------------- Set the kbuild verbosity. Can be assigned same values as "V=...". @@ -88,7 +93,8 @@ In most cases the name of the architecture is the same as the directory name found in the arch/ directory. But some architectures such as x86 and sparc have aliases. x86: i386 for 32 bit, x86_64 for 64 bit -sparc: sparc for 32 bit, sparc64 for 64 bit +sh: sh for 32 bit, sh64 for 64 bit +sparc: sparc32 for 32 bit, sparc64 for 64 bit CROSS_COMPILE -------------------------------------------------- @@ -148,15 +154,6 @@ stripped after they are installed. If INSTALL_MOD_STRIP is '1', then the default option --strip-debug will be used. Otherwise, INSTALL_MOD_STRIP value will be used as the options to the strip command. -INSTALL_FW_PATH --------------------------------------------------- -INSTALL_FW_PATH specifies where to install the firmware blobs. -The default value is: - - $(INSTALL_MOD_PATH)/lib/firmware - -The value can be overridden in which case the default value is ignored. - INSTALL_HDR_PATH -------------------------------------------------- INSTALL_HDR_PATH specifies where to install user space headers when diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt index 7233118f3a05..68c82914c0f3 100644 --- a/Documentation/kbuild/kconfig.txt +++ b/Documentation/kbuild/kconfig.txt @@ -2,9 +2,9 @@ This file contains some assistance for using "make *config". Use "make help" to list all of the possible configuration targets. -The xconfig ('qconf') and menuconfig ('mconf') programs also -have embedded help text. Be sure to check it for navigation, -search, and other general help text. +The xconfig ('qconf'), menuconfig ('mconf'), and nconfig ('nconf') +programs also have embedded help text. Be sure to check that for +navigation, search, and other general help text. ====================================================================== General @@ -17,13 +17,16 @@ this happens, using a previously working .config file and running for you, so you may find that you need to see what NEW kernel symbols have been introduced. -To see a list of new config symbols when using "make oldconfig", use +To see a list of new config symbols, use cp user/some/old.config .config make listnewconfig and the config program will list any new symbols, one per line. +Alternatively, you can use the brute force method: + + make oldconfig scripts/diffconfig .config.old .config | less ______________________________________________________________________ @@ -160,7 +163,7 @@ Searching in menuconfig: This lists all config symbols that contain "hotplug", e.g., HOTPLUG_CPU, MEMORY_HOTPLUG. - For search help, enter / followed TAB-TAB-TAB (to highlight + For search help, enter / followed by TAB-TAB (to highlight <Help>) and Enter. This will tell you that you can also use regular expressions (regexes) in the search string, so if you are not interested in MEMORY_HOTPLUG, you could try @@ -203,6 +206,39 @@ Example: ====================================================================== +nconfig +-------------------------------------------------- + +nconfig is an alternate text-based configurator. It lists function +keys across the bottom of the terminal (window) that execute commands. +You can also just use the corresponding numeric key to execute the +commands unless you are in a data entry window. E.g., instead of F6 +for Save, you can just press 6. + +Use F1 for Global help or F3 for the Short help menu. + +Searching in nconfig: + + You can search either in the menu entry "prompt" strings + or in the configuration symbols. + + Use / to begin a search through the menu entries. This does + not support regular expressions. Use <Down> or <Up> for + Next hit and Previous hit, respectively. Use <Esc> to + terminate the search mode. + + F8 (SymSearch) searches the configuration symbols for the + given string or regular expression (regex). + +NCONFIG_MODE +-------------------------------------------------- +This mode shows all sub-menus in one large tree. + +Example: + make NCONFIG_MODE=single_menu nconfig + + +====================================================================== xconfig -------------------------------------------------- @@ -230,8 +266,7 @@ gconfig Searching in gconfig: - None (gconfig isn't maintained as well as xconfig or menuconfig); - however, gconfig does have a few more viewing choices than - xconfig does. + There is no search command in gconfig. However, gconfig does + have several different viewing choices, modes, and options. ### diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index c13214d073a4..d3e5dd26db12 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -1490,7 +1490,7 @@ To remove an ARP target: To configure the interval between learning packet transmits: # echo 12 > /sys/class/net/bond0/bonding/lp_interval - NOTE: the lp_inteval is the number of seconds between instances where + NOTE: the lp_interval is the number of seconds between instances where the bonding driver sends learning packets to each slaves peer switch. The default interval is 1 second. diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst index 9708f5fa76de..f81111eba9c5 100644 --- a/Documentation/networking/e100.rst +++ b/Documentation/networking/e100.rst @@ -47,41 +47,45 @@ Driver Configuration Parameters The default value for each parameter is generally the recommended setting, unless otherwise noted. -Rx Descriptors: Number of receive descriptors. A receive descriptor is a data +Rx Descriptors: + Number of receive descriptors. A receive descriptor is a data structure that describes a receive buffer and its attributes to the network controller. The data in the descriptor is used by the controller to write data from the controller to host memory. In the 3.x.x driver the valid range for this parameter is 64-256. The default value is 256. This parameter can be changed using the command:: - ethtool -G eth? rx n + ethtool -G eth? rx n Where n is the number of desired Rx descriptors. -Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data +Tx Descriptors: + Number of transmit descriptors. A transmit descriptor is a data structure that describes a transmit buffer and its attributes to the network controller. The data in the descriptor is used by the controller to read data from the host memory to the controller. In the 3.x.x driver the valid range for this parameter is 64-256. The default value is 128. This parameter can be changed using the command:: - ethtool -G eth? tx n + ethtool -G eth? tx n Where n is the number of desired Tx descriptors. -Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by +Speed/Duplex: + The driver auto-negotiates the link speed and duplex settings by default. The ethtool utility can be used as follows to force speed/duplex.:: - ethtool -s eth? autoneg off speed {10|100} duplex {full|half} + ethtool -s eth? autoneg off speed {10|100} duplex {full|half} NOTE: setting the speed/duplex to incorrect values will cause the link to fail. -Event Log Message Level: The driver uses the message level flag to log events +Event Log Message Level: + The driver uses the message level flag to log events to syslog. The message level can be set at driver load time. It can also be set using the command:: - ethtool -s eth? msglvl n + ethtool -s eth? msglvl n Additional Configurations @@ -92,7 +96,7 @@ Configuring the Driver on Different Distributions Configuring a network driver to load properly when the system is started is distribution dependent. Typically, the configuration process involves -adding an alias line to /etc/modprobe.d/*.conf as well as editing other +adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other system startup scripts and/or configuration files. Many popular Linux distributions ship with tools to make these changes for you. To learn the proper way to configure a network device for your system, refer to @@ -160,7 +164,10 @@ This results in unbalanced receive traffic. If you have multiple interfaces in a server, either turn on ARP filtering by -(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter +(1) entering:: + + echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter + (this only works if your kernel's version is higher than 2.4.5), or (2) installing the interfaces in separate broadcast domains (either diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst index 144b87eef153..f10dd4086921 100644 --- a/Documentation/networking/e1000.rst +++ b/Documentation/networking/e1000.rst @@ -34,7 +34,8 @@ Command Line Parameters The default value for each parameter is generally the recommended setting, unless otherwise noted. -NOTES: For more information about the AutoNeg, Duplex, and Speed +NOTES: + For more information about the AutoNeg, Duplex, and Speed parameters, see the "Speed and Duplex Configuration" section in this document. @@ -45,22 +46,27 @@ NOTES: For more information about the AutoNeg, Duplex, and Speed AutoNeg ------- + (Supported only on adapters with copper connections) -Valid Range: 0x01-0x0F, 0x20-0x2F -Default Value: 0x2F + +:Valid Range: 0x01-0x0F, 0x20-0x2F +:Default Value: 0x2F This parameter is a bit-mask that specifies the speed and duplex settings advertised by the adapter. When this parameter is used, the Speed and Duplex parameters must not be specified. -NOTE: Refer to the Speed and Duplex section of this readme for more +NOTE: + Refer to the Speed and Duplex section of this readme for more information on the AutoNeg parameter. Duplex ------ + (Supported only on adapters with copper connections) -Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) -Default Value: 0 + +:Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) +:Default Value: 0 This defines the direction in which data is allowed to flow. Can be either one or two-directional. If both Duplex and the link partner are @@ -70,18 +76,22 @@ duplex. FlowControl ----------- -Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) -Default Value: Reads flow control settings from the EEPROM + +:Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) +:Default Value: Reads flow control settings from the EEPROM This parameter controls the automatic generation(Tx) and response(Rx) to Ethernet PAUSE frames. InterruptThrottleRate --------------------- + (not supported on Intel(R) 82542, 82543 or 82544-based adapters) -Valid Range: 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, - 4=simplified balancing) -Default Value: 3 + +:Valid Range: + 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, + 4=simplified balancing) +:Default Value: 3 The driver can limit the amount of interrupts per second that the adapter will generate for incoming packets. It does this by writing a value to the @@ -135,13 +145,15 @@ Setting InterruptThrottleRate to 0 turns off any interrupt moderation and may improve small packet latency, but is generally not suitable for bulk throughput traffic. -NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and +NOTE: + InterruptThrottleRate takes precedence over the TxAbsIntDelay and RxAbsIntDelay parameters. In other words, minimizing the receive and/or transmit absolute delays does not force the controller to generate more interrupts than what the Interrupt Throttle Rate allows. -CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection +CAUTION: + If you are using the Intel(R) PRO/1000 CT Network Connection (controller 82547), setting InterruptThrottleRate to a value greater than 75,000, may hang (stop transmitting) adapters under certain network conditions. If this occurs a NETDEV @@ -151,7 +163,8 @@ CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection hang, ensure that InterruptThrottleRate is set no greater than 75,000 and is not set to 0. -NOTE: When e1000 is loaded with default settings and multiple adapters +NOTE: + When e1000 is loaded with default settings and multiple adapters are in use simultaneously, the CPU utilization may increase non- linearly. In order to limit the CPU utilization without impacting the overall throughput, we recommend that you load the driver as @@ -168,9 +181,11 @@ NOTE: When e1000 is loaded with default settings and multiple adapters RxDescriptors ------------- -Valid Range: 48-256 for 82542 and 82543-based adapters - 48-4096 for all other supported adapters -Default Value: 256 + +:Valid Range: + - 48-256 for 82542 and 82543-based adapters + - 48-4096 for all other supported adapters +:Default Value: 256 This value specifies the number of receive buffer descriptors allocated by the driver. Increasing this value allows the driver to buffer more @@ -180,15 +195,17 @@ Each descriptor is 16 bytes. A receive buffer is also allocated for each descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending on the MTU setting. The maximum MTU size is 16110. -NOTE: MTU designates the frame size. It only needs to be set for Jumbo +NOTE: + MTU designates the frame size. It only needs to be set for Jumbo Frames. Depending on the available system resources, the request for a higher number of receive descriptors may be denied. In this case, use a lower number. RxIntDelay ---------- -Valid Range: 0-65535 (0=off) -Default Value: 0 + +:Valid Range: 0-65535 (0=off) +:Default Value: 0 This value delays the generation of receive interrupts in units of 1.024 microseconds. Receive interrupt reduction can improve CPU efficiency if @@ -198,7 +215,8 @@ of TCP traffic. If the system is reporting dropped receives, this value may be set too high, causing the driver to run out of available receive descriptors. -CAUTION: When setting RxIntDelay to a value other than 0, adapters may +CAUTION: + When setting RxIntDelay to a value other than 0, adapters may hang (stop transmitting) under certain network conditions. If this occurs a NETDEV WATCHDOG message is logged in the system event log. In addition, the controller is automatically reset, @@ -207,9 +225,11 @@ CAUTION: When setting RxIntDelay to a value other than 0, adapters may RxAbsIntDelay ------------- + (This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 128 + +:Valid Range: 0-65535 (0=off) +:Default Value: 128 This value, in units of 1.024 microseconds, limits the delay in which a receive interrupt is generated. Useful only if RxIntDelay is non-zero, @@ -220,9 +240,11 @@ conditions. Speed ----- + (This parameter is supported only on adapters with copper connections.) -Valid Settings: 0, 10, 100, 1000 -Default Value: 0 (auto-negotiate at all supported speeds) + +:Valid Settings: 0, 10, 100, 1000 +:Default Value: 0 (auto-negotiate at all supported speeds) Speed forces the line speed to the specified value in megabits per second (Mbps). If this parameter is not specified or is set to 0 and the link @@ -231,22 +253,26 @@ speed. Duplex should also be set when Speed is set to either 10 or 100. TxDescriptors ------------- -Valid Range: 48-256 for 82542 and 82543-based adapters - 48-4096 for all other supported adapters -Default Value: 256 + +:Valid Range: + - 48-256 for 82542 and 82543-based adapters + - 48-4096 for all other supported adapters +:Default Value: 256 This value is the number of transmit descriptors allocated by the driver. Increasing this value allows the driver to queue more transmits. Each descriptor is 16 bytes. -NOTE: Depending on the available system resources, the request for a +NOTE: + Depending on the available system resources, the request for a higher number of transmit descriptors may be denied. In this case, use a lower number. TxIntDelay ---------- -Valid Range: 0-65535 (0=off) -Default Value: 8 + +:Valid Range: 0-65535 (0=off) +:Default Value: 8 This value delays the generation of transmit interrupts in units of 1.024 microseconds. Transmit interrupt reduction can improve CPU @@ -256,9 +282,11 @@ causing the driver to run out of available transmit descriptors. TxAbsIntDelay ------------- + (This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 32 + +:Valid Range: 0-65535 (0=off) +:Default Value: 32 This value, in units of 1.024 microseconds, limits the delay in which a transmit interrupt is generated. Useful only if TxIntDelay is non-zero, @@ -269,18 +297,21 @@ network conditions. XsumRX ------ + (This parameter is NOT supported on the 82542-based adapter.) -Valid Range: 0-1 -Default Value: 1 + +:Valid Range: 0-1 +:Default Value: 1 A value of '1' indicates that the driver should enable IP checksum offload for received packets (both UDP and TCP) to the adapter hardware. Copybreak --------- -Valid Range: 0-xxxxxxx (0=off) -Default Value: 256 -Usage: modprobe e1000.ko copybreak=128 + +:Valid Range: 0-xxxxxxx (0=off) +:Default Value: 256 +:Usage: modprobe e1000.ko copybreak=128 Driver copies all packets below or equaling this size to a fresh RX buffer before handing it up the stack. @@ -292,8 +323,9 @@ it is also available during runtime at SmartPowerDownEnable -------------------- -Valid Range: 0-1 -Default Value: 0 (disabled) + +:Valid Range: 0-1 +:Default Value: 0 (disabled) Allows PHY to turn off in lower power states. The user can turn off this parameter in supported chipsets. @@ -309,14 +341,14 @@ fiber interface board only links at 1000 Mbps full-duplex. For copper-based boards, the keywords interact as follows: - The default operation is auto-negotiate. The board advertises all +- The default operation is auto-negotiate. The board advertises all supported speed and duplex combinations, and it links at the highest common speed and duplex mode IF the link partner is set to auto-negotiate. - If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps +- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps is advertised (The 1000BaseT spec requires auto-negotiation.) - If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- +- If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- negotiation is disabled, and the AutoNeg parameter is ignored. Partner SHOULD also be forced. @@ -328,13 +360,15 @@ process. The parameter may be specified as either a decimal or hexadecimal value as determined by the bitmap below. +============== ====== ====== ======= ======= ====== ====== ======= ====== Bit position 7 6 5 4 3 2 1 0 Decimal Value 128 64 32 16 8 4 2 1 Hex value 80 40 20 10 8 4 2 1 Speed (Mbps) N/A N/A 1000 N/A 100 100 10 10 Duplex Full Full Half Full Half +============== ====== ====== ======= ======= ====== ====== ======= ====== -Some examples of using AutoNeg: +Some examples of using AutoNeg:: modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half) modprobe e1000 AutoNeg=1 (Same as above) @@ -357,56 +391,59 @@ Additional Configurations Jumbo Frames ------------ -Jumbo Frames support is enabled by changing the MTU to a value larger -than the default of 1500. Use the ifconfig command to increase the MTU -size. For example:: + + Jumbo Frames support is enabled by changing the MTU to a value larger than + the default of 1500. Use the ifconfig command to increase the MTU size. + For example:: ifconfig eth<x> mtu 9000 up -This setting is not saved across reboots. It can be made permanent if -you add:: + This setting is not saved across reboots. It can be made permanent if + you add:: MTU=9000 -to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example -applies to the Red Hat distributions; other distributions may store this -setting in a different location. + to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example + applies to the Red Hat distributions; other distributions may store this + setting in a different location. + +Notes: + Degradation in throughput performance may be observed in some Jumbo frames + environments. If this is observed, increasing the application's socket buffer + size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. + See the specific application manual and /usr/src/linux*/Documentation/ + networking/ip-sysctl.txt for more details. -Notes: Degradation in throughput performance may be observed in some -Jumbo frames environments. If this is observed, increasing the -application's socket buffer size and/or increasing the -/proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific -application manual and /usr/src/linux*/Documentation/ -networking/ip-sysctl.txt for more details. + - The maximum MTU setting for Jumbo Frames is 16110. This value coincides + with the maximum Jumbo Frames size of 16128. -- The maximum MTU setting for Jumbo Frames is 16110. This value - coincides with the maximum Jumbo Frames size of 16128. + - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in + poor performance or loss of link. -- Using Jumbo frames at 10 or 100 Mbps is not supported and may result - in poor performance or loss of link. + - Adapters based on the Intel(R) 82542 and 82573V/E controller do not + support Jumbo Frames. These correspond to the following product names:: -- Adapters based on the Intel(R) 82542 and 82573V/E controller do not - support Jumbo Frames. These correspond to the following product names: - Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network - Connection + Intel(R) PRO/1000 Gigabit Server Adapter + Intel(R) PRO/1000 PM Network Connection ethtool ------- -The driver utilizes the ethtool interface for driver configuration and -diagnostics, as well as displaying statistical information. The ethtool -version 1.6 or later is required for this functionality. -The latest release of ethtool can be found from -https://www.kernel.org/pub/software/network/ethtool/ + The driver utilizes the ethtool interface for driver configuration and + diagnostics, as well as displaying statistical information. The ethtool + version 1.6 or later is required for this functionality. + + The latest release of ethtool can be found from + https://www.kernel.org/pub/software/network/ethtool/ Enabling Wake on LAN* (WoL) --------------------------- -WoL is configured through the ethtool* utility. -WoL will be enabled on the system during the next shut down or reboot. -For this driver version, in order to enable WoL, the e1000 driver must be -loaded when shutting down or rebooting the system. + WoL is configured through the ethtool* utility. + WoL will be enabled on the system during the next shut down or reboot. + For this driver version, in order to enable WoL, the e1000 driver must be + loaded when shutting down or rebooting the system. Support ======= diff --git a/MAINTAINERS b/MAINTAINERS index 93f189f0d60d..9b2bf134964e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -581,7 +581,7 @@ W: https://www.infradead.org/~dhowells/kafs/ AGPGART DRIVER M: David Airlie <airlied@linux.ie> -T: git git://people.freedesktop.org/~airlied/linux (part of drm maint) +T: git git://anongit.freedesktop.org/drm/drm S: Maintained F: drivers/char/agp/ F: include/linux/agp* @@ -2539,7 +2539,7 @@ S: Supported F: drivers/scsi/esas2r ATUSB IEEE 802.15.4 RADIO DRIVER -M: Stefan Schmidt <stefan@osg.samsung.com> +M: Stefan Schmidt <stefan@datenfreihafen.org> L: linux-wpan@vger.kernel.org S: Maintained F: drivers/net/ieee802154/atusb.c @@ -4476,6 +4476,7 @@ F: Documentation/blockdev/drbd/ DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> +R: "Rafael J. Wysocki" <rafael@kernel.org> T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git S: Supported F: Documentation/kobject.txt @@ -4646,7 +4647,7 @@ F: include/uapi/drm/vmwgfx_drm.h DRM DRIVERS M: David Airlie <airlied@linux.ie> L: dri-devel@lists.freedesktop.org -T: git git://people.freedesktop.org/~airlied/linux +T: git git://anongit.freedesktop.org/drm/drm B: https://bugs.freedesktop.org/ C: irc://chat.freenode.net/dri-devel S: Maintained @@ -5806,7 +5807,6 @@ F: include/linux/fsl/ FREESCALE SOC FS_ENET DRIVER M: Pantelis Antoniou <pantelis.antoniou@gmail.com> -M: Vitaly Bordug <vbordug@ru.mvista.com> L: linuxppc-dev@lists.ozlabs.org L: netdev@vger.kernel.org S: Maintained @@ -6925,7 +6925,7 @@ F: drivers/clk/clk-versaclock5.c IEEE 802.15.4 SUBSYSTEM M: Alexander Aring <alex.aring@gmail.com> -M: Stefan Schmidt <stefan@osg.samsung.com> +M: Stefan Schmidt <stefan@datenfreihafen.org> L: linux-wpan@vger.kernel.org W: http://wpan.cakelab.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git @@ -7112,6 +7112,7 @@ F: include/uapi/linux/input.h F: include/uapi/linux/input-event-codes.h F: include/linux/input/ F: Documentation/devicetree/bindings/input/ +F: Documentation/devicetree/bindings/serio/ F: Documentation/input/ INPUT MULTITOUCH (MT) PROTOCOL @@ -8645,7 +8646,7 @@ MARVELL MWIFIEX WIRELESS DRIVER M: Amitkumar Karwar <amitkarwar@gmail.com> M: Nishant Sarmukadam <nishants@marvell.com> M: Ganapathi Bhat <gbhat@marvell.com> -M: Xinming Hu <huxm@marvell.com> +M: Xinming Hu <huxinming820@gmail.com> L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/marvell/mwifiex/ @@ -9091,7 +9092,7 @@ S: Maintained F: drivers/usb/mtu3/ MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES -M: Peter Senna Tschudin <peter.senna@collabora.com> +M: Peter Senna Tschudin <peter.senna@gmail.com> M: Martin Donnelly <martin.donnelly@ge.com> M: Martyn Welch <martyn.welch@collabora.co.uk> S: Maintained @@ -10230,11 +10231,13 @@ F: sound/soc/codecs/sgtl5000* NXP TDA998X DRM DRIVER M: Russell King <linux@armlinux.org.uk> -S: Supported +S: Maintained T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-devel T: git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-fixes F: drivers/gpu/drm/i2c/tda998x_drv.c F: include/drm/i2c/tda998x.h +F: include/dt-bindings/display/tda998x.h +K: "nxp,tda998x" NXP TFA9879 DRIVER M: Peter Rosin <peda@axentia.se> @@ -11852,7 +11855,7 @@ S: Supported F: arch/hexagon/ QUALCOMM HIDMA DRIVER -M: Sinan Kaya <okaya@codeaurora.org> +M: Sinan Kaya <okaya@kernel.org> L: linux-arm-kernel@lists.infradead.org L: linux-arm-msm@vger.kernel.org L: dmaengine@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Merciless Moray # *DOCUMENTATION* @@ -353,9 +353,9 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \ else if [ -x /bin/bash ]; then echo /bin/bash; \ else echo sh; fi ; fi) -HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS) -HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS) -HOST_LFS_LIBS := $(shell getconf LFS_LIBS) +HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null) +HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null) +HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null) HOSTCC = gcc HOSTCXX = g++ @@ -507,11 +507,6 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLA KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO endif -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y) - CC_CAN_LINK := y - export CC_CAN_LINK -endif - # The expansion should be delayed until arch/$(SRCARCH)/Makefile is included. # Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile. # CC_VERSION_TEXT is referenced from Kconfig (so it needs export), @@ -1717,6 +1712,6 @@ endif # skip-makefile PHONY += FORCE FORCE: -# Declare the contents of the .PHONY variable as phony. We keep that +# Declare the contents of the PHONY variable as phony. We keep that # information in a variable so we can use it in if_changed and friends. .PHONY: $(PHONY) diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 6e921754c8fc..c210a25dd6da 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, struct rusage32 __user *, ur) { - unsigned int status = 0; struct rusage r; - long err = kernel_wait4(pid, &status, options, &r); + long err = kernel_wait4(pid, ustatus, options, &r); if (err <= 0) return err; - if (put_user(status, ustatus)) - return -EFAULT; if (!ur) return err; if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime)) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index e81bcd271be7..9cf59fc60eab 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -413,7 +413,7 @@ config ARC_HAS_DIV_REM config ARC_HAS_ACCL_REGS bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)" - default n + default y help Depending on the configuration, CPU can contain accumulator reg-pair (also referred to as r58:r59). These can also be used by gcc as GPR so diff --git a/arch/arc/Makefile b/arch/arc/Makefile index d37f49d6a27f..6c1b20dd76ad 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -16,7 +16,7 @@ endif KBUILD_DEFCONFIG := nsim_700_defconfig -cflags-y += -fno-common -pipe -fno-builtin -D__linux__ +cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 cflags-$(CONFIG_ISA_ARCV2) += -mcpu=archs @@ -140,16 +140,3 @@ dtbs: scripts archclean: $(Q)$(MAKE) $(clean)=$(boot) - -# Hacks to enable final link due to absence of link-time branch relexation -# and gcc choosing optimal(shorter) branches at -O3 -# -# vineetg Feb 2010: -mlong-calls switched off for overall kernel build -# However lib/decompress_inflate.o (.init.text) calls -# zlib_inflate_workspacesize (.text) causing relocation errors. -# Thus forcing all exten calls in this file to be long calls -export CFLAGS_decompress_inflate.o = -mmedium-calls -export CFLAGS_initramfs.o = -mmedium-calls -ifdef CONFIG_SMP -export CFLAGS_core.o = -mmedium-calls -endif diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 09f85154c5a4..a635ea972304 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 09fed3ef22b6..aa507e423075 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index ea2f6d817d1a..eba07f468654 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index ab231c040efe..098b19fbaa51 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index cf449cbf440d..0104c404d897 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 1b54c72f4296..6491be0ddbc9 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 31c2c70b34a1..99e05cf63fca 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index a578c721d50f..0dc4f9b737e7 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 37d7395f3272..be3c30a15e54 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 1e1470e2a7f0..3a74b9b21772 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 084a6e42685b..ea2834b4dc1d 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y CONFIG_PERF_EVENTS=y diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index f36d47990415..80a5a1b4924b 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -9,7 +9,6 @@ CONFIG_IKCONFIG_PROC=y # CONFIG_UTS_NS is not set # CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/" CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_KPROBES=y diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 1aca2e8fd1ba..2cc87f909747 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -56,7 +56,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index ec36d5b6d435..29f3988c9424 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -234,6 +234,9 @@ POP gp RESTORE_R12_TO_R0 +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif ld sp, [sp] /* restore original sp */ /* orig_r0, ECR, user_r25 skipped automatically */ .endm @@ -315,6 +318,9 @@ POP gp RESTORE_R12_TO_R0 +#ifdef CONFIG_ARC_CURR_IN_REG + ld r25, [sp, 12] +#endif ld sp, [sp] /* restore original sp */ /* orig_r0, ECR, user_r25 skipped automatically */ .endm diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index 51597f344a62..302b0db8ea2b 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -86,9 +86,6 @@ POP r1 POP r0 -#ifdef CONFIG_ARC_CURR_IN_REG - ld r25, [sp, 12] -#endif .endm /*-------------------------------------------------------------- diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h index c28e6c347b49..871f3cb16af9 100644 --- a/arch/arc/include/asm/mach_desc.h +++ b/arch/arc/include/asm/mach_desc.h @@ -34,9 +34,7 @@ struct machine_desc { const char *name; const char **dt_compat; void (*init_early)(void); -#ifdef CONFIG_SMP void (*init_per_cpu)(unsigned int); -#endif void (*init_machine)(void); void (*init_late)(void); diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 109baa06831c..09ddddf71cc5 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -105,7 +105,7 @@ typedef pte_t * pgtable_t; #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* Default Permissions for stack/heaps pages (Non Executable) */ -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE) +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define WANT_PAGE_VIRTUAL 1 diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 8ec5599a0957..cf4be70d5892 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -377,7 +377,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, /* Decode a PTE containing swap "identifier "into constituents */ #define __swp_type(pte_lookalike) (((pte_lookalike).val) & 0x1f) -#define __swp_offset(pte_lookalike) ((pte_lookalike).val << 13) +#define __swp_offset(pte_lookalike) ((pte_lookalike).val >> 13) /* NOPs, to keep generic kernel happy */ #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 538b36afe89e..62b185057c04 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -31,10 +31,10 @@ void __init init_IRQ(void) /* a SMP H/w block could do IPI IRQ request here */ if (plat_smp_ops.init_per_cpu) plat_smp_ops.init_per_cpu(smp_processor_id()); +#endif if (machine_desc->init_per_cpu) machine_desc->init_per_cpu(smp_processor_id()); -#endif } /* diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 5ac3b547453f..4674541eba3f 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -47,7 +47,8 @@ SYSCALL_DEFINE0(arc_gettls) SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) { struct pt_regs *regs = current_pt_regs(); - int uval = -EFAULT; + u32 uval; + int ret; /* * This is only for old cores lacking LLOCK/SCOND, which by defintion @@ -60,23 +61,47 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) /* Z indicates to userspace if operation succeded */ regs->status32 &= ~STATUS_Z_MASK; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) - return -EFAULT; + ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)); + if (!ret) + goto fail; +again: preempt_disable(); - if (__get_user(uval, uaddr)) - goto done; + ret = __get_user(uval, uaddr); + if (ret) + goto fault; - if (uval == expected) { - if (!__put_user(new, uaddr)) - regs->status32 |= STATUS_Z_MASK; - } + if (uval != expected) + goto out; -done: - preempt_enable(); + ret = __put_user(new, uaddr); + if (ret) + goto fault; + + regs->status32 |= STATUS_Z_MASK; +out: + preempt_enable(); return uval; + +fault: + preempt_enable(); + + if (unlikely(ret != -EFAULT)) + goto fail; + + down_read(¤t->mm->mmap_sem); + ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr, + FAULT_FLAG_WRITE, NULL); + up_read(¤t->mm->mmap_sem); + + if (likely(!ret)) + goto again; + +fail: + force_sig(SIGSEGV, current); + return ret; } #ifdef CONFIG_ISA_ARCV2 diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 19ab3cf98f0f..9356753c2ed8 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -7,5 +7,8 @@ menuconfig ARC_SOC_HSDK bool "ARC HS Development Kit SOC" + depends on ISA_ARCV2 + select ARC_HAS_ACCL_REGS select CLK_HSDK select RESET_HSDK + select MIGHT_HAVE_PCI diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 2958aedb649a..2588b842407c 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -42,6 +42,66 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108) #define SDIO_UHS_REG_EXT_DIV_2 (2 << 30) +#define HSDK_GPIO_INTC (ARC_PERIPHERAL_BASE + 0x3000) + +static void __init hsdk_enable_gpio_intc_wire(void) +{ + /* + * Peripherals on CPU Card are wired to cpu intc via intermediate + * DW APB GPIO blocks (mainly for debouncing) + * + * --------------------- + * | snps,archs-intc | + * --------------------- + * | + * ---------------------- + * | snps,archs-idu-intc | + * ---------------------- + * | | | | | + * | [eth] [USB] [... other peripherals] + * | + * ------------------- + * | snps,dw-apb-intc | + * ------------------- + * | | | | + * [Bt] [HAPS] [... other peripherals] + * + * Current implementation of "irq-dw-apb-ictl" driver doesn't work well + * with stacked INTCs. In particular problem happens if its master INTC + * not yet instantiated. See discussion here - + * https://lkml.org/lkml/2015/3/4/755 + * + * So setup the first gpio block as a passive pass thru and hide it from + * DT hardware topology - connect intc directly to cpu intc + * The GPIO "wire" needs to be init nevertheless (here) + * + * One side adv is that peripheral interrupt handling avoids one nested + * intc ISR hop + * + * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping" + * we have the following GPIO input lines used as sources of interrupt: + * - GPIO[0] - Bluetooth interrupt of RS9113 module + * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector) + * - GPIO[3] - Audio codec (MAX9880A) interrupt + * - GPIO[8-23] - Available on Arduino and PMOD_x headers + * For now there's no use of Arduino and PMOD_x headers in Linux + * use-case so we only enable lines 0, 2 and 3. + * + * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf + */ +#define GPIO_INTEN (HSDK_GPIO_INTC + 0x30) +#define GPIO_INTMASK (HSDK_GPIO_INTC + 0x34) +#define GPIO_INTTYPE_LEVEL (HSDK_GPIO_INTC + 0x38) +#define GPIO_INT_POLARITY (HSDK_GPIO_INTC + 0x3c) +#define GPIO_INT_CONNECTED_MASK 0x0d + + iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK); + iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK); + iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL); + iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY); + iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN); +} + static void __init hsdk_init_early(void) { /* @@ -62,6 +122,8 @@ static void __init hsdk_init_early(void) * minimum possible div-by-2. */ iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT); + + hsdk_enable_gpio_intc_wire(); } static const char *hsdk_compat[] __initconst = { diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index f9e8667f5886..73b514dddf65 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -168,7 +168,6 @@ AM33XX_IOPAD(0x8f0, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_dat3.mmc0_dat3 */ AM33XX_IOPAD(0x904, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_cmd.mmc0_cmd */ AM33XX_IOPAD(0x900, PIN_INPUT_PULLUP | MUX_MODE0) /* mmc0_clk.mmc0_clk */ - AM33XX_IOPAD(0x9a0, PIN_INPUT | MUX_MODE4) /* mcasp0_aclkr.mmc0_sdwp */ >; }; diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi index ca294914bbb1..23ea381d363f 100644 --- a/arch/arm/boot/dts/am3517.dtsi +++ b/arch/arm/boot/dts/am3517.dtsi @@ -39,6 +39,8 @@ ti,davinci-ctrl-ram-size = <0x2000>; ti,davinci-rmii-en = /bits/ 8 <1>; local-mac-address = [ 00 00 00 00 00 00 ]; + clocks = <&emac_ick>; + clock-names = "ick"; }; davinci_mdio: ethernet@5c030000 { @@ -49,6 +51,8 @@ bus_freq = <1000000>; #address-cells = <1>; #size-cells = <0>; + clocks = <&emac_fck>; + clock-names = "fck"; }; uart4: serial@4809e000 { @@ -87,6 +91,11 @@ }; }; +/* Table Table 5-79 of the TRM shows 480ab000 is reserved */ +&usb_otg_hs { + status = "disabled"; +}; + &iva { status = "disabled"; }; diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 440351ad0b80..d4be3fd0b6f4 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -610,6 +610,8 @@ touchscreen-size-x = <480>; touchscreen-size-y = <272>; + + wakeup-source; }; tlv320aic3106: tlv320aic3106@1b { diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 18edc9bc7927..929459c42760 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -547,7 +547,7 @@ thermal: thermal@e8078 { compatible = "marvell,armada380-thermal"; - reg = <0xe4078 0x4>, <0xe4074 0x4>; + reg = <0xe4078 0x4>, <0xe4070 0x8>; status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 9dcd14edc202..e03495a799ce 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1580,7 +1580,6 @@ dr_mode = "otg"; snps,dis_u3_susphy_quirk; snps,dis_u2_susphy_quirk; - snps,dis_metastability_quirk; }; }; @@ -1608,6 +1607,7 @@ dr_mode = "otg"; snps,dis_u3_susphy_quirk; snps,dis_u2_susphy_quirk; + snps,dis_metastability_quirk; }; }; diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts index df9eca94d812..8a878687197b 100644 --- a/arch/arm/boot/dts/imx51-zii-rdu1.dts +++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts @@ -770,7 +770,7 @@ pinctrl_ts: tsgrp { fsl,pins = < - MX51_PAD_CSI1_D8__GPIO3_12 0x85 + MX51_PAD_CSI1_D8__GPIO3_12 0x04 MX51_PAD_CSI1_D9__GPIO3_13 0x85 >; }; diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi index 19a075aee19e..f14df0baf2ab 100644 --- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi @@ -692,7 +692,7 @@ dsa,member = <0 0>; eeprom-length = <512>; interrupt-parent = <&gpio6>; - interrupts = <3 IRQ_TYPE_EDGE_FALLING>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index bdf73cbcec3a..e7c3c563ff8f 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -159,13 +159,7 @@ dais = <&mcbsp2_port>, <&mcbsp3_port>; }; -}; - -&dss { - status = "okay"; -}; -&gpio6 { pwm8: dmtimer-pwm-8 { pinctrl-names = "default"; pinctrl-0 = <&vibrator_direction_pin>; @@ -192,7 +186,10 @@ pwm-names = "enable", "direction"; direction-duty-cycle-ns = <10000000>; }; +}; +&dss { + status = "okay"; }; &dsi1 { diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 054591dc9a00..4cd2f4a2bff4 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -141,9 +141,11 @@ CONFIG_USB_STORAGE=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_UDC=y CONFIG_USB_CHIPIDEA_HOST=y +CONFIG_USB_CHIPIDEA_ULPI=y CONFIG_NOP_USB_XCEIV=y CONFIG_USB_GADGET=y CONFIG_USB_ETH=m +CONFIG_USB_ULPI_BUS=y CONFIG_MMC=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index f70507ab91ee..200ebda47e0c 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -302,6 +302,7 @@ CONFIG_USB_STORAGE=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_UDC=y CONFIG_USB_CHIPIDEA_HOST=y +CONFIG_USB_CHIPIDEA_ULPI=y CONFIG_USB_SERIAL=m CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_FTDI_SIO=m @@ -338,6 +339,7 @@ CONFIG_USB_GADGETFS=m CONFIG_USB_FUNCTIONFS=m CONFIG_USB_MASS_STORAGE=m CONFIG_USB_G_SERIAL=m +CONFIG_USB_ULPI_BUS=y CONFIG_MMC=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y diff --git a/arch/arm/crypto/speck-neon-core.S b/arch/arm/crypto/speck-neon-core.S index 3c1e203e53b9..57caa742016e 100644 --- a/arch/arm/crypto/speck-neon-core.S +++ b/arch/arm/crypto/speck-neon-core.S @@ -272,9 +272,11 @@ * Allocate stack space to store 128 bytes worth of tweaks. For * performance, this space is aligned to a 16-byte boundary so that we * can use the load/store instructions that declare 16-byte alignment. + * For Thumb2 compatibility, don't do the 'bic' directly on 'sp'. */ - sub sp, #128 - bic sp, #0xf + sub r12, sp, #128 + bic r12, #0xf + mov sp, r12 .if \n == 64 // Load first tweak diff --git a/arch/arm/firmware/Makefile b/arch/arm/firmware/Makefile index a71f16536b6c..6e41336b0bc4 100644 --- a/arch/arm/firmware/Makefile +++ b/arch/arm/firmware/Makefile @@ -1 +1,4 @@ obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o + +# tf_generic_smc() fails to build with -fsanitize-coverage=trace-pc +KCOV_INSTRUMENT := n diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index dd546d65a383..7a9b86978ee1 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -177,7 +177,7 @@ M_CLASS(streq r3, [r12, #PMSAv8_MAIR1]) bic r0, r0, #CR_I #endif mcr p15, 0, r0, c1, c0, 0 @ write control reg - isb + instr_sync #elif defined (CONFIG_CPU_V7M) #ifdef CONFIG_ARM_MPU ldreq r3, [r12, MPU_CTRL] diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 225d1c58d2de..d9c299133111 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = { static int __init gate_vma_init(void) { + vma_init(&gate_vma, NULL); gate_vma.vm_page_prot = PAGE_READONLY_EXEC; return 0; } diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 69df3620eca5..1c73694c871a 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -109,6 +109,45 @@ void omap5_erratum_workaround_801819(void) static inline void omap5_erratum_workaround_801819(void) { } #endif +#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR +/* + * Configure ACR and enable ACTLR[0] (Enable invalidates of BTB with + * ICIALLU) to activate the workaround for secondary Core. + * NOTE: it is assumed that the primary core's configuration is done + * by the boot loader (kernel will detect a misconfiguration and complain + * if this is not done). + * + * In General Purpose(GP) devices, ACR bit settings can only be done + * by ROM code in "secure world" using the smc call and there is no + * option to update the "firmware" on such devices. This also works for + * High security(HS) devices, as a backup option in case the + * "update" is not done in the "security firmware". + */ +static void omap5_secondary_harden_predictor(void) +{ + u32 acr, acr_mask; + + asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr)); + + /* + * ACTLR[0] (Enable invalidates of BTB with ICIALLU) + */ + acr_mask = BIT(0); + + /* Do we already have it done.. if yes, skip expensive smc */ + if ((acr & acr_mask) == acr_mask) + return; + + acr |= acr_mask; + omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr); + + pr_debug("%s: ARM ACR setup for CVE_2017_5715 applied on CPU%d\n", + __func__, smp_processor_id()); +} +#else +static inline void omap5_secondary_harden_predictor(void) { } +#endif + static void omap4_secondary_init(unsigned int cpu) { /* @@ -131,6 +170,8 @@ static void omap4_secondary_init(unsigned int cpu) set_cntfreq(); /* Configure ACR to disable streaming WA for 801819 */ omap5_erratum_workaround_801819(); + /* Enable ACR to allow for ICUALLU workaround */ + omap5_secondary_harden_predictor(); } /* diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c index 9c10248fadcc..4e8c2116808e 100644 --- a/arch/arm/mach-pxa/irq.c +++ b/arch/arm/mach-pxa/irq.c @@ -185,7 +185,7 @@ static int pxa_irq_suspend(void) { int i; - for (i = 0; i < pxa_internal_irq_nr / 32; i++) { + for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) { void __iomem *base = irq_base(i); saved_icmr[i] = __raw_readl(base + ICMR); @@ -204,7 +204,7 @@ static void pxa_irq_resume(void) { int i; - for (i = 0; i < pxa_internal_irq_nr / 32; i++) { + for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) { void __iomem *base = irq_base(i); __raw_writel(saved_icmr[i], base + ICMR); diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 39aef4876ed4..8db62cc54a6a 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -237,8 +237,8 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); + vma_init(&vma, mm); vma.vm_flags = VM_EXEC; - vma.vm_mm = mm; flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE); flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index c186474422f3..0cc8e04295a4 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -736,20 +736,29 @@ static int __mark_rodata_ro(void *unused) return 0; } +static int kernel_set_to_readonly __read_mostly; + void mark_rodata_ro(void) { + kernel_set_to_readonly = 1; stop_machine(__mark_rodata_ro, NULL, NULL); debug_checkwx(); } void set_kernel_text_rw(void) { + if (!kernel_set_to_readonly) + return; + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false, current->active_mm); } void set_kernel_text_ro(void) { + if (!kernel_set_to_readonly) + return; + set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true, current->active_mm); } diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 6e8b71613039..f6a62ae44a65 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1844,7 +1844,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* there are 2 passes here */ bpf_jit_dump(prog->len, image_size, 2, ctx.target); - set_memory_ro((unsigned long)header, header->pages); + bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)ctx.target; prog->jited = 1; prog->jited_len = image_size; diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 45272266dafb..e7101b19d590 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=-p --no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) GZFLAGS :=-9 @@ -60,15 +60,15 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ AS += -EB -LD += -EB -LDFLAGS += -maarch64linuxb +# We must use the linux target here, since distributions don't tend to package +# the ELF linker scripts with binutils, and this results in a build failure. +LDFLAGS += -EB -maarch64linuxb UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ AS += -EL -LD += -EL -LDFLAGS += -maarch64linux +LDFLAGS += -EL -maarch64linux # See comment above UTS_MACHINE := aarch64 endif diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index fa8b3fe932e6..6495cc51246f 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -29,20 +29,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy); static __must_check inline bool may_use_simd(void) { /* - * The raw_cpu_read() is racy if called with preemption enabled. - * This is not a bug: kernel_neon_busy is only set when - * preemption is disabled, so we cannot migrate to another CPU - * while it is set, nor can we migrate to a CPU where it is set. - * So, if we find it clear on some CPU then we're guaranteed to - * find it clear on any CPU we could migrate to. - * - * If we are in between kernel_neon_begin()...kernel_neon_end(), - * the flag will be set, but preemption is also disabled, so we - * can't migrate to another CPU and spuriously see it become - * false. + * kernel_neon_busy is only set while preemption is disabled, + * and is clear whenever preemption is enabled. Since + * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy + * cannot change under our feet -- if it's set we cannot be + * migrated, and if it's clear we cannot be migrated to a CPU + * where it is set. */ return !in_irq() && !irqs_disabled() && !in_nmi() && - !raw_cpu_read(kernel_neon_busy); + !this_cpu_read(kernel_neon_busy); } #else /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..d87f2d646caa 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,9 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma; + + vma_init(&vma, tlb->mm); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..c6d80743f4ed 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..1854e49aa18a 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,11 +108,13 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; + vma_init(&vma, mm); + for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = ptep_get_and_clear(mm, addr, ptep); @@ -145,9 +147,10 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma; unsigned long i, saddr = addr; + vma_init(&vma, mm); for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) pte_clear(mm, addr, ptep); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..9abf8a1e7b25 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -611,11 +611,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..db89e7306081 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -120,7 +120,7 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned */ struct vm_area_struct vma; - vma.vm_mm = tlb->mm; + vma_init(&vma, tlb->mm); /* flush the address range from the tlb: */ flush_tlb_range(&vma, start, end); /* now flush the virt. page-table area mapping the address range: */ diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 3b38c717008a..46bff1661836 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t DPRINT(("smpl_buf @%p\n", smpl_buf)); /* allocate vma */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { DPRINT(("Cannot allocate vma\n")); goto error_kmem; } - INIT_LIST_HEAD(&vma->anon_vma_chain); /* * partially initialize the vma for the sampling buffer */ - vma->vm_mm = mm; vma->vm_file = get_file(filp); vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t return 0; error: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); error_kmem: pfm_rvfree(smpl_buf, size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 18278b448530..e6c6dfd98de2 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -114,10 +114,8 @@ ia64_init_addr_space (void) * the problem. When the process attempts to write to the register backing store * for the first time, it will get a SEGFAULT in this case. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -125,7 +123,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -133,10 +131,8 @@ ia64_init_addr_space (void) /* map NaT-page at address zero to speed up speculative dereferencing of NULL: */ if (!(current->personality & MMAP_PAGE_ZERO)) { - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (vma) { - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = current->mm; vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | @@ -144,7 +140,7 @@ ia64_init_addr_space (void) down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return; } up_write(¤t->mm->mmap_sem); @@ -277,7 +273,7 @@ static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index 8b707c249026..12fe700632f4 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -44,6 +44,7 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, unsigned long address) { + pgtable_page_dtor(page); __free_page(page); } @@ -74,8 +75,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, return page; } -extern inline void pte_free(struct mm_struct *mm, struct page *page) +static inline void pte_free(struct mm_struct *mm, struct page *page) { + pgtable_page_dtor(page); __free_page(page); } diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 10a405d593df..c782b10ddf50 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 8c9cbf13d32a..6054d49e608e 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; - - /* - * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" - * Enable ExternalSync for sync instruction to take effect - */ - set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 0bc270806ec5..ae461d91cd1f 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,8 +681,6 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) -/* ExternalSync */ -#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) -__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 8d85046adcc8..9670e70139fd 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -29,6 +29,7 @@ #include <linux/kallsyms.h> #include <linux/random.h> #include <linux/prctl.h> +#include <linux/nmi.h> #include <asm/asm.h> #include <asm/bootinfo.h> @@ -655,28 +656,42 @@ unsigned long arch_align_stack(unsigned long sp) return sp & ALMASK; } -static void arch_dump_stack(void *info) +static DEFINE_PER_CPU(call_single_data_t, backtrace_csd); +static struct cpumask backtrace_csd_busy; + +static void handle_backtrace(void *info) { - struct pt_regs *regs; + nmi_cpu_backtrace(get_irq_regs()); + cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy); +} - regs = get_irq_regs(); +static void raise_backtrace(cpumask_t *mask) +{ + call_single_data_t *csd; + int cpu; - if (regs) - show_regs(regs); + for_each_cpu(cpu, mask) { + /* + * If we previously sent an IPI to the target CPU & it hasn't + * cleared its bit in the busy cpumask then it didn't handle + * our previous IPI & it's not safe for us to reuse the + * call_single_data_t. + */ + if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) { + pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n", + cpu); + continue; + } - dump_stack(); + csd = &per_cpu(backtrace_csd, cpu); + csd->func = handle_backtrace; + smp_call_function_single_async(cpu, csd); + } } void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { - long this_cpu = get_cpu(); - - if (cpumask_test_cpu(this_cpu, mask) && !exclude_self) - dump_stack(); - - smp_call_function_many(mask, arch_dump_stack, NULL, 1); - - put_cpu(); + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace); } int mips_get_process_fp_mode(struct task_struct *task) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index d67fa74622ee..8d505a21396e 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -351,6 +351,7 @@ static void __show_regs(const struct pt_regs *regs) void show_regs(struct pt_regs *regs) { __show_regs((struct pt_regs *)regs); + dump_stack(); } void show_registers(struct pt_regs *regs) diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c index 1986e09fb457..1601d90b087b 100644 --- a/arch/mips/mm/ioremap.c +++ b/arch/mips/mm/ioremap.c @@ -9,6 +9,7 @@ #include <linux/export.h> #include <asm/addrspace.h> #include <asm/byteorder.h> +#include <linux/ioport.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -98,6 +99,20 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr, return error; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; i++) { + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + } + + return 0; +} + /* * Generic mapping function (not visible outside): */ @@ -116,8 +131,8 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr, void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long flags) { + unsigned long offset, pfn, last_pfn; struct vm_struct * area; - unsigned long offset; phys_addr_t last_addr; void * addr; @@ -137,18 +152,16 @@ void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long return (void __iomem *) CKSEG1ADDR(phys_addr); /* - * Don't allow anybody to remap normal RAM that we're using.. + * Don't allow anybody to remap RAM that may be allocated by the page + * allocator, since that could lead to races & data clobbering. */ - if (phys_addr < virt_to_phys(high_memory)) { - char *t_addr, *t_end; - struct page *page; - - t_addr = __va(phys_addr); - t_end = t_addr + (size - 1); - - for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++) - if(!PageReserved(page)) - return NULL; + pfn = PFN_DOWN(phys_addr); + last_pfn = PFN_DOWN(last_addr); + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) { + WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", + &phys_addr, &last_addr); + return NULL; } /* diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 9632436d74d7..c2e94cf5ecda 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 6aed974276d8..34f7222c5efe 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -12,17 +12,17 @@ config NDS32 select CLONE_BACKWARDS select COMMON_CLK select DMA_NONCOHERENT_OPS - select GENERIC_ASHLDI3 - select GENERIC_ASHRDI3 - select GENERIC_LSHRDI3 - select GENERIC_CMPDI2 - select GENERIC_MULDI3 - select GENERIC_UCMPDI2 select GENERIC_ATOMIC64 select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW + select GENERIC_LIB_ASHLDI3 + select GENERIC_LIB_ASHRDI3 + select GENERIC_LIB_CMPDI2 + select GENERIC_LIB_LSHRDI3 + select GENERIC_LIB_MULDI3 + select GENERIC_LIB_UCMPDI2 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 513bb2e9baf9..031c676821ff 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -34,10 +34,12 @@ ifdef CONFIG_CPU_LITTLE_ENDIAN KBUILD_CFLAGS += $(call cc-option, -EL) KBUILD_AFLAGS += $(call cc-option, -EL) LDFLAGS += $(call cc-option, -EL) +CHECKFLAGS += -D__NDS32_EL__ else KBUILD_CFLAGS += $(call cc-option, -EB) KBUILD_AFLAGS += $(call cc-option, -EB) LDFLAGS += $(call cc-option, -EB) +CHECKFLAGS += -D__NDS32_EB__ endif boot := arch/nds32/boot diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 10b48f0d8e85..8b26198d51bb 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -8,6 +8,8 @@ #define PG_dcache_dirty PG_arch_1 +void flush_icache_range(unsigned long start, unsigned long end); +void flush_icache_page(struct vm_area_struct *vma, struct page *page); #ifdef CONFIG_CPU_CACHE_ALIASING void flush_cache_mm(struct mm_struct *mm); void flush_cache_dup_mm(struct mm_struct *mm); @@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma, void flush_kernel_dcache_page(struct page *page); void flush_kernel_vmap_range(void *addr, int size); void invalidate_kernel_vmap_range(void *addr, int size); -void flush_icache_range(unsigned long start, unsigned long end); -void flush_icache_page(struct vm_area_struct *vma, struct page *page); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages) #else #include <asm-generic/cacheflush.h> +#undef flush_icache_range +#undef flush_icache_page +#undef flush_icache_user_range +void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len); #endif #endif /* __NDS32_CACHEFLUSH_H__ */ diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h index eab5e84bd991..cb6cb91cfdf8 100644 --- a/arch/nds32/include/asm/futex.h +++ b/arch/nds32/include/asm/futex.h @@ -16,7 +16,7 @@ " .popsection\n" \ " .pushsection .fixup,\"ax\"\n" \ "4: move %0, " err_reg "\n" \ - " j 3b\n" \ + " b 3b\n" \ " .popsection" #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c index 2f5b2ccebe47..63a1a5ef5219 100644 --- a/arch/nds32/kernel/setup.c +++ b/arch/nds32/kernel/setup.c @@ -278,7 +278,8 @@ static void __init setup_memory(void) void __init setup_arch(char **cmdline_p) { - early_init_devtree( __dtb_start); + early_init_devtree(__atags_pointer ? \ + phys_to_virt(__atags_pointer) : __dtb_start); setup_cpuinfo(); diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index ce8fd34497bf..254703653b6f 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -13,7 +13,39 @@ extern struct cache_info L1_cache_info[2]; -#ifndef CONFIG_CPU_CACHE_ALIASING +void flush_icache_range(unsigned long start, unsigned long end) +{ + unsigned long line_size, flags; + line_size = L1_cache_info[DCACHE].line_size; + start = start & ~(line_size - 1); + end = (end + line_size - 1) & ~(line_size - 1); + local_irq_save(flags); + cpu_cache_wbinval_range(start, end, 1); + local_irq_restore(flags); +} +EXPORT_SYMBOL(flush_icache_range); + +void flush_icache_page(struct vm_area_struct *vma, struct page *page) +{ + unsigned long flags; + unsigned long kaddr; + local_irq_save(flags); + kaddr = (unsigned long)kmap_atomic(page); + cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); + kunmap_atomic((void *)kaddr); + local_irq_restore(flags); +} +EXPORT_SYMBOL(flush_icache_page); + +void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, + unsigned long addr, int len) +{ + unsigned long kaddr; + kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK); + flush_icache_range(kaddr, kaddr + len); + kunmap_atomic((void *)kaddr); +} + void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t * pte) { @@ -35,19 +67,15 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) || (vma->vm_flags & VM_EXEC)) { - - if (!PageHighMem(page)) { - cpu_cache_wbinval_page((unsigned long) - page_address(page), - vma->vm_flags & VM_EXEC); - } else { - unsigned long kaddr = (unsigned long)kmap_atomic(page); - cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); - kunmap_atomic((void *)kaddr); - } + unsigned long kaddr; + local_irq_save(flags); + kaddr = (unsigned long)kmap_atomic(page); + cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC); + kunmap_atomic((void *)kaddr); + local_irq_restore(flags); } } -#else +#ifdef CONFIG_CPU_CACHE_ALIASING extern pte_t va_present(struct mm_struct *mm, unsigned long addr); static inline unsigned long aliasing(unsigned long addr, unsigned long page) @@ -317,52 +345,4 @@ void invalidate_kernel_vmap_range(void *addr, int size) local_irq_restore(flags); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); - -void flush_icache_range(unsigned long start, unsigned long end) -{ - unsigned long line_size, flags; - line_size = L1_cache_info[DCACHE].line_size; - start = start & ~(line_size - 1); - end = (end + line_size - 1) & ~(line_size - 1); - local_irq_save(flags); - cpu_cache_wbinval_range(start, end, 1); - local_irq_restore(flags); -} -EXPORT_SYMBOL(flush_icache_range); - -void flush_icache_page(struct vm_area_struct *vma, struct page *page) -{ - unsigned long flags; - local_irq_save(flags); - cpu_cache_wbinval_page((unsigned long)page_address(page), - vma->vm_flags & VM_EXEC); - local_irq_restore(flags); -} - -void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, - pte_t * pte) -{ - struct page *page; - unsigned long flags; - unsigned long pfn = pte_pfn(*pte); - - if (!pfn_valid(pfn)) - return; - - if (vma->vm_mm == current->active_mm) { - local_irq_save(flags); - __nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN); - __nds32__tlbop_rwr(*pte); - __nds32__isb(); - local_irq_restore(flags); - } - - page = pfn_to_page(pfn); - if (test_and_clear_bit(PG_dcache_dirty, &page->flags) || - (vma->vm_flags & VM_EXEC)) { - local_irq_save(flags); - cpu_dcache_wbinval_page((unsigned long)page_address(page)); - local_irq_restore(flags); - } -} #endif diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 3e1a46615120..8999b9226512 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -98,8 +98,12 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte) __free_page(pte); } +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pgtable_page_dtor(pte); \ + tlb_remove_page((tlb), (pte)); \ +} while (0) -#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte)) #define pmd_pgtable(pmd) pmd_page(pmd) #define check_pgt_cache() do { } while (0) diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index 690d55272ba6..0c826ad6e994 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -277,12 +277,6 @@ EXCEPTION_ENTRY(_data_page_fault_handler) l.addi r3,r1,0 // pt_regs /* r4 set be EXCEPTION_HANDLE */ // effective address of fault - /* - * __PHX__: TODO - * - * all this can be written much simpler. look at - * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part - */ #ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX l.lwz r6,PT_PC(r3) // address of an offending insn l.lwz r6,0(r6) // instruction that caused pf @@ -314,7 +308,7 @@ EXCEPTION_ENTRY(_data_page_fault_handler) #else - l.lwz r6,PT_SR(r3) // SR + l.mfspr r6,r0,SPR_SR // SR l.andi r6,r6,SPR_SR_DSX // check for delay slot exception l.sfne r6,r0 // exception happened in delay slot l.bnf 7f diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index fb02b2a1d6f2..9fc6b60140f0 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -210,8 +210,7 @@ * r4 - EEAR exception EA * r10 - current pointing to current_thread_info struct * r12 - syscall 0, since we didn't come from syscall - * r13 - temp it actually contains new SR, not needed anymore - * r31 - handler address of the handler we'll jump to + * r30 - handler address of the handler we'll jump to * * handler has to save remaining registers to the exception * ksp frame *before* tainting them! @@ -244,6 +243,7 @@ /* r1 is KSP, r30 is __pa(KSP) */ ;\ tophys (r30,r1) ;\ l.sw PT_GPR12(r30),r12 ;\ + /* r4 use for tmp before EA */ ;\ l.mfspr r12,r0,SPR_EPCR_BASE ;\ l.sw PT_PC(r30),r12 ;\ l.mfspr r12,r0,SPR_ESR_BASE ;\ @@ -263,7 +263,10 @@ /* r12 == 1 if we come from syscall */ ;\ CLEAR_GPR(r12) ;\ /* ----- turn on MMU ----- */ ;\ - l.ori r30,r0,(EXCEPTION_SR) ;\ + /* Carry DSX into exception SR */ ;\ + l.mfspr r30,r0,SPR_SR ;\ + l.andi r30,r30,SPR_SR_DSX ;\ + l.ori r30,r30,(EXCEPTION_SR) ;\ l.mtspr r0,r30,SPR_ESR_BASE ;\ /* r30: EA address of handler */ ;\ LOAD_SYMBOL_2_GPR(r30,handler) ;\ diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index fac246e6f37a..d8981cbb852a 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -300,7 +300,7 @@ static inline int in_delay_slot(struct pt_regs *regs) return 0; } #else - return regs->sr & SPR_SR_DSX; + return mfspr(SPR_SR) & SPR_SR_DSX; #endif } diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 2ea575cb3401..fb96206de317 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -243,6 +243,7 @@ endif cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 +cpu-as-$(CONFIG_E500) += -Wa,-me500 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 896efa559996..79d570cbf332 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa); + unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index e734f6e45abc..689306118b48 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -144,7 +144,9 @@ power9_restore_additional_sprs: mtspr SPRN_MMCR1, r4 ld r3, STOP_MMCR2(r13) + ld r4, PACA_SPRG_VDSO(r13) mtspr SPRN_MMCR2, r3 + mtspr SPRN_SPRG3, r4 blr /* diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d066e37551ec..8c456fa691a5 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, /* This only handles v2 IOMMU type, v1 is handled via ioctl() */ return H_TOO_HARD; - if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa))) + if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa))) return H_HARDWARE; if (mm_iommu_mapped_inc(mem)) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 925fc316a104..5b298f5a1a14 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (!mem) return H_TOO_HARD; - if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))) + if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift, + &hpa))) return H_HARDWARE; pua = (void *) vmalloc_to_phys(pua); @@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K); if (mem) - prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0; + prereg = mm_iommu_ua_to_hpa_rm(mem, ua, + IOMMU_PAGE_SHIFT_4K, &tces) == 0; } if (!prereg) { diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index abb43646927a..a4ca57612558 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -19,6 +19,7 @@ #include <linux/hugetlb.h> #include <linux/swap.h> #include <asm/mmu_context.h> +#include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); @@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t { struct rcu_head rcu; unsigned long used; atomic64_t mapped; + unsigned int pageshift; u64 ua; /* userspace address */ u64 entries; /* number of entries in hpas[] */ u64 *hpas; /* vmalloc'ed */ @@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, { struct mm_iommu_table_group_mem_t *mem; long i, j, ret = 0, locked_entries = 0; + unsigned int pageshift; + unsigned long flags; struct page *page = NULL; mutex_lock(&mem_list_mutex); @@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, goto unlock_exit; } + /* + * For a starting point for a maximum page size calculation + * we use @ua and @entries natural alignment to allow IOMMU pages + * smaller than huge pages but still bigger than PAGE_SIZE. + */ + mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT)); mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0]))); if (!mem->hpas) { kfree(mem); @@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries, } } populate: + pageshift = PAGE_SHIFT; + if (PageCompound(page)) { + pte_t *pte; + struct page *head = compound_head(page); + unsigned int compshift = compound_order(head); + + local_irq_save(flags); /* disables as well */ + pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift); + local_irq_restore(flags); + + /* Double check it is still the same pinned page */ + if (pte && pte_page(*pte) == head && + pageshift == compshift) + pageshift = max_t(unsigned int, pageshift, + PAGE_SHIFT); + } + mem->pageshift = min(mem->pageshift, pageshift); mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; } @@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, EXPORT_SYMBOL_GPL(mm_iommu_find); long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; u64 *va = &mem->hpas[entry]; @@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + *hpa = *va | (ua & ~PAGE_MASK); return 0; @@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa); long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, - unsigned long ua, unsigned long *hpa) + unsigned long ua, unsigned int pageshift, unsigned long *hpa) { const long entry = (ua - mem->ua) >> PAGE_SHIFT; void *va = &mem->hpas[entry]; @@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (entry >= mem->entries) return -EFAULT; + if (pageshift > mem->pageshift) + return -EFAULT; + pa = (void *) vmalloc_to_phys(va); if (!pa) return -EFAULT; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 380cbf9a40d9..c0a9bcd28356 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; + u32 tmp_idx; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -637,11 +638,7 @@ emit_clear: case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not word-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); + tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); /* add value from src_reg into this */ @@ -649,32 +646,16 @@ emit_clear: /* store result back */ PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); - /* otherwise, let's try once more */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - /* exit if the store was not successful */ - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not doubleword-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4)); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); + tmp_idx = ctx->idx * 4; PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 47166ad2a669..196978733e64 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, { int nr, dotted; unsigned long first_adr; - unsigned long inst, last_inst = 0; + unsigned int inst, last_inst = 0; unsigned char val[4]; dotted = 0; @@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8lx", adr, inst); + printf(REG" %.8x", adr, inst); printf("\t"); dump_func(inst, adr); printf("\n"); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f12680c9b947..4764fdeb4f1f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -107,6 +107,7 @@ config ARCH_RV32I select GENERIC_LIB_ASHLDI3 select GENERIC_LIB_ASHRDI3 select GENERIC_LIB_LSHRDI3 + select GENERIC_LIB_UCMPDI2 config ARCH_RV64I bool "RV64I" diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h index 5cae4c30cd8e..1e0dfc36aab9 100644 --- a/arch/riscv/include/uapi/asm/elf.h +++ b/arch/riscv/include/uapi/asm/elf.h @@ -21,8 +21,13 @@ typedef struct user_regs_struct elf_gregset_t; typedef union __riscv_fp_state elf_fpregset_t; -#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32) -#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff) +#if __riscv_xlen == 64 +#define ELF_RISCV_R_SYM(r_info) ELF64_R_SYM(r_info) +#define ELF_RISCV_R_TYPE(r_info) ELF64_R_TYPE(r_info) +#else +#define ELF_RISCV_R_SYM(r_info) ELF32_R_SYM(r_info) +#define ELF_RISCV_R_TYPE(r_info) ELF32_R_TYPE(r_info) +#endif /* * RISC-V relocation types diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index b74cbfbce2d0..7bcdaed15703 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -16,10 +16,6 @@ #include <linux/irqchip.h> #include <linux/irqdomain.h> -#ifdef CONFIG_RISCV_INTC -#include <linux/irqchip/irq-riscv-intc.h> -#endif - void __init init_IRQ(void) { irqchip_init(); diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1d5e9b934b8c..3303ed2cd419 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -37,7 +37,7 @@ static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v) static int apply_r_riscv_branch_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; u32 imm12 = (offset & 0x1000) << (31 - 12); u32 imm11 = (offset & 0x800) >> (11 - 7); u32 imm10_5 = (offset & 0x7e0) << (30 - 10); @@ -50,7 +50,7 @@ static int apply_r_riscv_branch_rela(struct module *me, u32 *location, static int apply_r_riscv_jal_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; u32 imm20 = (offset & 0x100000) << (31 - 20); u32 imm19_12 = (offset & 0xff000); u32 imm11 = (offset & 0x800) << (20 - 11); @@ -63,7 +63,7 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location, static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; u16 imm8 = (offset & 0x100) << (12 - 8); u16 imm7_6 = (offset & 0xc0) >> (6 - 5); u16 imm5 = (offset & 0x20) >> (5 - 2); @@ -78,7 +78,7 @@ static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location, static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; u16 imm11 = (offset & 0x800) << (12 - 11); u16 imm10 = (offset & 0x400) >> (10 - 8); u16 imm9_8 = (offset & 0x300) << (12 - 11); @@ -96,7 +96,7 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location, static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; s32 hi20; if (offset != (s32)offset) { @@ -178,7 +178,7 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location, static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; s32 hi20; /* Always emit the got entry */ @@ -200,7 +200,7 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location, static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; s32 fill_v = offset; u32 hi20, lo12; @@ -227,7 +227,7 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, static int apply_r_riscv_call_rela(struct module *me, u32 *location, Elf_Addr v) { - s64 offset = (void *)v - (void *)location; + ptrdiff_t offset = (void *)v - (void *)location; s32 fill_v = offset; u32 hi20, lo12; @@ -263,14 +263,14 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location, static int apply_r_riscv_add32_rela(struct module *me, u32 *location, Elf_Addr v) { - *(u32 *)location += (*(u32 *)v); + *(u32 *)location += (u32)v; return 0; } static int apply_r_riscv_sub32_rela(struct module *me, u32 *location, Elf_Addr v) { - *(u32 *)location -= (*(u32 *)v); + *(u32 *)location -= (u32)v; return 0; } @@ -347,7 +347,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, unsigned int j; for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) { - u64 hi20_loc = + unsigned long hi20_loc = sechdrs[sechdrs[relsec].sh_info].sh_addr + rel[j].r_offset; u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info); @@ -360,12 +360,12 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, Elf_Sym *hi20_sym = (Elf_Sym *)sechdrs[symindex].sh_addr + ELF_RISCV_R_SYM(rel[j].r_info); - u64 hi20_sym_val = + unsigned long hi20_sym_val = hi20_sym->st_value + rel[j].r_addend; /* Calculate lo12 */ - u64 offset = hi20_sym_val - hi20_loc; + size_t offset = hi20_sym_val - hi20_loc; if (IS_ENABLED(CONFIG_MODULE_SECTIONS) && hi20_type == R_RISCV_GOT_HI20) { offset = module_emit_got_entry( diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index ba3e80712797..9f82a7e34c64 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -50,7 +50,7 @@ static int riscv_gpr_set(struct task_struct *target, struct pt_regs *regs; regs = task_pt_regs(target); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, ®s, 0, -1); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1); return ret; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index ee44a48faf79..f0d2070866d4 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -220,8 +220,3 @@ void __init setup_arch(char **cmdline_p) riscv_fill_hwcap(); } -static int __init riscv_device_init(void) -{ - return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); -} -subsys_initcall_sync(riscv_device_init); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c77df8142be2..58a522f9bcc3 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -28,7 +28,9 @@ static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; +#ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn)); +#endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; free_area_init_nodes(max_zone_pfns); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index baed39772c84..8a1863d9ed53 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -140,7 +140,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_GCC_PLUGINS + select HAVE_GCC_PLUGINS if BROKEN select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -160,6 +160,7 @@ config S390 select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select MODULES_USE_ELF_RELA diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index 607c5e9fba3d..2ce28bf0c5ec 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -183,3 +183,4 @@ COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb); COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer); COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags); COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) +COMPAT_SYSCALL_WRAP4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index f03402efab4b..150130c897c3 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -357,6 +357,10 @@ ENTRY(system_call) stg %r2,__PT_R2(%r11) # store return value .Lsysc_return: +#ifdef CONFIG_DEBUG_RSEQ + lgr %r2,%r11 + brasl %r14,rseq_syscall +#endif LOCKDEP_SYS_EXIT .Lsysc_tif: TSTMSK __PT_FLAGS(%r11),_PIF_WORK @@ -1265,7 +1269,7 @@ cleanup_critical: jl 0f clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end jl .Lcleanup_load_fpu_regs -0: BR_EX %r14 +0: BR_EX %r14,%r11 .align 8 .Lcleanup_table: @@ -1301,7 +1305,7 @@ cleanup_critical: ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit - BR_EX %r14 + BR_EX %r14,%r11 #endif .Lcleanup_system_call: diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 2d2960ab3e10..22f08245aa5d 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -498,7 +498,7 @@ void do_signal(struct pt_regs *regs) } /* No longer in a system call */ clear_pt_regs_flag(regs, PIF_SYSCALL); - + rseq_signal_deliver(&ksig, regs); if (is_compat_task()) handle_signal32(&ksig, oldset, regs); else @@ -537,4 +537,5 @@ void do_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 8b210ead7956..022fc099b628 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -389,3 +389,5 @@ 379 common statx sys_statx compat_sys_statx 380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi 381 common kexec_file_load sys_kexec_file_load compat_sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +383 common rseq sys_rseq compat_sys_rseq diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 84bd6329a88d..e3bd5627afef 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -252,6 +252,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) spin_unlock_bh(&mm->context.lock); if (mask != 0) return; + } else { + atomic_xor_bits(&page->_refcount, 3U << 24); } pgtable_page_dtor(page); @@ -304,6 +306,8 @@ static void __tlb_remove_table(void *_table) break; /* fallthrough */ case 3: /* 4K page table with pgstes */ + if (mask & 3) + atomic_xor_bits(&page->_refcount, 3 << 24); pgtable_page_dtor(page); __free_page(page); break; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index d2db8acb1a55..5f0234ec8038 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1286,6 +1286,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) goto free_addrs; } if (bpf_jit_prog(&jit, fp)) { + bpf_jit_binary_free(header); fp = orig_fp; goto free_addrs; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f1dbb4ee19d7..887d3a7bb646 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -63,7 +63,7 @@ config X86 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 - select ARCH_HAS_UACCESS_MCSAFE if X86_64 + select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index e57665b4ba1c..e98522ea6f09 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -114,18 +114,12 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) struct pci_setup_rom *rom = NULL; efi_status_t status; unsigned long size; - uint64_t attributes, romsize; + uint64_t romsize; void *romimage; - status = efi_call_proto(efi_pci_io_protocol, attributes, pci, - EfiPciIoAttributeOperationGet, 0ULL, - &attributes); - if (status != EFI_SUCCESS) - return status; - /* - * Some firmware images contain EFI function pointers at the place where the - * romimage and romsize fields are supposed to be. Typically the EFI + * Some firmware images contain EFI function pointers at the place where + * the romimage and romsize fields are supposed to be. Typically the EFI * code is mapped at high addresses, translating to an unrealistically * large romsize. The UEFI spec limits the size of option ROMs to 16 * MiB so we reject any ROMs over 16 MiB in size to catch this. diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 9254e0b6cc06..717bf0776421 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -535,6 +535,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail) movdqu STATE3, 0x40(STATEP) FRAME_END + ret ENDPROC(crypto_aegis128_aesni_enc_tail) .macro decrypt_block a s0 s1 s2 s3 s4 i diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S index 9263c344f2c7..4eda2b8db9e1 100644 --- a/arch/x86/crypto/aegis128l-aesni-asm.S +++ b/arch/x86/crypto/aegis128l-aesni-asm.S @@ -645,6 +645,7 @@ ENTRY(crypto_aegis128l_aesni_enc_tail) state_store0 FRAME_END + ret ENDPROC(crypto_aegis128l_aesni_enc_tail) /* diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S index 1d977d515bf9..32aae8397268 100644 --- a/arch/x86/crypto/aegis256-aesni-asm.S +++ b/arch/x86/crypto/aegis256-aesni-asm.S @@ -543,6 +543,7 @@ ENTRY(crypto_aegis256_aesni_enc_tail) state_store0 FRAME_END + ret ENDPROC(crypto_aegis256_aesni_enc_tail) /* diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S index 37d422e77931..07653d4582a6 100644 --- a/arch/x86/crypto/morus1280-avx2-asm.S +++ b/arch/x86/crypto/morus1280-avx2-asm.S @@ -453,6 +453,7 @@ ENTRY(crypto_morus1280_avx2_enc_tail) vmovdqu STATE4, (4 * 32)(%rdi) FRAME_END + ret ENDPROC(crypto_morus1280_avx2_enc_tail) /* diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S index 1fe637c7be9d..bd1aa1b60869 100644 --- a/arch/x86/crypto/morus1280-sse2-asm.S +++ b/arch/x86/crypto/morus1280-sse2-asm.S @@ -652,6 +652,7 @@ ENTRY(crypto_morus1280_sse2_enc_tail) movdqu STATE4_HI, (9 * 16)(%rdi) FRAME_END + ret ENDPROC(crypto_morus1280_sse2_enc_tail) /* diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S index 71c72a0a0862..efa02816d921 100644 --- a/arch/x86/crypto/morus640-sse2-asm.S +++ b/arch/x86/crypto/morus640-sse2-asm.S @@ -437,6 +437,7 @@ ENTRY(crypto_morus640_sse2_enc_tail) movdqu STATE4, (4 * 16)(%rdi) FRAME_END + ret ENDPROC(crypto_morus640_sse2_enc_tail) /* diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8a10a045b57b..8cf03f101938 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu) ds->bts_buffer_base = (unsigned long) cea; ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); - ds->bts_absolute_maximum = ds->bts_buffer_base + max; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); + max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; + ds->bts_absolute_maximum = ds->bts_buffer_base + + max * BTS_RECORD_SIZE; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - + (max / 16) * BTS_RECORD_SIZE; return 0; } diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index f68855499391..402338365651 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -114,6 +114,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); } + if (nr_bank < 0) + goto ipi_mask_ex_done; if (!nr_bank) ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; @@ -158,6 +160,9 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) for_each_cpu(cur_cpu, mask) { vcpu = hv_cpu_number_to_vp_number(cur_cpu); + if (vcpu == VP_INVAL) + goto ipi_mask_done; + /* * This particular version of the IPI hypercall can * only target upto 64 CPUs. diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 4c431e1c1eff..1ff420217298 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -265,7 +265,7 @@ void __init hyperv_init(void) { u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; - int cpuhp; + int cpuhp, i; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; @@ -293,6 +293,9 @@ void __init hyperv_init(void) if (!hv_vp_index) return; + for (i = 0; i < num_possible_cpus(); i++) + hv_vp_index[i] = VP_INVAL; + hv_vp_assist_page = kcalloc(num_possible_cpus(), sizeof(*hv_vp_assist_page), GFP_KERNEL); if (!hv_vp_assist_page) { diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index c356098b6fb9..4d4015ddcf26 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,8 +7,6 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H -#include <asm/nospec-branch.h> - #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ - firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); - firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 219faaec51df..990770f9e76b 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -46,6 +46,65 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +#ifndef __x86_64__ +/* 32 bit */ + +#define _ASM_ARG1 _ASM_AX +#define _ASM_ARG2 _ASM_DX +#define _ASM_ARG3 _ASM_CX + +#define _ASM_ARG1L eax +#define _ASM_ARG2L edx +#define _ASM_ARG3L ecx + +#define _ASM_ARG1W ax +#define _ASM_ARG2W dx +#define _ASM_ARG3W cx + +#define _ASM_ARG1B al +#define _ASM_ARG2B dl +#define _ASM_ARG3B cl + +#else +/* 64 bit */ + +#define _ASM_ARG1 _ASM_DI +#define _ASM_ARG2 _ASM_SI +#define _ASM_ARG3 _ASM_DX +#define _ASM_ARG4 _ASM_CX +#define _ASM_ARG5 r8 +#define _ASM_ARG6 r9 + +#define _ASM_ARG1Q rdi +#define _ASM_ARG2Q rsi +#define _ASM_ARG3Q rdx +#define _ASM_ARG4Q rcx +#define _ASM_ARG5Q r8 +#define _ASM_ARG6Q r9 + +#define _ASM_ARG1L edi +#define _ASM_ARG2L esi +#define _ASM_ARG3L edx +#define _ASM_ARG4L ecx +#define _ASM_ARG5L r8d +#define _ASM_ARG6L r9d + +#define _ASM_ARG1W di +#define _ASM_ARG2W si +#define _ASM_ARG3W dx +#define _ASM_ARG4W cx +#define _ASM_ARG5W r8w +#define _ASM_ARG6W r9w + +#define _ASM_ARG1B dil +#define _ASM_ARG2B sil +#define _ASM_ARG3B dl +#define _ASM_ARG4B cl +#define _ASM_ARG5B r8b +#define _ASM_ARG6B r9b + +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 89f08955fff7..c4fc17220df9 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -13,7 +13,7 @@ * Interrupt control: */ -static inline unsigned long native_save_fl(void) +extern inline unsigned long native_save_fl(void) { unsigned long flags; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 3cd14311edfa..5a7375ed5f7c 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -9,6 +9,8 @@ #include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> +#define VP_INVAL U32_MAX + struct ms_hyperv_info { u32 features; u32 misc_features; @@ -20,7 +22,6 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; - /* * Generate the guest ID. */ @@ -281,6 +282,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, */ for_each_cpu(cpu, cpus) { vcpu = hv_cpu_number_to_vp_number(cpu); + if (vcpu == VP_INVAL) + return -1; vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; __set_bit(vcpu_offset, (unsigned long *) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 62acb613114b..a9d637bc301d 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len) unsigned long ret; __uaccess_begin(); - ret = memcpy_mcsafe(to, from, len); + /* + * Note, __memcpy_mcsafe() is explicitly used since it can + * handle exceptions / faults. memcpy_mcsafe() may fall back to + * memcpy() which lacks this handling. + */ + ret = __memcpy_mcsafe(to, from, len); __uaccess_end(); return ret; } diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02d6f5cf4e70..8824d01c0c35 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -61,6 +61,7 @@ obj-y += alternative.o i8253.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o +obj-y += irqflags.o obj-y += process.o obj-y += fpu/ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5d0de79fdab0..ec00d1ff5098 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -240,6 +240,7 @@ #include <asm/olpc.h> #include <asm/paravirt.h> #include <asm/reboot.h> +#include <asm/nospec-branch.h> #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) extern int (*console_blank_hook)(int); @@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, &call->esi); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); @@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call) gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); + firmware_restrict_branch_speculation_start(); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); APM_DO_RESTORE_SEGS; + firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 082d7875cef8..38915fbfae73 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -543,7 +543,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) nodes_per_socket = ((value >> 3) & 7) + 1; } - if (c->x86 >= 0x15 && c->x86 <= 0x17) { + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && + c->x86 >= 0x15 && c->x86 <= 0x17) { unsigned int bit; switch (c->x86) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 404df26b7de8..5c0ea39311fe 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -155,7 +155,8 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) hostval |= ssbd_tif_to_spec_ctrl(ti->flags); if (hostval != guestval) { @@ -533,9 +534,10 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may * use a completely different MSR and bit dependent on family. */ - if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !static_cpu_has(X86_FEATURE_AMD_SSBD)) { x86_amd_ssb_disable(); - else { + } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c102ad51025e..8c50754c09c1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s, if (check_interval == old_check_interval) return ret; - if (check_interval < 1) - check_interval = 1; - mutex_lock(&mce_sysfs_mutex); mce_restart(); mutex_unlock(&mce_sysfs_mutex); diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4021d3859499..40eee6cc4124 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -106,7 +106,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) memset(line, 0, LINE_SIZE); - length = strncpy_from_user(line, buf, LINE_SIZE - 1); + len = min_t(size_t, len, LINE_SIZE - 1); + length = strncpy_from_user(line, buf, len); if (length < 0) return length; diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S new file mode 100644 index 000000000000..ddeeaac8adda --- /dev/null +++ b/arch/x86/kernel/irqflags.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <asm/asm.h> +#include <asm/export.h> +#include <linux/linkage.h> + +/* + * unsigned long native_save_fl(void) + */ +ENTRY(native_save_fl) + pushf + pop %_ASM_AX + ret +ENDPROC(native_save_fl) +EXPORT_SYMBOL(native_save_fl) + +/* + * void native_restore_fl(unsigned long flags) + * %eax/%rdi: flags + */ +ENTRY(native_restore_fl) + push %_ASM_ARG1 + popf + ret +ENDPROC(native_restore_fl) +EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index bf8d1eb7fca3..3b8e7c13c614 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -138,6 +138,7 @@ static unsigned long kvm_get_tsc_khz(void) src = &hv_clock[cpu].pvti; tsc_khz = pvclock_tsc_khz(src); put_cpu(); + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); return tsc_khz; } @@ -319,6 +320,8 @@ void __init kvmclock_init(void) printk(KERN_INFO "kvm-clock: Using msrs %x and %x", msr_kvm_system_time, msr_kvm_wall_clock); + pvclock_set_pvti_cpu0_va(hv_clock); + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); @@ -366,14 +369,11 @@ int __init kvm_setup_vsyscall_timeinfo(void) vcpu_time = &hv_clock[cpu].pvti; flags = pvclock_read_flags(vcpu_time); - if (!(flags & PVCLOCK_TSC_STABLE_BIT)) { - put_cpu(); - return 1; - } - - pvclock_set_pvti_cpu0_va(hv_clock); put_cpu(); + if (!(flags & PVCLOCK_TSC_STABLE_BIT)) + return 1; + kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif return 0; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2f7d1d2a5c3..db9656e13ea0 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -221,6 +221,11 @@ static void notrace start_secondary(void *unused) #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); + /* + * Initialize the CR4 shadow before doing anything that could + * try to read it. + */ + cr4_init_shadow(); __flush_tlb_all(); #endif load_current_idt(); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 92fd433c50b9..1bbec387d289 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -85,7 +85,7 @@ config KVM_AMD_SEV def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" depends on KVM_AMD && X86_64 - depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) ---help--- Provides support for launching Encrypted VMs on AMD processors. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..6b8f11521c41 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1689f433f3a0..e30da9a2430c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2571,6 +2571,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); + unsigned long fs_base, kernel_gs_base; #endif int i; @@ -2586,12 +2587,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; #ifdef CONFIG_X86_64 - save_fsgs_for_kvm(); - vmx->host_state.fs_sel = current->thread.fsindex; - vmx->host_state.gs_sel = current->thread.gsindex; -#else - savesegment(fs, vmx->host_state.fs_sel); - savesegment(gs, vmx->host_state.gs_sel); + if (likely(is_64bit_mm(current->mm))) { + save_fsgs_for_kvm(); + vmx->host_state.fs_sel = current->thread.fsindex; + vmx->host_state.gs_sel = current->thread.gsindex; + fs_base = current->thread.fsbase; + kernel_gs_base = current->thread.gsbase; + } else { +#endif + savesegment(fs, vmx->host_state.fs_sel); + savesegment(gs, vmx->host_state.gs_sel); +#ifdef CONFIG_X86_64 + fs_base = read_msr(MSR_FS_BASE); + kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + } #endif if (!(vmx->host_state.fs_sel & 7)) { vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); @@ -2611,10 +2620,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) savesegment(ds, vmx->host_state.ds_sel); savesegment(es, vmx->host_state.es_sel); - vmcs_writel(HOST_FS_BASE, current->thread.fsbase); + vmcs_writel(HOST_FS_BASE, fs_base); vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu)); - vmx->msr_host_kernel_gs_base = current->thread.gsbase; + vmx->msr_host_kernel_gs_base = kernel_gs_base; if (is_long_mode(&vmx->vcpu)) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else @@ -4322,11 +4331,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs_conf->revision_id = KVM_EVMCS_VERSION; - else - vmcs_conf->revision_id = vmx_msr_low; + vmcs_conf->revision_id = vmx_msr_low; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; @@ -4396,7 +4401,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmcs_config.size); - vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ + + /* KVM supports Enlightened VMCS v1 only */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = KVM_EVMCS_VERSION; + else + vmcs->revision_id = vmcs_config.revision_id; + return vmcs; } @@ -4564,6 +4575,19 @@ static __init int alloc_kvm_area(void) return -ENOMEM; } + /* + * When eVMCS is enabled, alloc_vmcs_cpu() sets + * vmcs->revision_id to KVM_EVMCS_VERSION instead of + * revision_id reported by MSR_IA32_VMX_BASIC. + * + * However, even though not explictly documented by + * TLFS, VMXArea passed as VMXON argument should + * still be marked with revision_id reported by + * physical CPU. + */ + if (static_branch_unlikely(&enable_evmcs)) + vmcs->revision_id = vmcs_config.revision_id; + per_cpu(vmxarea, cpu) = vmcs; } return 0; @@ -11753,7 +11777,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u32 msr_entry_idx; u32 exit_qual; int r; @@ -11775,10 +11798,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) nested_get_vmcs12_pages(vcpu, vmcs12); r = EXIT_REASON_MSR_LOAD_FAIL; - msr_entry_idx = nested_vmx_load_msr(vcpu, - vmcs12->vm_entry_msr_load_addr, - vmcs12->vm_entry_msr_load_count); - if (msr_entry_idx) + exit_qual = nested_vmx_load_msr(vcpu, + vmcs12->vm_entry_msr_load_addr, + vmcs12->vm_entry_msr_load_count); + if (exit_qual) goto fail; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0046aa70205a..2b812b3c5088 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1097,6 +1097,7 @@ static u32 msr_based_features[] = { MSR_F10H_DECFG, MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, }; static unsigned int num_msr_based_features; @@ -1105,7 +1106,8 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case MSR_IA32_UCODE_REV: - rdmsrl(msr->index, msr->data); + case MSR_IA32_ARCH_CAPABILITIES: + rdmsrl_safe(msr->index, &msr->data); break; default: if (kvm_x86_ops->get_msr_feature(msr)) diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 2e9ee023e6bc..81a8e33115ad 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -6,7 +6,7 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string targets += $(purgatory-y) PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) -$(obj)/sha256.o: $(srctree)/lib/sha256.c +$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE $(call if_changed_rule,cc_o_c) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 8d4e2e1ae60b..439a94bf89ad 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1207,12 +1207,20 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_setup_features(); - xen_setup_machphys_mapping(); - /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops.patch = paravirt_patch_default; pv_cpu_ops = xen_cpu_ops; + xen_init_irq_ops(); + + /* + * Setup xen_vcpu early because it is needed for + * local_irq_disable(), irqs_disabled(), e.g. in printk(). + * + * Don't do the full vcpu_info placement stuff until we have + * the cpu_possible_mask and a non-dummy shared_info. + */ + xen_vcpu_info_reset(0); x86_platform.get_nmi_reason = xen_get_nmi_reason; @@ -1225,10 +1233,12 @@ asmlinkage __visible void __init xen_start_kernel(void) * Set up some pagetable state before starting to set any ptes. */ + xen_setup_machphys_mapping(); xen_init_mmu_ops(); /* Prevent unwanted bits from being set in PTEs. */ __supported_pte_mask &= ~_PAGE_GLOBAL; + __default_kernel_pte_mask &= ~_PAGE_GLOBAL; /* * Prevent page tables from being allocated in highmem, even @@ -1249,20 +1259,9 @@ asmlinkage __visible void __init xen_start_kernel(void) get_cpu_cap(&boot_cpu_data); x86_configure_nx(); - xen_init_irq_ops(); - /* Let's presume PV guests always boot on vCPU with id 0. */ per_cpu(xen_vcpu_id, 0) = 0; - /* - * Setup xen_vcpu early because idt_setup_early_handler needs it for - * local_irq_disable(), irqs_disabled(). - * - * Don't do the full vcpu_info placement stuff until we have - * the cpu_possible_mask and a non-dummy shared_info. - */ - xen_vcpu_info_reset(0); - idt_setup_early_handler(); xen_init_capabilities(); diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 74179852e46c..7515a19fd324 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -128,8 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = { void __init xen_init_irq_ops(void) { - /* For PVH we use default pv_irq_ops settings. */ - if (!xen_feature(XENFEAT_hvm_callback_vector)) - pv_irq_ops = xen_irq_ops; + pv_irq_ops = xen_irq_ops; x86_init.irqs.intr_init = xen_init_IRQ; } diff --git a/block/bio.c b/block/bio.c index 67eff5eddc49..047c5dca6d90 100644 --- a/block/bio.c +++ b/block/bio.c @@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - size_t offset, diff; + size_t offset; ssize_t size; size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; - nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; + idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; /* * Deep magic below: We need to walk the pinned pages backwards @@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) bio->bi_iter.bi_size += size; bio->bi_vcnt += nr_pages; - diff = (nr_pages * PAGE_SIZE - offset) - size; - while (nr_pages--) { - bv[nr_pages].bv_page = pages[nr_pages]; - bv[nr_pages].bv_len = PAGE_SIZE; - bv[nr_pages].bv_offset = 0; + while (idx--) { + bv[idx].bv_page = pages[idx]; + bv[idx].bv_len = PAGE_SIZE; + bv[idx].bv_offset = 0; } bv[0].bv_offset += offset; bv[0].bv_len -= offset; - if (diff) - bv[bio->bi_vcnt - 1].bv_len -= diff; + bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size; iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) @@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); + bio->bi_iter.bi_done = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/block/blk-mq.c b/block/blk-mq.c index 95919268564b..654b0dc7e001 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq) bool shared = false; int cpu; - if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) != - MQ_RQ_IN_FLIGHT) + if (!blk_mq_mark_complete(rq)) return; - if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); diff --git a/block/bsg.c b/block/bsg.c index 66602c489956..3da540faf673 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -267,8 +267,6 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode) } else if (hdr->din_xfer_len) { ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp), hdr->din_xfer_len, GFP_KERNEL); - } else { - ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL); } if (ret) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 314c52c967e5..c166f424871c 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1155,8 +1155,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, /* make one iovec available as scatterlist */ err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen); - if (err < 0) + if (err < 0) { + rsgl->sg_num_bytes = 0; return err; + } /* chain the new scatterlist with previous one */ if (areq->last_rsgl) diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index fc0c2e2328cd..fe9d46d81750 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -51,16 +51,23 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state) return_ACPI_STATUS(status); } - /* - * 1) Disable all GPEs - * 2) Enable all wakeup GPEs - */ + /* Disable all GPEs */ status = acpi_hw_disable_all_gpes(); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); } + /* + * If the target sleep state is S5, clear all GPEs and fixed events too + */ + if (sleep_state == ACPI_STATE_S5) { + status = acpi_hw_clear_acpi_status(); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + } acpi_gbl_system_awake_and_running = FALSE; + /* Enable all wakeup GPEs */ status = acpi_hw_enable_all_wakeup_gpes(); if (ACPI_FAILURE(status)) { return_ACPI_STATUS(status); diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index bc5f05906bd1..ee840be150b5 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) status = acpi_ps_create_op(walk_state, aml_op_start, &op); if (ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by + * executing it as a control method. However, if we encounter + * an error while loading the table, we need to keep trying to + * load the table rather than aborting the table load. Set the + * status to AE_OK to proceed with the table load. + */ + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status == AE_ALREADY_EXISTS) { + status = AE_OK; + } if (status == AE_CTRL_PARSE_CONTINUE) { continue; } @@ -694,6 +706,20 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) acpi_ps_next_parse_state(walk_state, op, status); if (status == AE_CTRL_PENDING) { status = AE_OK; + } else + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by + * executing it as a control method. However, if we encounter + * an error while loading the table, we need to keep trying to + * load the table rather than aborting the table load. Set the + * status to AE_OK to proceed with the table load. If we get a + * failure at this point, it means that the dispatcher got an + * error while processing Op (most likely an AML operand error. + */ + status = AE_OK; } } diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c index 5a64ddaed8a3..e47430272692 100644 --- a/drivers/acpi/acpica/uterror.c +++ b/drivers/acpi/acpica/uterror.c @@ -182,19 +182,19 @@ acpi_ut_prefixed_namespace_error(const char *module_name, switch (lookup_status) { case AE_ALREADY_EXISTS: - acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR); + acpi_os_printf(ACPI_MSG_BIOS_ERROR); message = "Failure creating"; break; case AE_NOT_FOUND: - acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR); + acpi_os_printf(ACPI_MSG_BIOS_ERROR); message = "Could not resolve"; break; default: - acpi_os_printf("\n" ACPI_MSG_ERROR); + acpi_os_printf(ACPI_MSG_ERROR); message = "Failure resolving"; break; } diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index b0113a5802a3..d79ad844c78f 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -717,10 +717,11 @@ void battery_hook_register(struct acpi_battery_hook *hook) */ pr_err("extension failed to load: %s", hook->name); __battery_hook_unregister(hook, 0); - return; + goto end; } } pr_info("new extension: %s\n", hook->name); +end: mutex_unlock(&hook_mutex); } EXPORT_SYMBOL_GPL(battery_hook_register); @@ -732,7 +733,7 @@ EXPORT_SYMBOL_GPL(battery_hook_register); */ static void battery_hook_add_battery(struct acpi_battery *battery) { - struct acpi_battery_hook *hook_node; + struct acpi_battery_hook *hook_node, *tmp; mutex_lock(&hook_mutex); INIT_LIST_HEAD(&battery->list); @@ -744,15 +745,15 @@ static void battery_hook_add_battery(struct acpi_battery *battery) * when a battery gets hotplugged or initialized * during the battery module initialization. */ - list_for_each_entry(hook_node, &battery_hook_list, list) { + list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) { if (hook_node->add_battery(battery->bat)) { /* * The notification of the extensions has failed, to * prevent further errors we will unload the extension. */ - __battery_hook_unregister(hook_node, 0); pr_err("error in extension, unloading: %s", hook_node->name); + __battery_hook_unregister(hook_node, 0); } } mutex_unlock(&hook_mutex); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 442a9e24f439..917f77f4cb55 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2042,7 +2042,7 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = { .ident = "Thinkpad X1 Carbon 6th", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"), }, }, { }, diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index d15814e1727f..7c479002e798 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -408,6 +408,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, const guid_t *guid; int rc, i; + if (cmd_rc) + *cmd_rc = -EINVAL; func = cmd; if (cmd == ND_CMD_CALL) { call_pkg = buf; @@ -518,6 +520,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, * If we return an error (like elsewhere) then caller wouldn't * be able to rely upon data returned to make calculation. */ + if (cmd_rc) + *cmd_rc = 0; return 0; } @@ -1273,7 +1277,7 @@ static ssize_t scrub_show(struct device *dev, mutex_lock(&acpi_desc->init_mutex); rc = sprintf(buf, "%d%s", acpi_desc->scrub_count, - work_busy(&acpi_desc->dwork.work) + acpi_desc->scrub_busy && !acpi_desc->cancel ? "+\n" : "\n"); mutex_unlock(&acpi_desc->init_mutex); } @@ -2939,6 +2943,32 @@ static unsigned int __acpi_nfit_scrub(struct acpi_nfit_desc *acpi_desc, return 0; } +static void __sched_ars(struct acpi_nfit_desc *acpi_desc, unsigned int tmo) +{ + lockdep_assert_held(&acpi_desc->init_mutex); + + acpi_desc->scrub_busy = 1; + /* note this should only be set from within the workqueue */ + if (tmo) + acpi_desc->scrub_tmo = tmo; + queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ); +} + +static void sched_ars(struct acpi_nfit_desc *acpi_desc) +{ + __sched_ars(acpi_desc, 0); +} + +static void notify_ars_done(struct acpi_nfit_desc *acpi_desc) +{ + lockdep_assert_held(&acpi_desc->init_mutex); + + acpi_desc->scrub_busy = 0; + acpi_desc->scrub_count++; + if (acpi_desc->scrub_count_state) + sysfs_notify_dirent(acpi_desc->scrub_count_state); +} + static void acpi_nfit_scrub(struct work_struct *work) { struct acpi_nfit_desc *acpi_desc; @@ -2949,14 +2979,10 @@ static void acpi_nfit_scrub(struct work_struct *work) mutex_lock(&acpi_desc->init_mutex); query_rc = acpi_nfit_query_poison(acpi_desc); tmo = __acpi_nfit_scrub(acpi_desc, query_rc); - if (tmo) { - queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ); - acpi_desc->scrub_tmo = tmo; - } else { - acpi_desc->scrub_count++; - if (acpi_desc->scrub_count_state) - sysfs_notify_dirent(acpi_desc->scrub_count_state); - } + if (tmo) + __sched_ars(acpi_desc, tmo); + else + notify_ars_done(acpi_desc); memset(acpi_desc->ars_status, 0, acpi_desc->max_ars); mutex_unlock(&acpi_desc->init_mutex); } @@ -3037,7 +3063,7 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) break; } - queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0); + sched_ars(acpi_desc); return 0; } @@ -3239,7 +3265,7 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags) } } if (scheduled) { - queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0); + sched_ars(acpi_desc); dev_dbg(dev, "ars_scan triggered\n"); } mutex_unlock(&acpi_desc->init_mutex); diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 7d15856a739f..a97ff42fe311 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -203,6 +203,7 @@ struct acpi_nfit_desc { unsigned int max_ars; unsigned int scrub_count; unsigned int scrub_mode; + unsigned int scrub_busy:1; unsigned int cancel:1; unsigned long dimm_cmd_force_en; unsigned long bus_cmd_force_en; diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index e5ea1974d1e3..d1e26cb599bf 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -481,8 +481,14 @@ static int topology_get_acpi_cpu_tag(struct acpi_table_header *table, if (cpu_node) { cpu_node = acpi_find_processor_package_id(table, cpu_node, level, flag); - /* Only the first level has a guaranteed id */ - if (level == 0) + /* + * As per specification if the processor structure represents + * an actual processor, then ACPI processor ID must be valid. + * For processor containers ACPI_PPTT_ACPI_PROCESSOR_ID_VALID + * should be set if the UID is valid + */ + if (level == 0 || + cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID) return cpu_node->acpi_processor_id; return ACPI_PTR_DIFF(cpu_node, table); } diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 2b16e7c8fff3..39b181d6bd0d 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -398,7 +398,6 @@ config SATA_DWC_VDEBUG config SATA_HIGHBANK tristate "Calxeda Highbank SATA support" - depends on HAS_DMA depends on ARCH_HIGHBANK || COMPILE_TEST help This option enables support for the Calxeda Highbank SoC's @@ -408,7 +407,6 @@ config SATA_HIGHBANK config SATA_MV tristate "Marvell SATA support" - depends on HAS_DMA depends on PCI || ARCH_DOVE || ARCH_MV78XX0 || \ ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST select GENERIC_PHY diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 738fb22978dd..b2b9eba1d214 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -400,6 +400,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */ { PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */ { PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */ + { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -1280,6 +1281,59 @@ static bool ahci_broken_suspend(struct pci_dev *pdev) return strcmp(buf, dmi->driver_data) < 0; } +static bool ahci_broken_lpm(struct pci_dev *pdev) +{ + static const struct dmi_system_id sysids[] = { + /* Various Lenovo 50 series have LPM issues with older BIOSen */ + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X250"), + }, + .driver_data = "20180406", /* 1.31 */ + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L450"), + }, + .driver_data = "20180420", /* 1.28 */ + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T450s"), + }, + .driver_data = "20180315", /* 1.33 */ + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"), + }, + /* + * Note date based on release notes, 2.35 has been + * reported to be good, but I've been unable to get + * a hold of the reporter to get the DMI BIOS date. + * TODO: fix this. + */ + .driver_data = "20180310", /* 2.35 */ + }, + { } /* terminate list */ + }; + const struct dmi_system_id *dmi = dmi_first_match(sysids); + int year, month, date; + char buf[9]; + + if (!dmi) + return false; + + dmi_get_date(DMI_BIOS_DATE, &year, &month, &date); + snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date); + + return strcmp(buf, dmi->driver_data) < 0; +} + static bool ahci_broken_online(struct pci_dev *pdev) { #define ENCODE_BUSDEVFN(bus, slot, func) \ @@ -1694,6 +1748,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) "quirky BIOS, skipping spindown on poweroff\n"); } + if (ahci_broken_lpm(pdev)) { + pi.flags |= ATA_FLAG_NO_LPM; + dev_warn(&pdev->dev, + "BIOS update required for Link Power Management support\n"); + } + if (ahci_broken_suspend(pdev)) { hpriv->flags |= AHCI_HFLAG_NO_SUSPEND; dev_warn(&pdev->dev, diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index 0045dacd814b..72d90b4c3aae 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -82,7 +82,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv) * * Return: 0 on success; Error code otherwise. */ -int ahci_mvebu_stop_engine(struct ata_port *ap) +static int ahci_mvebu_stop_engine(struct ata_port *ap) { void __iomem *port_mmio = ahci_port_base(ap); u32 tmp, port_fbs; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 965842a08743..09620c2ffa0f 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -35,6 +35,7 @@ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/module.h> +#include <linux/nospec.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/interrupt.h> @@ -1146,10 +1147,12 @@ static ssize_t ahci_led_store(struct ata_port *ap, const char *buf, /* get the slot number from the message */ pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8; - if (pmp < EM_MAX_SLOTS) + if (pmp < EM_MAX_SLOTS) { + pmp = array_index_nospec(pmp, EM_MAX_SLOTS); emp = &pp->em_priv[pmp]; - else + } else { return -EINVAL; + } /* mask off the activity bits if we are in sw_activity * mode, user should turn off sw_activity before setting diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 27d15ed7fa3d..cc71c63df381 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2493,6 +2493,9 @@ int ata_dev_configure(struct ata_device *dev) (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2) dev->horkage |= ATA_HORKAGE_NOLPM; + if (ap->flags & ATA_FLAG_NO_LPM) + dev->horkage |= ATA_HORKAGE_NOLPM; + if (dev->horkage & ATA_HORKAGE_NOLPM) { ata_dev_warn(dev, "LPM support broken, forcing max_power\n"); dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index d5412145d76d..01306c018398 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -614,8 +614,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) { struct ata_queued_cmd *qc; - for (i = 0; i < ATA_MAX_QUEUE; i++) { - qc = __ata_qc_from_tag(ap, i); + ata_qc_for_each_raw(ap, qc, i) { if (qc->flags & ATA_QCFLAG_ACTIVE && qc->scsicmd == scmd) break; @@ -818,14 +817,13 @@ EXPORT_SYMBOL_GPL(ata_port_wait_eh); static int ata_eh_nr_in_flight(struct ata_port *ap) { + struct ata_queued_cmd *qc; unsigned int tag; int nr = 0; /* count only non-internal commands */ - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - if (ata_tag_internal(tag)) - continue; - if (ata_qc_from_tag(ap, tag)) + ata_qc_for_each(ap, qc, tag) { + if (qc) nr++; } @@ -847,13 +845,13 @@ void ata_eh_fastdrain_timerfn(struct timer_list *t) goto out_unlock; if (cnt == ap->fastdrain_cnt) { + struct ata_queued_cmd *qc; unsigned int tag; /* No progress during the last interval, tag all * in-flight qcs as timed out and freeze the port. */ - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag); + ata_qc_for_each(ap, qc, tag) { if (qc) qc->err_mask |= AC_ERR_TIMEOUT; } @@ -999,6 +997,7 @@ void ata_port_schedule_eh(struct ata_port *ap) static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link) { + struct ata_queued_cmd *qc; int tag, nr_aborted = 0; WARN_ON(!ap->ops->error_handler); @@ -1007,9 +1006,7 @@ static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link) ata_eh_set_pending(ap, 0); /* include internal tag in iteration */ - for (tag = 0; tag <= ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag); - + ata_qc_for_each_with_internal(ap, qc, tag) { if (qc && (!link || qc->dev->link == link)) { qc->flags |= ATA_QCFLAG_FAILED; ata_qc_complete(qc); @@ -1712,9 +1709,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) return; /* has LLDD analyzed already? */ - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - qc = __ata_qc_from_tag(ap, tag); - + ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_FAILED)) continue; @@ -2136,6 +2131,7 @@ static void ata_eh_link_autopsy(struct ata_link *link) { struct ata_port *ap = link->ap; struct ata_eh_context *ehc = &link->eh_context; + struct ata_queued_cmd *qc; struct ata_device *dev; unsigned int all_err_mask = 0, eflags = 0; int tag, nr_failed = 0, nr_quiet = 0; @@ -2168,9 +2164,7 @@ static void ata_eh_link_autopsy(struct ata_link *link) all_err_mask |= ehc->i.err_mask; - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag); - + ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_FAILED) || ata_dev_phys_link(qc->dev) != link) continue; @@ -2436,6 +2430,7 @@ static void ata_eh_link_report(struct ata_link *link) { struct ata_port *ap = link->ap; struct ata_eh_context *ehc = &link->eh_context; + struct ata_queued_cmd *qc; const char *frozen, *desc; char tries_buf[6] = ""; int tag, nr_failed = 0; @@ -2447,9 +2442,7 @@ static void ata_eh_link_report(struct ata_link *link) if (ehc->i.desc[0] != '\0') desc = ehc->i.desc; - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag); - + ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_FAILED) || ata_dev_phys_link(qc->dev) != link || ((qc->flags & ATA_QCFLAG_QUIET) && @@ -2511,8 +2504,7 @@ static void ata_eh_link_report(struct ata_link *link) ehc->i.serror & SERR_DEV_XCHG ? "DevExch " : ""); #endif - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag); + ata_qc_for_each_raw(ap, qc, tag) { struct ata_taskfile *cmd = &qc->tf, *res = &qc->result_tf; char data_buf[20] = ""; char cdb_buf[70] = ""; @@ -3992,12 +3984,11 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset, */ void ata_eh_finish(struct ata_port *ap) { + struct ata_queued_cmd *qc; int tag; /* retry or finish qcs */ - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag); - + ata_qc_for_each_raw(ap, qc, tag) { if (!(qc->flags & ATA_QCFLAG_FAILED)) continue; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 6a91d04351d9..aad1b01447de 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3805,10 +3805,20 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc) */ goto invalid_param_len; } - if (block > dev->n_sectors) - goto out_of_range; all = cdb[14] & 0x1; + if (all) { + /* + * Ignore the block address (zone ID) as defined by ZBC. + */ + block = 0; + } else if (block >= dev->n_sectors) { + /* + * Block must be a valid zone ID (a zone start LBA). + */ + fp = 2; + goto invalid_fld; + } if (ata_ncq_enabled(qc->dev) && ata_fpdma_zac_mgmt_out_supported(qc->dev)) { @@ -3837,10 +3847,6 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc) invalid_fld: ata_scsi_set_invalid_field(qc->dev, scmd, fp, 0xff); return 1; - out_of_range: - /* "Logical Block Address out of range" */ - ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x21, 0x00); - return 1; invalid_param_len: /* "Parameter list length error" */ ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x1a, 0x0); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index b8d9cfc60374..4dc528bf8e85 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -395,12 +395,6 @@ static inline unsigned int sata_fsl_tag(unsigned int tag, { /* We let libATA core do actual (queue) tag allocation */ - /* all non NCQ/queued commands should have tag#0 */ - if (ata_tag_internal(tag)) { - DPRINTK("mapping internal cmds to tag#0\n"); - return 0; - } - if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) { DPRINTK("tag %d invalid : out of range\n", tag); return 0; @@ -1229,8 +1223,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) /* Workaround for data length mismatch errata */ if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) { - for (tag = 0; tag < ATA_MAX_QUEUE; tag++) { - qc = ata_qc_from_tag(ap, tag); + ata_qc_for_each_with_internal(ap, qc, tag) { if (qc && ata_is_atapi(qc->tf.protocol)) { u32 hcontrol; /* Set HControl[27] to clear error registers */ diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 10ae11aa1926..72c9b922a77b 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -675,7 +675,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev) struct ata_port *ap = ata_shost_to_port(sdev->host); struct nv_adma_port_priv *pp = ap->private_data; struct nv_adma_port_priv *port0, *port1; - struct scsi_device *sdev0, *sdev1; struct pci_dev *pdev = to_pci_dev(ap->host->dev); unsigned long segment_boundary, flags; unsigned short sg_tablesize; @@ -736,8 +735,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev) port0 = ap->host->ports[0]->private_data; port1 = ap->host->ports[1]->private_data; - sdev0 = ap->host->ports[0]->link.device[0].sdev; - sdev1 = ap->host->ports[1]->link.device[0].sdev; if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) || (port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) { /* diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index ff81a576347e..82532c299bb5 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -1618,7 +1618,7 @@ static int rx_init(struct atm_dev *dev) skb_queue_head_init(&iadev->rx_dma_q); iadev->rx_free_desc_qhead = NULL; - iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL); + iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL); if (!iadev->rx_open) { printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n", dev->number); diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index a8d2eb0ceb8d..2c288d1f42bb 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) return -EFAULT; if (pool < 0 || pool > ZATM_LAST_POOL) return -EINVAL; + pool = array_index_nospec(pool, + ZATM_LAST_POOL + 1); if (copy_from_user(&info, &((struct zatm_pool_req __user *) arg)->info, sizeof(info))) return -EFAULT; diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 1435d7281c66..6ebcd65d64b6 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -434,14 +434,6 @@ re_probe: goto probe_failed; } - /* - * Ensure devices are listed in devices_kset in correct order - * It's important to move Dev to the end of devices_kset before - * calling .probe, because it could be recursive and parent Dev - * should always go first - */ - devices_kset_move_last(dev); - if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index c298de8a8308..9e8484189034 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2235,7 +2235,7 @@ static void genpd_dev_pm_sync(struct device *dev) } static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np, - unsigned int index) + unsigned int index, bool power_on) { struct of_phandle_args pd_args; struct generic_pm_domain *pd; @@ -2271,9 +2271,11 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np, dev->pm_domain->detach = genpd_dev_pm_detach; dev->pm_domain->sync = genpd_dev_pm_sync; - genpd_lock(pd); - ret = genpd_power_on(pd, 0); - genpd_unlock(pd); + if (power_on) { + genpd_lock(pd); + ret = genpd_power_on(pd, 0); + genpd_unlock(pd); + } if (ret) genpd_remove_device(pd, dev); @@ -2307,7 +2309,7 @@ int genpd_dev_pm_attach(struct device *dev) "#power-domain-cells") != 1) return 0; - return __genpd_dev_pm_attach(dev, dev->of_node, 0); + return __genpd_dev_pm_attach(dev, dev->of_node, 0, true); } EXPORT_SYMBOL_GPL(genpd_dev_pm_attach); @@ -2359,14 +2361,14 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev, } /* Try to attach the device to the PM domain at the specified index. */ - ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index); + ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index, false); if (ret < 1) { device_unregister(genpd_dev); return ret ? ERR_PTR(ret) : NULL; } - pm_runtime_set_active(genpd_dev); pm_runtime_enable(genpd_dev); + genpd_queue_power_off_work(dev_to_genpd(genpd_dev)); return genpd_dev; } diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 1476cb3439f4..5e793dd7adfb 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -282,8 +282,8 @@ void drbd_request_endio(struct bio *bio) what = COMPLETED_OK; } - bio_put(req->private_bio); req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status)); + bio_put(bio); /* not req_mod(), we need irqsave here! */ spin_lock_irqsave(&device->resource->req_lock, flags); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d6b6f434fd4b..4cb1d1be3cfb 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1613,6 +1613,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, arg = (unsigned long) compat_ptr(arg); case LOOP_SET_FD: case LOOP_CHANGE_FD: + case LOOP_SET_BLOCK_SIZE: err = lo_ioctl(bdev, mode, cmd, arg); break; default: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 74a05561b620..3fb95c8d9fd8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -112,12 +112,16 @@ struct nbd_device { struct task_struct *task_setup; }; +#define NBD_CMD_REQUEUED 1 + struct nbd_cmd { struct nbd_device *nbd; + struct mutex lock; int index; int cookie; - struct completion send_complete; blk_status_t status; + unsigned long flags; + u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd) return disk_to_dev(nbd->disk); } +static void nbd_requeue_cmd(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) + blk_mq_requeue_request(req, true); +} + +#define NBD_COOKIE_BITS 32 + +static u64 nbd_cmd_handle(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + u32 tag = blk_mq_unique_tag(req); + u64 cookie = cmd->cmd_cookie; + + return (cookie << NBD_COOKIE_BITS) | tag; +} + +static u32 nbd_handle_to_tag(u64 handle) +{ + return (u32)handle; +} + +static u32 nbd_handle_to_cookie(u64 handle) +{ + return (u32)(handle >> NBD_COOKIE_BITS); +} + static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { @@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } config = nbd->config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", @@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - blk_mq_requeue_request(req, true); + mutex_unlock(&cmd->lock); + nbd_requeue_cmd(cmd); nbd_config_put(nbd); return BLK_EH_DONE; } @@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } set_bit(NBD_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: @@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; + u64 handle; u32 type; u32 nbd_cmd_flags = 0; - u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); @@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) goto send_pages; } iov_iter_advance(&from, sent); + } else { + cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; @@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &tag, sizeof(tag)); + handle = nbd_cmd_handle(cmd); + memcpy(request.handle, &handle, sizeof(handle)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), @@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -541,6 +583,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), @@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; + u64 handle; u16 hwq; u32 tag; struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; struct iov_iter to; + int ret = 0; reply.magic = 0; iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); @@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(u32)); - + memcpy(&handle, reply.handle, sizeof(handle)); + tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], @@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); + + mutex_lock(&cmd->lock); + if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { + dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", + req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); + ret = -ENOENT; + goto out; + } + if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", + req); + ret = -ENOENT; + goto out; + } if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); @@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (nbd_disconnected(config) || config->num_connections <= 1) { cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - return ERR_PTR(-EIO); + ret = -EIO; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } - } else { - /* See the comment in nbd_queue_rq. */ - wait_for_completion(&cmd->send_complete); } - return cmd; +out: + mutex_unlock(&cmd->lock); + return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) @@ -805,7 +864,7 @@ again: */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; goto out; } @@ -818,7 +877,7 @@ again: dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; } out: @@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ - init_completion(&cmd->send_complete); + mutex_lock(&cmd->lock); + clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In @@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_IOERR; else if (!ret) ret = BLK_STS_OK; - complete(&cmd->send_complete); + mutex_unlock(&cmd->lock); return ret; } @@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; + cmd->flags = 0; + mutex_init(&cmd->lock); return 0; } diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 1cc29629d238..80d60f43db56 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -169,9 +169,9 @@ static int sysc_get_clocks(struct sysc *ddata) const char *name; int nr_fck = 0, nr_ick = 0, i, error = 0; - ddata->clock_roles = devm_kzalloc(ddata->dev, - sizeof(*ddata->clock_roles) * + ddata->clock_roles = devm_kcalloc(ddata->dev, SYSC_MAX_CLOCKS, + sizeof(*ddata->clock_roles), GFP_KERNEL); if (!ddata->clock_roles) return -ENOMEM; @@ -200,8 +200,8 @@ static int sysc_get_clocks(struct sysc *ddata) return -EINVAL; } - ddata->clocks = devm_kzalloc(ddata->dev, - sizeof(*ddata->clocks) * ddata->nr_clocks, + ddata->clocks = devm_kcalloc(ddata->dev, + ddata->nr_clocks, sizeof(*ddata->clocks), GFP_KERNEL); if (!ddata->clocks) return -ENOMEM; diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c index 53fe633df1e8..c9bf2c219841 100644 --- a/drivers/char/agp/alpha-agp.c +++ b/drivers/char/agp/alpha-agp.c @@ -11,7 +11,7 @@ #include "agp.h" -static int alpha_core_agp_vm_fault(struct vm_fault *vmf) +static vm_fault_t alpha_core_agp_vm_fault(struct vm_fault *vmf) { alpha_agp_info *agp = agp_bridge->dev_private_data; dma_addr_t dma_addr; diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index e50c29c97ca7..c69e39fdd02b 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -156,7 +156,7 @@ static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table) /* Address to map to */ pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp); - aperturebase = tmp << 25; + aperturebase = (u64)tmp << 25; aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK); enable_gart_translation(hammer, gatt_table); @@ -277,7 +277,7 @@ static int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, u16 cap) pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order); nb_order = (nb_order >> 1) & 7; pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base); - nb_aper = nb_base << 25; + nb_aper = (u64)nb_base << 25; /* Northbridge seems to contain crap. Try the AGP bridge. */ diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index ad353be871bf..90ec010bffbd 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2088,8 +2088,10 @@ static int try_smi_init(struct smi_info *new_smi) return 0; out_err: - ipmi_unregister_smi(new_smi->intf); - new_smi->intf = NULL; + if (new_smi->intf) { + ipmi_unregister_smi(new_smi->intf); + new_smi->intf = NULL; + } kfree(init_name); diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index fbfc05e3f3d1..bb882ab161fe 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -210,34 +210,23 @@ static void kcs_bmc_handle_cmd(struct kcs_bmc *kcs_bmc) int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc) { unsigned long flags; - int ret = 0; + int ret = -ENODATA; u8 status; spin_lock_irqsave(&kcs_bmc->lock, flags); - if (!kcs_bmc->running) { - kcs_force_abort(kcs_bmc); - ret = -ENODEV; - goto out_unlock; - } - - status = read_status(kcs_bmc) & (KCS_STATUS_IBF | KCS_STATUS_CMD_DAT); - - switch (status) { - case KCS_STATUS_IBF | KCS_STATUS_CMD_DAT: - kcs_bmc_handle_cmd(kcs_bmc); - break; - - case KCS_STATUS_IBF: - kcs_bmc_handle_data(kcs_bmc); - break; + status = read_status(kcs_bmc); + if (status & KCS_STATUS_IBF) { + if (!kcs_bmc->running) + kcs_force_abort(kcs_bmc); + else if (status & KCS_STATUS_CMD_DAT) + kcs_bmc_handle_cmd(kcs_bmc); + else + kcs_bmc_handle_data(kcs_bmc); - default: - ret = -ENODATA; - break; + ret = 0; } -out_unlock: spin_unlock_irqrestore(&kcs_bmc->lock, flags); return ret; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index ffeb60d3434c..df66a9dd0aae 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma) #endif if (vma->vm_flags & VM_SHARED) return shmem_zero_setup(vma); + vma_set_anonymous(vma); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index cd888d4ee605..bd449ad52442 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1895,14 +1895,22 @@ static int write_pool(struct entropy_store *r, const char __user *buffer, size_t count) { size_t bytes; - __u32 buf[16]; + __u32 t, buf[16]; const char __user *p = buffer; while (count > 0) { + int b, i = 0; + bytes = min(count, sizeof(buf)); if (copy_from_user(&buf, p, bytes)) return -EFAULT; + for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) { + if (!arch_get_random_int(&t)) + break; + buf[i] ^= t; + } + count -= bytes; p += bytes; diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index ae40cbe770f0..0bb25dd009d1 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -96,7 +96,7 @@ obj-$(CONFIG_ARCH_SPRD) += sprd/ obj-$(CONFIG_ARCH_STI) += st/ obj-$(CONFIG_ARCH_STRATIX10) += socfpga/ obj-$(CONFIG_ARCH_SUNXI) += sunxi/ -obj-$(CONFIG_ARCH_SUNXI) += sunxi-ng/ +obj-$(CONFIG_SUNXI_CCU) += sunxi-ng/ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-y += ti/ obj-$(CONFIG_CLK_UNIPHIER) += uniphier/ diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 38b366b00c57..7b70a074095d 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -24,7 +24,7 @@ #define ASPEED_MPLL_PARAM 0x20 #define ASPEED_HPLL_PARAM 0x24 #define AST2500_HPLL_BYPASS_EN BIT(20) -#define AST2400_HPLL_STRAPPED BIT(18) +#define AST2400_HPLL_PROGRAMMED BIT(18) #define AST2400_HPLL_BYPASS_EN BIT(17) #define ASPEED_MISC_CTRL 0x2c #define UART_DIV13_EN BIT(12) @@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = { [ASPEED_CLK_GATE_GCLK] = { 1, 7, "gclk-gate", NULL, 0 }, /* 2D engine */ [ASPEED_CLK_GATE_MCLK] = { 2, -1, "mclk-gate", "mpll", CLK_IS_CRITICAL }, /* SDRAM */ [ASPEED_CLK_GATE_VCLK] = { 3, 6, "vclk-gate", NULL, 0 }, /* Video Capture */ - [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", 0 }, /* PCIe/PCI */ - [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, 0 }, /* DAC */ + [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", CLK_IS_CRITICAL }, /* PCIe/PCI */ + [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, CLK_IS_CRITICAL }, /* DAC */ [ASPEED_CLK_GATE_REFCLK] = { 6, -1, "refclk-gate", "clkin", CLK_IS_CRITICAL }, [ASPEED_CLK_GATE_USBPORT2CLK] = { 7, 3, "usb-port2-gate", NULL, 0 }, /* USB2.0 Host port 2 */ [ASPEED_CLK_GATE_LCLK] = { 8, 5, "lclk-gate", NULL, 0 }, /* LPC */ @@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw) { struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); u32 clk = BIT(gate->clock_idx); + u32 rst = BIT(gate->reset_idx); u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk; u32 reg; + /* + * If the IP is in reset, treat the clock as not enabled, + * this happens with some clocks such as the USB one when + * coming from cold reset. Without this, aspeed_clk_enable() + * will fail to lift the reset. + */ + if (gate->reset_idx >= 0) { + regmap_read(gate->map, ASPEED_RESET_CTRL, ®); + if (reg & rst) + return 0; + } + regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); return ((reg & clk) == enval) ? 1 : 0; @@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver); static void __init aspeed_ast2400_cc(struct regmap *map) { struct clk_hw *hw; - u32 val, freq, div; + u32 val, div, clkin, hpll; + const u16 hpll_rates[][4] = { + {384, 360, 336, 408}, + {400, 375, 350, 425}, + }; + int rate; /* * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by * strapping */ regmap_read(map, ASPEED_STRAP, &val); - if (val & CLKIN_25MHZ_EN) - freq = 25000000; - else if (val & AST2400_CLK_SOURCE_SEL) - freq = 48000000; - else - freq = 24000000; - hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq); - pr_debug("clkin @%u MHz\n", freq / 1000000); + rate = (val >> 8) & 3; + if (val & CLKIN_25MHZ_EN) { + clkin = 25000000; + hpll = hpll_rates[1][rate]; + } else if (val & AST2400_CLK_SOURCE_SEL) { + clkin = 48000000; + hpll = hpll_rates[0][rate]; + } else { + clkin = 24000000; + hpll = hpll_rates[0][rate]; + } + hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin); + pr_debug("clkin @%u MHz\n", clkin / 1000000); /* * High-speed PLL clock derived from the crystal. This the CPU clock, - * and we assume that it is enabled + * and we assume that it is enabled. It can be configured through the + * HPLL_PARAM register, or set to a specified frequency by strapping. */ regmap_read(map, ASPEED_HPLL_PARAM, &val); - WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured"); - aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val); + if (val & AST2400_HPLL_PROGRAMMED) + hw = aspeed_ast2400_calc_pll("hpll", val); + else + hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0, + hpll * 1000000); + + aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw; /* * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9760b526ca31..e2ed078abd90 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -24,7 +24,6 @@ #include <linux/pm_runtime.h> #include <linux/sched.h> #include <linux/clkdev.h> -#include <linux/stringify.h> #include "clk.h" @@ -2559,7 +2558,7 @@ static const struct { unsigned long flag; const char *name; } clk_flags[] = { -#define ENTRY(f) { f, __stringify(f) } +#define ENTRY(f) { f, #f } ENTRY(CLK_SET_RATE_GATE), ENTRY(CLK_SET_PARENT_GATE), ENTRY(CLK_SET_RATE_PARENT), diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c index aae62a5b8734..d1bbee19ed0f 100644 --- a/drivers/clk/davinci/da8xx-cfgchip.c +++ b/drivers/clk/davinci/da8xx-cfgchip.c @@ -672,7 +672,7 @@ static int of_da8xx_usb_phy_clk_init(struct device *dev, struct regmap *regmap) usb1 = da8xx_cfgchip_register_usb1_clk48(dev, regmap); if (IS_ERR(usb1)) { - if (PTR_ERR(usb0) == -EPROBE_DEFER) + if (PTR_ERR(usb1) == -EPROBE_DEFER) return -EPROBE_DEFER; dev_warn(dev, "Failed to register usb1_clk48 (%ld)\n", diff --git a/drivers/clk/davinci/psc.h b/drivers/clk/davinci/psc.h index 6a42529d31a9..cc5614567a70 100644 --- a/drivers/clk/davinci/psc.h +++ b/drivers/clk/davinci/psc.h @@ -107,7 +107,7 @@ extern const struct davinci_psc_init_data of_da850_psc1_init_data; #ifdef CONFIG_ARCH_DAVINCI_DM355 extern const struct davinci_psc_init_data dm355_psc_init_data; #endif -#ifdef CONFIG_ARCH_DAVINCI_DM356 +#ifdef CONFIG_ARCH_DAVINCI_DM365 extern const struct davinci_psc_init_data dm365_psc_init_data; #endif #ifdef CONFIG_ARCH_DAVINCI_DM644x diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c index 58f546e04807..e4cf96ba704e 100644 --- a/drivers/clk/meson/clk-audio-divider.c +++ b/drivers/clk/meson/clk-audio-divider.c @@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw, struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk); unsigned long divider; - divider = meson_parm_read(clk->map, &adiv->div); + divider = meson_parm_read(clk->map, &adiv->div) + 1; return DIV_ROUND_UP_ULL((u64)parent_rate, divider); } diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 240658404367..177fffb9ebef 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index 6860bd5a37c5..44e4e27eddad 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -35,6 +35,7 @@ #define CLK_SEL 0x10 #define CLK_DIS 0x14 +#define ARMADA_37XX_DVFS_LOAD_1 1 #define LOAD_LEVEL_NR 4 #define ARMADA_37XX_NB_L0L1 0x18 @@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate, return -EINVAL; } +/* + * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz + * respectively) to L0 frequency (1.2 Ghz) requires a significant + * amount of time to let VDD stabilize to the appropriate + * voltage. This amount of time is large enough that it cannot be + * covered by the hardware countdown register. Due to this, the CPU + * might start operating at L0 before the voltage is stabilized, + * leading to CPU stalls. + * + * To work around this problem, we prevent switching directly from the + * L2/L3 frequencies to the L0 frequency, and instead switch to the L1 + * frequency in-between. The sequence therefore becomes: + * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ) + * 2. Sleep 20ms for stabling VDD voltage + * 3. Then switch from L1(600MHZ) to L0(1200Mhz). + */ +static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base) +{ + unsigned int cur_level; + + if (rate != 1200 * 1000 * 1000) + return; + + regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level); + cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK; + if (cur_level <= ARMADA_37XX_DVFS_LOAD_1) + return; + + regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD, + ARMADA_37XX_NB_CPU_LOAD_MASK, + ARMADA_37XX_DVFS_LOAD_1); + msleep(20); +} + static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, */ reg = ARMADA_37XX_NB_CPU_LOAD; mask = ARMADA_37XX_NB_CPU_LOAD_MASK; + + clk_pm_cpu_set_rate_wa(rate, base); + regmap_update_bits(base, reg, mask, load_level); return rate; diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 9f35b3fe1d97..ff8d66fd94e6 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = { static struct clk_branch gcc_ufs_tx_symbol_0_clk = { .halt_reg = 0x75018, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x75018, .enable_mask = BIT(0), diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c index 1a25ee4f3658..4b20d1b67a1b 100644 --- a/drivers/clk/qcom/mmcc-msm8996.c +++ b/drivers/clk/qcom/mmcc-msm8996.c @@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = { .name = "mmagic_bimc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = ALWAYS_ON, }; static struct gdsc mmagic_video_gdsc = { diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile index acaa14cfa25c..49454700f2e5 100644 --- a/drivers/clk/sunxi-ng/Makefile +++ b/drivers/clk/sunxi-ng/Makefile @@ -1,24 +1,24 @@ # SPDX-License-Identifier: GPL-2.0 # Common objects -lib-$(CONFIG_SUNXI_CCU) += ccu_common.o -lib-$(CONFIG_SUNXI_CCU) += ccu_mmc_timing.o -lib-$(CONFIG_SUNXI_CCU) += ccu_reset.o +obj-y += ccu_common.o +obj-y += ccu_mmc_timing.o +obj-y += ccu_reset.o # Base clock types -lib-$(CONFIG_SUNXI_CCU) += ccu_div.o -lib-$(CONFIG_SUNXI_CCU) += ccu_frac.o -lib-$(CONFIG_SUNXI_CCU) += ccu_gate.o -lib-$(CONFIG_SUNXI_CCU) += ccu_mux.o -lib-$(CONFIG_SUNXI_CCU) += ccu_mult.o -lib-$(CONFIG_SUNXI_CCU) += ccu_phase.o -lib-$(CONFIG_SUNXI_CCU) += ccu_sdm.o +obj-y += ccu_div.o +obj-y += ccu_frac.o +obj-y += ccu_gate.o +obj-y += ccu_mux.o +obj-y += ccu_mult.o +obj-y += ccu_phase.o +obj-y += ccu_sdm.o # Multi-factor clocks -lib-$(CONFIG_SUNXI_CCU) += ccu_nk.o -lib-$(CONFIG_SUNXI_CCU) += ccu_nkm.o -lib-$(CONFIG_SUNXI_CCU) += ccu_nkmp.o -lib-$(CONFIG_SUNXI_CCU) += ccu_nm.o -lib-$(CONFIG_SUNXI_CCU) += ccu_mp.o +obj-y += ccu_nk.o +obj-y += ccu_nkm.o +obj-y += ccu_nkmp.o +obj-y += ccu_nm.o +obj-y += ccu_mp.o # SoC support obj-$(CONFIG_SUN50I_A64_CCU) += ccu-sun50i-a64.o @@ -38,12 +38,3 @@ obj-$(CONFIG_SUN8I_R40_CCU) += ccu-sun8i-r40.o obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80.o obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-de.o obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-usb.o - -# The lib-y file goals is supposed to work only in arch/*/lib or lib/. In our -# case, we want to use that goal, but even though lib.a will be properly -# generated, it will not be linked in, eventually resulting in a linker error -# for missing symbols. -# -# We can work around that by explicitly adding lib.a to the obj-y goal. This is -# an undocumented behaviour, but works well for now. -obj-$(CONFIG_SUNXI_CCU) += lib.a diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 57cb2f00fc07..d8c7f5750cdb 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -735,7 +735,7 @@ static void __arch_timer_setup(unsigned type, clk->features |= CLOCK_EVT_FEAT_DYNIRQ; clk->name = "arch_mem_timer"; clk->rating = 400; - clk->cpumask = cpu_all_mask; + clk->cpumask = cpu_possible_mask; if (arch_timer_mem_use_virtual) { clk->set_state_shutdown = arch_timer_shutdown_virt_mem; clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ece120da3353..3c3971256130 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2394,6 +2394,18 @@ static bool __init intel_pstate_no_acpi_pss(void) return true; } +static bool __init intel_pstate_no_acpi_pcch(void) +{ + acpi_status status; + acpi_handle handle; + + status = acpi_get_handle(NULL, "\\_SB", &handle); + if (ACPI_FAILURE(status)) + return true; + + return !acpi_has_method(handle, "PCCH"); +} + static bool __init intel_pstate_has_acpi_ppc(void) { int i; @@ -2453,7 +2465,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void) switch (plat_info[idx].data) { case PSS: - return intel_pstate_no_acpi_pss(); + if (!intel_pstate_no_acpi_pss()) + return false; + + return intel_pstate_no_acpi_pcch(); case PPC: return intel_pstate_has_acpi_ppc() && !force_load; } diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 3f0ce2ae35ee..0c56c9759672 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -580,6 +580,10 @@ static int __init pcc_cpufreq_init(void) { int ret; + /* Skip initialization if another cpufreq driver is there. */ + if (cpufreq_get_current_driver()) + return 0; + if (acpi_disabled) return 0; diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 29389accf3e9..efc9a7ae4857 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -183,6 +183,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = { static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = { { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, + {} }; /* diff --git a/drivers/dax/device.c b/drivers/dax/device.c index de2f8297a210..108c37fca782 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -189,14 +189,16 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma, /* prevent private mappings from being established */ if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) { - dev_info(dev, "%s: %s: fail, attempted private mapping\n", + dev_info_ratelimited(dev, + "%s: %s: fail, attempted private mapping\n", current->comm, func); return -EINVAL; } mask = dax_region->align - 1; if (vma->vm_start & mask || vma->vm_end & mask) { - dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n", + dev_info_ratelimited(dev, + "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n", current->comm, func, vma->vm_start, vma->vm_end, mask); return -EINVAL; @@ -204,13 +206,15 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma, if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV && (vma->vm_flags & VM_DONTCOPY) == 0) { - dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n", + dev_info_ratelimited(dev, + "%s: %s: fail, dax range requires MADV_DONTFORK\n", current->comm, func); return -EINVAL; } if (!vma_is_dax(vma)) { - dev_info(dev, "%s: %s: fail, vma is not DAX capable\n", + dev_info_ratelimited(dev, + "%s: %s: fail, vma is not DAX capable\n", current->comm, func); return -EINVAL; } diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c index fa31cccbe04f..6bfa217ed6d0 100644 --- a/drivers/dma/k3dma.c +++ b/drivers/dma/k3dma.c @@ -794,7 +794,7 @@ static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct k3_dma_dev *d = ofdma->of_dma_data; unsigned int request = dma_spec->args[0]; - if (request > d->dma_requests) + if (request >= d->dma_requests) return NULL; return dma_get_slave_channel(&(d->chans[request].vc.chan)); diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index defcdde4d358..de0957fe9668 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -3033,7 +3033,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pd->src_addr_widths = PL330_DMA_BUSWIDTHS; pd->dst_addr_widths = PL330_DMA_BUSWIDTHS; pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); - pd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + pd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ? 1 : PL330_MAX_BURST); diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c index 9b5ca8691f27..a4a931ddf6f6 100644 --- a/drivers/dma/ti/omap-dma.c +++ b/drivers/dma/ti/omap-dma.c @@ -1485,7 +1485,11 @@ static int omap_dma_probe(struct platform_device *pdev) od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS; od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS; od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); - od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + if (__dma_omap15xx(od->plat->dma_attr)) + od->ddev.residue_granularity = + DMA_RESIDUE_GRANULARITY_DESCRIPTOR; + else + od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */ od->ddev.dev = &pdev->dev; INIT_LIST_HEAD(&od->ddev.channels); diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index dd4edd8f22ce..7fa793672a7a 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -455,8 +455,10 @@ static int altera_cvp_probe(struct pci_dev *pdev, mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name, &altera_cvp_ops, conf); - if (!mgr) - return -ENOMEM; + if (!mgr) { + ret = -ENOMEM; + goto err_unmap; + } pci_set_drvdata(pdev, mgr); diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index d3cf9502e7e7..58faeb1cef63 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node); fwspec.param_count = 2; fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET; - fwspec.param[1] = IRQ_TYPE_NONE; + /* + * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH + * temporarily. Anyway, ->irq_set_type() will override it later. + */ + fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH; return irq_create_fwspec_mapping(&fwspec); } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 28d968088131..53a14ee8ad6d 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np, * Note that active low is the default. */ if (IS_ENABLED(CONFIG_REGULATOR) && - (of_device_is_compatible(np, "reg-fixed-voltage") || + (of_device_is_compatible(np, "regulator-fixed") || + of_device_is_compatible(np, "reg-fixed-voltage") || of_device_is_compatible(np, "regulator-gpio"))) { /* * The regulator GPIO handles are specified such that the diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index f4c474a95875..71efcf38f11b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -57,6 +57,10 @@ #define ACP_I2S_COMP2_CAP_REG_OFFSET 0xa8 #define ACP_I2S_COMP1_PLAY_REG_OFFSET 0x6c #define ACP_I2S_COMP2_PLAY_REG_OFFSET 0x68 +#define ACP_BT_PLAY_REGS_START 0x14970 +#define ACP_BT_PLAY_REGS_END 0x14a24 +#define ACP_BT_COMP1_REG_OFFSET 0xac +#define ACP_BT_COMP2_REG_OFFSET 0xa8 #define mmACP_PGFSM_RETAIN_REG 0x51c9 #define mmACP_PGFSM_CONFIG_REG 0x51ca @@ -77,7 +81,7 @@ #define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE 0x000000FF #define ACP_TIMEOUT_LOOP 0x000000FF -#define ACP_DEVS 3 +#define ACP_DEVS 4 #define ACP_SRC_ID 162 enum { @@ -316,14 +320,13 @@ static int acp_hw_init(void *handle) if (adev->acp.acp_cell == NULL) return -ENOMEM; - adev->acp.acp_res = kcalloc(4, sizeof(struct resource), GFP_KERNEL); - + adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL); if (adev->acp.acp_res == NULL) { kfree(adev->acp.acp_cell); return -ENOMEM; } - i2s_pdata = kcalloc(2, sizeof(struct i2s_platform_data), GFP_KERNEL); + i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL); if (i2s_pdata == NULL) { kfree(adev->acp.acp_res); kfree(adev->acp.acp_cell); @@ -358,6 +361,20 @@ static int acp_hw_init(void *handle) i2s_pdata[1].i2s_reg_comp1 = ACP_I2S_COMP1_CAP_REG_OFFSET; i2s_pdata[1].i2s_reg_comp2 = ACP_I2S_COMP2_CAP_REG_OFFSET; + i2s_pdata[2].quirks = DW_I2S_QUIRK_COMP_REG_OFFSET; + switch (adev->asic_type) { + case CHIP_STONEY: + i2s_pdata[2].quirks |= DW_I2S_QUIRK_16BIT_IDX_OVERRIDE; + break; + default: + break; + } + + i2s_pdata[2].cap = DWC_I2S_PLAY | DWC_I2S_RECORD; + i2s_pdata[2].snd_rates = SNDRV_PCM_RATE_8000_96000; + i2s_pdata[2].i2s_reg_comp1 = ACP_BT_COMP1_REG_OFFSET; + i2s_pdata[2].i2s_reg_comp2 = ACP_BT_COMP2_REG_OFFSET; + adev->acp.acp_res[0].name = "acp2x_dma"; adev->acp.acp_res[0].flags = IORESOURCE_MEM; adev->acp.acp_res[0].start = acp_base; @@ -373,13 +390,18 @@ static int acp_hw_init(void *handle) adev->acp.acp_res[2].start = acp_base + ACP_I2S_CAP_REGS_START; adev->acp.acp_res[2].end = acp_base + ACP_I2S_CAP_REGS_END; - adev->acp.acp_res[3].name = "acp2x_dma_irq"; - adev->acp.acp_res[3].flags = IORESOURCE_IRQ; - adev->acp.acp_res[3].start = amdgpu_irq_create_mapping(adev, 162); - adev->acp.acp_res[3].end = adev->acp.acp_res[3].start; + adev->acp.acp_res[3].name = "acp2x_dw_bt_i2s_play_cap"; + adev->acp.acp_res[3].flags = IORESOURCE_MEM; + adev->acp.acp_res[3].start = acp_base + ACP_BT_PLAY_REGS_START; + adev->acp.acp_res[3].end = acp_base + ACP_BT_PLAY_REGS_END; + + adev->acp.acp_res[4].name = "acp2x_dma_irq"; + adev->acp.acp_res[4].flags = IORESOURCE_IRQ; + adev->acp.acp_res[4].start = amdgpu_irq_create_mapping(adev, 162); + adev->acp.acp_res[4].end = adev->acp.acp_res[4].start; adev->acp.acp_cell[0].name = "acp_audio_dma"; - adev->acp.acp_cell[0].num_resources = 4; + adev->acp.acp_cell[0].num_resources = 5; adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0]; adev->acp.acp_cell[0].platform_data = &adev->asic_type; adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type); @@ -396,6 +418,12 @@ static int acp_hw_init(void *handle) adev->acp.acp_cell[2].platform_data = &i2s_pdata[1]; adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data); + adev->acp.acp_cell[3].name = "designware-i2s"; + adev->acp.acp_cell[3].num_resources = 1; + adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3]; + adev->acp.acp_cell[3].platform_data = &i2s_pdata[2]; + adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data); + r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell, ACP_DEVS); if (r) @@ -451,7 +479,6 @@ static int acp_hw_init(void *handle) val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET); val &= ~ACP_SOFT_RESET__SoftResetAud_MASK; cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index e3ed08dca7b7..f8bbbb3a9504 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -243,6 +243,33 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev) return r; } +int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev) +{ + int r = 0; + + if (adev->kfd) + r = kgd2kfd->pre_reset(adev->kfd); + + return r; +} + +int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev) +{ + int r = 0; + + if (adev->kfd) + r = kgd2kfd->post_reset(adev->kfd); + + return r; +} + +void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)kgd; + + amdgpu_device_gpu_recover(adev, NULL, false); +} + int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, void **cpu_ptr) @@ -461,6 +488,14 @@ err: return ret; } +void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)kgd; + + amdgpu_dpm_switch_power_profile(adev, + PP_SMC_POWER_PROFILE_COMPUTE, !idle); +} + bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid) { if (adev->kfd) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index a8418a3f4e9d..2f379c183ed2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -119,6 +119,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm); int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine, uint32_t vmid, uint64_t gpu_addr, uint32_t *ib_cmd, uint32_t ib_len); +void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle); struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void); struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void); @@ -126,6 +127,12 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void); bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid); +int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev); + +int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev); + +void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd); + /* Shared API */ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, @@ -183,6 +190,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd, int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info, struct dma_fence **ef); +int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd, + struct kfd_vm_fault_info *info); + void amdgpu_amdkfd_gpuvm_init_mem_limits(void); void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index ea79908dac4c..ea3f698aef5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -145,6 +145,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid, uint32_t page_table_base); static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid); static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid); +static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd); /* Because of REG_GET_FIELD() being used, we put this function in the * asic specific file. @@ -216,6 +217,10 @@ static const struct kfd2kgd_calls kfd2kgd = { .invalidate_tlbs = invalidate_tlbs, .invalidate_tlbs_vmid = invalidate_tlbs_vmid, .submit_ib = amdgpu_amdkfd_submit_ib, + .get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info, + .read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg, + .gpu_recover = amdgpu_amdkfd_gpu_reset, + .set_compute_idle = amdgpu_amdkfd_set_compute_idle }; struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void) @@ -571,6 +576,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, unsigned long flags, end_jiffies; int retry; + if (adev->in_gpu_reset) + return -EIO; + acquire_queue(kgd, pipe_id, queue_id); WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, 0); @@ -882,6 +890,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid) int vmid; unsigned int tmp; + if (adev->in_gpu_reset) + return -EIO; + for (vmid = 0; vmid < 16; vmid++) { if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) continue; @@ -911,3 +922,19 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid) RREG32(mmVM_INVALIDATE_RESPONSE); return 0; } + + /** + * read_vmid_from_vmfault_reg - read vmid from register + * + * adev: amdgpu_device pointer + * @vmid: vmid pointer + * read vmid from register (CIK). + */ +static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd) +{ + struct amdgpu_device *adev = get_amdgpu_device(kgd); + + uint32_t status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); + + return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index 19dd665e7307..f6e53e9352bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -176,6 +176,9 @@ static const struct kfd2kgd_calls kfd2kgd = { .invalidate_tlbs = invalidate_tlbs, .invalidate_tlbs_vmid = invalidate_tlbs_vmid, .submit_ib = amdgpu_amdkfd_submit_ib, + .get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info, + .gpu_recover = amdgpu_amdkfd_gpu_reset, + .set_compute_idle = amdgpu_amdkfd_set_compute_idle }; struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void) @@ -568,6 +571,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, int retry; struct vi_mqd *m = get_mqd(mqd); + if (adev->in_gpu_reset) + return -EIO; + acquire_queue(kgd, pipe_id, queue_id); if (m->cp_hqd_vmid == 0) @@ -844,6 +850,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid) int vmid; unsigned int tmp; + if (adev->in_gpu_reset) + return -EIO; + for (vmid = 0; vmid < 16; vmid++) { if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 1db60aa5b7f0..8efedfcb9dfc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -213,6 +213,8 @@ static const struct kfd2kgd_calls kfd2kgd = { .invalidate_tlbs = invalidate_tlbs, .invalidate_tlbs_vmid = invalidate_tlbs_vmid, .submit_ib = amdgpu_amdkfd_submit_ib, + .gpu_recover = amdgpu_amdkfd_gpu_reset, + .set_compute_idle = amdgpu_amdkfd_set_compute_idle }; struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void) @@ -679,6 +681,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, uint32_t temp; struct v9_mqd *m = get_mqd(mqd); + if (adev->in_gpu_reset) + return -EIO; + acquire_queue(kgd, pipe_id, queue_id); if (m->cp_hqd_vmid == 0) @@ -866,6 +871,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid) int vmid; struct amdgpu_ring *ring = &adev->gfx.kiq.ring; + if (adev->in_gpu_reset) + return -EIO; + if (ring->ready) return invalidate_tlbs_with_kiq(adev, pasid); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index fa38a960ce00..8a707d8bbb1c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1621,6 +1621,20 @@ bo_reserve_failed: return ret; } +int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd, + struct kfd_vm_fault_info *mem) +{ + struct amdgpu_device *adev; + + adev = (struct amdgpu_device *)kgd; + if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) { + *mem = *adev->gmc.vm_fault_info; + mb(); + atomic_set(&adev->gmc.vm_fault_info_updated, 0); + } + return 0; +} + /* Evict a userptr BO by stopping the queues if necessary * * Runs in MMU notifier, may be in RECLAIM_FS context. This means it diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index b33f1680c9a3..a028661d9e20 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -575,6 +575,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = { { 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3ef34df8937b..1e66dfd0e39c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2843,6 +2843,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon) if (r) return r; + /* Make sure IB tests flushed */ + flush_delayed_work(&adev->late_init_work); + /* blat the mode back in */ if (fbcon) { if (!amdgpu_device_has_dc_support(adev)) { @@ -3307,6 +3310,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, atomic_inc(&adev->gpu_reset_counter); adev->in_gpu_reset = 1; + /* Block kfd */ + amdgpu_amdkfd_pre_reset(adev); + /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); @@ -3322,7 +3328,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, if (job && job->base.sched == &ring->sched) continue; - drm_sched_hw_job_reset(&ring->sched, &job->base); + drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL); /* after all hw jobs are reset, hw fence is meaningless, so force_completion */ amdgpu_fence_driver_force_completion(ring); @@ -3363,6 +3369,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter)); } + /*unlock kfd */ + 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_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 6cb4948233cb..bb5a47a45790 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -105,6 +105,8 @@ struct amdgpu_gmc { /* protects concurrent invalidation */ spinlock_t invalidate_lock; bool translate_further; + struct kfd_vm_fault_info *vm_fault_info; + atomic_t vm_fault_info_updated; const struct amdgpu_gmc_funcs *gmc_funcs; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 015613b4f98b..ece0ac703e27 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -495,11 +495,12 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev, eaddr = eaddr & ((1 << shift) - 1); flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; + if (vm->root.base.bo->shadow) + flags |= AMDGPU_GEM_CREATE_SHADOW; if (vm->use_cpu_for_update) flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; else - flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS | - AMDGPU_GEM_CREATE_SHADOW); + flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS; /* walk over the address space and allocate the page tables */ for (pt_idx = from; pt_idx <= to; ++pt_idx) { @@ -2616,7 +2617,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; if (vm->use_cpu_for_update) flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - else + else if (vm_context != AMDGPU_VM_CONTEXT_COMPUTE) flags |= AMDGPU_GEM_CREATE_SHADOW; size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level); @@ -2691,8 +2692,7 @@ error_free_sched_entity: * - pasid (old PASID is released, because compute manages its own PASIDs) * * Reinitializes the page directory to reflect the changed ATS - * setting. May leave behind an unused shadow BO for the page - * directory when switching from SDMA updates to CPU updates. + * setting. * * Returns: * 0 for success, -errno for errors. @@ -2742,6 +2742,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->pasid = 0; } + /* Free the shadow bo for compute VM */ + amdgpu_bo_unref(&vm->root.base.bo->shadow); + error: amdgpu_bo_unreserve(vm->root.base.bo); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 10920f0bd85f..36dc367c4b45 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -28,6 +28,7 @@ #include "cik.h" #include "gmc_v7_0.h" #include "amdgpu_ucode.h" +#include "amdgpu_amdkfd.h" #include "bif/bif_4_1_d.h" #include "bif/bif_4_1_sh_mask.h" @@ -1078,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle) adev->vm_manager.vram_base_offset = 0; } + adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info), + GFP_KERNEL); + if (!adev->gmc.vm_fault_info) + return -ENOMEM; + atomic_set(&adev->gmc.vm_fault_info_updated, 0); + return 0; } @@ -1087,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); + kfree(adev->gmc.vm_fault_info); gmc_v7_0_gart_fini(adev); amdgpu_bo_fini(adev); release_firmware(adev->gmc.fw); @@ -1276,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - u32 addr, status, mc_client; + u32 addr, status, mc_client, vmid; addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR); status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS); @@ -1301,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev, entry->pasid); } + vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, + VMID); + if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid) + && !atomic_read(&adev->gmc.vm_fault_info_updated)) { + struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info; + u32 protections = REG_GET_FIELD(status, + VM_CONTEXT1_PROTECTION_FAULT_STATUS, + PROTECTIONS); + + info->vmid = vmid; + info->mc_id = REG_GET_FIELD(status, + VM_CONTEXT1_PROTECTION_FAULT_STATUS, + MEMORY_CLIENT_ID); + info->status = status; + info->page_addr = addr; + info->prot_valid = protections & 0x7 ? true : false; + info->prot_read = protections & 0x8 ? true : false; + info->prot_write = protections & 0x10 ? true : false; + info->prot_exec = protections & 0x20 ? true : false; + mb(); + atomic_set(&adev->gmc.vm_fault_info_updated, 1); + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 75f3ffb2891e..70fc97b59b4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -26,6 +26,7 @@ #include "amdgpu.h" #include "gmc_v8_0.h" #include "amdgpu_ucode.h" +#include "amdgpu_amdkfd.h" #include "gmc/gmc_8_1_d.h" #include "gmc/gmc_8_1_sh_mask.h" @@ -1182,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle) adev->vm_manager.vram_base_offset = 0; } + adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info), + GFP_KERNEL); + if (!adev->gmc.vm_fault_info) + return -ENOMEM; + atomic_set(&adev->gmc.vm_fault_info_updated, 0); + return 0; } @@ -1191,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); + kfree(adev->gmc.vm_fault_info); gmc_v8_0_gart_fini(adev); amdgpu_bo_fini(adev); release_firmware(adev->gmc.fw); @@ -1426,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - u32 addr, status, mc_client; + u32 addr, status, mc_client, vmid; if (amdgpu_sriov_vf(adev)) { dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", @@ -1463,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, entry->pasid); } + vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, + VMID); + if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid) + && !atomic_read(&adev->gmc.vm_fault_info_updated)) { + struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info; + u32 protections = REG_GET_FIELD(status, + VM_CONTEXT1_PROTECTION_FAULT_STATUS, + PROTECTIONS); + + info->vmid = vmid; + info->mc_id = REG_GET_FIELD(status, + VM_CONTEXT1_PROTECTION_FAULT_STATUS, + MEMORY_CLIENT_ID); + info->status = status; + info->page_addr = addr; + info->prot_valid = protections & 0x7 ? true : false; + info->prot_read = protections & 0x8 ? true : false; + info->prot_write = protections & 0x10 ? true : false; + info->prot_exec = protections & 0x20 ? true : false; + mb(); + atomic_set(&adev->gmc.vm_fault_info_updated, 1); + } + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c index 49df6c791cfc..5d2475d5392c 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c @@ -25,12 +25,39 @@ #include "cik_int.h" static bool cik_event_interrupt_isr(struct kfd_dev *dev, - const uint32_t *ih_ring_entry) + const uint32_t *ih_ring_entry, + uint32_t *patched_ihre, + bool *patched_flag) { const struct cik_ih_ring_entry *ihre = (const struct cik_ih_ring_entry *)ih_ring_entry; + const struct kfd2kgd_calls *f2g = dev->kfd2kgd; unsigned int vmid, pasid; + /* This workaround is due to HW/FW limitation on Hawaii that + * VMID and PASID are not written into ih_ring_entry + */ + if ((ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT || + ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) && + dev->device_info->asic_family == CHIP_HAWAII) { + struct cik_ih_ring_entry *tmp_ihre = + (struct cik_ih_ring_entry *)patched_ihre; + + *patched_flag = true; + *tmp_ihre = *ihre; + + vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd); + pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid); + + tmp_ihre->ring_id &= 0x000000ff; + tmp_ihre->ring_id |= vmid << 8; + tmp_ihre->ring_id |= pasid << 16; + + return (pasid != 0) && + vmid >= dev->vm_info.first_vmid_kfd && + vmid <= dev->vm_info.last_vmid_kfd; + } + /* Only handle interrupts from KFD VMIDs */ vmid = (ihre->ring_id & 0x0000ff00) >> 8; if (vmid < dev->vm_info.first_vmid_kfd || @@ -48,18 +75,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev, return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE || ihre->source_id == CIK_INTSRC_SDMA_TRAP || ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG || - ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE; + ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE || + ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT || + ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT; } static void cik_event_interrupt_wq(struct kfd_dev *dev, const uint32_t *ih_ring_entry) { - unsigned int pasid; const struct cik_ih_ring_entry *ihre = (const struct cik_ih_ring_entry *)ih_ring_entry; uint32_t context_id = ihre->data & 0xfffffff; - - pasid = (ihre->ring_id & 0xffff0000) >> 16; + unsigned int vmid = (ihre->ring_id & 0x0000ff00) >> 8; + unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16; if (pasid == 0) return; @@ -72,6 +100,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev, kfd_signal_event_interrupt(pasid, context_id & 0xff, 8); else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE) kfd_signal_hw_exception_event(pasid); + else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT || + ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) { + struct kfd_vm_fault_info info; + + kfd_process_vm_fault(dev->dqm, pasid); + + memset(&info, 0, sizeof(info)); + dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info); + if (!info.page_addr && !info.status) + return; + + if (info.vmid == vmid) + kfd_signal_vm_fault_event(dev, pasid, &info); + else + kfd_signal_vm_fault_event(dev, pasid, NULL); + } } const struct kfd_event_interrupt_class event_interrupt_class_cik = { diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h index 109298b9d507..76f8677a7926 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_int.h +++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h @@ -20,8 +20,8 @@ * OTHER DEALINGS IN THE SOFTWARE. */ -#ifndef HSA_RADEON_CIK_INT_H_INCLUDED -#define HSA_RADEON_CIK_INT_H_INCLUDED +#ifndef CIK_INT_H_INCLUDED +#define CIK_INT_H_INCLUDED #include <linux/types.h> @@ -34,9 +34,10 @@ struct cik_ih_ring_entry { #define CIK_INTSRC_CP_END_OF_PIPE 0xB5 #define CIK_INTSRC_CP_BAD_OPCODE 0xB7 -#define CIK_INTSRC_DEQUEUE_COMPLETE 0xC6 #define CIK_INTSRC_SDMA_TRAP 0xE0 #define CIK_INTSRC_SQ_INTERRUPT_MSG 0xEF +#define CIK_INTSRC_GFX_PAGE_INV_FAULT 0x92 +#define CIK_INTSRC_GFX_MEM_PROT_FAULT 0x93 #endif diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index f68aef02fc1f..3621efbd5759 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -21,18 +21,21 @@ */ static const uint32_t cwsr_trap_gfx8_hex[] = { - 0xbf820001, 0xbf820125, + 0xbf820001, 0xbf82012b, 0xb8f4f802, 0x89748674, 0xb8f5f803, 0x8675ff75, - 0x00000400, 0xbf850011, + 0x00000400, 0xbf850017, 0xc00a1e37, 0x00000000, 0xbf8c007f, 0x87777978, - 0xbf840002, 0xb974f802, - 0xbe801d78, 0xb8f5f803, - 0x8675ff75, 0x000001ff, - 0xbf850002, 0x80708470, - 0x82718071, 0x8671ff71, - 0x0000ffff, 0xb974f802, + 0xbf840005, 0x8f728374, + 0xb972e0c2, 0xbf800002, + 0xb9740002, 0xbe801d78, + 0xb8f5f803, 0x8675ff75, + 0x000001ff, 0xbf850002, + 0x80708470, 0x82718071, + 0x8671ff71, 0x0000ffff, + 0x8f728374, 0xb972e0c2, + 0xbf800002, 0xb9740002, 0xbe801f70, 0xb8f5f803, 0x8675ff75, 0x00000100, 0xbf840006, 0xbefa0080, @@ -168,7 +171,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = { 0x807c847c, 0x806eff6e, 0x00000400, 0xbf0a757c, 0xbf85ffef, 0xbf9c0000, - 0xbf8200ca, 0xbef8007e, + 0xbf8200cd, 0xbef8007e, 0x8679ff7f, 0x0000ffff, 0x8779ff79, 0x00040000, 0xbefa0080, 0xbefb00ff, @@ -268,16 +271,18 @@ static const uint32_t cwsr_trap_gfx8_hex[] = { 0x8f739773, 0xb976f807, 0x8671ff71, 0x0000ffff, 0x86fe7e7e, 0x86ea6a6a, - 0xb974f802, 0xbf8a0000, - 0x95807370, 0xbf810000, + 0x8f768374, 0xb976e0c2, + 0xbf800002, 0xb9740002, + 0xbf8a0000, 0x95807370, + 0xbf810000, 0x00000000, }; static const uint32_t cwsr_trap_gfx9_hex[] = { - 0xbf820001, 0xbf82015a, + 0xbf820001, 0xbf82015d, 0xb8f8f802, 0x89788678, 0xb8f1f803, 0x866eff71, - 0x00000400, 0xbf850034, + 0x00000400, 0xbf850037, 0x866eff71, 0x00000800, 0xbf850003, 0x866eff71, 0x00000100, 0xbf840008, @@ -303,258 +308,261 @@ static const uint32_t cwsr_trap_gfx9_hex[] = { 0x8f6e8b77, 0x866eff6e, 0x001f8000, 0xb96ef807, 0x86fe7e7e, 0x86ea6a6a, - 0xb978f802, 0xbe801f6c, - 0x866dff6d, 0x0000ffff, - 0xbef00080, 0xb9700283, - 0xb8f02407, 0x8e709c70, - 0x876d706d, 0xb8f003c7, - 0x8e709b70, 0x876d706d, - 0xb8f0f807, 0x8670ff70, - 0x00007fff, 0xb970f807, - 0xbeee007e, 0xbeef007f, - 0xbefe0180, 0xbf900004, - 0x87708478, 0xb970f802, - 0xbf8e0002, 0xbf88fffe, - 0xb8f02a05, 0x80708170, - 0x8e708a70, 0xb8f11605, - 0x80718171, 0x8e718671, - 0x80707170, 0x80707e70, - 0x8271807f, 0x8671ff71, - 0x0000ffff, 0xc0471cb8, - 0x00000040, 0xbf8cc07f, - 0xc04b1d38, 0x00000048, - 0xbf8cc07f, 0xc0431e78, - 0x00000058, 0xbf8cc07f, - 0xc0471eb8, 0x0000005c, - 0xbf8cc07f, 0xbef4007e, - 0x8675ff7f, 0x0000ffff, - 0x8775ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x00807fac, 0x8670ff7f, - 0x08000000, 0x8f708370, - 0x87777077, 0x8670ff7f, - 0x70000000, 0x8f708170, - 0x87777077, 0xbefb007c, - 0xbefa0080, 0xb8fa2a05, - 0x807a817a, 0x8e7a8a7a, - 0xb8f01605, 0x80708170, - 0x8e708670, 0x807a707a, - 0xbef60084, 0xbef600ff, - 0x01000000, 0xbefe007c, - 0xbefc007a, 0xc0611efa, - 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, + 0x8f6e8378, 0xb96ee0c2, + 0xbf800002, 0xb9780002, + 0xbe801f6c, 0x866dff6d, + 0x0000ffff, 0xbef00080, + 0xb9700283, 0xb8f02407, + 0x8e709c70, 0x876d706d, + 0xb8f003c7, 0x8e709b70, + 0x876d706d, 0xb8f0f807, + 0x8670ff70, 0x00007fff, + 0xb970f807, 0xbeee007e, + 0xbeef007f, 0xbefe0180, + 0xbf900004, 0x87708478, + 0xb970f802, 0xbf8e0002, + 0xbf88fffe, 0xb8f02a05, + 0x80708170, 0x8e708a70, + 0xb8f11605, 0x80718171, + 0x8e718671, 0x80707170, + 0x80707e70, 0x8271807f, + 0x8671ff71, 0x0000ffff, + 0xc0471cb8, 0x00000040, + 0xbf8cc07f, 0xc04b1d38, + 0x00000048, 0xbf8cc07f, + 0xc0431e78, 0x00000058, + 0xbf8cc07f, 0xc0471eb8, + 0x0000005c, 0xbf8cc07f, + 0xbef4007e, 0x8675ff7f, + 0x0000ffff, 0x8775ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x00807fac, + 0x8670ff7f, 0x08000000, + 0x8f708370, 0x87777077, + 0x8670ff7f, 0x70000000, + 0x8f708170, 0x87777077, + 0xbefb007c, 0xbefa0080, + 0xb8fa2a05, 0x807a817a, + 0x8e7a8a7a, 0xb8f01605, + 0x80708170, 0x8e708670, + 0x807a707a, 0xbef60084, + 0xbef600ff, 0x01000000, 0xbefe007c, 0xbefc007a, - 0xc0611b3a, 0x0000007c, + 0xc0611efa, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611b7a, + 0xbefc007a, 0xc0611b3a, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, 0xbefc007a, - 0xc0611bba, 0x0000007c, + 0xc0611b7a, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611bfa, + 0xbefc007a, 0xc0611bba, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, 0xbefc007a, - 0xc0611e3a, 0x0000007c, - 0xbf8cc07f, 0x807a847a, - 0xbefc007e, 0xb8f1f803, - 0xbefe007c, 0xbefc007a, - 0xc0611c7a, 0x0000007c, + 0xc0611bfa, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611a3a, + 0xbefc007a, 0xc0611e3a, + 0x0000007c, 0xbf8cc07f, + 0x807a847a, 0xbefc007e, + 0xb8f1f803, 0xbefe007c, + 0xbefc007a, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, 0x807a847a, 0xbefc007e, 0xbefe007c, 0xbefc007a, - 0xc0611a7a, 0x0000007c, - 0xbf8cc07f, 0x807a847a, - 0xbefc007e, 0xb8fbf801, - 0xbefe007c, 0xbefc007a, - 0xc0611efa, 0x0000007c, + 0xc0611a3a, 0x0000007c, 0xbf8cc07f, 0x807a847a, - 0xbefc007e, 0x8670ff7f, - 0x04000000, 0xbeef0080, - 0x876f6f70, 0xb8fa2a05, + 0xbefc007e, 0xbefe007c, + 0xbefc007a, 0xc0611a7a, + 0x0000007c, 0xbf8cc07f, + 0x807a847a, 0xbefc007e, + 0xb8fbf801, 0xbefe007c, + 0xbefc007a, 0xc0611efa, + 0x0000007c, 0xbf8cc07f, + 0x807a847a, 0xbefc007e, + 0x8670ff7f, 0x04000000, + 0xbeef0080, 0x876f6f70, + 0xb8fa2a05, 0x807a817a, + 0x8e7a8a7a, 0xb8f11605, + 0x80718171, 0x8e718471, + 0x8e768271, 0xbef600ff, + 0x01000000, 0xbef20174, + 0x80747a74, 0x82758075, + 0xbefc0080, 0xbf800000, + 0xbe802b00, 0xbe822b02, + 0xbe842b04, 0xbe862b06, + 0xbe882b08, 0xbe8a2b0a, + 0xbe8c2b0c, 0xbe8e2b0e, + 0xc06b003a, 0x00000000, + 0xbf8cc07f, 0xc06b013a, + 0x00000010, 0xbf8cc07f, + 0xc06b023a, 0x00000020, + 0xbf8cc07f, 0xc06b033a, + 0x00000030, 0xbf8cc07f, + 0x8074c074, 0x82758075, + 0x807c907c, 0xbf0a717c, + 0xbf85ffe7, 0xbef40172, + 0xbefa0080, 0xbefe00c1, + 0xbeff00c1, 0xbee80080, + 0xbee90080, 0xbef600ff, + 0x01000000, 0xe0724000, + 0x7a1d0000, 0xe0724100, + 0x7a1d0100, 0xe0724200, + 0x7a1d0200, 0xe0724300, + 0x7a1d0300, 0xbefe00c1, + 0xbeff00c1, 0xb8f14306, + 0x8671c171, 0xbf84002c, + 0xbf8a0000, 0x8670ff6f, + 0x04000000, 0xbf840028, + 0x8e718671, 0x8e718271, + 0xbef60071, 0xb8fa2a05, 0x807a817a, 0x8e7a8a7a, - 0xb8f11605, 0x80718171, - 0x8e718471, 0x8e768271, + 0xb8f01605, 0x80708170, + 0x8e708670, 0x807a707a, + 0x807aff7a, 0x00000080, 0xbef600ff, 0x01000000, - 0xbef20174, 0x80747a74, - 0x82758075, 0xbefc0080, - 0xbf800000, 0xbe802b00, - 0xbe822b02, 0xbe842b04, - 0xbe862b06, 0xbe882b08, - 0xbe8a2b0a, 0xbe8c2b0c, - 0xbe8e2b0e, 0xc06b003a, - 0x00000000, 0xbf8cc07f, - 0xc06b013a, 0x00000010, - 0xbf8cc07f, 0xc06b023a, - 0x00000020, 0xbf8cc07f, - 0xc06b033a, 0x00000030, - 0xbf8cc07f, 0x8074c074, - 0x82758075, 0x807c907c, - 0xbf0a717c, 0xbf85ffe7, - 0xbef40172, 0xbefa0080, + 0xbefc0080, 0xd28c0002, + 0x000100c1, 0xd28d0003, + 0x000204c1, 0xd1060002, + 0x00011103, 0x7e0602ff, + 0x00000200, 0xbefc00ff, + 0x00010000, 0xbe800077, + 0x8677ff77, 0xff7fffff, + 0x8777ff77, 0x00058000, + 0xd8ec0000, 0x00000002, + 0xbf8cc07f, 0xe0765000, + 0x7a1d0002, 0x68040702, + 0xd0c9006a, 0x0000e302, + 0xbf87fff7, 0xbef70000, + 0xbefa00ff, 0x00000400, 0xbefe00c1, 0xbeff00c1, - 0xbee80080, 0xbee90080, + 0xb8f12a05, 0x80718171, + 0x8e718271, 0x8e768871, 0xbef600ff, 0x01000000, + 0xbefc0084, 0xbf0a717c, + 0xbf840015, 0xbf11017c, + 0x8071ff71, 0x00001000, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, 0xe0724000, 0x7a1d0000, 0xe0724100, 0x7a1d0100, 0xe0724200, 0x7a1d0200, 0xe0724300, 0x7a1d0300, + 0x807c847c, 0x807aff7a, + 0x00000400, 0xbf0a717c, + 0xbf85ffef, 0xbf9c0000, + 0xbf8200dc, 0xbef4007e, + 0x8675ff7f, 0x0000ffff, + 0x8775ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x00807fac, 0x866eff7f, + 0x08000000, 0x8f6e836e, + 0x87776e77, 0x866eff7f, + 0x70000000, 0x8f6e816e, + 0x87776e77, 0x866eff7f, + 0x04000000, 0xbf84001e, 0xbefe00c1, 0xbeff00c1, - 0xb8f14306, 0x8671c171, - 0xbf84002c, 0xbf8a0000, - 0x8670ff6f, 0x04000000, - 0xbf840028, 0x8e718671, - 0x8e718271, 0xbef60071, - 0xb8fa2a05, 0x807a817a, - 0x8e7a8a7a, 0xb8f01605, - 0x80708170, 0x8e708670, - 0x807a707a, 0x807aff7a, + 0xb8ef4306, 0x866fc16f, + 0xbf840019, 0x8e6f866f, + 0x8e6f826f, 0xbef6006f, + 0xb8f82a05, 0x80788178, + 0x8e788a78, 0xb8ee1605, + 0x806e816e, 0x8e6e866e, + 0x80786e78, 0x8078ff78, 0x00000080, 0xbef600ff, 0x01000000, 0xbefc0080, - 0xd28c0002, 0x000100c1, - 0xd28d0003, 0x000204c1, - 0xd1060002, 0x00011103, - 0x7e0602ff, 0x00000200, - 0xbefc00ff, 0x00010000, - 0xbe800077, 0x8677ff77, - 0xff7fffff, 0x8777ff77, - 0x00058000, 0xd8ec0000, - 0x00000002, 0xbf8cc07f, - 0xe0765000, 0x7a1d0002, - 0x68040702, 0xd0c9006a, - 0x0000e302, 0xbf87fff7, - 0xbef70000, 0xbefa00ff, - 0x00000400, 0xbefe00c1, - 0xbeff00c1, 0xb8f12a05, - 0x80718171, 0x8e718271, - 0x8e768871, 0xbef600ff, - 0x01000000, 0xbefc0084, - 0xbf0a717c, 0xbf840015, - 0xbf11017c, 0x8071ff71, - 0x00001000, 0x7e000300, + 0xe0510000, 0x781d0000, + 0xe0510100, 0x781d0000, + 0x807cff7c, 0x00000200, + 0x8078ff78, 0x00000200, + 0xbf0a6f7c, 0xbf85fff6, + 0xbef80080, 0xbefe00c1, + 0xbeff00c1, 0xb8ef2a05, + 0x806f816f, 0x8e6f826f, + 0x8e76886f, 0xbef600ff, + 0x01000000, 0xbeee0078, + 0x8078ff78, 0x00000400, + 0xbefc0084, 0xbf11087c, + 0x806fff6f, 0x00008000, + 0xe0524000, 0x781d0000, + 0xe0524100, 0x781d0100, + 0xe0524200, 0x781d0200, + 0xe0524300, 0x781d0300, + 0xbf8c0f70, 0x7e000300, 0x7e020301, 0x7e040302, - 0x7e060303, 0xe0724000, - 0x7a1d0000, 0xe0724100, - 0x7a1d0100, 0xe0724200, - 0x7a1d0200, 0xe0724300, - 0x7a1d0300, 0x807c847c, - 0x807aff7a, 0x00000400, - 0xbf0a717c, 0xbf85ffef, - 0xbf9c0000, 0xbf8200d9, - 0xbef4007e, 0x8675ff7f, - 0x0000ffff, 0x8775ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x00807fac, - 0x866eff7f, 0x08000000, - 0x8f6e836e, 0x87776e77, - 0x866eff7f, 0x70000000, - 0x8f6e816e, 0x87776e77, - 0x866eff7f, 0x04000000, - 0xbf84001e, 0xbefe00c1, - 0xbeff00c1, 0xb8ef4306, - 0x866fc16f, 0xbf840019, - 0x8e6f866f, 0x8e6f826f, - 0xbef6006f, 0xb8f82a05, + 0x7e060303, 0x807c847c, + 0x8078ff78, 0x00000400, + 0xbf0a6f7c, 0xbf85ffee, + 0xbf9c0000, 0xe0524000, + 0x6e1d0000, 0xe0524100, + 0x6e1d0100, 0xe0524200, + 0x6e1d0200, 0xe0524300, + 0x6e1d0300, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, 0x80786e78, - 0x8078ff78, 0x00000080, - 0xbef600ff, 0x01000000, - 0xbefc0080, 0xe0510000, - 0x781d0000, 0xe0510100, - 0x781d0000, 0x807cff7c, - 0x00000200, 0x8078ff78, - 0x00000200, 0xbf0a6f7c, - 0xbf85fff6, 0xbef80080, - 0xbefe00c1, 0xbeff00c1, - 0xb8ef2a05, 0x806f816f, - 0x8e6f826f, 0x8e76886f, - 0xbef600ff, 0x01000000, - 0xbeee0078, 0x8078ff78, - 0x00000400, 0xbefc0084, - 0xbf11087c, 0x806fff6f, - 0x00008000, 0xe0524000, - 0x781d0000, 0xe0524100, - 0x781d0100, 0xe0524200, - 0x781d0200, 0xe0524300, - 0x781d0300, 0xbf8c0f70, - 0x7e000300, 0x7e020301, - 0x7e040302, 0x7e060303, - 0x807c847c, 0x8078ff78, - 0x00000400, 0xbf0a6f7c, - 0xbf85ffee, 0xbf9c0000, - 0xe0524000, 0x6e1d0000, - 0xe0524100, 0x6e1d0100, - 0xe0524200, 0x6e1d0200, - 0xe0524300, 0x6e1d0300, + 0x80f8c078, 0xb8ef1605, + 0x806f816f, 0x8e6f846f, + 0x8e76826f, 0xbef600ff, + 0x01000000, 0xbefc006f, + 0xc031003a, 0x00000078, + 0x80f8c078, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe802d00, 0xbe822d02, + 0xbe842d04, 0xbe862d06, + 0xbe882d08, 0xbe8a2d0a, + 0xbe8c2d0c, 0xbe8e2d0e, + 0xbf06807c, 0xbf84fff0, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x80f8c078, - 0xb8ef1605, 0x806f816f, - 0x8e6f846f, 0x8e76826f, + 0x80786e78, 0xbef60084, 0xbef600ff, 0x01000000, - 0xbefc006f, 0xc031003a, - 0x00000078, 0x80f8c078, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe802d00, - 0xbe822d02, 0xbe842d04, - 0xbe862d06, 0xbe882d08, - 0xbe8a2d0a, 0xbe8c2d0c, - 0xbe8e2d0e, 0xbf06807c, - 0xbf84fff0, 0xb8f82a05, - 0x80788178, 0x8e788a78, - 0xb8ee1605, 0x806e816e, - 0x8e6e866e, 0x80786e78, - 0xbef60084, 0xbef600ff, - 0x01000000, 0xc0211bfa, + 0xc0211bfa, 0x00000078, + 0x80788478, 0xc0211b3a, 0x00000078, 0x80788478, - 0xc0211b3a, 0x00000078, - 0x80788478, 0xc0211b7a, + 0xc0211b7a, 0x00000078, + 0x80788478, 0xc0211eba, 0x00000078, 0x80788478, - 0xc0211eba, 0x00000078, - 0x80788478, 0xc0211efa, + 0xc0211efa, 0x00000078, + 0x80788478, 0xc0211c3a, 0x00000078, 0x80788478, - 0xc0211c3a, 0x00000078, - 0x80788478, 0xc0211c7a, + 0xc0211c7a, 0x00000078, + 0x80788478, 0xc0211a3a, 0x00000078, 0x80788478, - 0xc0211a3a, 0x00000078, - 0x80788478, 0xc0211a7a, + 0xc0211a7a, 0x00000078, + 0x80788478, 0xc0211cfa, 0x00000078, 0x80788478, - 0xc0211cfa, 0x00000078, - 0x80788478, 0xbf8cc07f, - 0xbefc006f, 0xbefe007a, - 0xbeff007b, 0x866f71ff, - 0x000003ff, 0xb96f4803, - 0x866f71ff, 0xfffff800, - 0x8f6f8b6f, 0xb96fa2c3, - 0xb973f801, 0xb8ee2a05, - 0x806e816e, 0x8e6e8a6e, - 0xb8ef1605, 0x806f816f, - 0x8e6f866f, 0x806e6f6e, - 0x806e746e, 0x826f8075, - 0x866fff6f, 0x0000ffff, - 0xc0071cb7, 0x00000040, - 0xc00b1d37, 0x00000048, - 0xc0031e77, 0x00000058, - 0xc0071eb7, 0x0000005c, - 0xbf8cc07f, 0x866fff6d, - 0xf0000000, 0x8f6f9c6f, - 0x8e6f906f, 0xbeee0080, - 0x876e6f6e, 0x866fff6d, - 0x08000000, 0x8f6f9b6f, - 0x8e6f8f6f, 0x876e6f6e, - 0x866fff70, 0x00800000, - 0x8f6f976f, 0xb96ef807, - 0x866dff6d, 0x0000ffff, - 0x86fe7e7e, 0x86ea6a6a, - 0xb970f802, 0xbf8a0000, + 0xbf8cc07f, 0xbefc006f, + 0xbefe007a, 0xbeff007b, + 0x866f71ff, 0x000003ff, + 0xb96f4803, 0x866f71ff, + 0xfffff800, 0x8f6f8b6f, + 0xb96fa2c3, 0xb973f801, + 0xb8ee2a05, 0x806e816e, + 0x8e6e8a6e, 0xb8ef1605, + 0x806f816f, 0x8e6f866f, + 0x806e6f6e, 0x806e746e, + 0x826f8075, 0x866fff6f, + 0x0000ffff, 0xc0071cb7, + 0x00000040, 0xc00b1d37, + 0x00000048, 0xc0031e77, + 0x00000058, 0xc0071eb7, + 0x0000005c, 0xbf8cc07f, + 0x866fff6d, 0xf0000000, + 0x8f6f9c6f, 0x8e6f906f, + 0xbeee0080, 0x876e6f6e, + 0x866fff6d, 0x08000000, + 0x8f6f9b6f, 0x8e6f8f6f, + 0x876e6f6e, 0x866fff70, + 0x00800000, 0x8f6f976f, + 0xb96ef807, 0x866dff6d, + 0x0000ffff, 0x86fe7e7e, + 0x86ea6a6a, 0x8f6e8370, + 0xb96ee0c2, 0xbf800002, + 0xb9700002, 0xbf8a0000, 0x95806f6c, 0xbf810000, }; diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm index a2a04bb64096..abe1a5da29fb 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm @@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_SHIFT = 23 var SQ_WAVE_STATUS_INST_ATC_MASK = 0x00800000 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT = 1 var SQ_WAVE_STATUS_SPI_PRIO_MASK = 0x00000006 +var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT = 0 +var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE = 1 +var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT = 3 +var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE = 29 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT = 12 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE = 9 @@ -251,7 +255,7 @@ if (!EMU_RUN_HACK) s_waitcnt lgkmcnt(0) s_or_b32 ttmp7, ttmp8, ttmp9 s_cbranch_scc0 L_NO_NEXT_TRAP //next level trap handler not been set - s_setreg_b32 hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC) + set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC) s_setpc_b64 [ttmp8,ttmp9] //jump to next level trap handler L_NO_NEXT_TRAP: @@ -262,7 +266,7 @@ L_NO_NEXT_TRAP: s_addc_u32 ttmp1, ttmp1, 0 L_EXCP_CASE: s_and_b32 ttmp1, ttmp1, 0xFFFF - s_setreg_b32 hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC) + set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC) s_rfe_b64 [ttmp0, ttmp1] end // ********* End handling of non-CWSR traps ******************* @@ -1053,7 +1057,7 @@ end s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff //pc[47:32] //Do it here in order not to affect STATUS s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 - s_setreg_b32 hwreg(HW_REG_STATUS), s_restore_status // SCC is included, which is changed by previous salu + set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu s_barrier //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time @@ -1134,3 +1138,11 @@ end function get_hwreg_size_bytes return 128 //HWREG size 128 bytes end + +function set_status_without_spi_prio(status, tmp) + // Do not restore STATUS.SPI_PRIO since scheduler may have raised it. + s_lshr_b32 tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT + s_setreg_b32 hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp + s_nop 0x2 // avoid S_SETREG => S_SETREG hazard + s_setreg_b32 hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status +end diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm index 998be96be736..0bb9c577b3a2 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm @@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_MASK = 0x00800000 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT = 1 var SQ_WAVE_STATUS_SPI_PRIO_MASK = 0x00000006 var SQ_WAVE_STATUS_HALT_MASK = 0x2000 +var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT = 0 +var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE = 1 +var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT = 3 +var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE = 29 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT = 12 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE = 9 @@ -317,7 +321,7 @@ L_EXCP_CASE: // Restore SQ_WAVE_STATUS. s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 - s_setreg_b32 hwreg(HW_REG_STATUS), s_save_status + set_status_without_spi_prio(s_save_status, ttmp2) s_rfe_b64 [ttmp0, ttmp1] end @@ -1120,7 +1124,7 @@ end s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff //pc[47:32] //Do it here in order not to affect STATUS s_and_b64 exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32 s_and_b64 vcc, vcc, vcc // Restore STATUS.VCCZ, not writable by s_setreg_b32 - s_setreg_b32 hwreg(HW_REG_STATUS), s_restore_status // SCC is included, which is changed by previous salu + set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu s_barrier //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time @@ -1212,3 +1216,11 @@ function ack_sqc_store_workaround s_waitcnt lgkmcnt(0) end end + +function set_status_without_spi_prio(status, tmp) + // Do not restore STATUS.SPI_PRIO since scheduler may have raised it. + s_lshr_b32 tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT + s_setreg_b32 hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp + s_nop 0x2 // avoid S_SETREG => S_SETREG hazard + s_setreg_b32 hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status +end diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f64c5551cdba..297b36c26a05 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -122,6 +122,9 @@ static int kfd_open(struct inode *inode, struct file *filep) if (IS_ERR(process)) return PTR_ERR(process); + if (kfd_is_locked()) + return -EAGAIN; + dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n", process->pasid, process->is_32bit_user_mode); @@ -389,6 +392,61 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p, return retval; } +static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p, + void *data) +{ + int retval; + const int max_num_cus = 1024; + struct kfd_ioctl_set_cu_mask_args *args = data; + struct queue_properties properties; + uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr; + size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32); + + if ((args->num_cu_mask % 32) != 0) { + pr_debug("num_cu_mask 0x%x must be a multiple of 32", + args->num_cu_mask); + return -EINVAL; + } + + properties.cu_mask_count = args->num_cu_mask; + if (properties.cu_mask_count == 0) { + pr_debug("CU mask cannot be 0"); + return -EINVAL; + } + + /* To prevent an unreasonably large CU mask size, set an arbitrary + * limit of max_num_cus bits. We can then just drop any CU mask bits + * past max_num_cus bits and just use the first max_num_cus bits. + */ + if (properties.cu_mask_count > max_num_cus) { + pr_debug("CU mask cannot be greater than 1024 bits"); + properties.cu_mask_count = max_num_cus; + cu_mask_size = sizeof(uint32_t) * (max_num_cus/32); + } + + properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL); + if (!properties.cu_mask) + return -ENOMEM; + + retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size); + if (retval) { + pr_debug("Could not copy CU mask from userspace"); + kfree(properties.cu_mask); + return -EFAULT; + } + + mutex_lock(&p->mutex); + + retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties); + + mutex_unlock(&p->mutex); + + if (retval) + kfree(properties.cu_mask); + + return retval; +} + static int kfd_ioctl_set_memory_policy(struct file *filep, struct kfd_process *p, void *data) { @@ -754,7 +812,6 @@ static int kfd_ioctl_get_clock_counters(struct file *filep, { struct kfd_ioctl_get_clock_counters_args *args = data; struct kfd_dev *dev; - struct timespec64 time; dev = kfd_device_by_id(args->gpu_id); if (dev) @@ -766,11 +823,8 @@ static int kfd_ioctl_get_clock_counters(struct file *filep, args->gpu_clock_counter = 0; /* No access to rdtsc. Using raw monotonic time */ - getrawmonotonic64(&time); - args->cpu_clock_counter = (uint64_t)timespec64_to_ns(&time); - - get_monotonic_boottime64(&time); - args->system_clock_counter = (uint64_t)timespec64_to_ns(&time); + args->cpu_clock_counter = ktime_get_raw_ns(); + args->system_clock_counter = ktime_get_boot_ns(); /* Since the counter is in nano-seconds we use 1GHz frequency */ args->system_clock_freq = 1000000000; @@ -1558,6 +1612,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU, kfd_ioctl_unmap_memory_from_gpu, 0), + AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_CU_MASK, + kfd_ioctl_set_cu_mask, 0), + }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 296b3f230280..ee4996029a86 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu, return 0; } +static struct kfd_mem_properties * +find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width, + struct kfd_topology_device *dev) +{ + struct kfd_mem_properties *props; + + list_for_each_entry(props, &dev->mem_props, list) { + if (props->heap_type == heap_type + && props->flags == flags + && props->width == width) + return props; + } + + return NULL; +} /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct * topology device present in the device_list */ @@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem, { struct kfd_mem_properties *props; struct kfd_topology_device *dev; + uint32_t heap_type; + uint64_t size_in_bytes; + uint32_t flags = 0; + uint32_t width; pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n", mem->proximity_domain); list_for_each_entry(dev, device_list, list) { if (mem->proximity_domain == dev->proximity_domain) { - props = kfd_alloc_struct(props); - if (!props) - return -ENOMEM; - /* We're on GPU node */ if (dev->node_props.cpu_cores_count == 0) { /* APU */ if (mem->visibility_type == 0) - props->heap_type = + heap_type = HSA_MEM_HEAP_TYPE_FB_PRIVATE; /* dGPU */ else - props->heap_type = mem->visibility_type; + heap_type = mem->visibility_type; } else - props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM; + heap_type = HSA_MEM_HEAP_TYPE_SYSTEM; if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE) - props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE; + flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE; if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE) - props->flags |= HSA_MEM_FLAGS_NON_VOLATILE; + flags |= HSA_MEM_FLAGS_NON_VOLATILE; - props->size_in_bytes = + size_in_bytes = ((uint64_t)mem->length_high << 32) + mem->length_low; - props->width = mem->width; + width = mem->width; + + /* Multiple banks of the same type are aggregated into + * one. User mode doesn't care about multiple physical + * memory segments. It's managed as a single virtual + * heap for user mode. + */ + props = find_subtype_mem(heap_type, flags, width, dev); + if (props) { + props->size_in_bytes += size_in_bytes; + break; + } + + props = kfd_alloc_struct(props); + if (!props) + return -ENOMEM; + + props->heap_type = heap_type; + props->flags = flags; + props->size_in_bytes = size_in_bytes; + props->width = width; dev->node_props.mem_banks_count++; list_add_tail(&props->list, &dev->mem_props); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index afb26f205d29..a3441b0e385b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -38,7 +38,6 @@ #include "kfd_dbgmgr.h" #include "kfd_dbgdev.h" #include "kfd_device_queue_manager.h" -#include "../../radeon/cik_reg.h" static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h index 03424c20920c..0619c777b47e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h @@ -60,6 +60,9 @@ enum { SH_REG_SIZE = SH_REG_END - SH_REG_BASE }; +/* SQ_CMD definitions */ +#define SQ_CMD 0x8DEC + enum SQ_IND_CMD_CMD { SQ_IND_CMD_CMD_NULL = 0x00000000, SQ_IND_CMD_CMD_HALT = 0x00000001, @@ -190,4 +193,38 @@ union ULARGE_INTEGER { void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev, enum DBGDEV_TYPE type); +union TCP_WATCH_CNTL_BITS { + struct { + uint32_t mask:24; + uint32_t vmid:4; + uint32_t atc:1; + uint32_t mode:2; + uint32_t valid:1; + } bitfields, bits; + uint32_t u32All; + signed int i32All; + float f32All; +}; + +enum { + ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL, + ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF, + ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000, + /* extend the mask to 26 bits in order to match the low address field */ + ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6, + ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF +}; + +enum { + MAX_TRAPID = 8, /* 3 bits in the bitfield. */ + MAX_WATCH_ADDRESSES = 4 +}; + +enum { + ADDRESS_WATCH_REG_ADDR_HI = 0, + ADDRESS_WATCH_REG_ADDR_LO, + ADDRESS_WATCH_REG_CNTL, + ADDRESS_WATCH_REG_MAX +}; + #endif /* KFD_DBGDEV_H_ */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c index 4bd6ebfaf425..ab37d36d9cd6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c @@ -21,6 +21,8 @@ */ #include <linux/debugfs.h> +#include <linux/uaccess.h> + #include "kfd_priv.h" static struct dentry *debugfs_root; @@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file) return single_open(file, show, NULL); } +static ssize_t kfd_debugfs_hang_hws_write(struct file *file, + const char __user *user_buf, size_t size, loff_t *ppos) +{ + struct kfd_dev *dev; + char tmp[16]; + uint32_t gpu_id; + int ret = -EINVAL; + + memset(tmp, 0, 16); + if (size >= 16) { + pr_err("Invalid input for gpu id.\n"); + goto out; + } + if (copy_from_user(tmp, user_buf, size)) { + ret = -EFAULT; + goto out; + } + if (kstrtoint(tmp, 10, &gpu_id)) { + pr_err("Invalid input for gpu id.\n"); + goto out; + } + dev = kfd_device_by_id(gpu_id); + if (dev) { + kfd_debugfs_hang_hws(dev); + ret = size; + } else + pr_err("Cannot find device %d.\n", gpu_id); + +out: + return ret; +} + static const struct file_operations kfd_debugfs_fops = { .owner = THIS_MODULE, .open = kfd_debugfs_open, @@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = { .release = single_release, }; +static const struct file_operations kfd_debugfs_hang_hws_fops = { + .owner = THIS_MODULE, + .open = kfd_debugfs_open, + .read = seq_read, + .write = kfd_debugfs_hang_hws_write, + .llseek = seq_lseek, + .release = single_release, +}; + void kfd_debugfs_init(void) { struct dentry *ent; @@ -65,6 +108,11 @@ void kfd_debugfs_init(void) ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root, kfd_debugfs_rls_by_device, &kfd_debugfs_fops); + + ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root, + NULL, + &kfd_debugfs_hang_hws_fops); + if (!ent) pr_warn("Failed to create rls in kfd debugfs\n"); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 7ee6cec2c060..1b048715ab8a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -30,7 +30,13 @@ #include "kfd_iommu.h" #define MQD_SIZE_ALIGNED 768 -static atomic_t kfd_device_suspended = ATOMIC_INIT(0); + +/* + * kfd_locked is used to lock the kfd driver during suspend or reset + * once locked, kfd driver will stop any further GPU execution. + * create process (open) will return -EAGAIN. + */ +static atomic_t kfd_locked = ATOMIC_INIT(0); #ifdef KFD_SUPPORT_IOMMU_V2 static const struct kfd_device_info kaveri_device_info = { @@ -46,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = { .supports_cwsr = false, .needs_iommu_device = true, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; static const struct kfd_device_info carrizo_device_info = { @@ -61,6 +68,22 @@ static const struct kfd_device_info carrizo_device_info = { .supports_cwsr = true, .needs_iommu_device = true, .needs_pci_atomics = false, + .num_sdma_engines = 2, +}; + +static const struct kfd_device_info raven_device_info = { + .asic_family = CHIP_RAVEN, + .max_pasid_bits = 16, + .max_no_of_hqd = 24, + .doorbell_size = 8, + .ih_ring_entry_size = 8 * sizeof(uint32_t), + .event_interrupt_class = &event_interrupt_class_v9, + .num_of_watch_points = 4, + .mqd_size_aligned = MQD_SIZE_ALIGNED, + .supports_cwsr = true, + .needs_iommu_device = true, + .needs_pci_atomics = true, + .num_sdma_engines = 1, }; #endif @@ -77,6 +100,7 @@ static const struct kfd_device_info hawaii_device_info = { .supports_cwsr = false, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; static const struct kfd_device_info tonga_device_info = { @@ -91,6 +115,7 @@ static const struct kfd_device_info tonga_device_info = { .supports_cwsr = false, .needs_iommu_device = false, .needs_pci_atomics = true, + .num_sdma_engines = 2, }; static const struct kfd_device_info tonga_vf_device_info = { @@ -105,6 +130,7 @@ static const struct kfd_device_info tonga_vf_device_info = { .supports_cwsr = false, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; static const struct kfd_device_info fiji_device_info = { @@ -119,6 +145,7 @@ static const struct kfd_device_info fiji_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = true, + .num_sdma_engines = 2, }; static const struct kfd_device_info fiji_vf_device_info = { @@ -133,6 +160,7 @@ static const struct kfd_device_info fiji_vf_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; @@ -148,6 +176,7 @@ static const struct kfd_device_info polaris10_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = true, + .num_sdma_engines = 2, }; static const struct kfd_device_info polaris10_vf_device_info = { @@ -162,6 +191,7 @@ static const struct kfd_device_info polaris10_vf_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; static const struct kfd_device_info polaris11_device_info = { @@ -176,6 +206,7 @@ static const struct kfd_device_info polaris11_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = true, + .num_sdma_engines = 2, }; static const struct kfd_device_info vega10_device_info = { @@ -190,6 +221,7 @@ static const struct kfd_device_info vega10_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; static const struct kfd_device_info vega10_vf_device_info = { @@ -204,6 +236,7 @@ static const struct kfd_device_info vega10_vf_device_info = { .supports_cwsr = true, .needs_iommu_device = false, .needs_pci_atomics = false, + .num_sdma_engines = 2, }; @@ -241,6 +274,7 @@ static const struct kfd_deviceid supported_devices[] = { { 0x9875, &carrizo_device_info }, /* Carrizo */ { 0x9876, &carrizo_device_info }, /* Carrizo */ { 0x9877, &carrizo_device_info }, /* Carrizo */ + { 0x15DD, &raven_device_info }, /* Raven */ #endif { 0x67A0, &hawaii_device_info }, /* Hawaii */ { 0x67A1, &hawaii_device_info }, /* Hawaii */ @@ -514,13 +548,54 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd) kfree(kfd); } +int kgd2kfd_pre_reset(struct kfd_dev *kfd) +{ + if (!kfd->init_complete) + return 0; + kgd2kfd_suspend(kfd); + + /* hold dqm->lock to prevent further execution*/ + dqm_lock(kfd->dqm); + + kfd_signal_reset_event(kfd); + return 0; +} + +/* + * Fix me. KFD won't be able to resume existing process for now. + * We will keep all existing process in a evicted state and + * wait the process to be terminated. + */ + +int kgd2kfd_post_reset(struct kfd_dev *kfd) +{ + int ret, count; + + if (!kfd->init_complete) + return 0; + + dqm_unlock(kfd->dqm); + + ret = kfd_resume(kfd); + if (ret) + return ret; + count = atomic_dec_return(&kfd_locked); + WARN_ONCE(count != 0, "KFD reset ref. error"); + return 0; +} + +bool kfd_is_locked(void) +{ + return (atomic_read(&kfd_locked) > 0); +} + void kgd2kfd_suspend(struct kfd_dev *kfd) { if (!kfd->init_complete) return; /* For first KFD device suspend all the KFD processes */ - if (atomic_inc_return(&kfd_device_suspended) == 1) + if (atomic_inc_return(&kfd_locked) == 1) kfd_suspend_all_processes(); kfd->dqm->ops.stop(kfd->dqm); @@ -539,7 +614,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd) if (ret) return ret; - count = atomic_dec_return(&kfd_device_suspended); + count = atomic_dec_return(&kfd_locked); WARN_ONCE(count < 0, "KFD suspend / resume ref. error"); if (count == 0) ret = kfd_resume_all_processes(); @@ -577,14 +652,24 @@ dqm_start_error: /* This is called directly from KGD at ISR. */ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry) { + uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE]; + bool is_patched = false; + if (!kfd->init_complete) return; + if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) { + dev_err_once(kfd_device, "Ring entry too small\n"); + return; + } + spin_lock(&kfd->interrupt_lock); if (kfd->interrupts_active - && interrupt_is_wanted(kfd, ih_ring_entry) - && enqueue_ih_ring_entry(kfd, ih_ring_entry)) + && interrupt_is_wanted(kfd, ih_ring_entry, + patched_ihre, &is_patched) + && enqueue_ih_ring_entry(kfd, + is_patched ? patched_ihre : ih_ring_entry)) queue_work(kfd->ih_wq, &kfd->interrupt_work); spin_unlock(&kfd->interrupt_lock); @@ -739,8 +824,8 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size, if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size) return -ENOMEM; - *mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO); - if ((*mem_obj) == NULL) + *mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL); + if (!(*mem_obj)) return -ENOMEM; pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size); @@ -857,3 +942,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj) kfree(mem_obj); return 0; } + +#if defined(CONFIG_DEBUG_FS) + +/* This function will send a package to HIQ to hang the HWS + * which will trigger a GPU reset and bring the HWS back to normal state + */ +int kfd_debugfs_hang_hws(struct kfd_dev *dev) +{ + int r = 0; + + if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) { + pr_err("HWS is not enabled"); + return -EINVAL; + } + + r = pm_debugfs_hang_hws(&dev->dqm->packets); + if (!r) + r = dqm_debugfs_execute_queues(dev->dqm); + + return r; +} + +#endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 668ad07ebe1f..ec0d62a16e53 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -61,6 +61,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, static void deallocate_sdma_queue(struct device_queue_manager *dqm, unsigned int sdma_queue_id); +static void kfd_process_hw_exception(struct work_struct *work); + static inline enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type) { @@ -99,6 +101,17 @@ unsigned int get_pipes_per_mec(struct device_queue_manager *dqm) return dqm->dev->shared_resources.num_pipe_per_mec; } +static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm) +{ + return dqm->dev->device_info->num_sdma_engines; +} + +unsigned int get_num_sdma_queues(struct device_queue_manager *dqm) +{ + return dqm->dev->device_info->num_sdma_engines + * KFD_SDMA_QUEUES_PER_ENGINE; +} + void program_sh_mem_settings(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { @@ -240,7 +253,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, print_queue(q); - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (dqm->total_queue_count >= max_num_of_queues_per_device) { pr_warn("Can't create new usermode queue because %d queues were already created\n", @@ -297,7 +310,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm, dqm->total_queue_count); out_unlock: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -346,10 +359,10 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { int retval; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; - mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE); - if (!mqd) + mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE); + if (!mqd_mgr) return -ENOMEM; retval = allocate_hqd(dqm, q); @@ -360,7 +373,7 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, if (retval) goto out_deallocate_hqd; - retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, + retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); if (retval) goto out_deallocate_doorbell; @@ -374,15 +387,15 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, if (!q->properties.is_active) return 0; - retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties, - q->process->mm); + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, + &q->properties, q->process->mm); if (retval) goto out_uninit_mqd; return 0; out_uninit_mqd: - mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); out_deallocate_doorbell: deallocate_doorbell(qpd, q); out_deallocate_hqd: @@ -399,11 +412,11 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, struct queue *q) { int retval; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) + if (!mqd_mgr) return -ENOMEM; if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) { @@ -420,14 +433,14 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_doorbell(qpd, q); - retval = mqd->destroy_mqd(mqd, q->mqd, + retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd, KFD_PREEMPT_TYPE_WAVEFRONT_RESET, KFD_UNMAP_LATENCY_MS, q->pipe, q->queue); if (retval == -ETIME) qpd->reset_wavefronts = true; - mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); list_del(&q->list); if (list_empty(&qpd->queues_list)) { @@ -457,9 +470,9 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, { int retval; - mutex_lock(&dqm->lock); + dqm_lock(dqm); retval = destroy_queue_nocpsch_locked(dqm, qpd, q); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -467,19 +480,19 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, static int update_queue(struct device_queue_manager *dqm, struct queue *q) { int retval; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; bool prev_active = false; - mutex_lock(&dqm->lock); + dqm_lock(dqm); pdd = kfd_get_process_device_data(q->device, q->process); if (!pdd) { retval = -ENODEV; goto out_unlock; } - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { + if (!mqd_mgr) { retval = -ENOMEM; goto out_unlock; } @@ -506,7 +519,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) } else if (prev_active && (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || q->properties.type == KFD_QUEUE_TYPE_SDMA)) { - retval = mqd->destroy_mqd(mqd, q->mqd, + retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd, KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN, KFD_UNMAP_LATENCY_MS, q->pipe, q->queue); if (retval) { @@ -515,7 +528,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) } } - retval = mqd->update_mqd(mqd, q->mqd, &q->properties); + retval = mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties); /* * check active state vs. the previous state and modify @@ -533,44 +546,44 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q) else if (q->properties.is_active && (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || q->properties.type == KFD_QUEUE_TYPE_SDMA)) - retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, &q->properties, q->process->mm); out_unlock: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } static struct mqd_manager *get_mqd_manager( struct device_queue_manager *dqm, enum KFD_MQD_TYPE type) { - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; if (WARN_ON(type >= KFD_MQD_TYPE_MAX)) return NULL; pr_debug("mqd type %d\n", type); - mqd = dqm->mqds[type]; - if (!mqd) { - mqd = mqd_manager_init(type, dqm->dev); - if (!mqd) + mqd_mgr = dqm->mqd_mgrs[type]; + if (!mqd_mgr) { + mqd_mgr = mqd_manager_init(type, dqm->dev); + if (!mqd_mgr) pr_err("mqd manager is NULL"); - dqm->mqds[type] = mqd; + dqm->mqd_mgrs[type] = mqd_mgr; } - return mqd; + return mqd_mgr; } static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { struct queue *q; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; int retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (qpd->evicted++ > 0) /* already evicted, do nothing */ goto out; @@ -582,16 +595,16 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, list_for_each_entry(q, &qpd->queues_list, list) { if (!q->properties.is_active) continue; - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { /* should not be here */ + if (!mqd_mgr) { /* should not be here */ pr_err("Cannot evict queue, mqd mgr is NULL\n"); retval = -ENOMEM; goto out; } q->properties.is_evicted = true; q->properties.is_active = false; - retval = mqd->destroy_mqd(mqd, q->mqd, + retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd, KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN, KFD_UNMAP_LATENCY_MS, q->pipe, q->queue); if (retval) @@ -600,7 +613,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, } out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -611,7 +624,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, struct kfd_process_device *pdd; int retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (qpd->evicted++ > 0) /* already evicted, do nothing */ goto out; @@ -633,7 +646,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -641,7 +654,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { struct queue *q; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; uint32_t pd_base; int retval = 0; @@ -650,7 +663,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, /* Retrieve PD base */ pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm); - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */ goto out; if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */ @@ -677,16 +690,16 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, list_for_each_entry(q, &qpd->queues_list, list) { if (!q->properties.is_evicted) continue; - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { /* should not be here */ + if (!mqd_mgr) { /* should not be here */ pr_err("Cannot restore queue, mqd mgr is NULL\n"); retval = -ENOMEM; goto out; } q->properties.is_evicted = false; q->properties.is_active = true; - retval = mqd->load_mqd(mqd, q->mqd, q->pipe, + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue, &q->properties, q->process->mm); if (retval) @@ -695,7 +708,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, } qpd->evicted = 0; out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -711,7 +724,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, /* Retrieve PD base */ pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm); - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */ goto out; if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */ @@ -739,7 +752,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, if (!retval) qpd->evicted = 0; out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -761,7 +774,7 @@ static int register_process(struct device_queue_manager *dqm, /* Retrieve PD base */ pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm); - mutex_lock(&dqm->lock); + dqm_lock(dqm); list_add(&n->list, &dqm->queues); /* Update PD Base in QPD */ @@ -769,9 +782,10 @@ static int register_process(struct device_queue_manager *dqm, retval = dqm->asic_ops.update_qpd(dqm, qpd); - dqm->processes_count++; + if (dqm->processes_count++ == 0) + dqm->dev->kfd2kgd->set_compute_idle(dqm->dev->kgd, false); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -786,20 +800,22 @@ static int unregister_process(struct device_queue_manager *dqm, list_empty(&qpd->queues_list) ? "empty" : "not empty"); retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); list_for_each_entry_safe(cur, next, &dqm->queues, list) { if (qpd == cur->qpd) { list_del(&cur->list); kfree(cur); - dqm->processes_count--; + if (--dqm->processes_count == 0) + dqm->dev->kfd2kgd->set_compute_idle( + dqm->dev->kgd, true); goto out; } } /* qpd not found in dqm list */ retval = 1; out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -838,7 +854,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm) if (!dqm->allocated_queues) return -ENOMEM; - mutex_init(&dqm->lock); + mutex_init(&dqm->lock_hidden); INIT_LIST_HEAD(&dqm->queues); dqm->queue_count = dqm->next_pipe_to_allocate = 0; dqm->sdma_queue_count = 0; @@ -853,7 +869,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm) } dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1; - dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1; + dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1; return 0; } @@ -866,8 +882,8 @@ static void uninitialize(struct device_queue_manager *dqm) kfree(dqm->allocated_queues); for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++) - kfree(dqm->mqds[i]); - mutex_destroy(&dqm->lock); + kfree(dqm->mqd_mgrs[i]); + mutex_destroy(&dqm->lock_hidden); kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem); } @@ -901,7 +917,7 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm, static void deallocate_sdma_queue(struct device_queue_manager *dqm, unsigned int sdma_queue_id) { - if (sdma_queue_id >= CIK_SDMA_QUEUES) + if (sdma_queue_id >= get_num_sdma_queues(dqm)) return; dqm->sdma_bitmap |= (1 << sdma_queue_id); } @@ -910,19 +926,19 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd) { - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; int retval; - mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA); - if (!mqd) + mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA); + if (!mqd_mgr) return -ENOMEM; retval = allocate_sdma_queue(dqm, &q->sdma_id); if (retval) return retval; - q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE; - q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE; + q->properties.sdma_queue_id = q->sdma_id / get_num_sdma_engines(dqm); + q->properties.sdma_engine_id = q->sdma_id % get_num_sdma_engines(dqm); retval = allocate_doorbell(qpd, q); if (retval) @@ -933,19 +949,20 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id); dqm->asic_ops.init_sdma_vm(dqm, q, qpd); - retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, + retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); if (retval) goto out_deallocate_doorbell; - retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL); + retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, 0, 0, &q->properties, + NULL); if (retval) goto out_uninit_mqd; return 0; out_uninit_mqd: - mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); out_deallocate_doorbell: deallocate_doorbell(qpd, q); out_deallocate_sdma_queue: @@ -1003,12 +1020,14 @@ static int initialize_cpsch(struct device_queue_manager *dqm) { pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm)); - mutex_init(&dqm->lock); + mutex_init(&dqm->lock_hidden); INIT_LIST_HEAD(&dqm->queues); dqm->queue_count = dqm->processes_count = 0; dqm->sdma_queue_count = 0; dqm->active_runlist = false; - dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1; + dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1; + + INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception); return 0; } @@ -1041,9 +1060,11 @@ static int start_cpsch(struct device_queue_manager *dqm) init_interrupts(dqm); - mutex_lock(&dqm->lock); + dqm_lock(dqm); + /* clear hang status when driver try to start the hw scheduler */ + dqm->is_hws_hang = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return 0; fail_allocate_vidmem: @@ -1055,9 +1076,9 @@ fail_packet_manager_init: static int stop_cpsch(struct device_queue_manager *dqm) { - mutex_lock(&dqm->lock); + dqm_lock(dqm); unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets); @@ -1069,11 +1090,11 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, struct kernel_queue *kq, struct qcm_process_device *qpd) { - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (dqm->total_queue_count >= max_num_of_queues_per_device) { pr_warn("Can't create new kernel queue because %d queues were already created\n", dqm->total_queue_count); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return -EPERM; } @@ -1089,7 +1110,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->queue_count++; qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return 0; } @@ -1098,7 +1119,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, struct kernel_queue *kq, struct qcm_process_device *qpd) { - mutex_lock(&dqm->lock); + dqm_lock(dqm); list_del(&kq->list); dqm->queue_count--; qpd->is_debug = false; @@ -1110,18 +1131,18 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count--; pr_debug("Total of %d queues are accountable so far\n", dqm->total_queue_count); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); } static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, struct qcm_process_device *qpd) { int retval; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (dqm->total_queue_count >= max_num_of_queues_per_device) { pr_warn("Can't create new usermode queue because %d queues were already created\n", @@ -1135,19 +1156,19 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (retval) goto out_unlock; q->properties.sdma_queue_id = - q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE; + q->sdma_id / get_num_sdma_engines(dqm); q->properties.sdma_engine_id = - q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE; + q->sdma_id % get_num_sdma_engines(dqm); } retval = allocate_doorbell(qpd, q); if (retval) goto out_deallocate_sdma_queue; - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { + if (!mqd_mgr) { retval = -ENOMEM; goto out_deallocate_doorbell; } @@ -1164,7 +1185,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, q->properties.tba_addr = qpd->tba_addr; q->properties.tma_addr = qpd->tma_addr; - retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj, + retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj, &q->gart_mqd_addr, &q->properties); if (retval) goto out_deallocate_doorbell; @@ -1188,7 +1209,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, pr_debug("Total of %d queues are accountable so far\n", dqm->total_queue_count); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; out_deallocate_doorbell: @@ -1197,7 +1218,8 @@ out_deallocate_sdma_queue: if (q->properties.type == KFD_QUEUE_TYPE_SDMA) deallocate_sdma_queue(dqm, q->sdma_id); out_unlock: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); + return retval; } @@ -1210,6 +1232,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr, while (*fence_addr != fence_value) { if (time_after(jiffies, end_jiffies)) { pr_err("qcm fence wait loop timeout expired\n"); + /* In HWS case, this is used to halt the driver thread + * in order not to mess up CP states before doing + * scandumps for FW debugging. + */ + while (halt_if_hws_hang) + schedule(); + return -ETIME; } schedule(); @@ -1254,6 +1283,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, { int retval = 0; + if (dqm->is_hws_hang) + return -EIO; if (!dqm->active_runlist) return retval; @@ -1292,9 +1323,13 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm, { int retval; + if (dqm->is_hws_hang) + return -EIO; retval = unmap_queues_cpsch(dqm, filter, filter_param); if (retval) { pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n"); + dqm->is_hws_hang = true; + schedule_work(&dqm->hw_exception_work); return retval; } @@ -1306,7 +1341,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, struct queue *q) { int retval; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; bool preempt_all_queues; preempt_all_queues = false; @@ -1314,7 +1349,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, retval = 0; /* remove queue from list to prevent rescheduling after preemption */ - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (qpd->is_debug) { /* @@ -1326,9 +1361,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, } - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { + if (!mqd_mgr) { retval = -ENOMEM; goto failed; } @@ -1350,7 +1385,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, qpd->reset_wavefronts = true; } - mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); /* * Unconditionally decrement this counter, regardless of the queue's @@ -1360,14 +1395,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, pr_debug("Total of %d queues are accountable so far\n", dqm->total_queue_count); - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; failed: failed_try_destroy_debugged_queue: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -1391,7 +1426,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm, if (!dqm->asic_ops.set_cache_memory_policy) return retval; - mutex_lock(&dqm->lock); + dqm_lock(dqm); if (alternate_aperture_size == 0) { /* base > limit disables APE1 */ @@ -1437,7 +1472,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm, qpd->sh_mem_ape1_limit); out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -1468,7 +1503,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm, struct device_process_node *cur, *next_dpn; int retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); /* Clear all user mode queues */ list_for_each_entry_safe(q, next, &qpd->queues_list, list) { @@ -1489,7 +1524,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm, } } - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -1500,14 +1535,14 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, int retval; struct queue *q, *next; struct kernel_queue *kq, *kq_next; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; struct device_process_node *cur, *next_dpn; enum kfd_unmap_queues_filter filter = KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES; retval = 0; - mutex_lock(&dqm->lock); + dqm_lock(dqm); /* Clean all kernel queues */ list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) { @@ -1542,7 +1577,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, } retval = execute_queues_cpsch(dqm, filter, 0); - if (retval || qpd->reset_wavefronts) { + if ((!dqm->is_hws_hang) && (retval || qpd->reset_wavefronts)) { pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev); dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process); qpd->reset_wavefronts = false; @@ -1550,19 +1585,19 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* lastly, free mqd resources */ list_for_each_entry_safe(q, next, &qpd->queues_list, list) { - mqd = dqm->ops.get_mqd_manager(dqm, + mqd_mgr = dqm->ops.get_mqd_manager(dqm, get_mqd_type_from_queue_type(q->properties.type)); - if (!mqd) { + if (!mqd_mgr) { retval = -ENOMEM; goto out; } list_del(&q->list); qpd->queue_count--; - mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj); + mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); } out: - mutex_unlock(&dqm->lock); + dqm_unlock(dqm); return retval; } @@ -1683,6 +1718,30 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm) kfree(dqm); } +int kfd_process_vm_fault(struct device_queue_manager *dqm, + unsigned int pasid) +{ + struct kfd_process_device *pdd; + struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); + int ret = 0; + + if (!p) + return -EINVAL; + pdd = kfd_get_process_device_data(dqm->dev, p); + if (pdd) + ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd); + kfd_unref_process(p); + + return ret; +} + +static void kfd_process_hw_exception(struct work_struct *work) +{ + struct device_queue_manager *dqm = container_of(work, + struct device_queue_manager, hw_exception_work); + dqm->dev->kfd2kgd->gpu_recover(dqm->dev->kgd); +} + #if defined(CONFIG_DEBUG_FS) static void seq_reg_dump(struct seq_file *m, @@ -1746,8 +1805,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data) } } - for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) { - for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) { + for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) { + for (queue = 0; queue < KFD_SDMA_QUEUES_PER_ENGINE; queue++) { r = dqm->dev->kfd2kgd->hqd_sdma_dump( dqm->dev->kgd, pipe, queue, &dump, &n_regs); if (r) @@ -1764,4 +1823,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data) return r; } +int dqm_debugfs_execute_queues(struct device_queue_manager *dqm) +{ + int r = 0; + + dqm_lock(dqm); + dqm->active_runlist = true; + r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); + dqm_unlock(dqm); + + return r; +} + #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 59a6b1956932..00da3169a004 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -26,15 +26,14 @@ #include <linux/rwsem.h> #include <linux/list.h> +#include <linux/mutex.h> +#include <linux/sched/mm.h> #include "kfd_priv.h" #include "kfd_mqd_manager.h" #define KFD_UNMAP_LATENCY_MS (4000) #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000) - -#define CIK_SDMA_QUEUES (4) -#define CIK_SDMA_QUEUES_PER_ENGINE (2) -#define CIK_SDMA_ENGINE_NUM (2) +#define KFD_SDMA_QUEUES_PER_ENGINE (2) struct device_process_node { struct qcm_process_device *qpd; @@ -170,11 +169,12 @@ struct device_queue_manager { struct device_queue_manager_ops ops; struct device_queue_manager_asic_ops asic_ops; - struct mqd_manager *mqds[KFD_MQD_TYPE_MAX]; + struct mqd_manager *mqd_mgrs[KFD_MQD_TYPE_MAX]; struct packet_manager packets; struct kfd_dev *dev; - struct mutex lock; + struct mutex lock_hidden; /* use dqm_lock/unlock(dqm) */ struct list_head queues; + unsigned int saved_flags; unsigned int processes_count; unsigned int queue_count; unsigned int sdma_queue_count; @@ -190,6 +190,10 @@ struct device_queue_manager { struct kfd_mem_obj *fence_mem; bool active_runlist; int sched_policy; + + /* hw exception */ + bool is_hws_hang; + struct work_struct hw_exception_work; }; void device_queue_manager_init_cik( @@ -207,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, unsigned int get_queues_num(struct device_queue_manager *dqm); unsigned int get_queues_per_pipe(struct device_queue_manager *dqm); unsigned int get_pipes_per_mec(struct device_queue_manager *dqm); +unsigned int get_num_sdma_queues(struct device_queue_manager *dqm); static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd) { @@ -219,4 +224,19 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd) return (pdd->lds_base >> 60) & 0x0E; } +/* The DQM lock can be taken in MMU notifiers. Make sure no reclaim-FS + * happens while holding this lock anywhere to prevent deadlocks when + * an MMU notifier runs in reclaim-FS context. + */ +static inline void dqm_lock(struct device_queue_manager *dqm) +{ + mutex_lock(&dqm->lock_hidden); + dqm->saved_flags = memalloc_nofs_save(); +} +static inline void dqm_unlock(struct device_queue_manager *dqm) +{ + memalloc_nofs_restore(dqm->saved_flags); + mutex_unlock(&dqm->lock_hidden); +} + #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c index 79e5bcf6367c..417515332c35 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c @@ -60,7 +60,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm, qpd->sh_mem_config = SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; - if (vega10_noretry && + if (noretry && !dqm->dev->device_info->needs_iommu_device) qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index c3744d89352c..ebe79bf00145 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -188,9 +188,9 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, *doorbell_off = kfd->doorbell_id_offset + inx; pr_debug("Get kernel queue doorbell\n" - " doorbell offset == 0x%08X\n" - " kernel address == %p\n", - *doorbell_off, (kfd->doorbell_kernel_ptr + inx)); + " doorbell offset == 0x%08X\n" + " doorbell index == 0x%x\n", + *doorbell_off, inx); return kfd->doorbell_kernel_ptr + inx; } @@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr) { unsigned int inx; - inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr); + inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr) + * sizeof(u32) / kfd->device_info->doorbell_size; mutex_lock(&kfd->doorbell_mutex); __clear_bit(inx, kfd->doorbell_available_index); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5562e94e786a..e9f0e0a1b41c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -850,6 +850,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p, ev->memory_exception_data = *ev_data; } + if (type == KFD_EVENT_TYPE_MEMORY) { + dev_warn(kfd_device, + "Sending SIGSEGV to HSA Process with PID %d ", + p->lead_thread->pid); + send_sig(SIGSEGV, p->lead_thread, 0); + } + /* Send SIGTERM no event of type "type" has been found*/ if (send_signal) { if (send_sigterm) { @@ -904,34 +911,41 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid, memory_exception_data.failure.NotPresent = 1; memory_exception_data.failure.NoExecute = 0; memory_exception_data.failure.ReadOnly = 0; - if (vma) { - if (vma->vm_start > address) { - memory_exception_data.failure.NotPresent = 1; - memory_exception_data.failure.NoExecute = 0; + if (vma && address >= vma->vm_start) { + memory_exception_data.failure.NotPresent = 0; + + if (is_write_requested && !(vma->vm_flags & VM_WRITE)) + memory_exception_data.failure.ReadOnly = 1; + else memory_exception_data.failure.ReadOnly = 0; - } else { - memory_exception_data.failure.NotPresent = 0; - if (is_write_requested && !(vma->vm_flags & VM_WRITE)) - memory_exception_data.failure.ReadOnly = 1; - else - memory_exception_data.failure.ReadOnly = 0; - if (is_execute_requested && !(vma->vm_flags & VM_EXEC)) - memory_exception_data.failure.NoExecute = 1; - else - memory_exception_data.failure.NoExecute = 0; - } + + if (is_execute_requested && !(vma->vm_flags & VM_EXEC)) + memory_exception_data.failure.NoExecute = 1; + else + memory_exception_data.failure.NoExecute = 0; } up_read(&mm->mmap_sem); mmput(mm); - mutex_lock(&p->event_mutex); + pr_debug("notpresent %d, noexecute %d, readonly %d\n", + memory_exception_data.failure.NotPresent, + memory_exception_data.failure.NoExecute, + memory_exception_data.failure.ReadOnly); - /* Lookup events by type and signal them */ - lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY, - &memory_exception_data); + /* Workaround on Raven to not kill the process when memory is freed + * before IOMMU is able to finish processing all the excessive PPRs + */ + if (dev->device_info->asic_family != CHIP_RAVEN) { + mutex_lock(&p->event_mutex); + + /* Lookup events by type and signal them */ + lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY, + &memory_exception_data); + + mutex_unlock(&p->event_mutex); + } - mutex_unlock(&p->event_mutex); kfd_unref_process(p); } #endif /* KFD_SUPPORT_IOMMU_V2 */ @@ -956,3 +970,67 @@ void kfd_signal_hw_exception_event(unsigned int pasid) mutex_unlock(&p->event_mutex); kfd_unref_process(p); } + +void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, + struct kfd_vm_fault_info *info) +{ + struct kfd_event *ev; + uint32_t id; + struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); + struct kfd_hsa_memory_exception_data memory_exception_data; + + if (!p) + return; /* Presumably process exited. */ + memset(&memory_exception_data, 0, sizeof(memory_exception_data)); + memory_exception_data.gpu_id = dev->id; + memory_exception_data.failure.imprecise = 1; + /* Set failure reason */ + if (info) { + memory_exception_data.va = (info->page_addr) << PAGE_SHIFT; + memory_exception_data.failure.NotPresent = + info->prot_valid ? 1 : 0; + memory_exception_data.failure.NoExecute = + info->prot_exec ? 1 : 0; + memory_exception_data.failure.ReadOnly = + info->prot_write ? 1 : 0; + memory_exception_data.failure.imprecise = 0; + } + mutex_lock(&p->event_mutex); + + id = KFD_FIRST_NONSIGNAL_EVENT_ID; + idr_for_each_entry_continue(&p->event_idr, ev, id) + if (ev->type == KFD_EVENT_TYPE_MEMORY) { + ev->memory_exception_data = memory_exception_data; + set_event(ev); + } + + mutex_unlock(&p->event_mutex); + kfd_unref_process(p); +} + +void kfd_signal_reset_event(struct kfd_dev *dev) +{ + struct kfd_hsa_hw_exception_data hw_exception_data; + struct kfd_process *p; + struct kfd_event *ev; + unsigned int temp; + uint32_t id, idx; + + /* Whole gpu reset caused by GPU hang and memory is lost */ + memset(&hw_exception_data, 0, sizeof(hw_exception_data)); + hw_exception_data.gpu_id = dev->id; + hw_exception_data.memory_lost = 1; + + idx = srcu_read_lock(&kfd_processes_srcu); + hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) { + mutex_lock(&p->event_mutex); + id = KFD_FIRST_NONSIGNAL_EVENT_ID; + idr_for_each_entry_continue(&p->event_idr, ev, id) + if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) { + ev->hw_exception_data = hw_exception_data; + set_event(ev); + } + mutex_unlock(&p->event_mutex); + } + srcu_read_unlock(&kfd_processes_srcu, idx); +} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h index abca5bfebbff..c7ac6c73af86 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h @@ -66,6 +66,7 @@ struct kfd_event { /* type specific data */ union { struct kfd_hsa_memory_exception_data memory_exception_data; + struct kfd_hsa_hw_exception_data hw_exception_data; }; }; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 37029baa3346..f836897bbf58 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -26,7 +26,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev, - const uint32_t *ih_ring_entry) + const uint32_t *ih_ring_entry, + uint32_t *patched_ihre, + bool *patched_flag) { uint16_t source_id, client_id, pasid, vmid; const uint32_t *data = ih_ring_entry; @@ -57,7 +59,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev, return source_id == SOC15_INTSRC_CP_END_OF_PIPE || source_id == SOC15_INTSRC_SDMA_TRAP || source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG || - source_id == SOC15_INTSRC_CP_BAD_OPCODE; + source_id == SOC15_INTSRC_CP_BAD_OPCODE || + client_id == SOC15_IH_CLIENTID_VMC || + client_id == SOC15_IH_CLIENTID_UTCL2; } static void event_interrupt_wq_v9(struct kfd_dev *dev, @@ -82,7 +86,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, kfd_signal_hw_exception_event(pasid); else if (client_id == SOC15_IH_CLIENTID_VMC || client_id == SOC15_IH_CLIENTID_UTCL2) { - /* TODO */ + struct kfd_vm_fault_info info = {0}; + uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry); + + info.vmid = vmid; + info.mc_id = client_id; + info.page_addr = ih_ring_entry[4] | + (uint64_t)(ih_ring_entry[5] & 0xf) << 32; + info.prot_valid = ring_id & 0x08; + info.prot_read = ring_id & 0x10; + info.prot_write = ring_id & 0x20; + + kfd_process_vm_fault(dev->dqm, pasid); + kfd_signal_vm_fault_event(dev, pasid, &info); } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c index db6d9336b80d..c56ac47cd318 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c @@ -151,13 +151,15 @@ static void interrupt_wq(struct work_struct *work) ih_ring_entry); } -bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry) +bool interrupt_is_wanted(struct kfd_dev *dev, + const uint32_t *ih_ring_entry, + uint32_t *patched_ihre, bool *flag) { /* integer and bitwise OR so there is no boolean short-circuiting */ unsigned int wanted = 0; wanted |= dev->device_info->event_interrupt_class->interrupt_isr(dev, - ih_ring_entry); + ih_ring_entry, patched_ihre, flag); return wanted != 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index c71817963eea..7a61f38c09e6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -190,7 +190,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid, { struct kfd_dev *dev; - dev_warn(kfd_device, + dev_warn_ratelimited(kfd_device, "Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X", PCI_BUS_NUM(pdev->devfn), PCI_SLOT(pdev->devfn), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 476951d8c91c..9f84b4d9fb88 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -59,7 +59,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, switch (type) { case KFD_QUEUE_TYPE_DIQ: case KFD_QUEUE_TYPE_HIQ: - kq->mqd = dev->dqm->ops.get_mqd_manager(dev->dqm, + kq->mqd_mgr = dev->dqm->ops.get_mqd_manager(dev->dqm, KFD_MQD_TYPE_HIQ); break; default: @@ -67,7 +67,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, return false; } - if (!kq->mqd) + if (!kq->mqd_mgr) return false; prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off); @@ -123,6 +123,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr; prop.eop_ring_buffer_address = kq->eop_gpu_addr; prop.eop_ring_buffer_size = PAGE_SIZE; + prop.cu_mask = NULL; if (init_queue(&kq->queue, &prop) != 0) goto err_init_queue; @@ -130,7 +131,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, kq->queue->device = dev; kq->queue->process = kfd_get_process(current); - retval = kq->mqd->init_mqd(kq->mqd, &kq->queue->mqd, + retval = kq->mqd_mgr->init_mqd(kq->mqd_mgr, &kq->queue->mqd, &kq->queue->mqd_mem_obj, &kq->queue->gart_mqd_addr, &kq->queue->properties); @@ -142,9 +143,9 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev, pr_debug("Assigning hiq to hqd\n"); kq->queue->pipe = KFD_CIK_HIQ_PIPE; kq->queue->queue = KFD_CIK_HIQ_QUEUE; - kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe, - kq->queue->queue, &kq->queue->properties, - NULL); + kq->mqd_mgr->load_mqd(kq->mqd_mgr, kq->queue->mqd, + kq->queue->pipe, kq->queue->queue, + &kq->queue->properties, NULL); } else { /* allocate fence for DIQ */ @@ -182,7 +183,7 @@ err_get_kernel_doorbell: static void uninitialize(struct kernel_queue *kq) { if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) - kq->mqd->destroy_mqd(kq->mqd, + kq->mqd_mgr->destroy_mqd(kq->mqd_mgr, kq->queue->mqd, KFD_PREEMPT_TYPE_WAVEFRONT_RESET, KFD_UNMAP_LATENCY_MS, @@ -191,7 +192,8 @@ static void uninitialize(struct kernel_queue *kq) else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ) kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj); - kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj); + kq->mqd_mgr->uninit_mqd(kq->mqd_mgr, kq->queue->mqd, + kq->queue->mqd_mem_obj); kfd_gtt_sa_free(kq->dev, kq->rptr_mem); kfd_gtt_sa_free(kq->dev, kq->wptr_mem); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h index 97aff2041a5d..a7116a939029 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h @@ -70,7 +70,7 @@ struct kernel_queue { /* data */ struct kfd_dev *dev; - struct mqd_manager *mqd; + struct mqd_manager *mqd_mgr; struct queue *queue; uint64_t pending_wptr64; uint32_t pending_wptr; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c index 76bf2dc8aec4..6e1f5c7c2d4b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c @@ -47,6 +47,8 @@ static const struct kgd2kfd_calls kgd2kfd = { .resume_mm = kgd2kfd_resume_mm, .schedule_evict_and_restore_process = kgd2kfd_schedule_evict_and_restore_process, + .pre_reset = kgd2kfd_pre_reset, + .post_reset = kgd2kfd_post_reset, }; int sched_policy = KFD_SCHED_POLICY_HWS; @@ -61,7 +63,7 @@ MODULE_PARM_DESC(hws_max_conc_proc, int cwsr_enable = 1; module_param(cwsr_enable, int, 0444); -MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))"); +MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = off, 1 = on (default))"); int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT; module_param(max_num_of_queues_per_device, int, 0444); @@ -83,13 +85,19 @@ module_param(ignore_crat, int, 0444); MODULE_PARM_DESC(ignore_crat, "Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)"); -int vega10_noretry; -module_param_named(noretry, vega10_noretry, int, 0644); +int noretry; +module_param(noretry, int, 0644); MODULE_PARM_DESC(noretry, - "Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)"); + "Set sh_mem_config.retry_disable on GFXv9+ dGPUs (0 = retry enabled (default), 1 = retry disabled)"); + +int halt_if_hws_hang; +module_param(halt_if_hws_hang, int, 0644); +MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); + static int amdkfd_init_completed; + int kgd2kfd_init(unsigned int interface_version, const struct kgd2kfd_calls **g2f) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c index 4b8eb506642b..3bc25ab84f34 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c @@ -21,7 +21,7 @@ * */ -#include "kfd_priv.h" +#include "kfd_mqd_manager.h" struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type, struct kfd_dev *dev) @@ -48,3 +48,42 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type, return NULL; } + +void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm, + const uint32_t *cu_mask, uint32_t cu_mask_count, + uint32_t *se_mask) +{ + struct kfd_cu_info cu_info; + uint32_t cu_per_sh[4] = {0}; + int i, se, cu = 0; + + mm->dev->kfd2kgd->get_cu_info(mm->dev->kgd, &cu_info); + + if (cu_mask_count > cu_info.cu_active_number) + cu_mask_count = cu_info.cu_active_number; + + for (se = 0; se < cu_info.num_shader_engines; se++) + for (i = 0; i < 4; i++) + cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]); + + /* Symmetrically map cu_mask to all SEs: + * cu_mask[0] bit0 -> se_mask[0] bit0; + * cu_mask[0] bit1 -> se_mask[1] bit0; + * ... (if # SE is 4) + * cu_mask[0] bit4 -> se_mask[0] bit1; + * ... + */ + se = 0; + for (i = 0; i < cu_mask_count; i++) { + if (cu_mask[i / 32] & (1 << (i % 32))) + se_mask[se] |= 1 << cu; + + do { + se++; + if (se == cu_info.num_shader_engines) { + se = 0; + cu++; + } + } while (cu >= cu_per_sh[se] && cu < 32); + } +} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h index 8972bcfbf701..4e84052d4e21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h @@ -93,4 +93,8 @@ struct mqd_manager { struct kfd_dev *dev; }; +void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm, + const uint32_t *cu_mask, uint32_t cu_mask_count, + uint32_t *se_mask); + #endif /* KFD_MQD_MANAGER_H_ */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c index 06eaa218eba6..47243165a082 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c @@ -41,6 +41,31 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd) return (struct cik_sdma_rlc_registers *)mqd; } +static void update_cu_mask(struct mqd_manager *mm, void *mqd, + struct queue_properties *q) +{ + struct cik_mqd *m; + uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ + + if (q->cu_mask_count == 0) + return; + + mqd_symmetrically_map_cu_mask(mm, + q->cu_mask, q->cu_mask_count, se_mask); + + m = get_mqd(mqd); + m->compute_static_thread_mgmt_se0 = se_mask[0]; + m->compute_static_thread_mgmt_se1 = se_mask[1]; + m->compute_static_thread_mgmt_se2 = se_mask[2]; + m->compute_static_thread_mgmt_se3 = se_mask[3]; + + pr_debug("Update cu mask to %#x %#x %#x %#x\n", + m->compute_static_thread_mgmt_se0, + m->compute_static_thread_mgmt_se1, + m->compute_static_thread_mgmt_se2, + m->compute_static_thread_mgmt_se3); +} + static int init_mqd(struct mqd_manager *mm, void **mqd, struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr, struct queue_properties *q) @@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd, if (q->format == KFD_QUEUE_FORMAT_AQL) m->cp_hqd_pq_control |= NO_UPDATE_RPTR; + update_cu_mask(mm, mqd, q); + q->is_active = (q->queue_size > 0 && q->queue_address != 0 && q->queue_percent > 0 && @@ -408,7 +435,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type, if (WARN_ON(type >= KFD_MQD_TYPE_MAX)) return NULL; - mqd = kzalloc(sizeof(*mqd), GFP_NOIO); + mqd = kzalloc(sizeof(*mqd), GFP_KERNEL); if (!mqd) return NULL; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index 684054ff02cd..f5fc3675f21e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -41,6 +41,31 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd) return (struct v9_sdma_mqd *)mqd; } +static void update_cu_mask(struct mqd_manager *mm, void *mqd, + struct queue_properties *q) +{ + struct v9_mqd *m; + uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ + + if (q->cu_mask_count == 0) + return; + + mqd_symmetrically_map_cu_mask(mm, + q->cu_mask, q->cu_mask_count, se_mask); + + m = get_mqd(mqd); + m->compute_static_thread_mgmt_se0 = se_mask[0]; + m->compute_static_thread_mgmt_se1 = se_mask[1]; + m->compute_static_thread_mgmt_se2 = se_mask[2]; + m->compute_static_thread_mgmt_se3 = se_mask[3]; + + pr_debug("update cu mask to %#x %#x %#x %#x\n", + m->compute_static_thread_mgmt_se0, + m->compute_static_thread_mgmt_se1, + m->compute_static_thread_mgmt_se2, + m->compute_static_thread_mgmt_se3); +} + static int init_mqd(struct mqd_manager *mm, void **mqd, struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr, struct queue_properties *q) @@ -55,7 +80,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd, * instead of sub-allocation function. */ if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) { - *mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO); + *mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL); if (!*mqd_mem_obj) return -ENOMEM; retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd, @@ -198,6 +223,8 @@ static int update_mqd(struct mqd_manager *mm, void *mqd, if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address) m->cp_hqd_ctx_save_control = 0; + update_cu_mask(mm, mqd, q); + q->is_active = (q->queue_size > 0 && q->queue_address != 0 && q->queue_percent > 0 && @@ -393,7 +420,7 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type, if (WARN_ON(type >= KFD_MQD_TYPE_MAX)) return NULL; - mqd = kzalloc(sizeof(*mqd), GFP_NOIO); + mqd = kzalloc(sizeof(*mqd), GFP_KERNEL); if (!mqd) return NULL; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c index 481307b8b4db..b81fda3754da 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c @@ -43,6 +43,31 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd) return (struct vi_sdma_mqd *)mqd; } +static void update_cu_mask(struct mqd_manager *mm, void *mqd, + struct queue_properties *q) +{ + struct vi_mqd *m; + uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */ + + if (q->cu_mask_count == 0) + return; + + mqd_symmetrically_map_cu_mask(mm, + q->cu_mask, q->cu_mask_count, se_mask); + + m = get_mqd(mqd); + m->compute_static_thread_mgmt_se0 = se_mask[0]; + m->compute_static_thread_mgmt_se1 = se_mask[1]; + m->compute_static_thread_mgmt_se2 = se_mask[2]; + m->compute_static_thread_mgmt_se3 = se_mask[3]; + + pr_debug("Update cu mask to %#x %#x %#x %#x\n", + m->compute_static_thread_mgmt_se0, + m->compute_static_thread_mgmt_se1, + m->compute_static_thread_mgmt_se2, + m->compute_static_thread_mgmt_se3); +} + static int init_mqd(struct mqd_manager *mm, void **mqd, struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr, struct queue_properties *q) @@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd, atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT | mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT; + update_cu_mask(mm, mqd, q); + q->is_active = (q->queue_size > 0 && q->queue_address != 0 && q->queue_percent > 0 && @@ -394,7 +421,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type, if (WARN_ON(type >= KFD_MQD_TYPE_MAX)) return NULL; - mqd = kzalloc(sizeof(*mqd), GFP_NOIO); + mqd = kzalloc(sizeof(*mqd), GFP_KERNEL); if (!mqd) return NULL; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index c317feb43f69..1092631765cb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -418,4 +418,30 @@ out: return 0; } +int pm_debugfs_hang_hws(struct packet_manager *pm) +{ + uint32_t *buffer, size; + int r = 0; + + size = pm->pmf->query_status_size; + mutex_lock(&pm->lock); + pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue, + size / sizeof(uint32_t), (unsigned int **)&buffer); + if (!buffer) { + pr_err("Failed to allocate buffer on kernel queue\n"); + r = -ENOMEM; + goto out; + } + memset(buffer, 0x55, size); + pm->priv_queue->ops.submit_packet(pm->priv_queue); + + pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.", + buffer[0], buffer[1], buffer[2], buffer[3], + buffer[4], buffer[5], buffer[6]); +out: + mutex_unlock(&pm->lock); + return r; +} + + #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 5e3990bb4c4b..f971710f1c91 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -73,7 +73,7 @@ /* * When working with cp scheduler we should assign the HIQ manually or via - * the radeon driver to a fixed hqd slot, here are the fixed HIQ hqd slot + * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot * definitions for Kaveri. In Kaveri only the first ME queues participates * in the cp scheduling taking that in mind we set the HIQ slot in the * second ME. @@ -142,7 +142,12 @@ extern int ignore_crat; /* * Set sh_mem_config.retry_disable on Vega10 */ -extern int vega10_noretry; +extern int noretry; + +/* + * Halt if HWS hang is detected + */ +extern int halt_if_hws_hang; /** * enum kfd_sched_policy @@ -180,9 +185,10 @@ enum cache_policy { struct kfd_event_interrupt_class { bool (*interrupt_isr)(struct kfd_dev *dev, - const uint32_t *ih_ring_entry); + const uint32_t *ih_ring_entry, uint32_t *patched_ihre, + bool *patched_flag); void (*interrupt_wq)(struct kfd_dev *dev, - const uint32_t *ih_ring_entry); + const uint32_t *ih_ring_entry); }; struct kfd_device_info { @@ -197,6 +203,7 @@ struct kfd_device_info { bool supports_cwsr; bool needs_iommu_device; bool needs_pci_atomics; + unsigned int num_sdma_engines; }; struct kfd_mem_obj { @@ -415,6 +422,9 @@ struct queue_properties { uint32_t ctl_stack_size; uint64_t tba_addr; uint64_t tma_addr; + /* Relevant for CU */ + uint32_t cu_mask_count; /* Must be a multiple of 32 */ + uint32_t *cu_mask; }; /** @@ -806,12 +816,18 @@ int kfd_interrupt_init(struct kfd_dev *dev); void kfd_interrupt_exit(struct kfd_dev *dev); void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry); bool enqueue_ih_ring_entry(struct kfd_dev *kfd, const void *ih_ring_entry); -bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry); +bool interrupt_is_wanted(struct kfd_dev *dev, + const uint32_t *ih_ring_entry, + uint32_t *patched_ihre, bool *flag); /* Power Management */ void kgd2kfd_suspend(struct kfd_dev *kfd); int kgd2kfd_resume(struct kfd_dev *kfd); +/* GPU reset */ +int kgd2kfd_pre_reset(struct kfd_dev *kfd); +int kgd2kfd_post_reset(struct kfd_dev *kfd); + /* amdkfd Apertures */ int kfd_init_apertures(struct kfd_process *process); @@ -838,6 +854,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm); struct kernel_queue *kernel_queue_init(struct kfd_dev *dev, enum kfd_queue_type type); void kernel_queue_uninit(struct kernel_queue *kq); +int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid); /* Process Queue Manager */ struct process_queue_node { @@ -858,6 +875,8 @@ int pqm_create_queue(struct process_queue_manager *pqm, int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid); int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, struct queue_properties *p); +int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid, + struct queue_properties *p); struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm, unsigned int qid); @@ -964,10 +983,17 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p, uint64_t *event_page_offset, uint32_t *event_slot_index); int kfd_event_destroy(struct kfd_process *p, uint32_t event_id); +void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, + struct kfd_vm_fault_info *info); + +void kfd_signal_reset_event(struct kfd_dev *dev); + void kfd_flush_tlb(struct kfd_process_device *pdd); int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p); +bool kfd_is_locked(void); + /* Debugfs */ #if defined(CONFIG_DEBUG_FS) @@ -980,6 +1006,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data); int kfd_debugfs_rls_by_device(struct seq_file *m, void *data); int pm_debugfs_runlist(struct seq_file *m, void *data); +int kfd_debugfs_hang_hws(struct kfd_dev *dev); +int pm_debugfs_hang_hws(struct packet_manager *pm); +int dqm_debugfs_execute_queues(struct device_queue_manager *dqm); + #else static inline void kfd_debugfs_init(void) {} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 1d80b4f7c681..4694386cc623 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -244,6 +244,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread) return ERR_PTR(-EINVAL); process = find_process(thread); + if (!process) + return ERR_PTR(-EINVAL); return process; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index d65ce0436b31..c8cad9c078ae 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, switch (type) { case KFD_QUEUE_TYPE_SDMA: - if (dev->dqm->queue_count >= - CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) { + if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) { pr_err("Over-subscription is not allowed for SDMA.\n"); retval = -EPERM; goto err_create_queue; @@ -209,7 +208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm, KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) && ((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) || (dev->dqm->queue_count >= get_queues_num(dev->dqm)))) { - pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n"); + pr_debug("Over-subscription is not allowed when amdkfd.sched_policy == 1\n"); retval = -EPERM; goto err_create_queue; } @@ -326,6 +325,8 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) if (retval != -ETIME) goto err_destroy_queue; } + kfree(pqn->q->properties.cu_mask); + pqn->q->properties.cu_mask = NULL; uninit_queue(pqn->q); } @@ -366,6 +367,34 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid, return 0; } +int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid, + struct queue_properties *p) +{ + int retval; + struct process_queue_node *pqn; + + pqn = get_queue_by_qid(pqm, qid); + if (!pqn) { + pr_debug("No queue %d exists for update operation\n", qid); + return -EFAULT; + } + + /* Free the old CU mask memory if it is already allocated, then + * allocate memory for the new CU mask. + */ + kfree(pqn->q->properties.cu_mask); + + pqn->q->properties.cu_mask_count = p->cu_mask_count; + pqn->q->properties.cu_mask = p->cu_mask; + + retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm, + pqn->q); + if (retval != 0) + return retval; + + return 0; +} + struct kernel_queue *pqm_get_kernel_queue( struct process_queue_manager *pqm, unsigned int qid) @@ -387,7 +416,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data) struct process_queue_node *pqn; struct queue *q; enum KFD_MQD_TYPE mqd_type; - struct mqd_manager *mqd_manager; + struct mqd_manager *mqd_mgr; int r = 0; list_for_each_entry(pqn, &pqm->queues, process_queue_list) { @@ -410,11 +439,11 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data) q->properties.type, q->device->id); continue; } - mqd_manager = q->device->dqm->ops.get_mqd_manager( + mqd_mgr = q->device->dqm->ops.get_mqd_manager( q->device->dqm, mqd_type); } else if (pqn->kq) { q = pqn->kq->queue; - mqd_manager = pqn->kq->mqd; + mqd_mgr = pqn->kq->mqd_mgr; switch (q->properties.type) { case KFD_QUEUE_TYPE_DIQ: seq_printf(m, " DIQ on device %x\n", @@ -434,7 +463,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data) continue; } - r = mqd_manager->debugfs_show_mqd(m, q->mqd); + r = mqd_mgr->debugfs_show_mqd(m, q->mqd); if (r != 0) break; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c index 9f0a217603ad..516795342dd2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c @@ -74,4 +74,3 @@ bool dm_read_persistent_data(struct dc_context *ctx, /**** power component interfaces ****/ - diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 5733fbee07f7..14391b06080c 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -47,6 +47,17 @@ enum kfd_preempt_type { KFD_PREEMPT_TYPE_WAVEFRONT_RESET, }; +struct kfd_vm_fault_info { + uint64_t page_addr; + uint32_t vmid; + uint32_t mc_id; + uint32_t status; + bool prot_valid; + bool prot_read; + bool prot_write; + bool prot_exec; +}; + struct kfd_cu_info { uint32_t num_shader_engines; uint32_t num_shader_arrays_per_engine; @@ -259,6 +270,21 @@ struct tile_config { * IB to the corresponding ring (ring type). The IB is executed with the * specified VMID in a user mode context. * + * @get_vm_fault_info: Return information about a recent VM fault on + * GFXv7 and v8. If multiple VM faults occurred since the last call of + * this function, it will return information about the first of those + * faults. On GFXv9 VM fault information is fully contained in the IH + * packet and this function is not needed. + * + * @read_vmid_from_vmfault_reg: On Hawaii the VMID is not set in the + * IH ring entry. This function allows the KFD ISR to get the VMID + * from the fault status register as early as possible. + * + * @gpu_recover: let kgd reset gpu after kfd detect CPC hang + * + * @set_compute_idle: Indicates that compute is idle on a device. This + * can be used to change power profiles depending on compute activity. + * * This structure contains function pointers to services that the kgd driver * provides to amdkfd driver. * @@ -374,6 +400,14 @@ struct kfd2kgd_calls { int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine, uint32_t vmid, uint64_t gpu_addr, uint32_t *ib_cmd, uint32_t ib_len); + + int (*get_vm_fault_info)(struct kgd_dev *kgd, + struct kfd_vm_fault_info *info); + uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd); + + void (*gpu_recover)(struct kgd_dev *kgd); + + void (*set_compute_idle)(struct kgd_dev *kgd, bool idle); }; /** @@ -399,6 +433,10 @@ struct kfd2kgd_calls { * @schedule_evict_and_restore_process: Schedules work queue that will prepare * for safe eviction of KFD BOs that belong to the specified process. * + * @pre_reset: Notifies amdkfd that amdgpu about to reset the gpu + * + * @post_reset: Notify amdkfd that amgpu successfully reseted the gpu + * * This structure contains function callback pointers so the kgd driver * will notify to the amdkfd about certain status changes. * @@ -417,6 +455,8 @@ struct kgd2kfd_calls { int (*resume_mm)(struct mm_struct *mm); int (*schedule_evict_and_restore_process)(struct mm_struct *mm, struct dma_fence *fence); + int (*pre_reset)(struct kfd_dev *kfd); + int (*post_reset)(struct kfd_dev *kfd); }; int kgd2kfd_init(unsigned interface_version, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c index f4f366b26fd1..cb3a5b1737c8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c @@ -226,6 +226,8 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address; + ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address; + return 0; } diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c index f3f08cd6e9ef..e4d67b70244d 100644 --- a/drivers/gpu/drm/arm/hdlcd_crtc.c +++ b/drivers/gpu/drm/arm/hdlcd_crtc.c @@ -229,6 +229,8 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = { static int hdlcd_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) { + int i; + struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; u32 src_h = state->src_h >> 16; @@ -238,20 +240,17 @@ static int hdlcd_plane_atomic_check(struct drm_plane *plane, return -EINVAL; } - if (!state->fb || !state->crtc) - return 0; - - crtc_state = drm_atomic_get_existing_crtc_state(state->state, - state->crtc); - if (!crtc_state) { - DRM_DEBUG_KMS("Invalid crtc state\n"); - return -EINVAL; + for_each_new_crtc_in_state(state->state, crtc, crtc_state, i) { + /* we cannot disable the plane while the CRTC is active */ + if (!state->fb && crtc_state->active) + return -EINVAL; + return drm_atomic_helper_check_plane_state(state, crtc_state, + DRM_PLANE_HELPER_NO_SCALING, + DRM_PLANE_HELPER_NO_SCALING, + false, true); } - return drm_atomic_helper_check_plane_state(state, crtc_state, - DRM_PLANE_HELPER_NO_SCALING, - DRM_PLANE_HELPER_NO_SCALING, - false, true); + return 0; } static void hdlcd_plane_atomic_update(struct drm_plane *plane, @@ -280,16 +279,10 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = { .atomic_update = hdlcd_plane_atomic_update, }; -static void hdlcd_plane_destroy(struct drm_plane *plane) -{ - drm_plane_helper_disable(plane, NULL); - drm_plane_cleanup(plane); -} - static const struct drm_plane_funcs hdlcd_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = hdlcd_plane_destroy, + .destroy = drm_plane_cleanup, .reset = drm_atomic_helper_plane_reset, .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, @@ -334,10 +327,8 @@ int hdlcd_setup_crtc(struct drm_device *drm) ret = drm_crtc_init_with_planes(drm, &hdlcd->crtc, primary, NULL, &hdlcd_crtc_funcs, NULL); - if (ret) { - hdlcd_plane_destroy(primary); + if (ret) return ret; - } drm_crtc_helper_add(&hdlcd->crtc, &hdlcd_crtc_helper_funcs); return 0; diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index feaa8bc3d7b7..0ed1cde98cf8 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -27,6 +27,7 @@ #include <drm/drm_fb_cma_helper.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_modeset_helper.h> #include <drm/drm_of.h> #include "hdlcd_drv.h" @@ -100,16 +101,9 @@ setup_fail: return ret; } -static void hdlcd_fb_output_poll_changed(struct drm_device *drm) -{ - struct hdlcd_drm_private *hdlcd = drm->dev_private; - - drm_fbdev_cma_hotplug_event(hdlcd->fbdev); -} - static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = { .fb_create = drm_gem_fb_create, - .output_poll_changed = hdlcd_fb_output_poll_changed, + .output_poll_changed = drm_fb_helper_output_poll_changed, .atomic_check = drm_atomic_helper_check, .atomic_commit = drm_atomic_helper_commit, }; @@ -124,13 +118,6 @@ static void hdlcd_setup_mode_config(struct drm_device *drm) drm->mode_config.funcs = &hdlcd_mode_config_funcs; } -static void hdlcd_lastclose(struct drm_device *drm) -{ - struct hdlcd_drm_private *hdlcd = drm->dev_private; - - drm_fbdev_cma_restore_mode(hdlcd->fbdev); -} - static irqreturn_t hdlcd_irq(int irq, void *arg) { struct drm_device *drm = arg; @@ -246,7 +233,7 @@ static struct drm_driver hdlcd_driver = { .driver_features = DRIVER_HAVE_IRQ | DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC, - .lastclose = hdlcd_lastclose, + .lastclose = drm_fb_helper_lastclose, .irq_handler = hdlcd_irq, .irq_preinstall = hdlcd_irq_preinstall, .irq_postinstall = hdlcd_irq_postinstall, @@ -321,14 +308,9 @@ static int hdlcd_drm_bind(struct device *dev) drm_mode_config_reset(drm); drm_kms_helper_poll_init(drm); - hdlcd->fbdev = drm_fbdev_cma_init(drm, 32, - drm->mode_config.num_connector); - - if (IS_ERR(hdlcd->fbdev)) { - ret = PTR_ERR(hdlcd->fbdev); - hdlcd->fbdev = NULL; + ret = drm_fb_cma_fbdev_init(drm, 32, 0); + if (ret) goto err_fbdev; - } ret = drm_dev_register(drm, 0); if (ret) @@ -337,15 +319,13 @@ static int hdlcd_drm_bind(struct device *dev) return 0; err_register: - if (hdlcd->fbdev) { - drm_fbdev_cma_fini(hdlcd->fbdev); - hdlcd->fbdev = NULL; - } + drm_fb_cma_fbdev_fini(drm); err_fbdev: drm_kms_helper_poll_fini(drm); err_vblank: pm_runtime_disable(drm->dev); err_pm_active: + drm_atomic_helper_shutdown(drm); component_unbind_all(dev, drm); err_unload: of_node_put(hdlcd->crtc.port); @@ -366,23 +346,23 @@ static void hdlcd_drm_unbind(struct device *dev) struct hdlcd_drm_private *hdlcd = drm->dev_private; drm_dev_unregister(drm); - if (hdlcd->fbdev) { - drm_fbdev_cma_fini(hdlcd->fbdev); - hdlcd->fbdev = NULL; - } + drm_fb_cma_fbdev_fini(drm); drm_kms_helper_poll_fini(drm); component_unbind_all(dev, drm); of_node_put(hdlcd->crtc.port); hdlcd->crtc.port = NULL; - pm_runtime_get_sync(drm->dev); + pm_runtime_get_sync(dev); + drm_crtc_vblank_off(&hdlcd->crtc); drm_irq_uninstall(drm); - pm_runtime_put_sync(drm->dev); - pm_runtime_disable(drm->dev); - of_reserved_mem_device_release(drm->dev); + drm_atomic_helper_shutdown(drm); + pm_runtime_put(dev); + if (pm_runtime_enabled(dev)) + pm_runtime_disable(dev); + of_reserved_mem_device_release(dev); drm_mode_config_cleanup(drm); - drm_dev_put(drm); drm->dev_private = NULL; dev_set_drvdata(dev, NULL); + drm_dev_put(drm); } static const struct component_master_ops hdlcd_master_ops = { @@ -427,35 +407,15 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match); static int __maybe_unused hdlcd_pm_suspend(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL; - - if (!hdlcd) - return 0; - drm_kms_helper_poll_disable(drm); - drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 1); - - hdlcd->state = drm_atomic_helper_suspend(drm); - if (IS_ERR(hdlcd->state)) { - drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0); - drm_kms_helper_poll_enable(drm); - return PTR_ERR(hdlcd->state); - } - - return 0; + return drm_mode_config_helper_suspend(drm); } static int __maybe_unused hdlcd_pm_resume(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL; - - if (!hdlcd) - return 0; - drm_atomic_helper_resume(drm, hdlcd->state); - drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0); - drm_kms_helper_poll_enable(drm); + drm_mode_config_helper_resume(drm); return 0; } diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h index 56f34dfff640..fd438d177b64 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.h +++ b/drivers/gpu/drm/arm/hdlcd_drv.h @@ -9,10 +9,8 @@ struct hdlcd_drm_private { void __iomem *mmio; struct clk *clk; - struct drm_fbdev_cma *fbdev; struct drm_crtc crtc; struct drm_plane *plane; - struct drm_atomic_state *state; #ifdef CONFIG_DEBUG_FS atomic_t buffer_underrun_count; atomic_t bus_error_count; diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile index ecf25cf9f9f5..9bc3c3213724 100644 --- a/drivers/gpu/drm/armada/Makefile +++ b/drivers/gpu/drm/armada/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 armada-y := armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \ - armada_gem.o armada_overlay.o armada_trace.o + armada_gem.o armada_overlay.o armada_plane.o armada_trace.o armada-y += armada_510.o armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c index 41a784f5a5e6..2f7c048c5361 100644 --- a/drivers/gpu/drm/armada/armada_510.c +++ b/drivers/gpu/drm/armada/armada_510.c @@ -27,6 +27,10 @@ static int armada510_crtc_init(struct armada_crtc *dcrtc, struct device *dev) /* Lower the watermark so to eliminate jitter at higher bandwidths */ armada_updatel(0x20, (1 << 11) | 0xff, dcrtc->base + LCD_CFG_RDREG4F); + /* Initialise SPU register */ + writel_relaxed(ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND, + dcrtc->base + LCD_SPU_ADV_REG); + return 0; } @@ -75,9 +79,27 @@ static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc, return 0; } +static void armada510_crtc_disable(struct armada_crtc *dcrtc) +{ + if (!IS_ERR(dcrtc->clk)) { + clk_disable_unprepare(dcrtc->clk); + dcrtc->clk = ERR_PTR(-EINVAL); + } +} + +static void armada510_crtc_enable(struct armada_crtc *dcrtc, + const struct drm_display_mode *mode) +{ + if (IS_ERR(dcrtc->clk)) { + dcrtc->clk = dcrtc->extclk[0]; + WARN_ON(clk_prepare_enable(dcrtc->clk)); + } +} + const struct armada_variant armada510_ops = { .has_spu_adv_reg = true, - .spu_adv_reg = ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND, .init = armada510_crtc_init, .compute_clock = armada510_crtc_compute_clock, + .disable = armada510_crtc_disable, + .enable = armada510_crtc_enable, }; diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 03eeee11dd5b..da9360688b55 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -11,6 +11,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <drm/drmP.h> +#include <drm/drm_atomic.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_plane_helper.h> #include <drm/drm_atomic_helper.h> @@ -19,33 +20,9 @@ #include "armada_fb.h" #include "armada_gem.h" #include "armada_hw.h" +#include "armada_plane.h" #include "armada_trace.h" -enum csc_mode { - CSC_AUTO = 0, - CSC_YUV_CCIR601 = 1, - CSC_YUV_CCIR709 = 2, - CSC_RGB_COMPUTER = 1, - CSC_RGB_STUDIO = 2, -}; - -static const uint32_t armada_primary_formats[] = { - DRM_FORMAT_UYVY, - DRM_FORMAT_YUYV, - DRM_FORMAT_VYUY, - DRM_FORMAT_YVYU, - DRM_FORMAT_ARGB8888, - DRM_FORMAT_ABGR8888, - DRM_FORMAT_XRGB8888, - DRM_FORMAT_XBGR8888, - DRM_FORMAT_RGB888, - DRM_FORMAT_BGR888, - DRM_FORMAT_ARGB1555, - DRM_FORMAT_ABGR1555, - DRM_FORMAT_RGB565, - DRM_FORMAT_BGR565, -}; - /* * A note about interlacing. Let's consider HDMI 1920x1080i. * The timing parameters we have from X are: @@ -115,15 +92,13 @@ armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs) } } -#define dpms_blanked(dpms) ((dpms) != DRM_MODE_DPMS_ON) - -static void armada_drm_crtc_update(struct armada_crtc *dcrtc) +static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable) { uint32_t dumb_ctrl; dumb_ctrl = dcrtc->cfg_dumb_ctrl; - if (!dpms_blanked(dcrtc->dpms)) + if (enable) dumb_ctrl |= CFG_DUMB_ENA; /* @@ -132,295 +107,26 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc) * force LCD_D[23:0] to output blank color, overriding the GPIO or * SPI usage. So leave it as-is unless in DUMB24_RGB888_0 mode. */ - if (dpms_blanked(dcrtc->dpms) && - (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) { + if (!enable && (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) { dumb_ctrl &= ~DUMB_MASK; dumb_ctrl |= DUMB_BLANK; } - /* - * The documentation doesn't indicate what the normal state of - * the sync signals are. Sebastian Hesselbart kindly probed - * these signals on his board to determine their state. - * - * The non-inverted state of the sync signals is active high. - * Setting these bits makes the appropriate signal active low. - */ - if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NCSYNC) - dumb_ctrl |= CFG_INV_CSYNC; - if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NHSYNC) - dumb_ctrl |= CFG_INV_HSYNC; - if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NVSYNC) - dumb_ctrl |= CFG_INV_VSYNC; - - if (dcrtc->dumb_ctrl != dumb_ctrl) { - dcrtc->dumb_ctrl = dumb_ctrl; - writel_relaxed(dumb_ctrl, dcrtc->base + LCD_SPU_DUMB_CTRL); - } -} - -void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb, - int x, int y) -{ - const struct drm_format_info *format = fb->format; - unsigned int num_planes = format->num_planes; - u32 addr = drm_fb_obj(fb)->dev_addr; - int i; - - if (num_planes > 3) - num_planes = 3; - - addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] + - x * format->cpp[0]; - - y /= format->vsub; - x /= format->hsub; - - for (i = 1; i < num_planes; i++) - addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] + - x * format->cpp[i]; - for (; i < 3; i++) - addrs[i] = 0; -} - -static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb, - int x, int y, struct armada_regs *regs, bool interlaced) -{ - unsigned pitch = fb->pitches[0]; - u32 addrs[3], addr_odd, addr_even; - unsigned i = 0; - - DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n", - pitch, x, y, fb->format->cpp[0] * 8); - - armada_drm_plane_calc_addrs(addrs, fb, x, y); - - addr_odd = addr_even = addrs[0]; - - if (interlaced) { - addr_even += pitch; - pitch *= 2; - } - - /* write offset, base, and pitch */ - armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0); - armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1); - armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH); - - return i; -} - -static void armada_drm_plane_work_call(struct armada_crtc *dcrtc, - struct armada_plane_work *work, - void (*fn)(struct armada_crtc *, struct armada_plane_work *)) -{ - struct armada_plane *dplane = drm_to_armada_plane(work->plane); - struct drm_pending_vblank_event *event; - struct drm_framebuffer *fb; - - if (fn) - fn(dcrtc, work); - drm_crtc_vblank_put(&dcrtc->crtc); - - event = work->event; - fb = work->old_fb; - if (event || fb) { - struct drm_device *dev = dcrtc->crtc.dev; - unsigned long flags; - - spin_lock_irqsave(&dev->event_lock, flags); - if (event) - drm_crtc_send_vblank_event(&dcrtc->crtc, event); - if (fb) - __armada_drm_queue_unref_work(dev, fb); - spin_unlock_irqrestore(&dev->event_lock, flags); - } - - if (work->need_kfree) - kfree(work); - - wake_up(&dplane->frame_wait); + armada_updatel(dumb_ctrl, + ~(CFG_INV_CSYNC | CFG_INV_HSYNC | CFG_INV_VSYNC), + dcrtc->base + LCD_SPU_DUMB_CTRL); } -static void armada_drm_plane_work_run(struct armada_crtc *dcrtc, - struct drm_plane *plane) -{ - struct armada_plane *dplane = drm_to_armada_plane(plane); - struct armada_plane_work *work = xchg(&dplane->work, NULL); - - /* Handle any pending frame work. */ - if (work) - armada_drm_plane_work_call(dcrtc, work, work->fn); -} - -int armada_drm_plane_work_queue(struct armada_crtc *dcrtc, - struct armada_plane_work *work) -{ - struct armada_plane *plane = drm_to_armada_plane(work->plane); - int ret; - - ret = drm_crtc_vblank_get(&dcrtc->crtc); - if (ret) - return ret; - - ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0; - if (ret) - drm_crtc_vblank_put(&dcrtc->crtc); - - return ret; -} - -int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout) -{ - return wait_event_timeout(plane->frame_wait, !plane->work, timeout); -} - -void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc, - struct armada_plane *dplane) -{ - struct armada_plane_work *work = xchg(&dplane->work, NULL); - - if (work) - armada_drm_plane_work_call(dcrtc, work, work->cancel); -} - -static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc, - struct armada_plane_work *work) -{ - unsigned long flags; - - spin_lock_irqsave(&dcrtc->irq_lock, flags); - armada_drm_crtc_update_regs(dcrtc, work->regs); - spin_unlock_irqrestore(&dcrtc->irq_lock, flags); -} - -static void armada_drm_crtc_complete_disable_work(struct armada_crtc *dcrtc, - struct armada_plane_work *work) -{ - unsigned long flags; - - if (dcrtc->plane == work->plane) - dcrtc->plane = NULL; - - spin_lock_irqsave(&dcrtc->irq_lock, flags); - armada_drm_crtc_update_regs(dcrtc, work->regs); - spin_unlock_irqrestore(&dcrtc->irq_lock, flags); -} - -static struct armada_plane_work * -armada_drm_crtc_alloc_plane_work(struct drm_plane *plane) -{ - struct armada_plane_work *work; - int i = 0; - - work = kzalloc(sizeof(*work), GFP_KERNEL); - if (!work) - return NULL; - - work->plane = plane; - work->fn = armada_drm_crtc_complete_frame_work; - work->need_kfree = true; - armada_reg_queue_end(work->regs, i); - - return work; -} - -static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc, - struct drm_framebuffer *fb, bool force) -{ - struct armada_plane_work *work; - - if (!fb) - return; - - if (force) { - /* Display is disabled, so just drop the old fb */ - drm_framebuffer_put(fb); - return; - } - - work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary); - if (work) { - work->old_fb = fb; - - if (armada_drm_plane_work_queue(dcrtc, work) == 0) - return; - - kfree(work); - } - - /* - * Oops - just drop the reference immediately and hope for - * the best. The worst that will happen is the buffer gets - * reused before it has finished being displayed. - */ - drm_framebuffer_put(fb); -} - -static void armada_drm_vblank_off(struct armada_crtc *dcrtc) -{ - /* - * Tell the DRM core that vblank IRQs aren't going to happen for - * a while. This cleans up any pending vblank events for us. - */ - drm_crtc_vblank_off(&dcrtc->crtc); - armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary); -} - -/* The mode_config.mutex will be held for this call */ -static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms) -{ - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - - if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) { - if (dpms_blanked(dpms)) - armada_drm_vblank_off(dcrtc); - else if (!IS_ERR(dcrtc->clk)) - WARN_ON(clk_prepare_enable(dcrtc->clk)); - dcrtc->dpms = dpms; - armada_drm_crtc_update(dcrtc); - if (!dpms_blanked(dpms)) - drm_crtc_vblank_on(&dcrtc->crtc); - else if (!IS_ERR(dcrtc->clk)) - clk_disable_unprepare(dcrtc->clk); - } else if (dcrtc->dpms != dpms) { - dcrtc->dpms = dpms; - } -} - -/* - * Prepare for a mode set. Turn off overlay to ensure that we don't end - * up with the overlay size being bigger than the active screen size. - * We rely upon X refreshing this state after the mode set has completed. - * - * The mode_config.mutex will be held for this call - */ -static void armada_drm_crtc_prepare(struct drm_crtc *crtc) -{ - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct drm_plane *plane; - - /* - * If we have an overlay plane associated with this CRTC, disable - * it before the modeset to avoid its coordinates being outside - * the new mode parameters. - */ - plane = dcrtc->plane; - if (plane) { - drm_plane_force_disable(plane); - WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane), - HZ)); - } -} - -/* The mode_config.mutex will be held for this call */ -static void armada_drm_crtc_commit(struct drm_crtc *crtc) +static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + struct drm_pending_vblank_event *event; - if (dcrtc->dpms != DRM_MODE_DPMS_ON) { - dcrtc->dpms = DRM_MODE_DPMS_ON; - armada_drm_crtc_update(dcrtc); + /* If we have an event, we need vblank events enabled */ + event = xchg(&crtc->state->event, NULL); + if (event) { + WARN_ON(drm_crtc_vblank_get(crtc) != 0); + dcrtc->event = event; } } @@ -465,8 +171,8 @@ static void armada_drm_crtc_enable_irq(struct armada_crtc *dcrtc, u32 mask) static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) { + struct drm_pending_vblank_event *event; void __iomem *base = dcrtc->base; - struct drm_plane *ovl_plane; if (stat & DMA_FF_UNDERFLOW) DRM_ERROR("video underflow on crtc %u\n", dcrtc->num); @@ -476,10 +182,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) if (stat & VSYNC_IRQ) drm_crtc_handle_vblank(&dcrtc->crtc); - ovl_plane = dcrtc->plane; - if (ovl_plane) - armada_drm_plane_work_run(dcrtc, ovl_plane); - spin_lock(&dcrtc->irq_lock); if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) { int i = stat & GRA_FRAME_IRQ0 ? 0 : 1; @@ -495,22 +197,35 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) writel_relaxed(val, base + LCD_SPU_ADV_REG); } - if (stat & DUMB_FRAMEDONE && dcrtc->cursor_update) { - writel_relaxed(dcrtc->cursor_hw_pos, - base + LCD_SPU_HWC_OVSA_HPXL_VLN); - writel_relaxed(dcrtc->cursor_hw_sz, - base + LCD_SPU_HWC_HPXL_VLN); - armada_updatel(CFG_HWC_ENA, - CFG_HWC_ENA | CFG_HWC_1BITMOD | CFG_HWC_1BITENA, - base + LCD_SPU_DMA_CTRL0); - dcrtc->cursor_update = false; + if (stat & dcrtc->irq_ena & DUMB_FRAMEDONE) { + if (dcrtc->update_pending) { + armada_drm_crtc_update_regs(dcrtc, dcrtc->regs); + dcrtc->update_pending = false; + } + if (dcrtc->cursor_update) { + writel_relaxed(dcrtc->cursor_hw_pos, + base + LCD_SPU_HWC_OVSA_HPXL_VLN); + writel_relaxed(dcrtc->cursor_hw_sz, + base + LCD_SPU_HWC_HPXL_VLN); + armada_updatel(CFG_HWC_ENA, + CFG_HWC_ENA | CFG_HWC_1BITMOD | + CFG_HWC_1BITENA, + base + LCD_SPU_DMA_CTRL0); + dcrtc->cursor_update = false; + } armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA); } - spin_unlock(&dcrtc->irq_lock); - if (stat & GRA_FRAME_IRQ) - armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary); + if (stat & VSYNC_IRQ && !dcrtc->update_pending) { + event = xchg(&dcrtc->event, NULL); + if (event) { + spin_lock(&dcrtc->crtc.dev->event_lock); + drm_crtc_send_vblank_event(&dcrtc->crtc, event); + spin_unlock(&dcrtc->crtc.dev->event_lock); + drm_crtc_vblank_put(&dcrtc->crtc); + } + } } static irqreturn_t armada_drm_irq(int irq, void *arg) @@ -519,8 +234,9 @@ static irqreturn_t armada_drm_irq(int irq, void *arg) u32 v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR); /* - * This is rediculous - rather than writing bits to clear, we - * have to set the actual status register value. This is racy. + * Reading the ISR appears to clear bits provided CLEAN_SPU_IRQ_ISR + * is set. Writing has some other effect to acknowledge the IRQ - + * without this, we only get a single IRQ. */ writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR); @@ -536,107 +252,16 @@ static irqreturn_t armada_drm_irq(int irq, void *arg) return IRQ_NONE; } -static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc) -{ - struct drm_display_mode *adj = &dcrtc->crtc.mode; - uint32_t val = 0; - - if (dcrtc->csc_yuv_mode == CSC_YUV_CCIR709) - val |= CFG_CSC_YUV_CCIR709; - if (dcrtc->csc_rgb_mode == CSC_RGB_STUDIO) - val |= CFG_CSC_RGB_STUDIO; - - /* - * In auto mode, set the colorimetry, based upon the HDMI spec. - * 1280x720p, 1920x1080p and 1920x1080i use ITU709, others use - * ITU601. It may be more appropriate to set this depending on - * the source - but what if the graphic frame is YUV and the - * video frame is RGB? - */ - if ((adj->hdisplay == 1280 && adj->vdisplay == 720 && - !(adj->flags & DRM_MODE_FLAG_INTERLACE)) || - (adj->hdisplay == 1920 && adj->vdisplay == 1080)) { - if (dcrtc->csc_yuv_mode == CSC_AUTO) - val |= CFG_CSC_YUV_CCIR709; - } - - /* - * We assume we're connected to a TV-like device, so the YUV->RGB - * conversion should produce a limited range. We should set this - * depending on the connectors attached to this CRTC, and what - * kind of device they report being connected. - */ - if (dcrtc->csc_rgb_mode == CSC_AUTO) - val |= CFG_CSC_RGB_STUDIO; - - return val; -} - -static void armada_drm_gra_plane_regs(struct armada_regs *regs, - struct drm_framebuffer *fb, struct armada_plane_state *state, - int x, int y, bool interlaced) -{ - unsigned int i; - u32 ctrl0; - - i = armada_drm_crtc_calc_fb(fb, x, y, regs, interlaced); - armada_reg_queue_set(regs, i, state->dst_yx, LCD_SPU_GRA_OVSA_HPXL_VLN); - armada_reg_queue_set(regs, i, state->src_hw, LCD_SPU_GRA_HPXL_VLN); - armada_reg_queue_set(regs, i, state->dst_hw, LCD_SPU_GZM_HPXL_VLN); - - ctrl0 = state->ctrl0; - if (interlaced) - ctrl0 |= CFG_GRA_FTOGGLE; - - armada_reg_queue_mod(regs, i, ctrl0, CFG_GRAFORMAT | - CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV | - CFG_SWAPYU | CFG_YUV2RGB) | - CFG_PALETTE_ENA | CFG_GRA_FTOGGLE | - CFG_GRA_HSMOOTH | CFG_GRA_ENA, - LCD_SPU_DMA_CTRL0); - armada_reg_queue_end(regs, i); -} - -static void armada_drm_primary_set(struct drm_crtc *crtc, - struct drm_plane *plane, int x, int y) -{ - struct armada_plane_state *state = &drm_to_armada_plane(plane)->state; - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct armada_regs regs[8]; - bool interlaced = dcrtc->interlaced; - - armada_drm_gra_plane_regs(regs, plane->fb, state, x, y, interlaced); - armada_drm_crtc_update_regs(dcrtc, regs); -} - /* The mode_config.mutex will be held for this call */ -static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, - struct drm_display_mode *mode, struct drm_display_mode *adj, - int x, int y, struct drm_framebuffer *old_fb) +static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) { + struct drm_display_mode *adj = &crtc->state->adjusted_mode; struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); struct armada_regs regs[17]; uint32_t lm, rm, tm, bm, val, sclk; unsigned long flags; unsigned i; - bool interlaced; - - drm_framebuffer_get(crtc->primary->fb); - - interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE); - - val = CFG_GRA_ENA; - val |= CFG_GRA_FMT(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt); - val |= CFG_GRA_MOD(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->mod); - - if (drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt > CFG_420) - val |= CFG_PALETTE_ENA; - - drm_to_armada_plane(crtc->primary)->state.ctrl0 = val; - drm_to_armada_plane(crtc->primary)->state.src_hw = - drm_to_armada_plane(crtc->primary)->state.dst_hw = - adj->crtc_vdisplay << 16 | adj->crtc_hdisplay; - drm_to_armada_plane(crtc->primary)->state.dst_yx = 0; + bool interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE); i = 0; rm = adj->crtc_hsync_start - adj->crtc_hdisplay; @@ -644,35 +269,15 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, bm = adj->crtc_vsync_start - adj->crtc_vdisplay; tm = adj->crtc_vtotal - adj->crtc_vsync_end; - DRM_DEBUG_DRIVER("H: %d %d %d %d lm %d rm %d\n", - adj->crtc_hdisplay, - adj->crtc_hsync_start, - adj->crtc_hsync_end, - adj->crtc_htotal, lm, rm); - DRM_DEBUG_DRIVER("V: %d %d %d %d tm %d bm %d\n", - adj->crtc_vdisplay, - adj->crtc_vsync_start, - adj->crtc_vsync_end, - adj->crtc_vtotal, tm, bm); - - /* Wait for pending flips to complete */ - armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary), - MAX_SCHEDULE_TIMEOUT); - - drm_crtc_vblank_off(crtc); - - val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA; - if (val != dcrtc->dumb_ctrl) { - dcrtc->dumb_ctrl = val; - writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL); - } - - /* - * If we are blanked, we would have disabled the clock. Re-enable - * it so that compute_clock() does the right thing. - */ - if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms)) - WARN_ON(clk_prepare_enable(dcrtc->clk)); + DRM_DEBUG_KMS("[CRTC:%d:%s] mode " DRM_MODE_FMT "\n", + crtc->base.id, crtc->name, + adj->base.id, adj->name, adj->vrefresh, adj->clock, + adj->crtc_hdisplay, adj->crtc_hsync_start, + adj->crtc_hsync_end, adj->crtc_htotal, + adj->crtc_vdisplay, adj->crtc_vsync_start, + adj->crtc_vsync_end, adj->crtc_vtotal, + adj->type, adj->flags); + DRM_DEBUG_KMS("lm %d rm %d tm %d bm %d\n", lm, rm, tm, bm); /* Now compute the divider for real */ dcrtc->variant->compute_clock(dcrtc, adj, &sclk); @@ -689,25 +294,20 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, spin_lock_irqsave(&dcrtc->irq_lock, flags); - /* Ensure graphic fifo is enabled */ - armada_reg_queue_mod(regs, i, 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1); - /* Even interlaced/progressive frame */ dcrtc->v[1].spu_v_h_total = adj->crtc_vtotal << 16 | adj->crtc_htotal; dcrtc->v[1].spu_v_porch = tm << 16 | bm; val = adj->crtc_hsync_start; - dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN | - dcrtc->variant->spu_adv_reg; + dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN; if (interlaced) { /* Odd interlaced frame */ + val -= adj->crtc_htotal / 2; + dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN; dcrtc->v[0].spu_v_h_total = dcrtc->v[1].spu_v_h_total + (1 << 16); dcrtc->v[0].spu_v_porch = dcrtc->v[1].spu_v_porch + 1; - val = adj->crtc_hsync_start - adj->crtc_htotal / 2; - dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN | - dcrtc->variant->spu_adv_reg; } else { dcrtc->v[0] = dcrtc->v[1]; } @@ -720,77 +320,136 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc, armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_h_total, LCD_SPUT_V_H_TOTAL); - if (dcrtc->variant->has_spu_adv_reg) { + if (dcrtc->variant->has_spu_adv_reg) armada_reg_queue_mod(regs, i, dcrtc->v[0].spu_adv_reg, ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF | ADV_VSYNCOFFEN, LCD_SPU_ADV_REG); - } val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0; armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1); - val = dcrtc->spu_iopad_ctrl | armada_drm_crtc_calculate_csc(dcrtc); - armada_reg_queue_set(regs, i, val, LCD_SPU_IOPAD_CONTROL); + /* + * The documentation doesn't indicate what the normal state of + * the sync signals are. Sebastian Hesselbart kindly probed + * these signals on his board to determine their state. + * + * The non-inverted state of the sync signals is active high. + * Setting these bits makes the appropriate signal active low. + */ + val = 0; + if (adj->flags & DRM_MODE_FLAG_NCSYNC) + val |= CFG_INV_CSYNC; + if (adj->flags & DRM_MODE_FLAG_NHSYNC) + val |= CFG_INV_HSYNC; + if (adj->flags & DRM_MODE_FLAG_NVSYNC) + val |= CFG_INV_VSYNC; + armada_reg_queue_mod(regs, i, val, CFG_INV_CSYNC | CFG_INV_HSYNC | + CFG_INV_VSYNC, LCD_SPU_DUMB_CTRL); armada_reg_queue_end(regs, i); armada_drm_crtc_update_regs(dcrtc, regs); - - armada_drm_primary_set(crtc, crtc->primary, x, y); spin_unlock_irqrestore(&dcrtc->irq_lock, flags); +} - armada_drm_crtc_update(dcrtc); +static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) +{ + struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - drm_crtc_vblank_on(crtc); - armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms)); + DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); - return 0; + dcrtc->regs_idx = 0; + dcrtc->regs = dcrtc->atomic_regs; } -/* The mode_config.mutex will be held for this call */ -static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, - struct drm_framebuffer *old_fb) +static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct armada_regs regs[4]; - unsigned i; - i = armada_drm_crtc_calc_fb(crtc->primary->fb, crtc->x, crtc->y, regs, - dcrtc->interlaced); - armada_reg_queue_end(regs, i); + DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); + + armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx); + + /* + * If we aren't doing a full modeset, then we need to queue + * the event here. + */ + if (!drm_atomic_crtc_needs_modeset(crtc->state)) { + dcrtc->update_pending = true; + armada_drm_crtc_queue_state_event(crtc); + spin_lock_irq(&dcrtc->irq_lock); + armada_drm_crtc_enable_irq(dcrtc, DUMB_FRAMEDONE_ENA); + spin_unlock_irq(&dcrtc->irq_lock); + } else { + spin_lock_irq(&dcrtc->irq_lock); + armada_drm_crtc_update_regs(dcrtc, dcrtc->regs); + spin_unlock_irq(&dcrtc->irq_lock); + } +} - /* Wait for pending flips to complete */ - armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary), - MAX_SCHEDULE_TIMEOUT); +static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + struct drm_pending_vblank_event *event; - /* Take a reference to the new fb as we're using it */ - drm_framebuffer_get(crtc->primary->fb); + DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); - /* Update the base in the CRTC */ - armada_drm_crtc_update_regs(dcrtc, regs); + drm_crtc_vblank_off(crtc); + armada_drm_crtc_update(dcrtc, false); - /* Drop our previously held reference */ - armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms)); + if (!crtc->state->active) { + /* + * This modeset will be leaving the CRTC disabled, so + * call the backend to disable upstream clocks etc. + */ + if (dcrtc->variant->disable) + dcrtc->variant->disable(dcrtc); - return 0; + /* + * We will not receive any further vblank events. + * Send the flip_done event manually. + */ + event = crtc->state->event; + crtc->state->event = NULL; + if (event) { + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, event); + spin_unlock_irq(&crtc->dev->event_lock); + } + } } -/* The mode_config.mutex will be held for this call */ -static void armada_drm_crtc_disable(struct drm_crtc *crtc) +static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) { - armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); + struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + + DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); + + if (!old_state->active) { + /* + * This modeset is enabling the CRTC after it having + * been disabled. Reverse the call to ->disable in + * the atomic_disable(). + */ + if (dcrtc->variant->enable) + dcrtc->variant->enable(dcrtc, &crtc->state->adjusted_mode); + } + armada_drm_crtc_update(dcrtc, true); + drm_crtc_vblank_on(crtc); - /* Disable our primary plane when we disable the CRTC. */ - crtc->primary->funcs->disable_plane(crtc->primary, NULL); + armada_drm_crtc_queue_state_event(crtc); } static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = { - .dpms = armada_drm_crtc_dpms, - .prepare = armada_drm_crtc_prepare, - .commit = armada_drm_crtc_commit, .mode_fixup = armada_drm_crtc_mode_fixup, - .mode_set = armada_drm_crtc_mode_set, - .mode_set_base = armada_drm_crtc_mode_set_base, - .disable = armada_drm_crtc_disable, + .mode_set_nofb = armada_drm_crtc_mode_set_nofb, + .atomic_begin = armada_drm_crtc_atomic_begin, + .atomic_flush = armada_drm_crtc_atomic_flush, + .atomic_disable = armada_drm_crtc_atomic_disable, + .atomic_enable = armada_drm_crtc_atomic_enable, }; static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix, @@ -883,7 +542,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload) if (!dcrtc->cursor_obj || !h || !w) { spin_lock_irq(&dcrtc->irq_lock); - armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA); dcrtc->cursor_update = false; armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0); spin_unlock_irq(&dcrtc->irq_lock); @@ -907,7 +565,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload) if (dcrtc->cursor_hw_sz != (h << 16 | w)) { spin_lock_irq(&dcrtc->irq_lock); - armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA); dcrtc->cursor_update = false; armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0); spin_unlock_irq(&dcrtc->irq_lock); @@ -1015,8 +672,8 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc) priv->dcrtc[dcrtc->num] = NULL; drm_crtc_cleanup(&dcrtc->crtc); - if (!IS_ERR(dcrtc->clk)) - clk_disable_unprepare(dcrtc->clk); + if (dcrtc->variant->disable) + dcrtc->variant->disable(dcrtc); writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ENA); @@ -1025,361 +682,51 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc) kfree(dcrtc); } -/* - * The mode_config lock is held here, to prevent races between this - * and a mode_set. - */ -static int armada_drm_crtc_page_flip(struct drm_crtc *crtc, - struct drm_framebuffer *fb, struct drm_pending_vblank_event *event, uint32_t page_flip_flags, - struct drm_modeset_acquire_ctx *ctx) -{ - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct armada_plane_work *work; - unsigned i; - int ret; - - /* We don't support changing the pixel format */ - if (fb->format != crtc->primary->fb->format) - return -EINVAL; - - work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary); - if (!work) - return -ENOMEM; - - work->event = event; - work->old_fb = dcrtc->crtc.primary->fb; - - i = armada_drm_crtc_calc_fb(fb, crtc->x, crtc->y, work->regs, - dcrtc->interlaced); - armada_reg_queue_end(work->regs, i); - - /* - * Ensure that we hold a reference on the new framebuffer. - * This has to match the behaviour in mode_set. - */ - drm_framebuffer_get(fb); - - ret = armada_drm_plane_work_queue(dcrtc, work); - if (ret) { - /* Undo our reference above */ - drm_framebuffer_put(fb); - kfree(work); - return ret; - } - - /* - * Don't take a reference on the new framebuffer; - * drm_mode_page_flip_ioctl() has already grabbed a reference and - * will _not_ drop that reference on successful return from this - * function. Simply mark this new framebuffer as the current one. - */ - dcrtc->crtc.primary->fb = fb; - - /* - * Finally, if the display is blanked, we won't receive an - * interrupt, so complete it now. - */ - if (dpms_blanked(dcrtc->dpms)) - armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary); - - return 0; -} - -static int -armada_drm_crtc_set_property(struct drm_crtc *crtc, - struct drm_property *property, uint64_t val) -{ - struct armada_private *priv = crtc->dev->dev_private; - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - bool update_csc = false; - - if (property == priv->csc_yuv_prop) { - dcrtc->csc_yuv_mode = val; - update_csc = true; - } else if (property == priv->csc_rgb_prop) { - dcrtc->csc_rgb_mode = val; - update_csc = true; - } - - if (update_csc) { - uint32_t val; - - val = dcrtc->spu_iopad_ctrl | - armada_drm_crtc_calculate_csc(dcrtc); - writel_relaxed(val, dcrtc->base + LCD_SPU_IOPAD_CONTROL); - } - - return 0; -} - /* These are called under the vbl_lock. */ static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + unsigned long flags; + spin_lock_irqsave(&dcrtc->irq_lock, flags); armada_drm_crtc_enable_irq(dcrtc, VSYNC_IRQ_ENA); + spin_unlock_irqrestore(&dcrtc->irq_lock, flags); return 0; } static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc) { struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); + unsigned long flags; + spin_lock_irqsave(&dcrtc->irq_lock, flags); armada_drm_crtc_disable_irq(dcrtc, VSYNC_IRQ_ENA); + spin_unlock_irqrestore(&dcrtc->irq_lock, flags); } static const struct drm_crtc_funcs armada_crtc_funcs = { + .reset = drm_atomic_helper_crtc_reset, .cursor_set = armada_drm_crtc_cursor_set, .cursor_move = armada_drm_crtc_cursor_move, .destroy = armada_drm_crtc_destroy, - .set_config = drm_crtc_helper_set_config, - .page_flip = armada_drm_crtc_page_flip, - .set_property = armada_drm_crtc_set_property, + .set_config = drm_atomic_helper_set_config, + .page_flip = drm_atomic_helper_page_flip, + .atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .enable_vblank = armada_drm_crtc_enable_vblank, .disable_vblank = armada_drm_crtc_disable_vblank, }; -static void armada_drm_primary_update_state(struct drm_plane_state *state, - struct armada_regs *regs) -{ - struct armada_plane *dplane = drm_to_armada_plane(state->plane); - struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc); - struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb); - bool was_disabled; - unsigned int idx = 0; - u32 val; - - val = CFG_GRA_FMT(dfb->fmt) | CFG_GRA_MOD(dfb->mod); - if (dfb->fmt > CFG_420) - val |= CFG_PALETTE_ENA; - if (state->visible) - val |= CFG_GRA_ENA; - if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst)) - val |= CFG_GRA_HSMOOTH; - - was_disabled = !(dplane->state.ctrl0 & CFG_GRA_ENA); - if (was_disabled) - armada_reg_queue_mod(regs, idx, - 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1); - - dplane->state.ctrl0 = val; - dplane->state.src_hw = (drm_rect_height(&state->src) & 0xffff0000) | - drm_rect_width(&state->src) >> 16; - dplane->state.dst_hw = drm_rect_height(&state->dst) << 16 | - drm_rect_width(&state->dst); - dplane->state.dst_yx = state->dst.y1 << 16 | state->dst.x1; - - armada_drm_gra_plane_regs(regs + idx, &dfb->fb, &dplane->state, - state->src.x1 >> 16, state->src.y1 >> 16, - dcrtc->interlaced); - - dplane->state.vsync_update = !was_disabled; - dplane->state.changed = true; -} - -static int armada_drm_primary_update(struct drm_plane *plane, - struct drm_crtc *crtc, struct drm_framebuffer *fb, - int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h, - uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h, - struct drm_modeset_acquire_ctx *ctx) -{ - struct armada_plane *dplane = drm_to_armada_plane(plane); - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct armada_plane_work *work; - struct drm_plane_state state = { - .plane = plane, - .crtc = crtc, - .fb = fb, - .src_x = src_x, - .src_y = src_y, - .src_w = src_w, - .src_h = src_h, - .crtc_x = crtc_x, - .crtc_y = crtc_y, - .crtc_w = crtc_w, - .crtc_h = crtc_h, - .rotation = DRM_MODE_ROTATE_0, - }; - struct drm_crtc_state crtc_state = { - .crtc = crtc, - .enable = crtc->enabled, - .mode = crtc->mode, - }; - int ret; - - ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0, - INT_MAX, true, false); - if (ret) - return ret; - - work = &dplane->works[dplane->next_work]; - work->fn = armada_drm_crtc_complete_frame_work; - - if (plane->fb != fb) { - /* - * Take a reference on the new framebuffer - we want to - * hold on to it while the hardware is displaying it. - */ - drm_framebuffer_reference(fb); - - work->old_fb = plane->fb; - } else { - work->old_fb = NULL; - } - - armada_drm_primary_update_state(&state, work->regs); - - if (!dplane->state.changed) - return 0; - - /* Wait for pending work to complete */ - if (armada_drm_plane_work_wait(dplane, HZ / 10) == 0) - armada_drm_plane_work_cancel(dcrtc, dplane); - - if (!dplane->state.vsync_update) { - work->fn(dcrtc, work); - if (work->old_fb) - drm_framebuffer_unreference(work->old_fb); - return 0; - } - - /* Queue it for update on the next interrupt if we are enabled */ - ret = armada_drm_plane_work_queue(dcrtc, work); - if (ret) { - work->fn(dcrtc, work); - if (work->old_fb) - drm_framebuffer_unreference(work->old_fb); - } - - dplane->next_work = !dplane->next_work; - - return 0; -} - -int armada_drm_plane_disable(struct drm_plane *plane, - struct drm_modeset_acquire_ctx *ctx) -{ - struct armada_plane *dplane = drm_to_armada_plane(plane); - struct armada_crtc *dcrtc; - struct armada_plane_work *work; - unsigned int idx = 0; - u32 sram_para1, enable_mask; - - if (!plane->crtc) - return 0; - - /* - * Arrange to power down most RAMs and FIFOs if this is the primary - * plane, otherwise just the YUV FIFOs for the overlay plane. - */ - if (plane->type == DRM_PLANE_TYPE_PRIMARY) { - sram_para1 = CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 | - CFG_PDWN32x32 | CFG_PDWN64x66; - enable_mask = CFG_GRA_ENA; - } else { - sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66; - enable_mask = CFG_DMA_ENA; - } - - dplane->state.ctrl0 &= ~enable_mask; - - dcrtc = drm_to_armada_crtc(plane->crtc); - - /* - * Try to disable the plane and drop our ref on the framebuffer - * at the next frame update. If we fail for any reason, disable - * the plane immediately. - */ - work = &dplane->works[dplane->next_work]; - work->fn = armada_drm_crtc_complete_disable_work; - work->cancel = armada_drm_crtc_complete_disable_work; - work->old_fb = plane->fb; - - armada_reg_queue_mod(work->regs, idx, - 0, enable_mask, LCD_SPU_DMA_CTRL0); - armada_reg_queue_mod(work->regs, idx, - sram_para1, 0, LCD_SPU_SRAM_PARA1); - armada_reg_queue_end(work->regs, idx); - - /* Wait for any preceding work to complete, but don't wedge */ - if (WARN_ON(!armada_drm_plane_work_wait(dplane, HZ))) - armada_drm_plane_work_cancel(dcrtc, dplane); - - if (armada_drm_plane_work_queue(dcrtc, work)) { - work->fn(dcrtc, work); - if (work->old_fb) - drm_framebuffer_unreference(work->old_fb); - } - - dplane->next_work = !dplane->next_work; - - return 0; -} - -static const struct drm_plane_funcs armada_primary_plane_funcs = { - .update_plane = armada_drm_primary_update, - .disable_plane = armada_drm_plane_disable, - .destroy = drm_primary_helper_destroy, -}; - -int armada_drm_plane_init(struct armada_plane *plane) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(plane->works); i++) - plane->works[i].plane = &plane->base; - - init_waitqueue_head(&plane->frame_wait); - - return 0; -} - -static const struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = { - { CSC_AUTO, "Auto" }, - { CSC_YUV_CCIR601, "CCIR601" }, - { CSC_YUV_CCIR709, "CCIR709" }, -}; - -static const struct drm_prop_enum_list armada_drm_csc_rgb_enum_list[] = { - { CSC_AUTO, "Auto" }, - { CSC_RGB_COMPUTER, "Computer system" }, - { CSC_RGB_STUDIO, "Studio" }, -}; - -static int armada_drm_crtc_create_properties(struct drm_device *dev) -{ - struct armada_private *priv = dev->dev_private; - - if (priv->csc_yuv_prop) - return 0; - - priv->csc_yuv_prop = drm_property_create_enum(dev, 0, - "CSC_YUV", armada_drm_csc_yuv_enum_list, - ARRAY_SIZE(armada_drm_csc_yuv_enum_list)); - priv->csc_rgb_prop = drm_property_create_enum(dev, 0, - "CSC_RGB", armada_drm_csc_rgb_enum_list, - ARRAY_SIZE(armada_drm_csc_rgb_enum_list)); - - if (!priv->csc_yuv_prop || !priv->csc_rgb_prop) - return -ENOMEM; - - return 0; -} - static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, struct resource *res, int irq, const struct armada_variant *variant, struct device_node *port) { struct armada_private *priv = drm->dev_private; struct armada_crtc *dcrtc; - struct armada_plane *primary; + struct drm_plane *primary; void __iomem *base; int ret; - ret = armada_drm_crtc_create_properties(drm); - if (ret) - return ret; - base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) return PTR_ERR(base); @@ -1397,8 +744,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, dcrtc->base = base; dcrtc->num = drm->mode_config.num_crtc; dcrtc->clk = ERR_PTR(-EINVAL); - dcrtc->csc_yuv_mode = CSC_AUTO; - dcrtc->csc_rgb_mode = CSC_AUTO; dcrtc->cfg_dumb_ctrl = DUMB24_RGB888_0; dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24; spin_lock_init(&dcrtc->irq_lock); @@ -1415,6 +760,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1); writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1); writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA); + readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR); writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR); ret = devm_request_irq(dev, irq, armada_drm_irq, 0, "armada_drm_crtc", @@ -1441,39 +787,23 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev, goto err_crtc; } - ret = armada_drm_plane_init(primary); - if (ret) { - kfree(primary); - goto err_crtc; - } - - ret = drm_universal_plane_init(drm, &primary->base, 0, - &armada_primary_plane_funcs, - armada_primary_formats, - ARRAY_SIZE(armada_primary_formats), - NULL, - DRM_PLANE_TYPE_PRIMARY, NULL); + ret = armada_drm_primary_plane_init(drm, primary); if (ret) { kfree(primary); goto err_crtc; } - ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL, + ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, primary, NULL, &armada_crtc_funcs, NULL); if (ret) goto err_crtc_init; drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs); - drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop, - dcrtc->csc_yuv_mode); - drm_object_attach_property(&dcrtc->crtc.base, priv->csc_rgb_prop, - dcrtc->csc_rgb_mode); - return armada_overlay_plane_create(drm, 1 << dcrtc->num); err_crtc_init: - primary->base.funcs->destroy(&primary->base); + primary->funcs->destroy(primary); err_crtc: kfree(dcrtc); diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h index 445829b8877a..7ebd337b60af 100644 --- a/drivers/gpu/drm/armada/armada_crtc.h +++ b/drivers/gpu/drm/armada/armada_crtc.h @@ -32,49 +32,8 @@ struct armada_regs { armada_reg_queue_mod(_r, _i, 0, 0, ~0) struct armada_crtc; -struct armada_plane; struct armada_variant; -struct armada_plane_work { - void (*fn)(struct armada_crtc *, struct armada_plane_work *); - void (*cancel)(struct armada_crtc *, struct armada_plane_work *); - bool need_kfree; - struct drm_plane *plane; - struct drm_framebuffer *old_fb; - struct drm_pending_vblank_event *event; - struct armada_regs regs[14]; -}; - -struct armada_plane_state { - u16 src_x; - u16 src_y; - u32 src_hw; - u32 dst_hw; - u32 dst_yx; - u32 ctrl0; - bool changed; - bool vsync_update; -}; - -struct armada_plane { - struct drm_plane base; - wait_queue_head_t frame_wait; - bool next_work; - struct armada_plane_work works[2]; - struct armada_plane_work *work; - struct armada_plane_state state; -}; -#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base) - -int armada_drm_plane_init(struct armada_plane *plane); -int armada_drm_plane_work_queue(struct armada_crtc *dcrtc, - struct armada_plane_work *work); -int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout); -void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc, - struct armada_plane *plane); -void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb, - int x, int y); - struct armada_crtc { struct drm_crtc crtc; const struct armada_variant *variant; @@ -89,10 +48,6 @@ struct armada_crtc { } v[2]; bool interlaced; bool cursor_update; - uint8_t csc_yuv_mode; - uint8_t csc_rgb_mode; - - struct drm_plane *plane; struct armada_gem_object *cursor_obj; int cursor_x; @@ -102,21 +57,22 @@ struct armada_crtc { uint32_t cursor_w; uint32_t cursor_h; - int dpms; uint32_t cfg_dumb_ctrl; - uint32_t dumb_ctrl; uint32_t spu_iopad_ctrl; spinlock_t irq_lock; uint32_t irq_ena; + + bool update_pending; + struct drm_pending_vblank_event *event; + struct armada_regs atomic_regs[32]; + struct armada_regs *regs; + unsigned int regs_idx; }; #define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc) void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *); -int armada_drm_plane_disable(struct drm_plane *plane, - struct drm_modeset_acquire_ctx *ctx); - extern struct platform_driver armada_lcd_platform_driver; #endif diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h index cc4c557c9f66..f09083ff15d3 100644 --- a/drivers/gpu/drm/armada/armada_drm.h +++ b/drivers/gpu/drm/armada/armada_drm.h @@ -42,11 +42,12 @@ struct armada_private; struct armada_variant { bool has_spu_adv_reg; - uint32_t spu_adv_reg; int (*init)(struct armada_crtc *, struct device *); int (*compute_clock)(struct armada_crtc *, const struct drm_display_mode *, uint32_t *); + void (*disable)(struct armada_crtc *); + void (*enable)(struct armada_crtc *, const struct drm_display_mode *); }; /* Variant ops */ @@ -54,14 +55,10 @@ extern const struct armada_variant armada510_ops; struct armada_private { struct drm_device drm; - struct work_struct fb_unref_work; - DECLARE_KFIFO(fb_unref, struct drm_framebuffer *, 8); struct drm_fb_helper *fbdev; struct armada_crtc *dcrtc[2]; struct drm_mm linear; /* protected by linear_lock */ struct mutex linear_lock; - struct drm_property *csc_yuv_prop; - struct drm_property *csc_rgb_prop; struct drm_property *colorkey_prop; struct drm_property *colorkey_min_prop; struct drm_property *colorkey_max_prop; @@ -76,13 +73,6 @@ struct armada_private { #endif }; -void __armada_drm_queue_unref_work(struct drm_device *, - struct drm_framebuffer *); -void armada_drm_queue_unref_work(struct drm_device *, - struct drm_framebuffer *); - -extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs; - int armada_fbdev_init(struct drm_device *); void armada_fbdev_fini(struct drm_device *); diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index 4b11b6b52f1d..fa31589b4fc0 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -9,46 +9,18 @@ #include <linux/component.h> #include <linux/module.h> #include <linux/of_graph.h> +#include <drm/drm_atomic_helper.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_of.h> #include "armada_crtc.h" #include "armada_drm.h" #include "armada_gem.h" +#include "armada_fb.h" #include "armada_hw.h" #include <drm/armada_drm.h> #include "armada_ioctlP.h" -static void armada_drm_unref_work(struct work_struct *work) -{ - struct armada_private *priv = - container_of(work, struct armada_private, fb_unref_work); - struct drm_framebuffer *fb; - - while (kfifo_get(&priv->fb_unref, &fb)) - drm_framebuffer_put(fb); -} - -/* Must be called with dev->event_lock held */ -void __armada_drm_queue_unref_work(struct drm_device *dev, - struct drm_framebuffer *fb) -{ - struct armada_private *priv = dev->dev_private; - - WARN_ON(!kfifo_put(&priv->fb_unref, fb)); - schedule_work(&priv->fb_unref_work); -} - -void armada_drm_queue_unref_work(struct drm_device *dev, - struct drm_framebuffer *fb) -{ - unsigned long flags; - - spin_lock_irqsave(&dev->event_lock, flags); - __armada_drm_queue_unref_work(dev, fb); - spin_unlock_irqrestore(&dev->event_lock, flags); -} - static struct drm_ioctl_desc armada_ioctls[] = { DRM_IOCTL_DEF_DRV(ARMADA_GEM_CREATE, armada_gem_create_ioctl,0), DRM_IOCTL_DEF_DRV(ARMADA_GEM_MMAP, armada_gem_mmap_ioctl, 0), @@ -72,11 +44,18 @@ static struct drm_driver armada_drm_driver = { .desc = "Armada SoC DRM", .date = "20120730", .driver_features = DRIVER_GEM | DRIVER_MODESET | - DRIVER_PRIME, + DRIVER_PRIME | DRIVER_ATOMIC, .ioctls = armada_ioctls, .fops = &armada_drm_fops, }; +static const struct drm_mode_config_funcs armada_drm_mode_config_funcs = { + .fb_create = armada_fb_create, + .output_poll_changed = drm_fb_helper_output_poll_changed, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + static int armada_drm_bind(struct device *dev) { struct armada_private *priv; @@ -109,7 +88,7 @@ static int armada_drm_bind(struct device *dev) /* * The drm_device structure must be at the start of - * armada_private for drm_dev_unref() to work correctly. + * armada_private for drm_dev_put() to work correctly. */ BUILD_BUG_ON(offsetof(struct armada_private, drm) != 0); @@ -125,9 +104,6 @@ static int armada_drm_bind(struct device *dev) dev_set_drvdata(dev, &priv->drm); - INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work); - INIT_KFIFO(priv->fb_unref); - /* Mode setting support */ drm_mode_config_init(&priv->drm); priv->drm.mode_config.min_width = 320; @@ -155,6 +131,8 @@ static int armada_drm_bind(struct device *dev) priv->drm.irq_enabled = true; + drm_mode_config_reset(&priv->drm); + ret = armada_fbdev_init(&priv->drm); if (ret) goto err_comp; @@ -179,8 +157,7 @@ static int armada_drm_bind(struct device *dev) err_kms: drm_mode_config_cleanup(&priv->drm); drm_mm_takedown(&priv->linear); - flush_work(&priv->fb_unref_work); - drm_dev_unref(&priv->drm); + drm_dev_put(&priv->drm); return ret; } @@ -198,9 +175,8 @@ static void armada_drm_unbind(struct device *dev) drm_mode_config_cleanup(&priv->drm); drm_mm_takedown(&priv->linear); - flush_work(&priv->fb_unref_work); - drm_dev_unref(&priv->drm); + drm_dev_put(&priv->drm); } static int compare_of(struct device *dev, void *data) diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c index edd15126bde9..6bd638a54579 100644 --- a/drivers/gpu/drm/armada/armada_fb.c +++ b/drivers/gpu/drm/armada/armada_fb.c @@ -84,7 +84,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev, return dfb; } -static struct drm_framebuffer *armada_fb_create(struct drm_device *dev, +struct drm_framebuffer *armada_fb_create(struct drm_device *dev, struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode) { struct armada_gem_object *obj; @@ -138,8 +138,3 @@ static struct drm_framebuffer *armada_fb_create(struct drm_device *dev, DRM_ERROR("failed to initialize framebuffer: %d\n", ret); return ERR_PTR(ret); } - -const struct drm_mode_config_funcs armada_drm_mode_config_funcs = { - .fb_create = armada_fb_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, -}; diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h index 5c130ff5da77..476daad0a36a 100644 --- a/drivers/gpu/drm/armada/armada_fb.h +++ b/drivers/gpu/drm/armada/armada_fb.h @@ -19,5 +19,6 @@ struct armada_framebuffer { struct armada_framebuffer *armada_framebuffer_create(struct drm_device *, const struct drm_mode_fb_cmd2 *, struct armada_gem_object *); - +struct drm_framebuffer *armada_fb_create(struct drm_device *dev, + struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode); #endif diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index 2a59db0994b2..8d23700848df 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -24,7 +24,7 @@ static /*const*/ struct fb_ops armada_fb_ops = { .fb_imageblit = drm_fb_helper_cfb_imageblit, }; -static int armada_fb_create(struct drm_fb_helper *fbh, +static int armada_fbdev_create(struct drm_fb_helper *fbh, struct drm_fb_helper_surface_size *sizes) { struct drm_device *dev = fbh->dev; @@ -108,7 +108,7 @@ static int armada_fb_probe(struct drm_fb_helper *fbh, int ret = 0; if (!fbh->fb) { - ret = armada_fb_create(fbh, sizes); + ret = armada_fbdev_create(fbh, sizes); if (ret == 0) ret = 1; } diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 3fb37c75c065..892c1d9304bb 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -13,25 +13,14 @@ #include <drm/armada_drm.h> #include "armada_ioctlP.h" -static int armada_gem_vm_fault(struct vm_fault *vmf) +static vm_fault_t armada_gem_vm_fault(struct vm_fault *vmf) { struct drm_gem_object *gobj = vmf->vma->vm_private_data; struct armada_gem_object *obj = drm_to_armada_gem(gobj); unsigned long pfn = obj->phys_addr >> PAGE_SHIFT; - int ret; pfn += (vmf->address - vmf->vma->vm_start) >> PAGE_SHIFT; - ret = vm_insert_pfn(vmf->vma, vmf->address, pfn); - - switch (ret) { - case 0: - case -EBUSY: - return VM_FAULT_NOPAGE; - case -ENOMEM: - return VM_FAULT_OOM; - default: - return VM_FAULT_SIGBUS; - } + return vmf_insert_pfn(vmf->vma, vmf->address, pfn); } const struct vm_operations_struct armada_gem_vm_ops = { diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h index 27319a8335e2..277580b36758 100644 --- a/drivers/gpu/drm/armada/armada_hw.h +++ b/drivers/gpu/drm/armada/armada_hw.h @@ -160,6 +160,7 @@ enum { CFG_ALPHAM_GRA = 0x1 << 16, CFG_ALPHAM_CFG = 0x2 << 16, CFG_ALPHA_MASK = 0xff << 8, +#define CFG_ALPHA(x) ((x) << 8) CFG_PIXCMD_MASK = 0xff, }; @@ -315,4 +316,19 @@ enum { PWRDN_IRQ_LEVEL = 1 << 0, }; +static inline u32 armada_rect_hw_fp(struct drm_rect *r) +{ + return (drm_rect_height(r) & 0xffff0000) | drm_rect_width(r) >> 16; +} + +static inline u32 armada_rect_hw(struct drm_rect *r) +{ + return drm_rect_height(r) << 16 | (drm_rect_width(r) & 0x0000ffff); +} + +static inline u32 armada_rect_yx(struct drm_rect *r) +{ + return (r)->y1 << 16 | ((r)->x1 & 0x0000ffff); +} + #endif diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index c391955009d6..eb7dfb65ef47 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -7,346 +7,468 @@ * published by the Free Software Foundation. */ #include <drm/drmP.h> +#include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_plane_helper.h> +#include <drm/armada_drm.h> #include "armada_crtc.h" #include "armada_drm.h" #include "armada_fb.h" #include "armada_gem.h" #include "armada_hw.h" -#include <drm/armada_drm.h> #include "armada_ioctlP.h" +#include "armada_plane.h" #include "armada_trace.h" -struct armada_ovl_plane_properties { - uint32_t colorkey_yr; - uint32_t colorkey_ug; - uint32_t colorkey_vb; -#define K2R(val) (((val) >> 0) & 0xff) -#define K2G(val) (((val) >> 8) & 0xff) -#define K2B(val) (((val) >> 16) & 0xff) - int16_t brightness; - uint16_t contrast; - uint16_t saturation; - uint32_t colorkey_mode; -}; - -struct armada_ovl_plane { - struct armada_plane base; - struct armada_ovl_plane_properties prop; +#define DEFAULT_BRIGHTNESS 0 +#define DEFAULT_CONTRAST 0x4000 +#define DEFAULT_SATURATION 0x4000 +#define DEFAULT_ENCODING DRM_COLOR_YCBCR_BT601 + +struct armada_overlay_state { + struct drm_plane_state base; + u32 colorkey_yr; + u32 colorkey_ug; + u32 colorkey_vb; + u32 colorkey_mode; + u32 colorkey_enable; + s16 brightness; + u16 contrast; + u16 saturation; }; -#define drm_to_armada_ovl_plane(p) \ - container_of(p, struct armada_ovl_plane, base.base) - +#define drm_to_overlay_state(s) \ + container_of(s, struct armada_overlay_state, base) -static void -armada_ovl_update_attr(struct armada_ovl_plane_properties *prop, - struct armada_crtc *dcrtc) +static inline u32 armada_spu_contrast(struct drm_plane_state *state) { - writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y); - writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U); - writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V); + return drm_to_overlay_state(state)->brightness << 16 | + drm_to_overlay_state(state)->contrast; +} - writel_relaxed(prop->brightness << 16 | prop->contrast, - dcrtc->base + LCD_SPU_CONTRAST); +static inline u32 armada_spu_saturation(struct drm_plane_state *state) +{ /* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */ - writel_relaxed(prop->saturation << 16, - dcrtc->base + LCD_SPU_SATURATION); - writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE); - - spin_lock_irq(&dcrtc->irq_lock); - armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA, - CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK, - dcrtc->base + LCD_SPU_DMA_CTRL1); + return drm_to_overlay_state(state)->saturation << 16; +} - armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG); - spin_unlock_irq(&dcrtc->irq_lock); +static inline u32 armada_csc(struct drm_plane_state *state) +{ + /* + * The CFG_CSC_RGB_* settings control the output of the colour space + * converter, setting the range of output values it produces. Since + * we will be blending with the full-range graphics, we need to + * produce full-range RGB output from the conversion. + */ + return CFG_CSC_RGB_COMPUTER | + (state->color_encoding == DRM_COLOR_YCBCR_BT709 ? + CFG_CSC_YUV_CCIR709 : CFG_CSC_YUV_CCIR601); } /* === Plane support === */ -static void armada_ovl_plane_work(struct armada_crtc *dcrtc, - struct armada_plane_work *work) +static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane, + struct drm_plane_state *old_state) { - unsigned long flags; + struct drm_plane_state *state = plane->state; + struct armada_crtc *dcrtc; + struct armada_regs *regs; + unsigned int idx; + u32 cfg, cfg_mask, val; - trace_armada_ovl_plane_work(&dcrtc->crtc, work->plane); + DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name); - spin_lock_irqsave(&dcrtc->irq_lock, flags); - armada_drm_crtc_update_regs(dcrtc, work->regs); - spin_unlock_irqrestore(&dcrtc->irq_lock, flags); -} - -static void armada_ovl_plane_update_state(struct drm_plane_state *state, - struct armada_regs *regs) -{ - struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(state->plane); - struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb); - const struct drm_format_info *format; - unsigned int idx = 0; - bool fb_changed; - u32 val, ctrl0; - u16 src_x, src_y; + if (!state->fb || WARN_ON(!state->crtc)) + return; - ctrl0 = CFG_DMA_FMT(dfb->fmt) | CFG_DMA_MOD(dfb->mod) | CFG_CBSH_ENA; - if (state->visible) - ctrl0 |= CFG_DMA_ENA; - if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst)) - ctrl0 |= CFG_DMA_HSMOOTH; + DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n", + plane->base.id, plane->name, + state->crtc->base.id, state->crtc->name, + state->fb->base.id, + old_state->visible, state->visible); - /* - * Shifting a YUV packed format image by one pixel causes the U/V - * planes to swap. Compensate for it by also toggling the UV swap. - */ - format = dfb->fb.format; - if (format->num_planes == 1 && state->src.x1 >> 16 & (format->hsub - 1)) - ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV); + dcrtc = drm_to_armada_crtc(state->crtc); + regs = dcrtc->regs + dcrtc->regs_idx; - if (~dplane->base.state.ctrl0 & ctrl0 & CFG_DMA_ENA) { - /* Power up the Y/U/V FIFOs on ENA 0->1 transitions */ + idx = 0; + if (!old_state->visible && state->visible) armada_reg_queue_mod(regs, idx, 0, CFG_PDWN16x66 | CFG_PDWN32x66, LCD_SPU_SRAM_PARA1); - } - - fb_changed = dplane->base.base.fb != &dfb->fb || - dplane->base.state.src_x != state->src.x1 >> 16 || - dplane->base.state.src_y != state->src.y1 >> 16; - - dplane->base.state.vsync_update = fb_changed; - + val = armada_rect_hw_fp(&state->src); + if (armada_rect_hw_fp(&old_state->src) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_HPXL_VLN); + val = armada_rect_yx(&state->dst); + if (armada_rect_yx(&old_state->dst) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_OVSA_HPXL_VLN); + val = armada_rect_hw(&state->dst); + if (armada_rect_hw(&old_state->dst) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_DZM_HPXL_VLN); /* FIXME: overlay on an interlaced display */ - if (fb_changed) { - u32 addrs[3]; - - dplane->base.state.src_y = src_y = state->src.y1 >> 16; - dplane->base.state.src_x = src_x = state->src.x1 >> 16; + if (old_state->src.x1 != state->src.x1 || + old_state->src.y1 != state->src.y1 || + old_state->fb != state->fb) { + const struct drm_format_info *format; + u16 src_x, pitches[3]; + u32 addrs[2][3]; - armada_drm_plane_calc_addrs(addrs, &dfb->fb, src_x, src_y); + armada_drm_plane_calc(state, addrs, pitches, false); - armada_reg_queue_set(regs, idx, addrs[0], + armada_reg_queue_set(regs, idx, addrs[0][0], LCD_SPU_DMA_START_ADDR_Y0); - armada_reg_queue_set(regs, idx, addrs[1], + armada_reg_queue_set(regs, idx, addrs[0][1], LCD_SPU_DMA_START_ADDR_U0); - armada_reg_queue_set(regs, idx, addrs[2], + armada_reg_queue_set(regs, idx, addrs[0][2], LCD_SPU_DMA_START_ADDR_V0); - armada_reg_queue_set(regs, idx, addrs[0], + armada_reg_queue_set(regs, idx, addrs[1][0], LCD_SPU_DMA_START_ADDR_Y1); - armada_reg_queue_set(regs, idx, addrs[1], + armada_reg_queue_set(regs, idx, addrs[1][1], LCD_SPU_DMA_START_ADDR_U1); - armada_reg_queue_set(regs, idx, addrs[2], + armada_reg_queue_set(regs, idx, addrs[1][2], LCD_SPU_DMA_START_ADDR_V1); - val = dfb->fb.pitches[0] << 16 | dfb->fb.pitches[0]; - armada_reg_queue_set(regs, idx, val, - LCD_SPU_DMA_PITCH_YC); - val = dfb->fb.pitches[1] << 16 | dfb->fb.pitches[2]; - armada_reg_queue_set(regs, idx, val, - LCD_SPU_DMA_PITCH_UV); - } + val = pitches[0] << 16 | pitches[0]; + armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_YC); + val = pitches[1] << 16 | pitches[2]; + armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_UV); - val = (drm_rect_height(&state->src) & 0xffff0000) | - drm_rect_width(&state->src) >> 16; - if (dplane->base.state.src_hw != val) { - dplane->base.state.src_hw = val; - armada_reg_queue_set(regs, idx, val, - LCD_SPU_DMA_HPXL_VLN); - } + cfg = CFG_DMA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) | + CFG_DMA_MOD(drm_fb_to_armada_fb(state->fb)->mod) | + CFG_CBSH_ENA; + if (state->visible) + cfg |= CFG_DMA_ENA; - val = drm_rect_height(&state->dst) << 16 | drm_rect_width(&state->dst); - if (dplane->base.state.dst_hw != val) { - dplane->base.state.dst_hw = val; - armada_reg_queue_set(regs, idx, val, - LCD_SPU_DZM_HPXL_VLN); + /* + * Shifting a YUV packed format image by one pixel causes the + * U/V planes to swap. Compensate for it by also toggling + * the UV swap. + */ + format = state->fb->format; + src_x = state->src.x1 >> 16; + if (format->num_planes == 1 && src_x & (format->hsub - 1)) + cfg ^= CFG_DMA_MOD(CFG_SWAPUV); + cfg_mask = CFG_CBSH_ENA | CFG_DMAFORMAT | + CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | + CFG_SWAPYU | CFG_YUV2RGB) | + CFG_DMA_FTOGGLE | CFG_DMA_TSTMODE | + CFG_DMA_ENA; + } else if (old_state->visible != state->visible) { + cfg = state->visible ? CFG_DMA_ENA : 0; + cfg_mask = CFG_DMA_ENA; + } else { + cfg = cfg_mask = 0; } - - val = state->dst.y1 << 16 | state->dst.x1; - if (dplane->base.state.dst_yx != val) { - dplane->base.state.dst_yx = val; - armada_reg_queue_set(regs, idx, val, - LCD_SPU_DMA_OVSA_HPXL_VLN); + if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) || + drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) { + cfg_mask |= CFG_DMA_HSMOOTH; + if (drm_rect_width(&state->src) >> 16 != + drm_rect_width(&state->dst)) + cfg |= CFG_DMA_HSMOOTH; } - if (dplane->base.state.ctrl0 != ctrl0) { - dplane->base.state.ctrl0 = ctrl0; - armada_reg_queue_mod(regs, idx, ctrl0, - CFG_CBSH_ENA | CFG_DMAFORMAT | CFG_DMA_FTOGGLE | - CFG_DMA_HSMOOTH | CFG_DMA_TSTMODE | - CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | CFG_SWAPYU | - CFG_YUV2RGB) | CFG_DMA_ENA, - LCD_SPU_DMA_CTRL0); - dplane->base.state.vsync_update = true; - } + if (cfg_mask) + armada_reg_queue_mod(regs, idx, cfg, cfg_mask, + LCD_SPU_DMA_CTRL0); + + val = armada_spu_contrast(state); + if ((!old_state->visible && state->visible) || + armada_spu_contrast(old_state) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_CONTRAST); + val = armada_spu_saturation(state); + if ((!old_state->visible && state->visible) || + armada_spu_saturation(old_state) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION); + if (!old_state->visible && state->visible) + armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE); + val = armada_csc(state); + if ((!old_state->visible && state->visible) || + armada_csc(old_state) != val) + armada_reg_queue_mod(regs, idx, val, CFG_CSC_MASK, + LCD_SPU_IOPAD_CONTROL); + val = drm_to_overlay_state(state)->colorkey_yr; + if ((!old_state->visible && state->visible) || + drm_to_overlay_state(old_state)->colorkey_yr != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_Y); + val = drm_to_overlay_state(state)->colorkey_ug; + if ((!old_state->visible && state->visible) || + drm_to_overlay_state(old_state)->colorkey_ug != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_U); + val = drm_to_overlay_state(state)->colorkey_vb; + if ((!old_state->visible && state->visible) || + drm_to_overlay_state(old_state)->colorkey_vb != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_V); + val = drm_to_overlay_state(state)->colorkey_mode; + if ((!old_state->visible && state->visible) || + drm_to_overlay_state(old_state)->colorkey_mode != val) + armada_reg_queue_mod(regs, idx, val, CFG_CKMODE_MASK | + CFG_ALPHAM_MASK | CFG_ALPHA_MASK, + LCD_SPU_DMA_CTRL1); + val = drm_to_overlay_state(state)->colorkey_enable; + if (((!old_state->visible && state->visible) || + drm_to_overlay_state(old_state)->colorkey_enable != val) && + dcrtc->variant->has_spu_adv_reg) + armada_reg_queue_mod(regs, idx, val, ADV_GRACOLORKEY | + ADV_VIDCOLORKEY, LCD_SPU_ADV_REG); + + dcrtc->regs_idx += idx; +} + +static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct armada_crtc *dcrtc; + struct armada_regs *regs; + unsigned int idx = 0; + + DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name); + + if (!old_state->crtc) + return; - dplane->base.state.changed = idx != 0; + DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n", + plane->base.id, plane->name, + old_state->crtc->base.id, old_state->crtc->name, + old_state->fb->base.id); - armada_reg_queue_end(regs, idx); + dcrtc = drm_to_armada_crtc(old_state->crtc); + regs = dcrtc->regs + dcrtc->regs_idx; + + /* Disable plane and power down the YUV FIFOs */ + armada_reg_queue_mod(regs, idx, 0, CFG_DMA_ENA, LCD_SPU_DMA_CTRL0); + armada_reg_queue_mod(regs, idx, CFG_PDWN16x66 | CFG_PDWN32x66, 0, + LCD_SPU_SRAM_PARA1); + + dcrtc->regs_idx += idx; } +static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = { + .prepare_fb = armada_drm_plane_prepare_fb, + .cleanup_fb = armada_drm_plane_cleanup_fb, + .atomic_check = armada_drm_plane_atomic_check, + .atomic_update = armada_drm_overlay_plane_atomic_update, + .atomic_disable = armada_drm_overlay_plane_atomic_disable, +}; + static int -armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, +armada_overlay_plane_update(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_framebuffer *fb, int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h, uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h, struct drm_modeset_acquire_ctx *ctx) { - struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); - struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc); - struct armada_plane_work *work; - struct drm_plane_state state = { - .plane = plane, - .crtc = crtc, - .fb = fb, - .src_x = src_x, - .src_y = src_y, - .src_w = src_w, - .src_h = src_h, - .crtc_x = crtc_x, - .crtc_y = crtc_y, - .crtc_w = crtc_w, - .crtc_h = crtc_h, - .rotation = DRM_MODE_ROTATE_0, - }; - struct drm_crtc_state crtc_state = { - .crtc = crtc, - .enable = crtc->enabled, - .mode = crtc->mode, - }; - int ret; + struct drm_atomic_state *state; + struct drm_plane_state *plane_state; + int ret = 0; trace_armada_ovl_plane_update(plane, crtc, fb, crtc_x, crtc_y, crtc_w, crtc_h, src_x, src_y, src_w, src_h); - ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0, - INT_MAX, true, false); - if (ret) - return ret; - - work = &dplane->base.works[dplane->base.next_work]; - - if (plane->fb != fb) { - /* - * Take a reference on the new framebuffer - we want to - * hold on to it while the hardware is displaying it. - */ - drm_framebuffer_reference(fb); + state = drm_atomic_state_alloc(plane->dev); + if (!state) + return -ENOMEM; - work->old_fb = plane->fb; - } else { - work->old_fb = NULL; + state->acquire_ctx = ctx; + plane_state = drm_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) { + ret = PTR_ERR(plane_state); + goto fail; } - armada_ovl_plane_update_state(&state, work->regs); - - if (!dplane->base.state.changed) - return 0; - - /* Wait for pending work to complete */ - if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0) - armada_drm_plane_work_cancel(dcrtc, &dplane->base); + ret = drm_atomic_set_crtc_for_plane(plane_state, crtc); + if (ret != 0) + goto fail; + + drm_atomic_set_fb_for_plane(plane_state, fb); + plane_state->crtc_x = crtc_x; + plane_state->crtc_y = crtc_y; + plane_state->crtc_h = crtc_h; + plane_state->crtc_w = crtc_w; + plane_state->src_x = src_x; + plane_state->src_y = src_y; + plane_state->src_h = src_h; + plane_state->src_w = src_w; + + ret = drm_atomic_nonblocking_commit(state); +fail: + drm_atomic_state_put(state); + return ret; +} - /* Just updating the position/size? */ - if (!dplane->base.state.vsync_update) { - armada_ovl_plane_work(dcrtc, work); - return 0; - } +static void armada_ovl_plane_destroy(struct drm_plane *plane) +{ + drm_plane_cleanup(plane); + kfree(plane); +} - if (!dcrtc->plane) { - dcrtc->plane = plane; - armada_ovl_update_attr(&dplane->prop, dcrtc); +static void armada_overlay_reset(struct drm_plane *plane) +{ + struct armada_overlay_state *state; + + if (plane->state) + __drm_atomic_helper_plane_destroy_state(plane->state); + kfree(plane->state); + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (state) { + state->base.plane = plane; + state->base.color_encoding = DEFAULT_ENCODING; + state->base.color_range = DRM_COLOR_YCBCR_LIMITED_RANGE; + state->base.rotation = DRM_MODE_ROTATE_0; + state->colorkey_yr = 0xfefefe00; + state->colorkey_ug = 0x01010100; + state->colorkey_vb = 0x01010100; + state->colorkey_mode = CFG_CKMODE(CKMODE_RGB) | + CFG_ALPHAM_GRA | CFG_ALPHA(0); + state->colorkey_enable = ADV_GRACOLORKEY; + state->brightness = DEFAULT_BRIGHTNESS; + state->contrast = DEFAULT_CONTRAST; + state->saturation = DEFAULT_SATURATION; } - - /* Queue it for update on the next interrupt if we are enabled */ - ret = armada_drm_plane_work_queue(dcrtc, work); - if (ret) - DRM_ERROR("failed to queue plane work: %d\n", ret); - - dplane->base.next_work = !dplane->base.next_work; - - return 0; + plane->state = &state->base; } -static void armada_ovl_plane_destroy(struct drm_plane *plane) +struct drm_plane_state * +armada_overlay_duplicate_state(struct drm_plane *plane) { - struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); + struct armada_overlay_state *state; - drm_plane_cleanup(plane); + if (WARN_ON(!plane->state)) + return NULL; - kfree(dplane); + state = kmemdup(plane->state, sizeof(*state), GFP_KERNEL); + if (state) + __drm_atomic_helper_plane_duplicate_state(plane, &state->base); + return &state->base; } -static int armada_ovl_plane_set_property(struct drm_plane *plane, - struct drm_property *property, uint64_t val) +static int armada_overlay_set_property(struct drm_plane *plane, + struct drm_plane_state *state, struct drm_property *property, + uint64_t val) { struct armada_private *priv = plane->dev->dev_private; - struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane); - bool update_attr = false; +#define K2R(val) (((val) >> 0) & 0xff) +#define K2G(val) (((val) >> 8) & 0xff) +#define K2B(val) (((val) >> 16) & 0xff) if (property == priv->colorkey_prop) { #define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8) - dplane->prop.colorkey_yr = CCC(K2R(val)); - dplane->prop.colorkey_ug = CCC(K2G(val)); - dplane->prop.colorkey_vb = CCC(K2B(val)); + drm_to_overlay_state(state)->colorkey_yr = CCC(K2R(val)); + drm_to_overlay_state(state)->colorkey_ug = CCC(K2G(val)); + drm_to_overlay_state(state)->colorkey_vb = CCC(K2B(val)); #undef CCC - update_attr = true; } else if (property == priv->colorkey_min_prop) { - dplane->prop.colorkey_yr &= ~0x00ff0000; - dplane->prop.colorkey_yr |= K2R(val) << 16; - dplane->prop.colorkey_ug &= ~0x00ff0000; - dplane->prop.colorkey_ug |= K2G(val) << 16; - dplane->prop.colorkey_vb &= ~0x00ff0000; - dplane->prop.colorkey_vb |= K2B(val) << 16; - update_attr = true; + drm_to_overlay_state(state)->colorkey_yr &= ~0x00ff0000; + drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 16; + drm_to_overlay_state(state)->colorkey_ug &= ~0x00ff0000; + drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 16; + drm_to_overlay_state(state)->colorkey_vb &= ~0x00ff0000; + drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 16; } else if (property == priv->colorkey_max_prop) { - dplane->prop.colorkey_yr &= ~0xff000000; - dplane->prop.colorkey_yr |= K2R(val) << 24; - dplane->prop.colorkey_ug &= ~0xff000000; - dplane->prop.colorkey_ug |= K2G(val) << 24; - dplane->prop.colorkey_vb &= ~0xff000000; - dplane->prop.colorkey_vb |= K2B(val) << 24; - update_attr = true; + drm_to_overlay_state(state)->colorkey_yr &= ~0xff000000; + drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 24; + drm_to_overlay_state(state)->colorkey_ug &= ~0xff000000; + drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 24; + drm_to_overlay_state(state)->colorkey_vb &= ~0xff000000; + drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 24; } else if (property == priv->colorkey_val_prop) { - dplane->prop.colorkey_yr &= ~0x0000ff00; - dplane->prop.colorkey_yr |= K2R(val) << 8; - dplane->prop.colorkey_ug &= ~0x0000ff00; - dplane->prop.colorkey_ug |= K2G(val) << 8; - dplane->prop.colorkey_vb &= ~0x0000ff00; - dplane->prop.colorkey_vb |= K2B(val) << 8; - update_attr = true; + drm_to_overlay_state(state)->colorkey_yr &= ~0x0000ff00; + drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 8; + drm_to_overlay_state(state)->colorkey_ug &= ~0x0000ff00; + drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 8; + drm_to_overlay_state(state)->colorkey_vb &= ~0x0000ff00; + drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 8; } else if (property == priv->colorkey_alpha_prop) { - dplane->prop.colorkey_yr &= ~0x000000ff; - dplane->prop.colorkey_yr |= K2R(val); - dplane->prop.colorkey_ug &= ~0x000000ff; - dplane->prop.colorkey_ug |= K2G(val); - dplane->prop.colorkey_vb &= ~0x000000ff; - dplane->prop.colorkey_vb |= K2B(val); - update_attr = true; + drm_to_overlay_state(state)->colorkey_yr &= ~0x000000ff; + drm_to_overlay_state(state)->colorkey_yr |= K2R(val); + drm_to_overlay_state(state)->colorkey_ug &= ~0x000000ff; + drm_to_overlay_state(state)->colorkey_ug |= K2G(val); + drm_to_overlay_state(state)->colorkey_vb &= ~0x000000ff; + drm_to_overlay_state(state)->colorkey_vb |= K2B(val); } else if (property == priv->colorkey_mode_prop) { - dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK; - dplane->prop.colorkey_mode |= CFG_CKMODE(val); - update_attr = true; + if (val == CKMODE_DISABLE) { + drm_to_overlay_state(state)->colorkey_mode = + CFG_CKMODE(CKMODE_DISABLE) | + CFG_ALPHAM_CFG | CFG_ALPHA(255); + drm_to_overlay_state(state)->colorkey_enable = 0; + } else { + drm_to_overlay_state(state)->colorkey_mode = + CFG_CKMODE(val) | + CFG_ALPHAM_GRA | CFG_ALPHA(0); + drm_to_overlay_state(state)->colorkey_enable = + ADV_GRACOLORKEY; + } } else if (property == priv->brightness_prop) { - dplane->prop.brightness = val - 256; - update_attr = true; + drm_to_overlay_state(state)->brightness = val - 256; } else if (property == priv->contrast_prop) { - dplane->prop.contrast = val; - update_attr = true; + drm_to_overlay_state(state)->contrast = val; } else if (property == priv->saturation_prop) { - dplane->prop.saturation = val; - update_attr = true; + drm_to_overlay_state(state)->saturation = val; + } else { + return -EINVAL; } + return 0; +} - if (update_attr && dplane->base.base.crtc) - armada_ovl_update_attr(&dplane->prop, - drm_to_armada_crtc(dplane->base.base.crtc)); +static int armada_overlay_get_property(struct drm_plane *plane, + const struct drm_plane_state *state, struct drm_property *property, + uint64_t *val) +{ + struct armada_private *priv = plane->dev->dev_private; +#define C2K(c,s) (((c) >> (s)) & 0xff) +#define R2BGR(r,g,b,s) (C2K(r,s) << 0 | C2K(g,s) << 8 | C2K(b,s) << 16) + if (property == priv->colorkey_prop) { + /* Do best-efforts here for this property */ + *val = R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 16); + /* If min != max, or min != val, error out */ + if (*val != R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 24) || + *val != R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 8)) + return -EINVAL; + } else if (property == priv->colorkey_min_prop) { + *val = R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 16); + } else if (property == priv->colorkey_max_prop) { + *val = R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 24); + } else if (property == priv->colorkey_val_prop) { + *val = R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 8); + } else if (property == priv->colorkey_alpha_prop) { + *val = R2BGR(drm_to_overlay_state(state)->colorkey_yr, + drm_to_overlay_state(state)->colorkey_ug, + drm_to_overlay_state(state)->colorkey_vb, 0); + } else if (property == priv->colorkey_mode_prop) { + *val = (drm_to_overlay_state(state)->colorkey_mode & + CFG_CKMODE_MASK) >> ffs(CFG_CKMODE_MASK); + } else if (property == priv->brightness_prop) { + *val = drm_to_overlay_state(state)->brightness + 256; + } else if (property == priv->contrast_prop) { + *val = drm_to_overlay_state(state)->contrast; + } else if (property == priv->saturation_prop) { + *val = drm_to_overlay_state(state)->saturation; + } else { + return -EINVAL; + } return 0; } static const struct drm_plane_funcs armada_ovl_plane_funcs = { - .update_plane = armada_ovl_plane_update, - .disable_plane = armada_drm_plane_disable, + .update_plane = armada_overlay_plane_update, + .disable_plane = drm_atomic_helper_disable_plane, .destroy = armada_ovl_plane_destroy, - .set_property = armada_ovl_plane_set_property, + .reset = armada_overlay_reset, + .atomic_duplicate_state = armada_overlay_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, + .atomic_set_property = armada_overlay_set_property, + .atomic_get_property = armada_overlay_get_property, }; static const uint32_t armada_ovl_formats[] = { @@ -419,46 +541,31 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) { struct armada_private *priv = dev->dev_private; struct drm_mode_object *mobj; - struct armada_ovl_plane *dplane; + struct drm_plane *overlay; int ret; ret = armada_overlay_create_properties(dev); if (ret) return ret; - dplane = kzalloc(sizeof(*dplane), GFP_KERNEL); - if (!dplane) + overlay = kzalloc(sizeof(*overlay), GFP_KERNEL); + if (!overlay) return -ENOMEM; - ret = armada_drm_plane_init(&dplane->base); - if (ret) { - kfree(dplane); - return ret; - } - - dplane->base.works[0].fn = armada_ovl_plane_work; - dplane->base.works[1].fn = armada_ovl_plane_work; + drm_plane_helper_add(overlay, &armada_overlay_plane_helper_funcs); - ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs, + ret = drm_universal_plane_init(dev, overlay, crtcs, &armada_ovl_plane_funcs, armada_ovl_formats, ARRAY_SIZE(armada_ovl_formats), NULL, DRM_PLANE_TYPE_OVERLAY, NULL); if (ret) { - kfree(dplane); + kfree(overlay); return ret; } - dplane->prop.colorkey_yr = 0xfefefe00; - dplane->prop.colorkey_ug = 0x01010100; - dplane->prop.colorkey_vb = 0x01010100; - dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB); - dplane->prop.brightness = 0; - dplane->prop.contrast = 0x4000; - dplane->prop.saturation = 0x4000; - - mobj = &dplane->base.base.base; + mobj = &overlay->base; drm_object_attach_property(mobj, priv->colorkey_prop, 0x0101fe); drm_object_attach_property(mobj, priv->colorkey_min_prop, @@ -471,11 +578,19 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs) 0x000000); drm_object_attach_property(mobj, priv->colorkey_mode_prop, CKMODE_RGB); - drm_object_attach_property(mobj, priv->brightness_prop, 256); + drm_object_attach_property(mobj, priv->brightness_prop, + 256 + DEFAULT_BRIGHTNESS); drm_object_attach_property(mobj, priv->contrast_prop, - dplane->prop.contrast); + DEFAULT_CONTRAST); drm_object_attach_property(mobj, priv->saturation_prop, - dplane->prop.saturation); + DEFAULT_SATURATION); - return 0; + ret = drm_plane_create_color_properties(overlay, + BIT(DRM_COLOR_YCBCR_BT601) | + BIT(DRM_COLOR_YCBCR_BT709), + BIT(DRM_COLOR_YCBCR_LIMITED_RANGE), + DEFAULT_ENCODING, + DRM_COLOR_YCBCR_LIMITED_RANGE); + + return ret; } diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c new file mode 100644 index 000000000000..9f36423dd394 --- /dev/null +++ b/drivers/gpu/drm/armada/armada_plane.c @@ -0,0 +1,289 @@ +/* + * Copyright (C) 2012 Russell King + * Rewritten from the dovefb driver, and Armada510 manuals. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <drm/drmP.h> +#include <drm/drm_atomic.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_plane_helper.h> +#include "armada_crtc.h" +#include "armada_drm.h" +#include "armada_fb.h" +#include "armada_gem.h" +#include "armada_hw.h" +#include "armada_plane.h" +#include "armada_trace.h" + +static const uint32_t armada_primary_formats[] = { + DRM_FORMAT_UYVY, + DRM_FORMAT_YUYV, + DRM_FORMAT_VYUY, + DRM_FORMAT_YVYU, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_ABGR8888, + DRM_FORMAT_XRGB8888, + DRM_FORMAT_XBGR8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_BGR888, + DRM_FORMAT_ARGB1555, + DRM_FORMAT_ABGR1555, + DRM_FORMAT_RGB565, + DRM_FORMAT_BGR565, +}; + +void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3], + u16 pitches[3], bool interlaced) +{ + struct drm_framebuffer *fb = state->fb; + const struct drm_format_info *format = fb->format; + unsigned int num_planes = format->num_planes; + unsigned int x = state->src.x1 >> 16; + unsigned int y = state->src.y1 >> 16; + u32 addr = drm_fb_obj(fb)->dev_addr; + int i; + + DRM_DEBUG_KMS("pitch %u x %d y %d bpp %d\n", + fb->pitches[0], x, y, format->cpp[0] * 8); + + if (num_planes > 3) + num_planes = 3; + + addrs[0][0] = addr + fb->offsets[0] + y * fb->pitches[0] + + x * format->cpp[0]; + pitches[0] = fb->pitches[0]; + + y /= format->vsub; + x /= format->hsub; + + for (i = 1; i < num_planes; i++) { + addrs[0][i] = addr + fb->offsets[i] + y * fb->pitches[i] + + x * format->cpp[i]; + pitches[i] = fb->pitches[i]; + } + for (; i < 3; i++) { + addrs[0][i] = 0; + pitches[i] = 0; + } + if (interlaced) { + for (i = 0; i < 3; i++) { + addrs[1][i] = addrs[0][i] + pitches[i]; + pitches[i] *= 2; + } + } else { + for (i = 0; i < 3; i++) + addrs[1][i] = addrs[0][i]; + } +} + +static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state, + struct armada_regs *regs, bool interlaced) +{ + u16 pitches[3]; + u32 addrs[2][3]; + unsigned i = 0; + + armada_drm_plane_calc(state, addrs, pitches, interlaced); + + /* write offset, base, and pitch */ + armada_reg_queue_set(regs, i, addrs[0][0], LCD_CFG_GRA_START_ADDR0); + armada_reg_queue_set(regs, i, addrs[1][0], LCD_CFG_GRA_START_ADDR1); + armada_reg_queue_mod(regs, i, pitches[0], 0xffff, LCD_CFG_GRA_PITCH); + + return i; +} + +int armada_drm_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *state) +{ + DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n", + plane->base.id, plane->name, + state->fb ? state->fb->base.id : 0); + + /* + * Take a reference on the new framebuffer - we want to + * hold on to it while the hardware is displaying it. + */ + if (state->fb) + drm_framebuffer_get(state->fb); + return 0; +} + +void armada_drm_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n", + plane->base.id, plane->name, + old_state->fb ? old_state->fb->base.id : 0); + + if (old_state->fb) + drm_framebuffer_put(old_state->fb); +} + +int armada_drm_plane_atomic_check(struct drm_plane *plane, + struct drm_plane_state *state) +{ + if (state->fb && !WARN_ON(!state->crtc)) { + struct drm_crtc *crtc = state->crtc; + struct drm_crtc_state *crtc_state; + + if (state->state) + crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc); + else + crtc_state = crtc->state; + return drm_atomic_helper_check_plane_state(state, crtc_state, + 0, INT_MAX, + true, false); + } else { + state->visible = false; + } + return 0; +} + +static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct drm_plane_state *state = plane->state; + struct armada_crtc *dcrtc; + struct armada_regs *regs; + u32 cfg, cfg_mask, val; + unsigned int idx; + + DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name); + + if (!state->fb || WARN_ON(!state->crtc)) + return; + + DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n", + plane->base.id, plane->name, + state->crtc->base.id, state->crtc->name, + state->fb->base.id, + old_state->visible, state->visible); + + dcrtc = drm_to_armada_crtc(state->crtc); + regs = dcrtc->regs + dcrtc->regs_idx; + + idx = 0; + if (!old_state->visible && state->visible) { + val = CFG_PDWN64x66; + if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420) + val |= CFG_PDWN256x24; + armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1); + } + val = armada_rect_hw_fp(&state->src); + if (armada_rect_hw_fp(&old_state->src) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN); + val = armada_rect_yx(&state->dst); + if (armada_rect_yx(&old_state->dst) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN); + val = armada_rect_hw(&state->dst); + if (armada_rect_hw(&old_state->dst) != val) + armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN); + if (old_state->src.x1 != state->src.x1 || + old_state->src.y1 != state->src.y1 || + old_state->fb != state->fb || + state->crtc->state->mode_changed) { + idx += armada_drm_crtc_calc_fb(state, regs + idx, + dcrtc->interlaced); + } + if (old_state->fb != state->fb || + state->crtc->state->mode_changed) { + cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) | + CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod); + if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420) + cfg |= CFG_PALETTE_ENA; + if (state->visible) + cfg |= CFG_GRA_ENA; + if (dcrtc->interlaced) + cfg |= CFG_GRA_FTOGGLE; + cfg_mask = CFG_GRAFORMAT | + CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV | + CFG_SWAPYU | CFG_YUV2RGB) | + CFG_PALETTE_ENA | CFG_GRA_FTOGGLE | + CFG_GRA_ENA; + } else if (old_state->visible != state->visible) { + cfg = state->visible ? CFG_GRA_ENA : 0; + cfg_mask = CFG_GRA_ENA; + } else { + cfg = cfg_mask = 0; + } + if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) || + drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) { + cfg_mask |= CFG_GRA_HSMOOTH; + if (drm_rect_width(&state->src) >> 16 != + drm_rect_width(&state->dst)) + cfg |= CFG_GRA_HSMOOTH; + } + + if (cfg_mask) + armada_reg_queue_mod(regs, idx, cfg, cfg_mask, + LCD_SPU_DMA_CTRL0); + + dcrtc->regs_idx += idx; +} + +static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct armada_crtc *dcrtc; + struct armada_regs *regs; + unsigned int idx = 0; + + DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name); + + if (!old_state->crtc) + return; + + DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n", + plane->base.id, plane->name, + old_state->crtc->base.id, old_state->crtc->name, + old_state->fb->base.id); + + dcrtc = drm_to_armada_crtc(old_state->crtc); + regs = dcrtc->regs + dcrtc->regs_idx; + + /* Disable plane and power down most RAMs and FIFOs */ + armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0); + armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 | + CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66, + 0, LCD_SPU_SRAM_PARA1); + + dcrtc->regs_idx += idx; +} + +static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = { + .prepare_fb = armada_drm_plane_prepare_fb, + .cleanup_fb = armada_drm_plane_cleanup_fb, + .atomic_check = armada_drm_plane_atomic_check, + .atomic_update = armada_drm_primary_plane_atomic_update, + .atomic_disable = armada_drm_primary_plane_atomic_disable, +}; + +static const struct drm_plane_funcs armada_primary_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .destroy = drm_primary_helper_destroy, + .reset = drm_atomic_helper_plane_reset, + .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, +}; + +int armada_drm_primary_plane_init(struct drm_device *drm, + struct drm_plane *primary) +{ + int ret; + + drm_plane_helper_add(primary, &armada_primary_plane_helper_funcs); + + ret = drm_universal_plane_init(drm, primary, 0, + &armada_primary_plane_funcs, + armada_primary_formats, + ARRAY_SIZE(armada_primary_formats), + NULL, + DRM_PLANE_TYPE_PRIMARY, NULL); + + return ret; +} diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h new file mode 100644 index 000000000000..ff4281ba7fad --- /dev/null +++ b/drivers/gpu/drm/armada/armada_plane.h @@ -0,0 +1,15 @@ +#ifndef ARMADA_PLANE_H +#define ARMADA_PLANE_H + +void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3], + u16 pitches[3], bool interlaced); +int armada_drm_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *state); +void armada_drm_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state); +int armada_drm_plane_atomic_check(struct drm_plane *plane, + struct drm_plane_state *state); +int armada_drm_primary_plane_init(struct drm_device *drm, + struct drm_plane *primary); + +#endif diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index 250effa0e6b8..a6e8f4591e63 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -14,6 +14,7 @@ #include <drm/bridge/mhl.h> #include <drm/drm_crtc.h> #include <drm/drm_edid.h> +#include <drm/drm_encoder.h> #include <linux/clk.h> #include <linux/delay.h> @@ -72,9 +73,7 @@ struct sii8620 { struct regulator_bulk_data supplies[2]; struct mutex lock; /* context lock, protects fields below */ int error; - int pixel_clock; unsigned int use_packed_pixel:1; - int video_code; enum sii8620_mode mode; enum sii8620_sink_type sink_type; u8 cbus_status; @@ -82,7 +81,6 @@ struct sii8620 { u8 xstat[MHL_XDS_SIZE]; u8 devcap[MHL_DCAP_SIZE]; u8 xdevcap[MHL_XDC_SIZE]; - u8 avif[HDMI_INFOFRAME_SIZE(AVI)]; bool feature_complete; bool devcap_read; bool sink_detected; @@ -1017,21 +1015,36 @@ static void sii8620_stop_video(struct sii8620 *ctx) static void sii8620_set_format(struct sii8620 *ctx) { + u8 out_fmt; + if (sii8620_is_mhl3(ctx)) { sii8620_setbits(ctx, REG_M3_P0CTRL, BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED, ctx->use_packed_pixel ? ~0 : 0); } else { + if (ctx->use_packed_pixel) { + sii8620_write_seq_static(ctx, + REG_VID_MODE, BIT_VID_MODE_M1080P, + REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1, + REG_MHLTX_CTL6, 0x60 + ); + } else { sii8620_write_seq_static(ctx, REG_VID_MODE, 0, REG_MHL_TOP_CTL, 1, REG_MHLTX_CTL6, 0xa0 ); + } } + if (ctx->use_packed_pixel) + out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL); + else + out_fmt = VAL_TPI_FORMAT(RGB, FULL); + sii8620_write_seq(ctx, REG_TPI_INPUT, VAL_TPI_FORMAT(RGB, FULL), - REG_TPI_OUTPUT, VAL_TPI_FORMAT(RGB, FULL), + REG_TPI_OUTPUT, out_fmt, ); } @@ -1082,18 +1095,28 @@ static ssize_t mhl3_infoframe_pack(struct mhl3_infoframe *frame, return frm_len; } -static void sii8620_set_infoframes(struct sii8620 *ctx) +static void sii8620_set_infoframes(struct sii8620 *ctx, + struct drm_display_mode *mode) { struct mhl3_infoframe mhl_frm; union hdmi_infoframe frm; u8 buf[31]; int ret; + ret = drm_hdmi_avi_infoframe_from_display_mode(&frm.avi, + mode, + true); + if (ctx->use_packed_pixel) + frm.avi.colorspace = HDMI_COLORSPACE_YUV422; + + if (!ret) + ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf)); + if (ret > 0) + sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3); + if (!sii8620_is_mhl3(ctx) || !ctx->use_packed_pixel) { sii8620_write(ctx, REG_TPI_SC, BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI); - sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, ctx->avif + 3, - ARRAY_SIZE(ctx->avif) - 3); sii8620_write(ctx, REG_PKT_FILTER_0, BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT | BIT_PKT_FILTER_0_DROP_MPEG_PKT | @@ -1102,16 +1125,6 @@ static void sii8620_set_infoframes(struct sii8620 *ctx) return; } - ret = hdmi_avi_infoframe_init(&frm.avi); - frm.avi.colorspace = HDMI_COLORSPACE_YUV422; - frm.avi.active_aspect = HDMI_ACTIVE_ASPECT_PICTURE; - frm.avi.picture_aspect = HDMI_PICTURE_ASPECT_16_9; - frm.avi.colorimetry = HDMI_COLORIMETRY_ITU_709; - frm.avi.video_code = ctx->video_code; - if (!ret) - ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf)); - if (ret > 0) - sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3); sii8620_write(ctx, REG_PKT_FILTER_0, BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT | BIT_PKT_FILTER_0_DROP_MPEG_PKT | @@ -1131,6 +1144,9 @@ static void sii8620_set_infoframes(struct sii8620 *ctx) static void sii8620_start_video(struct sii8620 *ctx) { + struct drm_display_mode *mode = + &ctx->bridge.encoder->crtc->state->adjusted_mode; + if (!sii8620_is_mhl3(ctx)) sii8620_stop_video(ctx); @@ -1149,8 +1165,14 @@ static void sii8620_start_video(struct sii8620 *ctx) sii8620_set_format(ctx); if (!sii8620_is_mhl3(ctx)) { - sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), - MHL_DST_LM_CLK_MODE_NORMAL | MHL_DST_LM_PATH_ENABLED); + u8 link_mode = MHL_DST_LM_PATH_ENABLED; + + if (ctx->use_packed_pixel) + link_mode |= MHL_DST_LM_CLK_MODE_PACKED_PIXEL; + else + link_mode |= MHL_DST_LM_CLK_MODE_NORMAL; + + sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), link_mode); sii8620_set_auto_zone(ctx); } else { static const struct { @@ -1167,7 +1189,7 @@ static void sii8620_start_video(struct sii8620 *ctx) MHL_XDS_LINK_RATE_6_0_GBPS, 0x40 }, }; u8 p0_ctrl = BIT_M3_P0CTRL_MHL3_P0_PORT_EN; - int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3); + int clk = mode->clock * (ctx->use_packed_pixel ? 2 : 3); int i; for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i) @@ -1196,7 +1218,7 @@ static void sii8620_start_video(struct sii8620 *ctx) clk_spec[i].link_rate); } - sii8620_set_infoframes(ctx); + sii8620_set_infoframes(ctx, mode); } static void sii8620_disable_hpd(struct sii8620 *ctx) @@ -1661,14 +1683,18 @@ static void sii8620_status_dcap_ready(struct sii8620 *ctx) static void sii8620_status_changed_path(struct sii8620 *ctx) { - if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) { - sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), - MHL_DST_LM_CLK_MODE_NORMAL - | MHL_DST_LM_PATH_ENABLED); - } else { - sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), - MHL_DST_LM_CLK_MODE_NORMAL); - } + u8 link_mode; + + if (ctx->use_packed_pixel) + link_mode = MHL_DST_LM_CLK_MODE_PACKED_PIXEL; + else + link_mode = MHL_DST_LM_CLK_MODE_NORMAL; + + if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) + link_mode |= MHL_DST_LM_PATH_ENABLED; + + sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), + link_mode); } static void sii8620_msc_mr_write_stat(struct sii8620 *ctx) @@ -2242,8 +2268,6 @@ static bool sii8620_mode_fixup(struct drm_bridge *bridge, mutex_lock(&ctx->lock); ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode); - ctx->video_code = drm_match_cea_mode(adjusted_mode); - ctx->pixel_clock = adjusted_mode->clock; mutex_unlock(&ctx->lock); diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c index ddb1c5adebb9..988513346e9c 100644 --- a/drivers/gpu/drm/drm_dp_cec.c +++ b/drivers/gpu/drm/drm_dp_cec.c @@ -157,7 +157,7 @@ static void drm_dp_cec_adap_status(struct cec_adapter *adap, if (drm_dp_read_desc(aux, &desc, true)) return; - seq_printf(file, "OUI: %*pdH\n", + seq_printf(file, "OUI: %*phD\n", (int)sizeof(id->oui), id->oui); seq_printf(file, "ID: %*pE\n", (int)strnlen(id->device_id, sizeof(id->device_id)), diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 50c73c0a20b9..d638c0fb3418 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Clone the lessor file to create a new file for us */ DRM_DEBUG_LEASE("Allocating lease file\n"); - path_get(&lessor_file->f_path); - lessee_file = alloc_file(&lessor_file->f_path, - lessor_file->f_mode, - fops_get(lessor_file->f_inode->i_fop)); - + lessee_file = filp_clone_open(lessor_file); if (IS_ERR(lessee_file)) { ret = PTR_ERR(lessee_file); goto out_lessee; } - /* Initialize the new file for DRM */ - DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open); - ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file); - if (ret) - goto out_lessee_file; - lessee_priv = lessee_file->private_data; - /* Change the file to a master one */ drm_master_put(&lessee_priv->master); lessee_priv->master = lessee; @@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n"); return 0; -out_lessee_file: - fput(lessee_file); - out_lessee: drm_master_put(&lessee); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index bc73b7f5b9fc..80b75501f5c6 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -392,6 +392,7 @@ bool mipi_dsi_packet_format_is_short(u8 type) case MIPI_DSI_DCS_SHORT_WRITE: case MIPI_DSI_DCS_SHORT_WRITE_PARAM: case MIPI_DSI_DCS_READ: + case MIPI_DSI_DCS_COMPRESSION_MODE: case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE: return true; } @@ -410,6 +411,7 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short); bool mipi_dsi_packet_format_is_long(u8 type) { switch (type) { + case MIPI_DSI_PPS_LONG_WRITE: case MIPI_DSI_NULL_PACKET: case MIPI_DSI_BLANKING_PACKET: case MIPI_DSI_GENERIC_LONG_WRITE: diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index b25f98f33f6c..0e7fc3e7dfb4 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -30,6 +30,100 @@ #include <drm/drmP.h> #include <drm/drm_print.h> +void __drm_puts_coredump(struct drm_printer *p, const char *str) +{ + struct drm_print_iterator *iterator = p->arg; + ssize_t len; + + if (!iterator->remain) + return; + + if (iterator->offset < iterator->start) { + ssize_t copy; + + len = strlen(str); + + if (iterator->offset + len <= iterator->start) { + iterator->offset += len; + return; + } + + copy = len - (iterator->start - iterator->offset); + + if (copy > iterator->remain) + copy = iterator->remain; + + /* Copy out the bit of the string that we need */ + memcpy(iterator->data, + str + (iterator->start - iterator->offset), copy); + + iterator->offset = iterator->start + copy; + iterator->remain -= copy; + } else { + ssize_t pos = iterator->offset - iterator->start; + + len = min_t(ssize_t, strlen(str), iterator->remain); + + memcpy(iterator->data + pos, str, len); + + iterator->offset += len; + iterator->remain -= len; + } +} +EXPORT_SYMBOL(__drm_puts_coredump); + +void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) +{ + struct drm_print_iterator *iterator = p->arg; + size_t len; + char *buf; + + if (!iterator->remain) + return; + + /* Figure out how big the string will be */ + len = snprintf(NULL, 0, "%pV", vaf); + + /* This is the easiest path, we've already advanced beyond the offset */ + if (iterator->offset + len <= iterator->start) { + iterator->offset += len; + return; + } + + /* Then check if we can directly copy into the target buffer */ + if ((iterator->offset >= iterator->start) && (len < iterator->remain)) { + ssize_t pos = iterator->offset - iterator->start; + + snprintf(((char *) iterator->data) + pos, + iterator->remain, "%pV", vaf); + + iterator->offset += len; + iterator->remain -= len; + + return; + } + + /* + * Finally, hit the slow path and make a temporary string to copy over + * using _drm_puts_coredump + */ + buf = kmalloc(len + 1, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!buf) + return; + + snprintf(buf, len + 1, "%pV", vaf); + __drm_puts_coredump(p, (const char *) buf); + + kfree(buf); +} +EXPORT_SYMBOL(__drm_printfn_coredump); + +void __drm_puts_seq_file(struct drm_printer *p, const char *str) +{ + seq_puts(p->arg, str); +} +EXPORT_SYMBOL(__drm_puts_seq_file); + void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf) { seq_printf(p->arg, "%pV", vaf); @@ -49,6 +143,23 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf) EXPORT_SYMBOL(__drm_printfn_debug); /** + * drm_puts - print a const string to a &drm_printer stream + * @p: the &drm printer + * @str: const string + * + * Allow &drm_printer types that have a constant string + * option to use it. + */ +void drm_puts(struct drm_printer *p, const char *str) +{ + if (p->puts) + p->puts(p, str); + else + drm_printf(p, "%s", str); +} +EXPORT_SYMBOL(drm_puts); + +/** * drm_printf - print to a &drm_printer stream * @p: the &drm_printer * @f: format string diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c index 1f8031e30f53..cdb10f885a4f 100644 --- a/drivers/gpu/drm/drm_property.c +++ b/drivers/gpu/drm/drm_property.c @@ -532,7 +532,7 @@ static void drm_property_free_blob(struct kref *kref) drm_mode_object_unregister(blob->dev, &blob->base); - kfree(blob); + kvfree(blob); } /** @@ -559,7 +559,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length, if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob)) return ERR_PTR(-EINVAL); - blob = kzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL); + blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL); if (!blob) return ERR_PTR(-ENOMEM); @@ -576,7 +576,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length, ret = __drm_mode_object_add(dev, &blob->base, DRM_MODE_OBJECT_BLOB, true, drm_property_free_blob); if (ret) { - kfree(blob); + kvfree(blob); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 207532c05eb8..9b2720b41571 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -630,8 +630,11 @@ static struct platform_driver etnaviv_platform_driver = { }, }; +static struct platform_device *etnaviv_drm; + static int __init etnaviv_init(void) { + struct platform_device *pdev; int ret; struct device_node *np; @@ -643,7 +646,7 @@ static int __init etnaviv_init(void) ret = platform_driver_register(&etnaviv_platform_driver); if (ret != 0) - platform_driver_unregister(&etnaviv_gpu_driver); + goto unregister_gpu_driver; /* * If the DT contains at least one available GPU device, instantiate @@ -652,20 +655,33 @@ static int __init etnaviv_init(void) for_each_compatible_node(np, NULL, "vivante,gc") { if (!of_device_is_available(np)) continue; - - platform_device_register_simple("etnaviv", -1, NULL, 0); + pdev = platform_device_register_simple("etnaviv", -1, + NULL, 0); + if (IS_ERR(pdev)) { + ret = PTR_ERR(pdev); + of_node_put(np); + goto unregister_platform_driver; + } + etnaviv_drm = pdev; of_node_put(np); break; } + return 0; + +unregister_platform_driver: + platform_driver_unregister(&etnaviv_platform_driver); +unregister_gpu_driver: + platform_driver_unregister(&etnaviv_gpu_driver); return ret; } module_init(etnaviv_init); static void __exit etnaviv_exit(void) { - platform_driver_unregister(&etnaviv_gpu_driver); + platform_device_unregister(etnaviv_drm); platform_driver_unregister(&etnaviv_platform_driver); + platform_driver_unregister(&etnaviv_gpu_driver); } module_exit(etnaviv_exit); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h index d36c7bbe66db..8d02d1b7dcf5 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h @@ -18,6 +18,7 @@ #include <linux/time64.h> #include <linux/types.h> #include <linux/sizes.h> +#include <linux/mm_types.h> #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> @@ -53,7 +54,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file); int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma); -int etnaviv_gem_fault(struct vm_fault *vmf); +vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf); int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset); struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj); void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 209ef1274b80..1fa74226db91 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -169,31 +169,30 @@ int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma) return obj->ops->mmap(obj, vma); } -int etnaviv_gem_fault(struct vm_fault *vmf) +vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct drm_gem_object *obj = vma->vm_private_data; struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); struct page **pages, *page; pgoff_t pgoff; - int ret; + int err; /* * Make sure we don't parallel update on a fault, nor move or remove - * something from beneath our feet. Note that vm_insert_page() is + * something from beneath our feet. Note that vmf_insert_page() is * specifically coded to take care of this, so we don't have to. */ - ret = mutex_lock_interruptible(&etnaviv_obj->lock); - if (ret) - goto out; - + err = mutex_lock_interruptible(&etnaviv_obj->lock); + if (err) + return VM_FAULT_NOPAGE; /* make sure we have pages attached now */ pages = etnaviv_gem_get_pages(etnaviv_obj); mutex_unlock(&etnaviv_obj->lock); if (IS_ERR(pages)) { - ret = PTR_ERR(pages); - goto out; + err = PTR_ERR(pages); + return vmf_error(err); } /* We don't use vmf->pgoff since that has the fake offset: */ @@ -204,25 +203,7 @@ int etnaviv_gem_fault(struct vm_fault *vmf) VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address, page_to_pfn(page), page_to_pfn(page) << PAGE_SHIFT); - ret = vm_insert_page(vma, vmf->address, page); - -out: - switch (ret) { - case -EAGAIN: - case 0: - case -ERESTARTSYS: - case -EINTR: - case -EBUSY: - /* - * EBUSY is ok: this just means that another thread - * already did the job. - */ - return VM_FAULT_NOPAGE; - case -ENOMEM: - return VM_FAULT_OOM; - default: - return VM_FAULT_SIGBUS; - } + return vmf_insert_page(vma, vmf->address, page); } int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 46ecd3e66ac9..983e67f19e45 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -388,9 +388,9 @@ static void submit_cleanup(struct kref *kref) dma_fence_put(submit->in_fence); if (submit->out_fence) { /* first remove from IDR, so fence can not be found anymore */ - mutex_lock(&submit->gpu->fence_idr_lock); + mutex_lock(&submit->gpu->fence_lock); idr_remove(&submit->gpu->fence_idr, submit->out_fence_id); - mutex_unlock(&submit->gpu->fence_idr_lock); + mutex_unlock(&submit->gpu->fence_lock); dma_fence_put(submit->out_fence); } kfree(submit->pmrs); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 19b09a59e30e..f225fbc6edd2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -799,6 +799,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) free_buffer: etnaviv_cmdbuf_free(&gpu->buffer); + gpu->buffer.suballoc = NULL; destroy_iommu: etnaviv_iommu_destroy(gpu->mmu); gpu->mmu = NULL; @@ -1726,7 +1727,7 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) gpu->dev = &pdev->dev; mutex_init(&gpu->lock); - mutex_init(&gpu->fence_idr_lock); + mutex_init(&gpu->fence_lock); /* Map registers: */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index dd430f0f8ff5..9a75a6937268 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -118,7 +118,7 @@ struct etnaviv_gpu { u32 idle_mask; /* Fencing support */ - struct mutex fence_idr_lock; + struct mutex fence_lock; struct idr fence_idr; u32 next_fence; u32 active_fence; @@ -131,6 +131,9 @@ struct etnaviv_gpu { struct work_struct sync_point_work; int sync_point_event; + /* hang detection */ + u32 hangcheck_dma_addr; + void __iomem *mmio; int irq; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c index 71fbc1f96cb6..f1c88d8ad5ba 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c @@ -119,8 +119,7 @@ static size_t etnaviv_iommuv2_unmap(struct etnaviv_iommu_domain *domain, static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain) { - u32 *p; - int ret, i; + int ret; /* allocate scratch page */ etnaviv_domain->base.bad_page_cpu = @@ -131,9 +130,9 @@ static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain) ret = -ENOMEM; goto fail_mem; } - p = etnaviv_domain->base.bad_page_cpu; - for (i = 0; i < SZ_4K / 4; i++) - *p++ = 0xdead55aa; + + memset32(etnaviv_domain->base.bad_page_cpu, 0xdead55aa, + SZ_4K / sizeof(u32)); etnaviv_domain->pta_cpu = dma_alloc_wc(etnaviv_domain->base.dev, SZ_4K, &etnaviv_domain->pta_dma, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 590e44b0d963..69e9b431bf1f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -10,6 +10,7 @@ #include "etnaviv_gem.h" #include "etnaviv_gpu.h" #include "etnaviv_sched.h" +#include "state.xml.h" static int etnaviv_job_hang_limit = 0; module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444); @@ -85,6 +86,29 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); struct etnaviv_gpu *gpu = submit->gpu; + u32 dma_addr; + int change; + + /* + * If the GPU managed to complete this jobs fence, the timout is + * spurious. Bail out. + */ + if (fence_completed(gpu, submit->out_fence->seqno)) + return; + + /* + * If the GPU is still making forward progress on the front-end (which + * should never loop) we shift out the timeout to give it a chance to + * finish the job. + */ + dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS); + change = dma_addr - gpu->hangcheck_dma_addr; + if (change < 0 || change > 16) { + gpu->hangcheck_dma_addr = dma_addr; + schedule_delayed_work(&sched_job->work_tdr, + sched_job->sched->timeout); + return; + } /* block scheduler */ kthread_park(gpu->sched.thread); @@ -116,28 +140,38 @@ static const struct drm_sched_backend_ops etnaviv_sched_ops = { int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, struct etnaviv_gem_submit *submit) { - int ret; + int ret = 0; + + /* + * Hold the fence lock across the whole operation to avoid jobs being + * pushed out of order with regard to their sched fence seqnos as + * allocated in drm_sched_job_init. + */ + mutex_lock(&submit->gpu->fence_lock); ret = drm_sched_job_init(&submit->sched_job, sched_entity, submit->cmdbuf.ctx); if (ret) - return ret; + goto out_unlock; submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished); - mutex_lock(&submit->gpu->fence_idr_lock); submit->out_fence_id = idr_alloc_cyclic(&submit->gpu->fence_idr, submit->out_fence, 0, INT_MAX, GFP_KERNEL); - mutex_unlock(&submit->gpu->fence_idr_lock); - if (submit->out_fence_id < 0) - return -ENOMEM; + if (submit->out_fence_id < 0) { + ret = -ENOMEM; + goto out_unlock; + } /* the scheduler holds on to the job now */ kref_get(&submit->refcount); drm_sched_entity_push_job(&submit->sched_job, sched_entity); - return 0; +out_unlock: + mutex_unlock(&submit->gpu->fence_lock); + + return ret; } int etnaviv_sched_init(struct etnaviv_gpu *gpu) diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index eecdc327b9f8..a7c39f39793f 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -69,6 +69,7 @@ struct tda998x_priv { bool edid_delay_active; struct drm_encoder encoder; + struct drm_bridge bridge; struct drm_connector connector; struct tda998x_audio_port audio_port[2]; @@ -79,9 +80,10 @@ struct tda998x_priv { #define conn_to_tda998x_priv(x) \ container_of(x, struct tda998x_priv, connector) - #define enc_to_tda998x_priv(x) \ container_of(x, struct tda998x_priv, encoder) +#define bridge_to_tda998x_priv(x) \ + container_of(x, struct tda998x_priv, bridge) /* The TDA9988 series of devices use a paged register scheme.. to simplify * things we encode the page # in upper bits of the register #. To read/ @@ -762,7 +764,7 @@ static void tda998x_detect_work(struct work_struct *work) { struct tda998x_priv *priv = container_of(work, struct tda998x_priv, detect_work); - struct drm_device *dev = priv->encoder.dev; + struct drm_device *dev = priv->connector.dev; if (dev) drm_kms_helper_hotplug_event(dev); @@ -1104,29 +1106,6 @@ static int tda998x_audio_codec_init(struct tda998x_priv *priv, /* DRM connector functions */ -static int tda998x_connector_fill_modes(struct drm_connector *connector, - uint32_t maxX, uint32_t maxY) -{ - struct tda998x_priv *priv = conn_to_tda998x_priv(connector); - int ret; - - mutex_lock(&priv->audio_mutex); - ret = drm_helper_probe_single_connector_modes(connector, maxX, maxY); - - if (connector->edid_blob_ptr) { - struct edid *edid = (void *)connector->edid_blob_ptr->data; - - cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid); - - priv->sink_has_audio = drm_detect_monitor_audio(edid); - } else { - priv->sink_has_audio = false; - } - mutex_unlock(&priv->audio_mutex); - - return ret; -} - static enum drm_connector_status tda998x_connector_detect(struct drm_connector *connector, bool force) { @@ -1145,7 +1124,7 @@ static void tda998x_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs tda998x_connector_funcs = { .dpms = drm_helper_connector_dpms, .reset = drm_atomic_helper_connector_reset, - .fill_modes = tda998x_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .detect = tda998x_connector_detect, .destroy = tda998x_connector_destroy, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, @@ -1244,40 +1223,29 @@ static int tda998x_connector_get_modes(struct drm_connector *connector) } drm_connector_update_edid_property(connector, edid); + cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid); + + mutex_lock(&priv->audio_mutex); n = drm_add_edid_modes(connector, edid); + priv->sink_has_audio = drm_detect_monitor_audio(edid); + mutex_unlock(&priv->audio_mutex); kfree(edid); return n; } -static enum drm_mode_status tda998x_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - /* TDA19988 dotclock can go up to 165MHz */ - struct tda998x_priv *priv = conn_to_tda998x_priv(connector); - - if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000)) - return MODE_CLOCK_HIGH; - if (mode->htotal >= BIT(13)) - return MODE_BAD_HVALUE; - if (mode->vtotal >= BIT(11)) - return MODE_BAD_VVALUE; - return MODE_OK; -} - static struct drm_encoder * tda998x_connector_best_encoder(struct drm_connector *connector) { struct tda998x_priv *priv = conn_to_tda998x_priv(connector); - return &priv->encoder; + return priv->bridge.encoder; } static const struct drm_connector_helper_funcs tda998x_connector_helper_funcs = { .get_modes = tda998x_connector_get_modes, - .mode_valid = tda998x_connector_mode_valid, .best_encoder = tda998x_connector_best_encoder, }; @@ -1301,25 +1269,48 @@ static int tda998x_connector_init(struct tda998x_priv *priv, if (ret) return ret; - drm_connector_attach_encoder(&priv->connector, &priv->encoder); + drm_connector_attach_encoder(&priv->connector, + priv->bridge.encoder); return 0; } -/* DRM encoder functions */ +/* DRM bridge functions */ -static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) +static int tda998x_bridge_attach(struct drm_bridge *bridge) { - struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); - bool on; + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); - /* we only care about on or off: */ - on = mode == DRM_MODE_DPMS_ON; + return tda998x_connector_init(priv, bridge->dev); +} - if (on == priv->is_on) - return; +static void tda998x_bridge_detach(struct drm_bridge *bridge) +{ + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); - if (on) { + drm_connector_cleanup(&priv->connector); +} + +static enum drm_mode_status tda998x_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_mode *mode) +{ + /* TDA19988 dotclock can go up to 165MHz */ + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); + + if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000)) + return MODE_CLOCK_HIGH; + if (mode->htotal >= BIT(13)) + return MODE_BAD_HVALUE; + if (mode->vtotal >= BIT(11)) + return MODE_BAD_VVALUE; + return MODE_OK; +} + +static void tda998x_bridge_enable(struct drm_bridge *bridge) +{ + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); + + if (!priv->is_on) { /* enable video ports, audio will be enabled later */ reg_write(priv, REG_ENA_VP_0, 0xff); reg_write(priv, REG_ENA_VP_1, 0xff); @@ -1330,7 +1321,14 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) reg_write(priv, REG_VIP_CNTRL_2, priv->vip_cntrl_2); priv->is_on = true; - } else { + } +} + +static void tda998x_bridge_disable(struct drm_bridge *bridge) +{ + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); + + if (priv->is_on) { /* disable video ports */ reg_write(priv, REG_ENA_VP_0, 0x00); reg_write(priv, REG_ENA_VP_1, 0x00); @@ -1340,12 +1338,12 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) } } -static void -tda998x_encoder_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static void tda998x_bridge_mode_set(struct drm_bridge *bridge, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) { - struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); + struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge); + unsigned long tmds_clock; u16 ref_pix, ref_line, n_pix, n_line; u16 hs_pix_s, hs_pix_e; u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e; @@ -1416,12 +1414,19 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder, (mode->vsync_end - mode->vsync_start)/2; } - div = 148500 / mode->clock; - if (div != 0) { - div--; - if (div > 3) - div = 3; - } + tmds_clock = mode->clock; + + /* + * The divisor is power-of-2. The TDA9983B datasheet gives + * this as ranges of Msample/s, which is 10x the TMDS clock: + * 0 - 800 to 1500 Msample/s + * 1 - 400 to 800 Msample/s + * 2 - 200 to 400 Msample/s + * 3 - as 2 above + */ + for (div = 0; div < 3; div++) + if (80000 >> div <= tmds_clock) + break; mutex_lock(&priv->audio_mutex); @@ -1552,26 +1557,14 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder, mutex_unlock(&priv->audio_mutex); } -static void tda998x_destroy(struct tda998x_priv *priv) -{ - /* disable all IRQs and free the IRQ handler */ - cec_write(priv, REG_CEC_RXSHPDINTENA, 0); - reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD); - - if (priv->audio_pdev) - platform_device_unregister(priv->audio_pdev); - - if (priv->hdmi->irq) - free_irq(priv->hdmi->irq, priv); - - del_timer_sync(&priv->edid_delay_timer); - cancel_work_sync(&priv->detect_work); - - i2c_unregister_device(priv->cec); - - if (priv->cec_notify) - cec_notifier_put(priv->cec_notify); -} +static const struct drm_bridge_funcs tda998x_bridge_funcs = { + .attach = tda998x_bridge_attach, + .detach = tda998x_bridge_detach, + .mode_valid = tda998x_bridge_mode_valid, + .disable = tda998x_bridge_disable, + .mode_set = tda998x_bridge_mode_set, + .enable = tda998x_bridge_enable, +}; /* I2C driver functions */ @@ -1617,16 +1610,69 @@ static int tda998x_get_audio_ports(struct tda998x_priv *priv, return 0; } -static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) +static void tda998x_set_config(struct tda998x_priv *priv, + const struct tda998x_encoder_params *p) { + priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) | + (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) | + VIP_CNTRL_0_SWAP_B(p->swap_b) | + (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0); + priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) | + (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) | + VIP_CNTRL_1_SWAP_D(p->swap_d) | + (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0); + priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) | + (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) | + VIP_CNTRL_2_SWAP_F(p->swap_f) | + (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0); + + priv->audio_params = p->audio_params; +} + +static void tda998x_destroy(struct device *dev) +{ + struct tda998x_priv *priv = dev_get_drvdata(dev); + + drm_bridge_remove(&priv->bridge); + + /* disable all IRQs and free the IRQ handler */ + cec_write(priv, REG_CEC_RXSHPDINTENA, 0); + reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD); + + if (priv->audio_pdev) + platform_device_unregister(priv->audio_pdev); + + if (priv->hdmi->irq) + free_irq(priv->hdmi->irq, priv); + + del_timer_sync(&priv->edid_delay_timer); + cancel_work_sync(&priv->detect_work); + + i2c_unregister_device(priv->cec); + + if (priv->cec_notify) + cec_notifier_put(priv->cec_notify); +} + +static int tda998x_create(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); struct device_node *np = client->dev.of_node; struct i2c_board_info cec_info; + struct tda998x_priv *priv; u32 video; int rev_lo, rev_hi, ret; + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + dev_set_drvdata(dev, priv); + mutex_init(&priv->mutex); /* protect the page access */ mutex_init(&priv->audio_mutex); /* protect access from audio thread */ mutex_init(&priv->edid_mutex); + INIT_LIST_HEAD(&priv->bridge.list); init_waitqueue_head(&priv->edid_delay_waitq); timer_setup(&priv->edid_delay_timer, tda998x_edid_delay_done, 0); INIT_WORK(&priv->detect_work, tda998x_detect_work); @@ -1649,13 +1695,13 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) /* read version: */ rev_lo = reg_read(priv, REG_VERSION_LSB); if (rev_lo < 0) { - dev_err(&client->dev, "failed to read version: %d\n", rev_lo); + dev_err(dev, "failed to read version: %d\n", rev_lo); return rev_lo; } rev_hi = reg_read(priv, REG_VERSION_MSB); if (rev_hi < 0) { - dev_err(&client->dev, "failed to read version: %d\n", rev_hi); + dev_err(dev, "failed to read version: %d\n", rev_hi); return rev_hi; } @@ -1666,20 +1712,19 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) switch (priv->rev) { case TDA9989N2: - dev_info(&client->dev, "found TDA9989 n2"); + dev_info(dev, "found TDA9989 n2"); break; case TDA19989: - dev_info(&client->dev, "found TDA19989"); + dev_info(dev, "found TDA19989"); break; case TDA19989N2: - dev_info(&client->dev, "found TDA19989 n2"); + dev_info(dev, "found TDA19989 n2"); break; case TDA19988: - dev_info(&client->dev, "found TDA19988"); + dev_info(dev, "found TDA19988"); break; default: - dev_err(&client->dev, "found unsupported device: %04x\n", - priv->rev); + dev_err(dev, "found unsupported device: %04x\n", priv->rev); return -ENXIO; } @@ -1722,8 +1767,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) tda998x_irq_thread, irq_flags, "tda998x", priv); if (ret) { - dev_err(&client->dev, - "failed to request IRQ#%u: %d\n", + dev_err(dev, "failed to request IRQ#%u: %d\n", client->irq, ret); goto err_irq; } @@ -1732,13 +1776,13 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) cec_write(priv, REG_CEC_RXSHPDINTENA, CEC_RXSHPDLEV_HPD); } - priv->cec_notify = cec_notifier_get(&client->dev); + priv->cec_notify = cec_notifier_get(dev); if (!priv->cec_notify) { ret = -ENOMEM; goto fail; } - priv->cec_glue.parent = &client->dev; + priv->cec_glue.parent = dev; priv->cec_glue.data = priv; priv->cec_glue.init = tda998x_cec_hook_init; priv->cec_glue.exit = tda998x_cec_hook_exit; @@ -1768,61 +1812,44 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv) /* enable EDID read irq: */ reg_set(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD); - if (!np) - return 0; /* non-DT */ + if (np) { + /* get the device tree parameters */ + ret = of_property_read_u32(np, "video-ports", &video); + if (ret == 0) { + priv->vip_cntrl_0 = video >> 16; + priv->vip_cntrl_1 = video >> 8; + priv->vip_cntrl_2 = video; + } + + ret = tda998x_get_audio_ports(priv, np); + if (ret) + goto fail; - /* get the device tree parameters */ - ret = of_property_read_u32(np, "video-ports", &video); - if (ret == 0) { - priv->vip_cntrl_0 = video >> 16; - priv->vip_cntrl_1 = video >> 8; - priv->vip_cntrl_2 = video; + if (priv->audio_port[0].format != AFMT_UNUSED) + tda998x_audio_codec_init(priv, &client->dev); + } else if (dev->platform_data) { + tda998x_set_config(priv, dev->platform_data); } - ret = tda998x_get_audio_ports(priv, np); - if (ret) - goto fail; + priv->bridge.funcs = &tda998x_bridge_funcs; +#ifdef CONFIG_OF + priv->bridge.of_node = dev->of_node; +#endif - if (priv->audio_port[0].format != AFMT_UNUSED) - tda998x_audio_codec_init(priv, &client->dev); + drm_bridge_add(&priv->bridge); return 0; fail: - /* if encoder_init fails, the encoder slave is never registered, - * so cleanup here: - */ - i2c_unregister_device(priv->cec); - if (priv->cec_notify) - cec_notifier_put(priv->cec_notify); - if (client->irq) - free_irq(client->irq, priv); + tda998x_destroy(dev); err_irq: return ret; } -static void tda998x_encoder_prepare(struct drm_encoder *encoder) -{ - tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); -} - -static void tda998x_encoder_commit(struct drm_encoder *encoder) -{ - tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_ON); -} - -static const struct drm_encoder_helper_funcs tda998x_encoder_helper_funcs = { - .dpms = tda998x_encoder_dpms, - .prepare = tda998x_encoder_prepare, - .commit = tda998x_encoder_commit, - .mode_set = tda998x_encoder_mode_set, -}; +/* DRM encoder functions */ static void tda998x_encoder_destroy(struct drm_encoder *encoder) { - struct tda998x_priv *priv = enc_to_tda998x_priv(encoder); - - tda998x_destroy(priv); drm_encoder_cleanup(encoder); } @@ -1830,40 +1857,12 @@ static const struct drm_encoder_funcs tda998x_encoder_funcs = { .destroy = tda998x_encoder_destroy, }; -static void tda998x_set_config(struct tda998x_priv *priv, - const struct tda998x_encoder_params *p) -{ - priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) | - (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) | - VIP_CNTRL_0_SWAP_B(p->swap_b) | - (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0); - priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) | - (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) | - VIP_CNTRL_1_SWAP_D(p->swap_d) | - (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0); - priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) | - (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) | - VIP_CNTRL_2_SWAP_F(p->swap_f) | - (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0); - - priv->audio_params = p->audio_params; -} - -static int tda998x_bind(struct device *dev, struct device *master, void *data) +static int tda998x_encoder_init(struct device *dev, struct drm_device *drm) { - struct tda998x_encoder_params *params = dev->platform_data; - struct i2c_client *client = to_i2c_client(dev); - struct drm_device *drm = data; - struct tda998x_priv *priv; + struct tda998x_priv *priv = dev_get_drvdata(dev); u32 crtcs = 0; int ret; - priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - dev_set_drvdata(dev, priv); - if (dev->of_node) crtcs = drm_of_find_possible_crtcs(drm, dev->of_node); @@ -1875,40 +1874,36 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data) priv->encoder.possible_crtcs = crtcs; - ret = tda998x_create(client, priv); - if (ret) - return ret; - - if (!dev->of_node && params) - tda998x_set_config(priv, params); - - drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs); ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); if (ret) goto err_encoder; - ret = tda998x_connector_init(priv, drm); + ret = drm_bridge_attach(&priv->encoder, &priv->bridge, NULL); if (ret) - goto err_connector; + goto err_bridge; return 0; -err_connector: +err_bridge: drm_encoder_cleanup(&priv->encoder); err_encoder: - tda998x_destroy(priv); return ret; } +static int tda998x_bind(struct device *dev, struct device *master, void *data) +{ + struct drm_device *drm = data; + + return tda998x_encoder_init(dev, drm); +} + static void tda998x_unbind(struct device *dev, struct device *master, void *data) { struct tda998x_priv *priv = dev_get_drvdata(dev); - drm_connector_cleanup(&priv->connector); drm_encoder_cleanup(&priv->encoder); - tda998x_destroy(priv); } static const struct component_ops tda998x_ops = { @@ -1919,16 +1914,27 @@ static const struct component_ops tda998x_ops = { static int tda998x_probe(struct i2c_client *client, const struct i2c_device_id *id) { + int ret; + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { dev_warn(&client->dev, "adapter does not support I2C\n"); return -EIO; } - return component_add(&client->dev, &tda998x_ops); + + ret = tda998x_create(&client->dev); + if (ret) + return ret; + + ret = component_add(&client->dev, &tda998x_ops); + if (ret) + tda998x_destroy(&client->dev); + return ret; } static int tda998x_remove(struct i2c_client *client) { component_del(&client->dev, &tda998x_ops); + tda998x_destroy(&client->dev); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 0651e63b25fb..45e89b1e0481 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -863,6 +863,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, { struct intel_vgpu *vgpu = s->vgpu; struct intel_gvt *gvt = vgpu->gvt; + u32 ctx_sr_ctl; if (offset + 4 > gvt->device_info.mmio_size) { gvt_vgpu_err("%s access to (%x) outside of MMIO range\n", @@ -895,6 +896,28 @@ static int cmd_reg_handler(struct parser_exec_state *s, patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE); } + /* TODO + * Right now only scan LRI command on KBL and in inhibit context. + * It's good enough to support initializing mmio by lri command in + * vgpu inhibit context on KBL. + */ + if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) && + intel_gvt_mmio_is_in_ctx(gvt, offset) && + !strncmp(cmd, "lri", 3)) { + intel_gvt_hypervisor_read_gpa(s->vgpu, + s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4); + /* check inhibit context */ + if (ctx_sr_ctl & 1) { + u32 data = cmd_val(s, index + 1); + + if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset)) + intel_vgpu_mask_mmio_write(vgpu, + offset, &data, 4); + else + vgpu_vreg(vgpu, offset) = data; + } + } + /* TODO: Update the global mask if this MMIO is a masked-MMIO */ intel_gvt_mmio_set_cmd_accessed(gvt, offset); return 0; diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 6ee50cb328f8..3019dbc39aef 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -219,7 +219,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | (PORT_B << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { @@ -239,7 +239,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | (PORT_C << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { @@ -259,7 +259,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | TRANS_DDI_PORT_MASK); vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |= - (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | + (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI | (PORT_D << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); if (IS_BROADWELL(dev_priv)) { diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 39980dfbbebd..00aad8164dec 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1901,6 +1901,7 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu) vgpu_free_mm(mm); return ERR_PTR(-ENOMEM); } + mm->ggtt_mm.last_partial_off = -1UL; return mm; } @@ -1925,6 +1926,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); + mm->ggtt_mm.last_partial_off = -1UL; } vgpu_free_mm(mm); @@ -2177,6 +2179,62 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); + /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes + * write, we assume the two 4 bytes writes are consecutive. + * Otherwise, we abort and report error + */ + if (bytes < info->gtt_entry_size) { + if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) { + /* the first partial part*/ + ggtt_mm->ggtt_mm.last_partial_off = off; + ggtt_mm->ggtt_mm.last_partial_data = e.val64; + return 0; + } else if ((g_gtt_index == + (ggtt_mm->ggtt_mm.last_partial_off >> + info->gtt_entry_size_shift)) && + (off != ggtt_mm->ggtt_mm.last_partial_off)) { + /* the second partial part */ + + int last_off = ggtt_mm->ggtt_mm.last_partial_off & + (info->gtt_entry_size - 1); + + memcpy((void *)&e.val64 + last_off, + (void *)&ggtt_mm->ggtt_mm.last_partial_data + + last_off, bytes); + + ggtt_mm->ggtt_mm.last_partial_off = -1UL; + } else { + int last_offset; + + gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n", + ggtt_mm->ggtt_mm.last_partial_off, off, + bytes, info->gtt_entry_size); + + /* set host ggtt entry to scratch page and clear + * virtual ggtt entry as not present for last + * partially write offset + */ + last_offset = ggtt_mm->ggtt_mm.last_partial_off & + (~(info->gtt_entry_size - 1)); + + ggtt_get_host_entry(ggtt_mm, &m, last_offset); + ggtt_invalidate_pte(vgpu, &m); + ops->set_pfn(&m, gvt->gtt.scratch_mfn); + ops->clear_present(&m); + ggtt_set_host_entry(ggtt_mm, &m, last_offset); + ggtt_invalidate(gvt->dev_priv); + + ggtt_get_guest_entry(ggtt_mm, &e, last_offset); + ops->clear_present(&e); + ggtt_set_guest_entry(ggtt_mm, &e, last_offset); + + ggtt_mm->ggtt_mm.last_partial_off = off; + ggtt_mm->ggtt_mm.last_partial_data = e.val64; + + return 0; + } + } + if (ops->test_present(&e)) { gfn = ops->get_pfn(&e); m = e; diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index b7bf68cc8418..7a9b36176efb 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -157,6 +157,8 @@ struct intel_vgpu_mm { } ppgtt_mm; struct { void *virtual_ggtt; + unsigned long last_partial_off; + u64 last_partial_data; } ggtt_mm; }; }; diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index de2a3a2580be..9a9671522774 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -274,6 +274,8 @@ struct intel_gvt_mmio { #define F_CMD_ACCESSED (1 << 5) /* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) +/* This reg is saved/restored in context */ +#define F_IN_CTX (1 << 7) struct gvt_mmio_block *mmio_block; unsigned int num_mmio_block; @@ -655,6 +657,33 @@ static inline bool intel_gvt_mmio_has_mode_mask( return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK; } +/** + * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask + * @gvt: a GVT device + * @offset: register offset + * + * Returns: + * True if a MMIO has a in-context mask, false if it isn't. + * + */ +static inline bool intel_gvt_mmio_is_in_ctx( + struct intel_gvt *gvt, unsigned int offset) +{ + return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX; +} + +/** + * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context + * @gvt: a GVT device + * @offset: register offset + * + */ +static inline void intel_gvt_mmio_set_in_ctx( + struct intel_gvt *gvt, unsigned int offset) +{ + gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX; +} + int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu); void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu); int intel_gvt_debugfs_init(struct intel_gvt *gvt); diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 6b50f850dc28..7a58ca555197 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -3388,6 +3388,30 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, } /** + * intel_vgpu_mask_mmio_write - write mask register + * @vgpu: a vGPU + * @offset: access offset + * @p_data: write data buffer + * @bytes: access data length + * + * Returns: + * Zero on success, negative error code if failed. + */ +int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes) +{ + u32 mask, old_vreg; + + old_vreg = vgpu_vreg(vgpu, offset); + write_vreg(vgpu, offset, p_data, bytes); + mask = vgpu_vreg(vgpu, offset) >> 16; + vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) | + (vgpu_vreg(vgpu, offset) & mask); + + return 0; +} + +/** * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be * force-nopriv register * diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 718ab307a500..4d2f53ae9f0f 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -185,12 +185,6 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn, if (ret) return ret; - if (!pfn_valid(pfn)) { - gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn); - vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1); - return -EINVAL; - } - /* Setup DMA mapping. */ *dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev, *dma_addr); diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h index e474188b46d2..1ffc69eba30e 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.h +++ b/drivers/gpu/drm/i915/gvt/mmio.h @@ -99,4 +99,6 @@ bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt, int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset, void *pdata, unsigned int bytes, bool is_read); +int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes); #endif diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 20be9a92600f..42e1e6bdcc2c 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -587,7 +587,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt) for (mmio = gvt->engine_mmio_list.mmio; i915_mmio_reg_valid(mmio->reg); mmio++) { - if (mmio->in_context) + if (mmio->in_context) { gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++; + intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg); + } } } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index b3aefd623557..f9ce35da4123 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1218,7 +1218,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused) rpcurup, GT_PM_INTERVAL_TO_US(dev_priv, rpcurup)); seq_printf(m, "RP PREV UP: %d (%dus)\n", rpprevup, GT_PM_INTERVAL_TO_US(dev_priv, rpprevup)); - seq_printf(m, "Up threshold: %d%%\n", rps->up_threshold); + seq_printf(m, "Up threshold: %d%%\n", + rps->power.up_threshold); seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n", rpdownei, GT_PM_INTERVAL_TO_US(dev_priv, rpdownei)); @@ -1226,7 +1227,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused) rpcurdown, GT_PM_INTERVAL_TO_US(dev_priv, rpcurdown)); seq_printf(m, "RP PREV DOWN: %d (%dus)\n", rpprevdown, GT_PM_INTERVAL_TO_US(dev_priv, rpprevdown)); - seq_printf(m, "Down threshold: %d%%\n", rps->down_threshold); + seq_printf(m, "Down threshold: %d%%\n", + rps->power.down_threshold); max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 : rp_state_cap >> 16) & 0xff; @@ -2218,6 +2220,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data) seq_printf(m, "CPU waiting? %d\n", count_irq_waiters(dev_priv)); seq_printf(m, "Boosts outstanding? %d\n", atomic_read(&rps->num_waiters)); + seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive)); seq_printf(m, "Frequency requested %d\n", intel_gpu_freq(dev_priv, rps->cur_freq)); seq_printf(m, " min hard:%d, soft:%d; max soft:%d, hard:%d\n", @@ -2261,13 +2264,13 @@ static int i915_rps_boost_info(struct seq_file *m, void *data) intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); seq_printf(m, "\nRPS Autotuning (current \"%s\" window):\n", - rps_power_to_str(rps->power)); + rps_power_to_str(rps->power.mode)); seq_printf(m, " Avg. up: %d%% [above threshold? %d%%]\n", rpup && rpupei ? 100 * rpup / rpupei : 0, - rps->up_threshold); + rps->power.up_threshold); seq_printf(m, " Avg. down: %d%% [below threshold? %d%%]\n", rpdown && rpdownei ? 100 * rpdown / rpdownei : 0, - rps->down_threshold); + rps->power.down_threshold); } else { seq_puts(m, "\nRPS Autotuning inactive\n"); } @@ -2606,13 +2609,22 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data) "sink internal error", }; struct drm_connector *connector = m->private; + struct drm_i915_private *dev_priv = to_i915(connector->dev); struct intel_dp *intel_dp = enc_to_intel_dp(&intel_attached_encoder(connector)->base); + int ret; + + if (!CAN_PSR(dev_priv)) { + seq_puts(m, "PSR Unsupported\n"); + return -ENODEV; + } if (connector->status != connector_status_connected) return -ENODEV; - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) == 1) { + ret = drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val); + + if (ret == 1) { const char *str = "unknown"; val &= DP_PSR_SINK_STATE_MASK; @@ -2620,7 +2632,7 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data) str = sink_status[val]; seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str); } else { - DRM_ERROR("dpcd read (at %u) failed\n", DP_PSR_STATUS); + return ret; } return 0; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0f49f9988dfa..4aca5344863d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -779,11 +779,17 @@ struct intel_rps { u8 rp0_freq; /* Non-overclocked max frequency. */ u16 gpll_ref_freq; /* vlv/chv GPLL reference frequency */ - u8 up_threshold; /* Current %busy required to uplock */ - u8 down_threshold; /* Current %busy required to downclock */ - int last_adj; - enum { LOW_POWER, BETWEEN, HIGH_POWER } power; + + struct { + struct mutex mutex; + + enum { LOW_POWER, BETWEEN, HIGH_POWER } mode; + unsigned int interactive; + + u8 up_threshold; /* Current %busy required to uplock */ + u8 down_threshold; /* Current %busy required to downclock */ + } power; bool enabled; atomic_t num_waiters; @@ -3422,6 +3428,8 @@ extern void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv); extern bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val); extern void intel_init_pch_refclk(struct drm_i915_private *dev_priv); extern int intel_set_rps(struct drm_i915_private *dev_priv, u8 val); +extern void intel_rps_mark_interactive(struct drm_i915_private *i915, + bool interactive); extern bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8c81cf3aa182..f7f2aa71d8d9 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -31,6 +31,7 @@ #include <linux/stop_machine.h> #include <linux/zlib.h> #include <drm/drm_print.h> +#include <linux/ascii85.h> #include "i915_gpu_error.h" #include "i915_drv.h" @@ -517,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) va_end(args); } -static int -ascii85_encode_len(int len) -{ - return DIV_ROUND_UP(len, 4); -} - -static bool -ascii85_encode(u32 in, char *out) -{ - int i; - - if (in == 0) - return false; - - out[5] = '\0'; - for (i = 5; i--; ) { - out[i] = '!' + in % 85; - in /= 85; - } - - return true; -} - static void print_error_obj(struct drm_i915_error_state_buf *m, struct intel_engine_cs *engine, const char *name, struct drm_i915_error_object *obj) { - char out[6]; + char out[ASCII85_BUFSZ]; int page; if (!obj) @@ -567,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m, len -= obj->unused; len = ascii85_encode_len(len); - for (i = 0; i < len; i++) { - if (ascii85_encode(obj->pages[page][i], out)) - err_puts(m, out); - else - err_puts(m, "z"); - } + for (i = 0; i < len; i++) + err_puts(m, ascii85_encode(obj->pages[page][i], out)); } err_puts(m, "\n"); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 5dadefca2ad2..90628a47ae17 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1265,9 +1265,9 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir) c0 = max(render, media); c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */ - if (c0 > time * rps->up_threshold) + if (c0 > time * rps->power.up_threshold) events = GEN6_PM_RP_UP_THRESHOLD; - else if (c0 < time * rps->down_threshold) + else if (c0 < time * rps->power.down_threshold) events = GEN6_PM_RP_DOWN_THRESHOLD; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 8af945d8a995..91e7483228e1 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2780,9 +2780,6 @@ enum i915_power_well_id { #define GEN8_4x4_STC_OPTIMIZATION_DISABLE (1 << 6) #define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE (1 << 1) -#define GEN10_CACHE_MODE_SS _MMIO(0xe420) -#define FLOAT_BLEND_OPTIMIZATION_ENABLE (1 << 4) - #define GEN6_BLITTER_ECOSKPD _MMIO(0x221d0) #define GEN6_BLITTER_LOCK_SHIFT 16 #define GEN6_BLITTER_FBC_NOTIFY (1 << 3) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 87e4cfbfd096..ed3fa1c8a983 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13104,6 +13104,19 @@ intel_prepare_plane_fb(struct drm_plane *plane, add_rps_boost_after_vblank(new_state->crtc, new_state->fence); } + /* + * We declare pageflips to be interactive and so merit a small bias + * towards upclocking to deliver the frame on time. By only changing + * the RPS thresholds to sample more regularly and aim for higher + * clocks we can hopefully deliver low power workloads (like kodi) + * that are not quite steady state without resorting to forcing + * maximum clocks following a vblank miss (see do_rps_boost()). + */ + if (!intel_state->rps_interactive) { + intel_rps_mark_interactive(dev_priv, true); + intel_state->rps_interactive = true; + } + return 0; } @@ -13120,8 +13133,15 @@ void intel_cleanup_plane_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { + struct intel_atomic_state *intel_state = + to_intel_atomic_state(old_state->state); struct drm_i915_private *dev_priv = to_i915(plane->dev); + if (intel_state->rps_interactive) { + intel_rps_mark_interactive(dev_priv, false); + intel_state->rps_interactive = false; + } + /* Should only be called after a successful intel_prepare_plane_fb()! */ mutex_lock(&dev_priv->drm.struct_mutex); intel_plane_unpin_fb(to_intel_plane_state(old_state)); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index c275f91244a6..17af06d8a43e 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -484,6 +484,8 @@ struct intel_atomic_state { */ bool skip_intermediate_wm; + bool rps_interactive; + /* Gen9+ only */ struct skl_ddb_values wm_results; diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index 6269750e2b54..430732720e65 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -126,9 +126,7 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) return platdev; } - pm_runtime_forbid(&platdev->dev); - pm_runtime_set_active(&platdev->dev); - pm_runtime_enable(&platdev->dev); + pm_runtime_no_callbacks(&platdev->dev); return platdev; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 7312ecb73415..43ae9de12ba3 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -6264,42 +6264,15 @@ static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val) return limits; } -static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) +static void rps_set_power(struct drm_i915_private *dev_priv, int new_power) { struct intel_rps *rps = &dev_priv->gt_pm.rps; - int new_power; u32 threshold_up = 0, threshold_down = 0; /* in % */ u32 ei_up = 0, ei_down = 0; - new_power = rps->power; - switch (rps->power) { - case LOW_POWER: - if (val > rps->efficient_freq + 1 && - val > rps->cur_freq) - new_power = BETWEEN; - break; - - case BETWEEN: - if (val <= rps->efficient_freq && - val < rps->cur_freq) - new_power = LOW_POWER; - else if (val >= rps->rp0_freq && - val > rps->cur_freq) - new_power = HIGH_POWER; - break; + lockdep_assert_held(&rps->power.mutex); - case HIGH_POWER: - if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 && - val < rps->cur_freq) - new_power = BETWEEN; - break; - } - /* Max/min bins are special */ - if (val <= rps->min_freq_softlimit) - new_power = LOW_POWER; - if (val >= rps->max_freq_softlimit) - new_power = HIGH_POWER; - if (new_power == rps->power) + if (new_power == rps->power.mode) return; /* Note the units here are not exactly 1us, but 1280ns. */ @@ -6362,12 +6335,71 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) GEN6_RP_DOWN_IDLE_AVG); skip_hw_write: - rps->power = new_power; - rps->up_threshold = threshold_up; - rps->down_threshold = threshold_down; + rps->power.mode = new_power; + rps->power.up_threshold = threshold_up; + rps->power.down_threshold = threshold_down; +} + +static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val) +{ + struct intel_rps *rps = &dev_priv->gt_pm.rps; + int new_power; + + new_power = rps->power.mode; + switch (rps->power.mode) { + case LOW_POWER: + if (val > rps->efficient_freq + 1 && + val > rps->cur_freq) + new_power = BETWEEN; + break; + + case BETWEEN: + if (val <= rps->efficient_freq && + val < rps->cur_freq) + new_power = LOW_POWER; + else if (val >= rps->rp0_freq && + val > rps->cur_freq) + new_power = HIGH_POWER; + break; + + case HIGH_POWER: + if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 && + val < rps->cur_freq) + new_power = BETWEEN; + break; + } + /* Max/min bins are special */ + if (val <= rps->min_freq_softlimit) + new_power = LOW_POWER; + if (val >= rps->max_freq_softlimit) + new_power = HIGH_POWER; + + mutex_lock(&rps->power.mutex); + if (rps->power.interactive) + new_power = HIGH_POWER; + rps_set_power(dev_priv, new_power); + mutex_unlock(&rps->power.mutex); rps->last_adj = 0; } +void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive) +{ + struct intel_rps *rps = &i915->gt_pm.rps; + + if (INTEL_GEN(i915) < 6) + return; + + mutex_lock(&rps->power.mutex); + if (interactive) { + if (!rps->power.interactive++ && READ_ONCE(i915->gt.awake)) + rps_set_power(i915, HIGH_POWER); + } else { + GEM_BUG_ON(!rps->power.interactive); + rps->power.interactive--; + } + mutex_unlock(&rps->power.mutex); +} + static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) { struct intel_rps *rps = &dev_priv->gt_pm.rps; @@ -6780,7 +6812,7 @@ static void reset_rps(struct drm_i915_private *dev_priv, u8 freq = rps->cur_freq; /* force a reset */ - rps->power = -1; + rps->power.mode = -1; rps->cur_freq = -1; if (set(dev_priv, freq)) @@ -9604,6 +9636,7 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val) void intel_pm_setup(struct drm_i915_private *dev_priv) { mutex_init(&dev_priv->pcu_lock); + mutex_init(&dev_priv->gt_pm.rps.power.mutex); atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0); diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index f8bb32e974f6..4bcdeaf8d98f 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -508,9 +508,6 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3, GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC); - /* WaEnableFloatBlendOptimization:icl */ - WA_SET_BIT_MASKED(GEN10_CACHE_MODE_SS, FLOAT_BLEND_OPTIMIZATION_ENABLE); - return 0; } diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index f0122afcf2a8..5ea0c82f9957 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -35,11 +35,6 @@ #define MAX_CRTC 4 -struct imx_drm_device { - struct drm_device *drm; - struct drm_atomic_state *state; -}; - #if IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION) static int legacyfb_depth = 16; module_param(legacyfb_depth, int, 0444); @@ -218,22 +213,12 @@ static int compare_of(struct device *dev, void *data) static int imx_drm_bind(struct device *dev) { struct drm_device *drm; - struct imx_drm_device *imxdrm; int ret; drm = drm_dev_alloc(&imx_drm_driver, dev); if (IS_ERR(drm)) return PTR_ERR(drm); - imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL); - if (!imxdrm) { - ret = -ENOMEM; - goto err_put; - } - - imxdrm->drm = drm; - drm->dev_private = imxdrm; - /* * enable drm irq mode. * - with irq_enabled = true, we can use the vblank feature. @@ -305,7 +290,6 @@ err_unbind: component_unbind_all(drm->dev, drm); err_kms: drm_mode_config_cleanup(drm); -err_put: drm_dev_put(drm); return ret; @@ -354,37 +338,15 @@ static int imx_drm_platform_remove(struct platform_device *pdev) static int imx_drm_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct imx_drm_device *imxdrm; - - /* The drm_dev is NULL before .load hook is called */ - if (drm_dev == NULL) - return 0; - - drm_kms_helper_poll_disable(drm_dev); - imxdrm = drm_dev->dev_private; - imxdrm->state = drm_atomic_helper_suspend(drm_dev); - if (IS_ERR(imxdrm->state)) { - drm_kms_helper_poll_enable(drm_dev); - return PTR_ERR(imxdrm->state); - } - - return 0; + return drm_mode_config_helper_suspend(drm_dev); } static int imx_drm_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct imx_drm_device *imx_drm; - if (drm_dev == NULL) - return 0; - - imx_drm = drm_dev->dev_private; - drm_atomic_helper_resume(drm_dev, imx_drm->state); - drm_kms_helper_poll_enable(drm_dev); - - return 0; + return drm_mode_config_helper_resume(drm_dev); } #endif diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 38cbde971b48..843a9d40c05e 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -12,6 +12,7 @@ config DRM_MSM select SHMEM select TMPFS select QCOM_SCM + select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE select PM_OPP diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index cd40c050b2d7..7c773e003663 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y := -Idrivers/gpu/drm/msm +ccflags-y += -Idrivers/gpu/drm/msm/disp/dpu1 ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi msm-y := \ @@ -45,6 +46,33 @@ msm-y := \ disp/mdp5/mdp5_mixer.o \ disp/mdp5/mdp5_plane.o \ disp/mdp5/mdp5_smp.o \ + disp/dpu1/dpu_core_irq.o \ + disp/dpu1/dpu_core_perf.o \ + disp/dpu1/dpu_crtc.o \ + disp/dpu1/dpu_encoder.o \ + disp/dpu1/dpu_encoder_phys_cmd.o \ + disp/dpu1/dpu_encoder_phys_vid.o \ + disp/dpu1/dpu_formats.o \ + disp/dpu1/dpu_hw_blk.o \ + disp/dpu1/dpu_hw_catalog.o \ + disp/dpu1/dpu_hw_cdm.o \ + disp/dpu1/dpu_hw_ctl.o \ + disp/dpu1/dpu_hw_interrupts.o \ + disp/dpu1/dpu_hw_intf.o \ + disp/dpu1/dpu_hw_lm.o \ + disp/dpu1/dpu_hw_pingpong.o \ + disp/dpu1/dpu_hw_sspp.o \ + disp/dpu1/dpu_hw_top.o \ + disp/dpu1/dpu_hw_util.o \ + disp/dpu1/dpu_hw_vbif.o \ + disp/dpu1/dpu_io_util.o \ + disp/dpu1/dpu_irq.o \ + disp/dpu1/dpu_kms.o \ + disp/dpu1/dpu_mdss.o \ + disp/dpu1/dpu_plane.o \ + disp/dpu1/dpu_power_handle.o \ + disp/dpu1/dpu_rm.o \ + disp/dpu1/dpu_vbif.o \ msm_atomic.o \ msm_debugfs.o \ msm_drv.o \ @@ -62,7 +90,8 @@ msm-y := \ msm_ringbuffer.o \ msm_submitqueue.o -msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o +msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \ + disp/dpu1/dpu_dbg.o msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 3ebbeb3a9b68..669c2d4b070d 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -411,15 +411,6 @@ static const unsigned int a3xx_registers[] = { ~0 /* sentinel */ }; -#ifdef CONFIG_DEBUG_FS -static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m) -{ - seq_printf(m, "status: %08x\n", - gpu_read(gpu, REG_A3XX_RBBM_STATUS)); - adreno_show(gpu, m); -} -#endif - /* would be nice to not have to duplicate the _show() stuff with printk(): */ static void a3xx_dump(struct msm_gpu *gpu) { @@ -427,6 +418,21 @@ static void a3xx_dump(struct msm_gpu *gpu) gpu_read(gpu, REG_A3XX_RBBM_STATUS)); adreno_dump(gpu); } + +static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu) +{ + struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL); + + if (!state) + return ERR_PTR(-ENOMEM); + + adreno_gpu_state_get(gpu, state); + + state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS); + + return state; +} + /* Register offset defines for A3XX */ static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE), @@ -450,9 +456,11 @@ static const struct adreno_gpu_funcs funcs = { .active_ring = adreno_active_ring, .irq = a3xx_irq, .destroy = a3xx_destroy, -#ifdef CONFIG_DEBUG_FS - .show = a3xx_show, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, #endif + .gpu_state_get = a3xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, }, }; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 16d3d596638e..7c4e6dc1ed59 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -455,15 +455,19 @@ static const unsigned int a4xx_registers[] = { ~0 /* sentinel */ }; -#ifdef CONFIG_DEBUG_FS -static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m) +static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu) { - seq_printf(m, "status: %08x\n", - gpu_read(gpu, REG_A4XX_RBBM_STATUS)); - adreno_show(gpu, m); + struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL); + + if (!state) + return ERR_PTR(-ENOMEM); + + adreno_gpu_state_get(gpu, state); + state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS); + + return state; } -#endif /* Register offset defines for A4XX, in order of enum adreno_regs */ static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { @@ -538,9 +542,11 @@ static const struct adreno_gpu_funcs funcs = { .active_ring = adreno_active_ring, .irq = a4xx_irq, .destroy = a4xx_destroy, -#ifdef CONFIG_DEBUG_FS - .show = a4xx_show, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, #endif + .gpu_state_get = a4xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, }, .get_timestamp = a4xx_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index d39400e5bc42..bd84f71d27d8 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -19,6 +19,7 @@ #include <linux/soc/qcom/mdt_loader.h> #include <linux/pm_opp.h> #include <linux/nvmem-consumer.h> +#include <linux/iopoll.h> #include "msm_gem.h" #include "msm_mmu.h" #include "a5xx_gpu.h" @@ -1123,8 +1124,9 @@ static const u32 a5xx_registers[] = { 0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB, 0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05, 0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3, - 0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F, - 0xB9A0, 0xB9BF, ~0 + 0xEAA5, 0xEAC2, 0xA800, 0xA800, 0xA820, 0xA828, 0xA840, 0xA87D, + 0XA880, 0xA88D, 0xA890, 0xA8A3, 0xA8D0, 0xA8D8, 0xA8E0, 0xA8F5, + 0xAC60, 0xAC60, ~0, }; static void a5xx_dump(struct msm_gpu *gpu) @@ -1195,19 +1197,231 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) return 0; } -#ifdef CONFIG_DEBUG_FS -static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m) +struct a5xx_crashdumper { + void *ptr; + struct drm_gem_object *bo; + u64 iova; +}; + +struct a5xx_gpu_state { + struct msm_gpu_state base; + u32 *hlsqregs; +}; + +#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \ + readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \ + interval, timeout) + +static int a5xx_crashdumper_init(struct msm_gpu *gpu, + struct a5xx_crashdumper *dumper) { - seq_printf(m, "status: %08x\n", - gpu_read(gpu, REG_A5XX_RBBM_STATUS)); + dumper->ptr = msm_gem_kernel_new_locked(gpu->dev, + SZ_1M, MSM_BO_UNCACHED, gpu->aspace, + &dumper->bo, &dumper->iova); - /* - * Temporarily disable hardware clock gating before going into - * adreno_show to avoid issues while reading the registers - */ + if (IS_ERR(dumper->ptr)) + return PTR_ERR(dumper->ptr); + + return 0; +} + +static void a5xx_crashdumper_free(struct msm_gpu *gpu, + struct a5xx_crashdumper *dumper) +{ + msm_gem_put_iova(dumper->bo, gpu->aspace); + msm_gem_put_vaddr(dumper->bo); + + drm_gem_object_unreference(dumper->bo); +} + +static int a5xx_crashdumper_run(struct msm_gpu *gpu, + struct a5xx_crashdumper *dumper) +{ + u32 val; + + if (IS_ERR_OR_NULL(dumper->ptr)) + return -EINVAL; + + gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, + REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + + gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1); + + return gpu_poll_timeout(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, val, + val & 0x04, 100, 10000); +} + +/* + * These are a list of the registers that need to be read through the HLSQ + * aperture through the crashdumper. These are not nominally accessible from + * the CPU on a secure platform. + */ +static const struct { + u32 type; + u32 regoffset; + u32 count; +} a5xx_hlsq_aperture_regs[] = { + { 0x35, 0xe00, 0x32 }, /* HSLQ non-context */ + { 0x31, 0x2080, 0x1 }, /* HLSQ 2D context 0 */ + { 0x33, 0x2480, 0x1 }, /* HLSQ 2D context 1 */ + { 0x32, 0xe780, 0x62 }, /* HLSQ 3D context 0 */ + { 0x34, 0xef80, 0x62 }, /* HLSQ 3D context 1 */ + { 0x3f, 0x0ec0, 0x40 }, /* SP non-context */ + { 0x3d, 0x2040, 0x1 }, /* SP 2D context 0 */ + { 0x3b, 0x2440, 0x1 }, /* SP 2D context 1 */ + { 0x3e, 0xe580, 0x170 }, /* SP 3D context 0 */ + { 0x3c, 0xed80, 0x170 }, /* SP 3D context 1 */ + { 0x3a, 0x0f00, 0x1c }, /* TP non-context */ + { 0x38, 0x2000, 0xa }, /* TP 2D context 0 */ + { 0x36, 0x2400, 0xa }, /* TP 2D context 1 */ + { 0x39, 0xe700, 0x80 }, /* TP 3D context 0 */ + { 0x37, 0xef00, 0x80 }, /* TP 3D context 1 */ +}; + +static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu, + struct a5xx_gpu_state *a5xx_state) +{ + struct a5xx_crashdumper dumper = { 0 }; + u32 offset, count = 0; + u64 *ptr; + int i; + + if (a5xx_crashdumper_init(gpu, &dumper)) + return; + + /* The script will be written at offset 0 */ + ptr = dumper.ptr; + + /* Start writing the data at offset 256k */ + offset = dumper.iova + (256 * SZ_1K); + + /* Count how many additional registers to get from the HLSQ aperture */ + for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) + count += a5xx_hlsq_aperture_regs[i].count; + + a5xx_state->hlsqregs = kcalloc(count, sizeof(u32), GFP_KERNEL); + if (!a5xx_state->hlsqregs) + return; + + /* Build the crashdump script */ + for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) { + u32 type = a5xx_hlsq_aperture_regs[i].type; + u32 c = a5xx_hlsq_aperture_regs[i].count; + + /* Write the register to select the desired bank */ + *ptr++ = ((u64) type << 8); + *ptr++ = (((u64) REG_A5XX_HLSQ_DBG_READ_SEL) << 44) | + (1 << 21) | 1; + + *ptr++ = offset; + *ptr++ = (((u64) REG_A5XX_HLSQ_DBG_AHB_READ_APERTURE) << 44) + | c; + + offset += c * sizeof(u32); + } + + /* Write two zeros to close off the script */ + *ptr++ = 0; + *ptr++ = 0; + + if (a5xx_crashdumper_run(gpu, &dumper)) { + kfree(a5xx_state->hlsqregs); + a5xx_crashdumper_free(gpu, &dumper); + return; + } + + /* Copy the data from the crashdumper to the state */ + memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K), + count * sizeof(u32)); + + a5xx_crashdumper_free(gpu, &dumper); +} + +static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu) +{ + struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state), + GFP_KERNEL); + + if (!a5xx_state) + return ERR_PTR(-ENOMEM); + + /* Temporarily disable hardware clock gating before reading the hw */ a5xx_set_hwcg(gpu, false); - adreno_show(gpu, m); + + /* First get the generic state from the adreno core */ + adreno_gpu_state_get(gpu, &(a5xx_state->base)); + + a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS); + + /* Get the HLSQ regs with the help of the crashdumper */ + a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state); + a5xx_set_hwcg(gpu, true); + + return &a5xx_state->base; +} + +static void a5xx_gpu_state_destroy(struct kref *kref) +{ + struct msm_gpu_state *state = container_of(kref, + struct msm_gpu_state, ref); + struct a5xx_gpu_state *a5xx_state = container_of(state, + struct a5xx_gpu_state, base); + + kfree(a5xx_state->hlsqregs); + + adreno_gpu_state_destroy(state); + kfree(a5xx_state); +} + +int a5xx_gpu_state_put(struct msm_gpu_state *state) +{ + if (IS_ERR_OR_NULL(state)) + return 1; + + return kref_put(&state->ref, a5xx_gpu_state_destroy); +} + + +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) +void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p) +{ + int i, j; + u32 pos = 0; + struct a5xx_gpu_state *a5xx_state = container_of(state, + struct a5xx_gpu_state, base); + + if (IS_ERR_OR_NULL(state)) + return; + + adreno_show(gpu, state, p); + + /* Dump the additional a5xx HLSQ registers */ + if (!a5xx_state->hlsqregs) + return; + + drm_printf(p, "registers-hlsq:\n"); + + for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) { + u32 o = a5xx_hlsq_aperture_regs[i].regoffset; + u32 c = a5xx_hlsq_aperture_regs[i].count; + + for (j = 0; j < c; j++, pos++, o++) { + /* + * To keep the crashdump simple we pull the entire range + * for each register type but not all of the registers + * in the range are valid. Fortunately invalid registers + * stick out like a sore thumb with a value of + * 0xdeadbeef + */ + if (a5xx_state->hlsqregs[pos] == 0xdeadbeef) + continue; + + drm_printf(p, " - { offset: 0x%04x, value: 0x%08x }\n", + o << 2, a5xx_state->hlsqregs[pos]); + } + } } #endif @@ -1239,11 +1453,15 @@ static const struct adreno_gpu_funcs funcs = { .active_ring = a5xx_active_ring, .irq = a5xx_irq, .destroy = a5xx_destroy, -#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) .show = a5xx_show, +#endif +#if defined(CONFIG_DEBUG_FS) .debugfs_init = a5xx_debugfs_init, #endif .gpu_busy = a5xx_gpu_busy, + .gpu_state_get = a5xx_gpu_state_get, + .gpu_state_put = a5xx_gpu_state_put, }, .get_timestamp = a5xx_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 0ae5ace65462..44813624a286 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -35,6 +35,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a300_pfp.fw", }, .gmem = SZ_256K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a3xx_gpu_init, }, { .rev = ADRENO_REV(3, 0, 6, 0), @@ -45,6 +46,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a300_pfp.fw", }, .gmem = SZ_128K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a3xx_gpu_init, }, { .rev = ADRENO_REV(3, 2, ANY_ID, ANY_ID), @@ -55,6 +57,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a300_pfp.fw", }, .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a3xx_gpu_init, }, { .rev = ADRENO_REV(3, 3, 0, ANY_ID), @@ -65,6 +68,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a330_pfp.fw", }, .gmem = SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a3xx_gpu_init, }, { .rev = ADRENO_REV(4, 2, 0, ANY_ID), @@ -75,6 +79,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a420_pfp.fw", }, .gmem = (SZ_1M + SZ_512K), + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a4xx_gpu_init, }, { .rev = ADRENO_REV(4, 3, 0, ANY_ID), @@ -85,6 +90,7 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_PFP] = "a420_pfp.fw", }, .gmem = (SZ_1M + SZ_512K), + .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a4xx_gpu_init, }, { .rev = ADRENO_REV(5, 3, 0, 2), @@ -96,6 +102,11 @@ static const struct adreno_info gpulist[] = { [ADRENO_FW_GPMU] = "a530v3_gpmu.fw2", }, .gmem = SZ_1M, + /* + * Increase inactive period to 250 to avoid bouncing + * the GDSC which appears to make it grumpy + */ + .inactive_period = 250, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_FAULT_DETECT_MASK, .init = a5xx_gpu_init, @@ -158,7 +169,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) mutex_lock(&dev->struct_mutex); ret = msm_gpu_hw_init(gpu); mutex_unlock(&dev->struct_mutex); - pm_runtime_put_sync(&pdev->dev); + pm_runtime_put_autosuspend(&pdev->dev); if (ret) { dev_err(dev->dev, "gpu hw init failed: %d\n", ret); return NULL; @@ -316,6 +327,7 @@ static int adreno_suspend(struct device *dev) #endif static const struct dev_pm_ops adreno_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL) }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 17d0506d058c..38ac50b73829 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -17,6 +17,7 @@ * this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/ascii85.h> #include <linux/pm_opp.h> #include "adreno_gpu.h" #include "msm_gem.h" @@ -368,40 +369,185 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return false; } -#ifdef CONFIG_DEBUG_FS -void adreno_show(struct msm_gpu *gpu, struct seq_file *m) +int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + int i, count = 0; + + kref_init(&state->ref); + + ktime_get_real_ts64(&state->time); + + for (i = 0; i < gpu->nr_rings; i++) { + int size = 0, j; + + state->ring[i].fence = gpu->rb[i]->memptrs->fence; + state->ring[i].iova = gpu->rb[i]->iova; + state->ring[i].seqno = gpu->rb[i]->seqno; + state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]); + state->ring[i].wptr = get_wptr(gpu->rb[i]); + + /* Copy at least 'wptr' dwords of the data */ + size = state->ring[i].wptr; + + /* After wptr find the last non zero dword to save space */ + for (j = state->ring[i].wptr; j < MSM_GPU_RINGBUFFER_SZ >> 2; j++) + if (gpu->rb[i]->start[j]) + size = j + 1; + + if (size) { + state->ring[i].data = kmalloc(size << 2, GFP_KERNEL); + if (state->ring[i].data) { + memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2); + state->ring[i].data_size = size << 2; + } + } + } + + /* Count the number of registers */ + for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) + count += adreno_gpu->registers[i + 1] - + adreno_gpu->registers[i] + 1; + + state->registers = kcalloc(count * 2, sizeof(u32), GFP_KERNEL); + if (state->registers) { + int pos = 0; + + for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) { + u32 start = adreno_gpu->registers[i]; + u32 end = adreno_gpu->registers[i + 1]; + u32 addr; + + for (addr = start; addr <= end; addr++) { + state->registers[pos++] = addr; + state->registers[pos++] = gpu_read(gpu, addr); + } + } + + state->nr_registers = count; + } + + return 0; +} + +void adreno_gpu_state_destroy(struct msm_gpu_state *state) +{ int i; - seq_printf(m, "revision: %d (%d.%d.%d.%d)\n", + for (i = 0; i < ARRAY_SIZE(state->ring); i++) + kfree(state->ring[i].data); + + for (i = 0; state->bos && i < state->nr_bos; i++) + kvfree(state->bos[i].data); + + kfree(state->bos); + kfree(state->comm); + kfree(state->cmd); + kfree(state->registers); +} + +static void adreno_gpu_state_kref_destroy(struct kref *kref) +{ + struct msm_gpu_state *state = container_of(kref, + struct msm_gpu_state, ref); + + adreno_gpu_state_destroy(state); + kfree(state); +} + +int adreno_gpu_state_put(struct msm_gpu_state *state) +{ + if (IS_ERR_OR_NULL(state)) + return 1; + + return kref_put(&state->ref, adreno_gpu_state_kref_destroy); +} + +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + +static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len) +{ + char out[ASCII85_BUFSZ]; + long l, datalen, i; + + if (!ptr || !len) + return; + + /* + * Only dump the non-zero part of the buffer - rarely will any data + * completely fill the entire allocated size of the buffer + */ + for (datalen = 0, i = 0; i < len >> 2; i++) { + if (ptr[i]) + datalen = (i << 2) + 1; + } + + /* Skip printing the object if it is empty */ + if (datalen == 0) + return; + + l = ascii85_encode_len(datalen); + + drm_puts(p, " data: !!ascii85 |\n"); + drm_puts(p, " "); + + for (i = 0; i < l; i++) + drm_puts(p, ascii85_encode(ptr[i], out)); + + drm_puts(p, "\n"); +} + +void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + int i; + + if (IS_ERR_OR_NULL(state)) + return; + + drm_printf(p, "revision: %d (%d.%d.%d.%d)\n", adreno_gpu->info->revn, adreno_gpu->rev.core, adreno_gpu->rev.major, adreno_gpu->rev.minor, adreno_gpu->rev.patchid); - for (i = 0; i < gpu->nr_rings; i++) { - struct msm_ringbuffer *ring = gpu->rb[i]; + drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status); - seq_printf(m, "rb %d: fence: %d/%d\n", i, - ring->memptrs->fence, ring->seqno); + drm_puts(p, "ringbuffer:\n"); - seq_printf(m, " rptr: %d\n", - get_rptr(adreno_gpu, ring)); - seq_printf(m, "rb wptr: %d\n", get_wptr(ring)); + for (i = 0; i < gpu->nr_rings; i++) { + drm_printf(p, " - id: %d\n", i); + drm_printf(p, " iova: 0x%016llx\n", state->ring[i].iova); + drm_printf(p, " last-fence: %d\n", state->ring[i].seqno); + drm_printf(p, " retired-fence: %d\n", state->ring[i].fence); + drm_printf(p, " rptr: %d\n", state->ring[i].rptr); + drm_printf(p, " wptr: %d\n", state->ring[i].wptr); + drm_printf(p, " size: %d\n", MSM_GPU_RINGBUFFER_SZ); + + adreno_show_object(p, state->ring[i].data, + state->ring[i].data_size); } - /* dump these out in a form that can be parsed by demsm: */ - seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name); - for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) { - uint32_t start = adreno_gpu->registers[i]; - uint32_t end = adreno_gpu->registers[i+1]; - uint32_t addr; + if (state->bos) { + drm_puts(p, "bos:\n"); - for (addr = start; addr <= end; addr++) { - uint32_t val = gpu_read(gpu, addr); - seq_printf(m, "IO:R %08x %08x\n", addr<<2, val); + for (i = 0; i < state->nr_bos; i++) { + drm_printf(p, " - iova: 0x%016llx\n", + state->bos[i].iova); + drm_printf(p, " size: %zd\n", state->bos[i].size); + + adreno_show_object(p, state->bos[i].data, + state->bos[i].size); } } + + drm_puts(p, "registers:\n"); + + for (i = 0; i < state->nr_registers; i++) { + drm_printf(p, " - { offset: 0x%04x, value: 0x%08x }\n", + state->registers[i * 2] << 2, + state->registers[(i * 2) + 1]); + } } #endif @@ -565,7 +711,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, adreno_get_pwrlevels(&pdev->dev, gpu); - pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD); + pm_runtime_set_autosuspend_delay(&pdev->dev, + adreno_gpu->info->inactive_period); pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index d6b0e7b813f4..4406776597fd 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -84,6 +84,7 @@ struct adreno_info { enum adreno_quirks quirks; struct msm_gpu *(*init)(struct drm_device *dev); const char *zapfw; + u32 inactive_period; }; const struct adreno_info *adreno_info(struct adreno_rev rev); @@ -214,8 +215,9 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_file_private *ctx); void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring); -#ifdef CONFIG_DEBUG_FS -void adreno_show(struct msm_gpu *gpu, struct seq_file *m); +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) +void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p); #endif void adreno_dump_info(struct msm_gpu *gpu); void adreno_dump(struct msm_gpu *gpu); @@ -228,6 +230,11 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, void adreno_gpu_cleanup(struct adreno_gpu *gpu); +void adreno_gpu_state_destroy(struct msm_gpu_state *state); + +int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state); +int adreno_gpu_state_put(struct msm_gpu_state *state); + /* ringbuffer helpers (the parts that are adreno specific) */ static inline void diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c new file mode 100644 index 000000000000..879c13fe74e0 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c @@ -0,0 +1,479 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/debugfs.h> +#include <linux/irqdomain.h> +#include <linux/irq.h> +#include <linux/kthread.h> + +#include "dpu_core_irq.h" +#include "dpu_trace.h" + +/** + * dpu_core_irq_callback_handler - dispatch core interrupts + * @arg: private data of callback handler + * @irq_idx: interrupt index + */ +static void dpu_core_irq_callback_handler(void *arg, int irq_idx) +{ + struct dpu_kms *dpu_kms = arg; + struct dpu_irq *irq_obj = &dpu_kms->irq_obj; + struct dpu_irq_callback *cb; + unsigned long irq_flags; + + pr_debug("irq_idx=%d\n", irq_idx); + + if (list_empty(&irq_obj->irq_cb_tbl[irq_idx])) { + DRM_ERROR("no registered cb, idx:%d enable_count:%d\n", irq_idx, + atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx])); + } + + atomic_inc(&irq_obj->irq_counts[irq_idx]); + + /* + * Perform registered function callback + */ + spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags); + list_for_each_entry(cb, &irq_obj->irq_cb_tbl[irq_idx], list) + if (cb->func) + cb->func(cb->arg, irq_idx); + spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags); + + /* + * Clear pending interrupt status in HW. + * NOTE: dpu_core_irq_callback_handler is protected by top-level + * spinlock, so it is safe to clear any interrupt status here. + */ + dpu_kms->hw_intr->ops.clear_intr_status_nolock( + dpu_kms->hw_intr, + irq_idx); +} + +int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms, + enum dpu_intr_type intr_type, u32 instance_idx) +{ + if (!dpu_kms || !dpu_kms->hw_intr || + !dpu_kms->hw_intr->ops.irq_idx_lookup) + return -EINVAL; + + return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type, + instance_idx); +} + +/** + * _dpu_core_irq_enable - enable core interrupt given by the index + * @dpu_kms: Pointer to dpu kms context + * @irq_idx: interrupt index + */ +static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx) +{ + unsigned long irq_flags; + int ret = 0, enable_count; + + if (!dpu_kms || !dpu_kms->hw_intr || + !dpu_kms->irq_obj.enable_counts || + !dpu_kms->irq_obj.irq_counts) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]); + DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count); + trace_dpu_core_irq_enable_idx(irq_idx, enable_count); + + if (atomic_inc_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 1) { + ret = dpu_kms->hw_intr->ops.enable_irq( + dpu_kms->hw_intr, + irq_idx); + if (ret) + DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n", + irq_idx); + + DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret); + + spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags); + /* empty callback list but interrupt is enabled */ + if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx])) + DPU_ERROR("irq_idx=%d enabled with no callback\n", + irq_idx); + spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags); + } + + return ret; +} + +int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count) +{ + int i, ret = 0, counts; + + if (!dpu_kms || !irq_idxs || !irq_count) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]); + if (counts) + DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts); + + for (i = 0; (i < irq_count) && !ret; i++) + ret = _dpu_core_irq_enable(dpu_kms, irq_idxs[i]); + + return ret; +} + +/** + * _dpu_core_irq_disable - disable core interrupt given by the index + * @dpu_kms: Pointer to dpu kms context + * @irq_idx: interrupt index + */ +static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx) +{ + int ret = 0, enable_count; + + if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]); + DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count); + trace_dpu_core_irq_disable_idx(irq_idx, enable_count); + + if (atomic_dec_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 0) { + ret = dpu_kms->hw_intr->ops.disable_irq( + dpu_kms->hw_intr, + irq_idx); + if (ret) + DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n", + irq_idx); + DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret); + } + + return ret; +} + +int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count) +{ + int i, ret = 0, counts; + + if (!dpu_kms || !irq_idxs || !irq_count) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]); + if (counts == 2) + DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts); + + for (i = 0; (i < irq_count) && !ret; i++) + ret = _dpu_core_irq_disable(dpu_kms, irq_idxs[i]); + + return ret; +} + +u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear) +{ + if (!dpu_kms || !dpu_kms->hw_intr || + !dpu_kms->hw_intr->ops.get_interrupt_status) + return 0; + + if (irq_idx < 0) { + DPU_ERROR("[%pS] invalid irq_idx=%d\n", + __builtin_return_address(0), irq_idx); + return 0; + } + + return dpu_kms->hw_intr->ops.get_interrupt_status(dpu_kms->hw_intr, + irq_idx, clear); +} + +int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx, + struct dpu_irq_callback *register_irq_cb) +{ + unsigned long irq_flags; + + if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (!register_irq_cb || !register_irq_cb->func) { + DPU_ERROR("invalid irq_cb:%d func:%d\n", + register_irq_cb != NULL, + register_irq_cb ? + register_irq_cb->func != NULL : -1); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + + spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags); + trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb); + list_del_init(®ister_irq_cb->list); + list_add_tail(®ister_irq_cb->list, + &dpu_kms->irq_obj.irq_cb_tbl[irq_idx]); + spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags); + + return 0; +} + +int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx, + struct dpu_irq_callback *register_irq_cb) +{ + unsigned long irq_flags; + + if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + + if (!register_irq_cb || !register_irq_cb->func) { + DPU_ERROR("invalid irq_cb:%d func:%d\n", + register_irq_cb != NULL, + register_irq_cb ? + register_irq_cb->func != NULL : -1); + return -EINVAL; + } + + if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) { + DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx); + + spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags); + trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb); + list_del_init(®ister_irq_cb->list); + /* empty callback list but interrupt is still enabled */ + if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]) && + atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx])) + DPU_ERROR("irq_idx=%d enabled with no callback\n", irq_idx); + spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags); + + return 0; +} + +static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms) +{ + if (!dpu_kms || !dpu_kms->hw_intr || + !dpu_kms->hw_intr->ops.clear_all_irqs) + return; + + dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr); +} + +static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms) +{ + if (!dpu_kms || !dpu_kms->hw_intr || + !dpu_kms->hw_intr->ops.disable_all_irqs) + return; + + dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr); +} + +#ifdef CONFIG_DEBUG_FS +#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ +static int __prefix ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __prefix ## _show, inode->i_private); \ +} \ +static const struct file_operations __prefix ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __prefix ## _open, \ + .release = single_release, \ + .read = seq_read, \ + .llseek = seq_lseek, \ +} + +static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v) +{ + struct dpu_irq *irq_obj = s->private; + struct dpu_irq_callback *cb; + unsigned long irq_flags; + int i, irq_count, enable_count, cb_count; + + if (!irq_obj || !irq_obj->enable_counts || !irq_obj->irq_cb_tbl) { + DPU_ERROR("invalid parameters\n"); + return 0; + } + + for (i = 0; i < irq_obj->total_irqs; i++) { + spin_lock_irqsave(&irq_obj->cb_lock, irq_flags); + cb_count = 0; + irq_count = atomic_read(&irq_obj->irq_counts[i]); + enable_count = atomic_read(&irq_obj->enable_counts[i]); + list_for_each_entry(cb, &irq_obj->irq_cb_tbl[i], list) + cb_count++; + spin_unlock_irqrestore(&irq_obj->cb_lock, irq_flags); + + if (irq_count || enable_count || cb_count) + seq_printf(s, "idx:%d irq:%d enable:%d cb:%d\n", + i, irq_count, enable_count, cb_count); + } + + return 0; +} + +DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq); + +int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, + struct dentry *parent) +{ + dpu_kms->irq_obj.debugfs_file = debugfs_create_file("core_irq", 0600, + parent, &dpu_kms->irq_obj, + &dpu_debugfs_core_irq_fops); + + return 0; +} + +void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms) +{ + debugfs_remove(dpu_kms->irq_obj.debugfs_file); + dpu_kms->irq_obj.debugfs_file = NULL; +} + +#else +int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, + struct dentry *parent) +{ + return 0; +} + +void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms) +{ +} +#endif + +void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms) +{ + struct msm_drm_private *priv; + int i; + + if (!dpu_kms) { + DPU_ERROR("invalid dpu_kms\n"); + return; + } else if (!dpu_kms->dev) { + DPU_ERROR("invalid drm device\n"); + return; + } else if (!dpu_kms->dev->dev_private) { + DPU_ERROR("invalid device private\n"); + return; + } + priv = dpu_kms->dev->dev_private; + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + dpu_clear_all_irqs(dpu_kms); + dpu_disable_all_irqs(dpu_kms); + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + spin_lock_init(&dpu_kms->irq_obj.cb_lock); + + /* Create irq callbacks for all possible irq_idx */ + dpu_kms->irq_obj.total_irqs = dpu_kms->hw_intr->irq_idx_tbl_size; + dpu_kms->irq_obj.irq_cb_tbl = kcalloc(dpu_kms->irq_obj.total_irqs, + sizeof(struct list_head), GFP_KERNEL); + dpu_kms->irq_obj.enable_counts = kcalloc(dpu_kms->irq_obj.total_irqs, + sizeof(atomic_t), GFP_KERNEL); + dpu_kms->irq_obj.irq_counts = kcalloc(dpu_kms->irq_obj.total_irqs, + sizeof(atomic_t), GFP_KERNEL); + for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) { + INIT_LIST_HEAD(&dpu_kms->irq_obj.irq_cb_tbl[i]); + atomic_set(&dpu_kms->irq_obj.enable_counts[i], 0); + atomic_set(&dpu_kms->irq_obj.irq_counts[i], 0); + } +} + +int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms) +{ + return 0; +} + +void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms) +{ + struct msm_drm_private *priv; + int i; + + if (!dpu_kms) { + DPU_ERROR("invalid dpu_kms\n"); + return; + } else if (!dpu_kms->dev) { + DPU_ERROR("invalid drm device\n"); + return; + } else if (!dpu_kms->dev->dev_private) { + DPU_ERROR("invalid device private\n"); + return; + } + priv = dpu_kms->dev->dev_private; + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) + if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) || + !list_empty(&dpu_kms->irq_obj.irq_cb_tbl[i])) + DPU_ERROR("irq_idx=%d still enabled/registered\n", i); + + dpu_clear_all_irqs(dpu_kms); + dpu_disable_all_irqs(dpu_kms); + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + kfree(dpu_kms->irq_obj.irq_cb_tbl); + kfree(dpu_kms->irq_obj.enable_counts); + kfree(dpu_kms->irq_obj.irq_counts); + dpu_kms->irq_obj.irq_cb_tbl = NULL; + dpu_kms->irq_obj.enable_counts = NULL; + dpu_kms->irq_obj.irq_counts = NULL; + dpu_kms->irq_obj.total_irqs = 0; +} + +irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms) +{ + /* + * Read interrupt status from all sources. Interrupt status are + * stored within hw_intr. + * Function will also clear the interrupt status after reading. + * Individual interrupt status bit will only get stored if it + * is enabled. + */ + dpu_kms->hw_intr->ops.get_interrupt_statuses(dpu_kms->hw_intr); + + /* + * Dispatch to HW driver to handle interrupt lookup that is being + * fired. When matching interrupt is located, HW driver will call to + * dpu_core_irq_callback_handler with the irq_idx from the lookup table. + * dpu_core_irq_callback_handler will perform the registered function + * callback, and do the interrupt status clearing once the registered + * callback is finished. + */ + dpu_kms->hw_intr->ops.dispatch_irqs( + dpu_kms->hw_intr, + dpu_core_irq_callback_handler, + dpu_kms); + + return IRQ_HANDLED; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h new file mode 100644 index 000000000000..5e98bba46af5 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h @@ -0,0 +1,153 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef __DPU_CORE_IRQ_H__ +#define __DPU_CORE_IRQ_H__ + +#include "dpu_kms.h" +#include "dpu_hw_interrupts.h" + +/** + * dpu_core_irq_preinstall - perform pre-installation of core IRQ handler + * @dpu_kms: DPU handle + * @return: none + */ +void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms); + +/** + * dpu_core_irq_postinstall - perform post-installation of core IRQ handler + * @dpu_kms: DPU handle + * @return: 0 if success; error code otherwise + */ +int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms); + +/** + * dpu_core_irq_uninstall - uninstall core IRQ handler + * @dpu_kms: DPU handle + * @return: none + */ +void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms); + +/** + * dpu_core_irq - core IRQ handler + * @dpu_kms: DPU handle + * @return: interrupt handling status + */ +irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms); + +/** + * dpu_core_irq_idx_lookup - IRQ helper function for lookup irq_idx from HW + * interrupt mapping table. + * @dpu_kms: DPU handle + * @intr_type: DPU HW interrupt type for lookup + * @instance_idx: DPU HW block instance defined in dpu_hw_mdss.h + * @return: irq_idx or -EINVAL when fail to lookup + */ +int dpu_core_irq_idx_lookup( + struct dpu_kms *dpu_kms, + enum dpu_intr_type intr_type, + uint32_t instance_idx); + +/** + * dpu_core_irq_enable - IRQ helper function for enabling one or more IRQs + * @dpu_kms: DPU handle + * @irq_idxs: Array of irq index + * @irq_count: Number of irq_idx provided in the array + * @return: 0 for success enabling IRQ, otherwise failure + * + * This function increments count on each enable and decrements on each + * disable. Interrupts is enabled if count is 0 before increment. + */ +int dpu_core_irq_enable( + struct dpu_kms *dpu_kms, + int *irq_idxs, + uint32_t irq_count); + +/** + * dpu_core_irq_disable - IRQ helper function for disabling one of more IRQs + * @dpu_kms: DPU handle + * @irq_idxs: Array of irq index + * @irq_count: Number of irq_idx provided in the array + * @return: 0 for success disabling IRQ, otherwise failure + * + * This function increments count on each enable and decrements on each + * disable. Interrupts is disabled if count is 0 after decrement. + */ +int dpu_core_irq_disable( + struct dpu_kms *dpu_kms, + int *irq_idxs, + uint32_t irq_count); + +/** + * dpu_core_irq_read - IRQ helper function for reading IRQ status + * @dpu_kms: DPU handle + * @irq_idx: irq index + * @clear: True to clear the irq after read + * @return: non-zero if irq detected; otherwise no irq detected + */ +u32 dpu_core_irq_read( + struct dpu_kms *dpu_kms, + int irq_idx, + bool clear); + +/** + * dpu_core_irq_register_callback - For registering callback function on IRQ + * interrupt + * @dpu_kms: DPU handle + * @irq_idx: irq index + * @irq_cb: IRQ callback structure, containing callback function + * and argument. Passing NULL for irq_cb will unregister + * the callback for the given irq_idx + * This must exist until un-registration. + * @return: 0 for success registering callback, otherwise failure + * + * This function supports registration of multiple callbacks for each interrupt. + */ +int dpu_core_irq_register_callback( + struct dpu_kms *dpu_kms, + int irq_idx, + struct dpu_irq_callback *irq_cb); + +/** + * dpu_core_irq_unregister_callback - For unregistering callback function on IRQ + * interrupt + * @dpu_kms: DPU handle + * @irq_idx: irq index + * @irq_cb: IRQ callback structure, containing callback function + * and argument. Passing NULL for irq_cb will unregister + * the callback for the given irq_idx + * This must match with registration. + * @return: 0 for success registering callback, otherwise failure + * + * This function supports registration of multiple callbacks for each interrupt. + */ +int dpu_core_irq_unregister_callback( + struct dpu_kms *dpu_kms, + int irq_idx, + struct dpu_irq_callback *irq_cb); + +/** + * dpu_debugfs_core_irq_init - register core irq debugfs + * @dpu_kms: pointer to kms + * @parent: debugfs directory root + * @Return: 0 on success + */ +int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms, + struct dentry *parent); + +/** + * dpu_debugfs_core_irq_destroy - deregister core irq debugfs + * @dpu_kms: pointer to kms + */ +void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms); + +#endif /* __DPU_CORE_IRQ_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c new file mode 100644 index 000000000000..41c5191f9056 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -0,0 +1,637 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/debugfs.h> +#include <linux/errno.h> +#include <linux/mutex.h> +#include <linux/sort.h> +#include <linux/clk.h> +#include <linux/bitmap.h> + +#include "dpu_kms.h" +#include "dpu_trace.h" +#include "dpu_crtc.h" +#include "dpu_core_perf.h" + +#define DPU_PERF_MODE_STRING_SIZE 128 + +/** + * enum dpu_perf_mode - performance tuning mode + * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client + * @DPU_PERF_MODE_MINIMUM: performance bounded by minimum setting + * @DPU_PERF_MODE_FIXED: performance bounded by fixed setting + */ +enum dpu_perf_mode { + DPU_PERF_MODE_NORMAL, + DPU_PERF_MODE_MINIMUM, + DPU_PERF_MODE_FIXED, + DPU_PERF_MODE_MAX +}; + +static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc) +{ + struct msm_drm_private *priv; + + if (!crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid device\n"); + return NULL; + } + + priv = crtc->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid kms\n"); + return NULL; + } + + return to_dpu_kms(priv->kms); +} + +static bool _dpu_core_perf_crtc_is_power_on(struct drm_crtc *crtc) +{ + return dpu_crtc_is_enabled(crtc); +} + +static bool _dpu_core_video_mode_intf_connected(struct drm_crtc *crtc) +{ + struct drm_crtc *tmp_crtc; + bool intf_connected = false; + + if (!crtc) + goto end; + + drm_for_each_crtc(tmp_crtc, crtc->dev) { + if ((dpu_crtc_get_intf_mode(tmp_crtc) == INTF_MODE_VIDEO) && + _dpu_core_perf_crtc_is_power_on(tmp_crtc)) { + DPU_DEBUG("video interface connected crtc:%d\n", + tmp_crtc->base.id); + intf_connected = true; + goto end; + } + } + +end: + return intf_connected; +} + +static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms, + struct drm_crtc *crtc, + struct drm_crtc_state *state, + struct dpu_core_perf_params *perf) +{ + struct dpu_crtc_state *dpu_cstate; + int i; + + if (!kms || !kms->catalog || !crtc || !state || !perf) { + DPU_ERROR("invalid parameters\n"); + return; + } + + dpu_cstate = to_dpu_crtc_state(state); + memset(perf, 0, sizeof(struct dpu_core_perf_params)); + + if (!dpu_cstate->bw_control) { + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + perf->bw_ctl[i] = kms->catalog->perf.max_bw_high * + 1000ULL; + perf->max_per_pipe_ib[i] = perf->bw_ctl[i]; + } + perf->core_clk_rate = kms->perf.max_core_clk_rate; + } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + perf->bw_ctl[i] = 0; + perf->max_per_pipe_ib[i] = 0; + } + perf->core_clk_rate = 0; + } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) { + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + perf->bw_ctl[i] = kms->perf.fix_core_ab_vote; + perf->max_per_pipe_ib[i] = kms->perf.fix_core_ib_vote; + } + perf->core_clk_rate = kms->perf.fix_core_clk_rate; + } + + DPU_DEBUG( + "crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu llcc_ib=%llu llcc_ab=%llu mem_ib=%llu mem_ab=%llu\n", + crtc->base.id, perf->core_clk_rate, + perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MNOC], + perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC], + perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_LLCC], + perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC], + perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_EBI], + perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI]); +} + +int dpu_core_perf_crtc_check(struct drm_crtc *crtc, + struct drm_crtc_state *state) +{ + u32 bw, threshold; + u64 bw_sum_of_intfs = 0; + enum dpu_crtc_client_type curr_client_type; + bool is_video_mode; + struct dpu_crtc_state *dpu_cstate; + struct drm_crtc *tmp_crtc; + struct dpu_kms *kms; + int i; + + if (!crtc || !state) { + DPU_ERROR("invalid crtc\n"); + return -EINVAL; + } + + kms = _dpu_crtc_get_kms(crtc); + if (!kms || !kms->catalog) { + DPU_ERROR("invalid parameters\n"); + return 0; + } + + /* we only need bandwidth check on real-time clients (interfaces) */ + if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT) + return 0; + + dpu_cstate = to_dpu_crtc_state(state); + + /* obtain new values */ + _dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf); + + for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC; + i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl[i]; + curr_client_type = dpu_crtc_get_client_type(crtc); + + drm_for_each_crtc(tmp_crtc, crtc->dev) { + if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) && + (dpu_crtc_get_client_type(tmp_crtc) == + curr_client_type) && + (tmp_crtc != crtc)) { + struct dpu_crtc_state *tmp_cstate = + to_dpu_crtc_state(tmp_crtc->state); + + DPU_DEBUG("crtc:%d bw:%llu ctrl:%d\n", + tmp_crtc->base.id, + tmp_cstate->new_perf.bw_ctl[i], + tmp_cstate->bw_control); + /* + * For bw check only use the bw if the + * atomic property has been already set + */ + if (tmp_cstate->bw_control) + bw_sum_of_intfs += + tmp_cstate->new_perf.bw_ctl[i]; + } + } + + /* convert bandwidth to kb */ + bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000); + DPU_DEBUG("calculated bandwidth=%uk\n", bw); + + is_video_mode = dpu_crtc_get_intf_mode(crtc) == INTF_MODE_VIDEO; + threshold = (is_video_mode || + _dpu_core_video_mode_intf_connected(crtc)) ? + kms->catalog->perf.max_bw_low : + kms->catalog->perf.max_bw_high; + + DPU_DEBUG("final threshold bw limit = %d\n", threshold); + + if (!dpu_cstate->bw_control) { + DPU_DEBUG("bypass bandwidth check\n"); + } else if (!threshold) { + DPU_ERROR("no bandwidth limits specified\n"); + return -E2BIG; + } else if (bw > threshold) { + DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, + threshold); + return -E2BIG; + } + } + + return 0; +} + +static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, + struct drm_crtc *crtc, u32 bus_id) +{ + struct dpu_core_perf_params perf = { { 0 } }; + enum dpu_crtc_client_type curr_client_type + = dpu_crtc_get_client_type(crtc); + struct drm_crtc *tmp_crtc; + struct dpu_crtc_state *dpu_cstate; + int ret = 0; + + drm_for_each_crtc(tmp_crtc, crtc->dev) { + if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) && + curr_client_type == + dpu_crtc_get_client_type(tmp_crtc)) { + dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); + + perf.max_per_pipe_ib[bus_id] = + max(perf.max_per_pipe_ib[bus_id], + dpu_cstate->new_perf.max_per_pipe_ib[bus_id]); + + DPU_DEBUG("crtc=%d bus_id=%d bw=%llu\n", + tmp_crtc->base.id, bus_id, + dpu_cstate->new_perf.bw_ctl[bus_id]); + } + } + return ret; +} + +/** + * @dpu_core_perf_crtc_release_bw() - request zero bandwidth + * @crtc - pointer to a crtc + * + * Function checks a state variable for the crtc, if all pending commit + * requests are done, meaning no more bandwidth is needed, release + * bandwidth request. + */ +void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc) +{ + struct drm_crtc *tmp_crtc; + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *dpu_cstate; + struct dpu_kms *kms; + int i; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + + kms = _dpu_crtc_get_kms(crtc); + if (!kms || !kms->catalog) { + DPU_ERROR("invalid kms\n"); + return; + } + + dpu_crtc = to_dpu_crtc(crtc); + dpu_cstate = to_dpu_crtc_state(crtc->state); + + /* only do this for command mode rt client */ + if (dpu_crtc_get_intf_mode(crtc) != INTF_MODE_CMD) + return; + + /* + * If video interface present, cmd panel bandwidth cannot be + * released. + */ + if (dpu_crtc_get_intf_mode(crtc) == INTF_MODE_CMD) + drm_for_each_crtc(tmp_crtc, crtc->dev) { + if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) && + dpu_crtc_get_intf_mode(tmp_crtc) == + INTF_MODE_VIDEO) + return; + } + + /* Release the bandwidth */ + if (kms->perf.enable_bw_release) { + trace_dpu_cmd_release_bw(crtc->base.id); + DPU_DEBUG("Release BW crtc=%d\n", crtc->base.id); + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + dpu_crtc->cur_perf.bw_ctl[i] = 0; + _dpu_core_perf_crtc_update_bus(kms, crtc, i); + } + } +} + +static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate) +{ + struct dss_clk *core_clk = kms->perf.core_clk; + + if (core_clk->max_rate && (rate > core_clk->max_rate)) + rate = core_clk->max_rate; + + core_clk->rate = rate; + return msm_dss_clk_set_rate(core_clk, 1); +} + +static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms) +{ + u64 clk_rate = kms->perf.perf_tune.min_core_clk; + struct drm_crtc *crtc; + struct dpu_crtc_state *dpu_cstate; + + drm_for_each_crtc(crtc, kms->dev) { + if (_dpu_core_perf_crtc_is_power_on(crtc)) { + dpu_cstate = to_dpu_crtc_state(crtc->state); + clk_rate = max(dpu_cstate->new_perf.core_clk_rate, + clk_rate); + clk_rate = clk_round_rate(kms->perf.core_clk->clk, + clk_rate); + } + } + + if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) + clk_rate = kms->perf.fix_core_clk_rate; + + DPU_DEBUG("clk:%llu\n", clk_rate); + + return clk_rate; +} + +int dpu_core_perf_crtc_update(struct drm_crtc *crtc, + int params_changed, bool stop_req) +{ + struct dpu_core_perf_params *new, *old; + int update_bus = 0, update_clk = 0; + u64 clk_rate = 0; + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *dpu_cstate; + int i; + struct msm_drm_private *priv; + struct dpu_kms *kms; + int ret; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return -EINVAL; + } + + kms = _dpu_crtc_get_kms(crtc); + if (!kms || !kms->catalog) { + DPU_ERROR("invalid kms\n"); + return -EINVAL; + } + priv = kms->dev->dev_private; + + dpu_crtc = to_dpu_crtc(crtc); + dpu_cstate = to_dpu_crtc_state(crtc->state); + + DPU_DEBUG("crtc:%d stop_req:%d core_clk:%llu\n", + crtc->base.id, stop_req, kms->perf.core_clk_rate); + + old = &dpu_crtc->cur_perf; + new = &dpu_cstate->new_perf; + + if (_dpu_core_perf_crtc_is_power_on(crtc) && !stop_req) { + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + /* + * cases for bus bandwidth update. + * 1. new bandwidth vote - "ab or ib vote" is higher + * than current vote for update request. + * 2. new bandwidth vote - "ab or ib vote" is lower + * than current vote at end of commit or stop. + */ + if ((params_changed && ((new->bw_ctl[i] > + old->bw_ctl[i]) || + (new->max_per_pipe_ib[i] > + old->max_per_pipe_ib[i]))) || + (!params_changed && ((new->bw_ctl[i] < + old->bw_ctl[i]) || + (new->max_per_pipe_ib[i] < + old->max_per_pipe_ib[i])))) { + DPU_DEBUG( + "crtc=%d p=%d new_bw=%llu,old_bw=%llu\n", + crtc->base.id, params_changed, + new->bw_ctl[i], old->bw_ctl[i]); + old->bw_ctl[i] = new->bw_ctl[i]; + old->max_per_pipe_ib[i] = + new->max_per_pipe_ib[i]; + update_bus |= BIT(i); + } + } + + if ((params_changed && + (new->core_clk_rate > old->core_clk_rate)) || + (!params_changed && + (new->core_clk_rate < old->core_clk_rate))) { + old->core_clk_rate = new->core_clk_rate; + update_clk = 1; + } + } else { + DPU_DEBUG("crtc=%d disable\n", crtc->base.id); + memset(old, 0, sizeof(*old)); + memset(new, 0, sizeof(*new)); + update_bus = ~0; + update_clk = 1; + } + trace_dpu_perf_crtc_update(crtc->base.id, + new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC], + new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC], + new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI], + new->core_clk_rate, stop_req, + update_bus, update_clk); + + for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + if (update_bus & BIT(i)) { + ret = _dpu_core_perf_crtc_update_bus(kms, crtc, i); + if (ret) { + DPU_ERROR("crtc-%d: failed to update bw vote for bus-%d\n", + crtc->base.id, i); + return ret; + } + } + } + + /* + * Update the clock after bandwidth vote to ensure + * bandwidth is available before clock rate is increased. + */ + if (update_clk) { + clk_rate = _dpu_core_perf_get_core_clk_rate(kms); + + trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate); + + ret = _dpu_core_perf_set_core_clk_rate(kms, clk_rate); + if (ret) { + DPU_ERROR("failed to set %s clock rate %llu\n", + kms->perf.core_clk->clk_name, clk_rate); + return ret; + } + + kms->perf.core_clk_rate = clk_rate; + DPU_DEBUG("update clk rate = %lld HZ\n", clk_rate); + } + return 0; +} + +#ifdef CONFIG_DEBUG_FS + +static ssize_t _dpu_core_perf_mode_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + struct dpu_core_perf *perf = file->private_data; + struct dpu_perf_cfg *cfg = &perf->catalog->perf; + u32 perf_mode = 0; + char buf[10]; + + if (!perf) + return -ENODEV; + + if (count >= sizeof(buf)) + return -EFAULT; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + buf[count] = 0; /* end of string */ + + if (kstrtouint(buf, 0, &perf_mode)) + return -EFAULT; + + if (perf_mode >= DPU_PERF_MODE_MAX) + return -EFAULT; + + if (perf_mode == DPU_PERF_MODE_FIXED) { + DRM_INFO("fix performance mode\n"); + } else if (perf_mode == DPU_PERF_MODE_MINIMUM) { + /* run the driver with max clk and BW vote */ + perf->perf_tune.min_core_clk = perf->max_core_clk_rate; + perf->perf_tune.min_bus_vote = + (u64) cfg->max_bw_high * 1000; + DRM_INFO("minimum performance mode\n"); + } else if (perf_mode == DPU_PERF_MODE_NORMAL) { + /* reset the perf tune params to 0 */ + perf->perf_tune.min_core_clk = 0; + perf->perf_tune.min_bus_vote = 0; + DRM_INFO("normal performance mode\n"); + } + perf->perf_tune.mode = perf_mode; + + return count; +} + +static ssize_t _dpu_core_perf_mode_read(struct file *file, + char __user *buff, size_t count, loff_t *ppos) +{ + struct dpu_core_perf *perf = file->private_data; + int len = 0; + char buf[DPU_PERF_MODE_STRING_SIZE] = {'\0'}; + + if (!perf) + return -ENODEV; + + if (*ppos) + return 0; /* the end */ + + len = snprintf(buf, sizeof(buf), + "mode %d min_mdp_clk %llu min_bus_vote %llu\n", + perf->perf_tune.mode, + perf->perf_tune.min_core_clk, + perf->perf_tune.min_bus_vote); + if (len < 0 || len >= sizeof(buf)) + return 0; + + if ((count < sizeof(buf)) || copy_to_user(buff, buf, len)) + return -EFAULT; + + *ppos += len; /* increase offset */ + + return len; +} + +static const struct file_operations dpu_core_perf_mode_fops = { + .open = simple_open, + .read = _dpu_core_perf_mode_read, + .write = _dpu_core_perf_mode_write, +}; + +static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf) +{ + debugfs_remove_recursive(perf->debugfs_root); + perf->debugfs_root = NULL; +} + +int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf, + struct dentry *parent) +{ + struct dpu_mdss_cfg *catalog = perf->catalog; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + priv = perf->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid KMS reference\n"); + return -EINVAL; + } + + dpu_kms = to_dpu_kms(priv->kms); + + perf->debugfs_root = debugfs_create_dir("core_perf", parent); + if (!perf->debugfs_root) { + DPU_ERROR("failed to create core perf debugfs\n"); + return -EINVAL; + } + + debugfs_create_u64("max_core_clk_rate", 0600, perf->debugfs_root, + &perf->max_core_clk_rate); + debugfs_create_u64("core_clk_rate", 0600, perf->debugfs_root, + &perf->core_clk_rate); + debugfs_create_u32("enable_bw_release", 0600, perf->debugfs_root, + (u32 *)&perf->enable_bw_release); + debugfs_create_u32("threshold_low", 0600, perf->debugfs_root, + (u32 *)&catalog->perf.max_bw_low); + debugfs_create_u32("threshold_high", 0600, perf->debugfs_root, + (u32 *)&catalog->perf.max_bw_high); + debugfs_create_u32("min_core_ib", 0600, perf->debugfs_root, + (u32 *)&catalog->perf.min_core_ib); + debugfs_create_u32("min_llcc_ib", 0600, perf->debugfs_root, + (u32 *)&catalog->perf.min_llcc_ib); + debugfs_create_u32("min_dram_ib", 0600, perf->debugfs_root, + (u32 *)&catalog->perf.min_dram_ib); + debugfs_create_file("perf_mode", 0600, perf->debugfs_root, + (u32 *)perf, &dpu_core_perf_mode_fops); + debugfs_create_u64("fix_core_clk_rate", 0600, perf->debugfs_root, + &perf->fix_core_clk_rate); + debugfs_create_u64("fix_core_ib_vote", 0600, perf->debugfs_root, + &perf->fix_core_ib_vote); + debugfs_create_u64("fix_core_ab_vote", 0600, perf->debugfs_root, + &perf->fix_core_ab_vote); + + return 0; +} +#else +static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf) +{ +} + +int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf, + struct dentry *parent) +{ + return 0; +} +#endif + +void dpu_core_perf_destroy(struct dpu_core_perf *perf) +{ + if (!perf) { + DPU_ERROR("invalid parameters\n"); + return; + } + + dpu_core_perf_debugfs_destroy(perf); + perf->max_core_clk_rate = 0; + perf->core_clk = NULL; + perf->phandle = NULL; + perf->catalog = NULL; + perf->dev = NULL; +} + +int dpu_core_perf_init(struct dpu_core_perf *perf, + struct drm_device *dev, + struct dpu_mdss_cfg *catalog, + struct dpu_power_handle *phandle, + struct dss_clk *core_clk) +{ + perf->dev = dev; + perf->catalog = catalog; + perf->phandle = phandle; + perf->core_clk = core_clk; + + perf->max_core_clk_rate = core_clk->max_rate; + if (!perf->max_core_clk_rate) { + DPU_DEBUG("optional max core clk rate, use default\n"); + perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE; + } + + return 0; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h new file mode 100644 index 000000000000..fbcbe0c7527a --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -0,0 +1,133 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_CORE_PERF_H_ +#define _DPU_CORE_PERF_H_ + +#include <linux/types.h> +#include <linux/dcache.h> +#include <linux/mutex.h> +#include <drm/drm_crtc.h> + +#include "dpu_hw_catalog.h" +#include "dpu_power_handle.h" + +#define DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE 412500000 + +/** + * struct dpu_core_perf_params - definition of performance parameters + * @max_per_pipe_ib: maximum instantaneous bandwidth request + * @bw_ctl: arbitrated bandwidth request + * @core_clk_rate: core clock rate request + */ +struct dpu_core_perf_params { + u64 max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MAX]; + u64 bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MAX]; + u64 core_clk_rate; +}; + +/** + * struct dpu_core_perf_tune - definition of performance tuning control + * @mode: performance mode + * @min_core_clk: minimum core clock + * @min_bus_vote: minimum bus vote + */ +struct dpu_core_perf_tune { + u32 mode; + u64 min_core_clk; + u64 min_bus_vote; +}; + +/** + * struct dpu_core_perf - definition of core performance context + * @dev: Pointer to drm device + * @debugfs_root: top level debug folder + * @catalog: Pointer to catalog configuration + * @phandle: Pointer to power handler + * @core_clk: Pointer to core clock structure + * @core_clk_rate: current core clock rate + * @max_core_clk_rate: maximum allowable core clock rate + * @perf_tune: debug control for performance tuning + * @enable_bw_release: debug control for bandwidth release + * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2 + * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2 + * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2 + */ +struct dpu_core_perf { + struct drm_device *dev; + struct dentry *debugfs_root; + struct dpu_mdss_cfg *catalog; + struct dpu_power_handle *phandle; + struct dss_clk *core_clk; + u64 core_clk_rate; + u64 max_core_clk_rate; + struct dpu_core_perf_tune perf_tune; + u32 enable_bw_release; + u64 fix_core_clk_rate; + u64 fix_core_ib_vote; + u64 fix_core_ab_vote; +}; + +/** + * dpu_core_perf_crtc_check - validate performance of the given crtc state + * @crtc: Pointer to crtc + * @state: Pointer to new crtc state + * return: zero if success, or error code otherwise + */ +int dpu_core_perf_crtc_check(struct drm_crtc *crtc, + struct drm_crtc_state *state); + +/** + * dpu_core_perf_crtc_update - update performance of the given crtc + * @crtc: Pointer to crtc + * @params_changed: true if crtc parameters are modified + * @stop_req: true if this is a stop request + * return: zero if success, or error code otherwise + */ +int dpu_core_perf_crtc_update(struct drm_crtc *crtc, + int params_changed, bool stop_req); + +/** + * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc + * @crtc: Pointer to crtc + */ +void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc); + +/** + * dpu_core_perf_destroy - destroy the given core performance context + * @perf: Pointer to core performance context + */ +void dpu_core_perf_destroy(struct dpu_core_perf *perf); + +/** + * dpu_core_perf_init - initialize the given core performance context + * @perf: Pointer to core performance context + * @dev: Pointer to drm device + * @catalog: Pointer to catalog + * @phandle: Pointer to power handle + * @core_clk: pointer to core clock + */ +int dpu_core_perf_init(struct dpu_core_perf *perf, + struct drm_device *dev, + struct dpu_mdss_cfg *catalog, + struct dpu_power_handle *phandle, + struct dss_clk *core_clk); + +/** + * dpu_core_perf_debugfs_init - initialize debugfs for core performance context + * @perf: Pointer to core performance context + * @debugfs_parent: Pointer to parent debugfs + */ +int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf, + struct dentry *parent); + +#endif /* _DPU_CORE_PERF_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c new file mode 100644 index 000000000000..80cbf75bc2ff --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -0,0 +1,2138 @@ +/* + * Copyright (c) 2014-2018 The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include <linux/sort.h> +#include <linux/debugfs.h> +#include <linux/ktime.h> +#include <drm/drm_mode.h> +#include <drm/drm_crtc.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_flip_work.h> +#include <drm/drm_rect.h> + +#include "dpu_kms.h" +#include "dpu_hw_lm.h" +#include "dpu_hw_ctl.h" +#include "dpu_crtc.h" +#include "dpu_plane.h" +#include "dpu_encoder.h" +#include "dpu_vbif.h" +#include "dpu_power_handle.h" +#include "dpu_core_perf.h" +#include "dpu_trace.h" + +#define DPU_DRM_BLEND_OP_NOT_DEFINED 0 +#define DPU_DRM_BLEND_OP_OPAQUE 1 +#define DPU_DRM_BLEND_OP_PREMULTIPLIED 2 +#define DPU_DRM_BLEND_OP_COVERAGE 3 +#define DPU_DRM_BLEND_OP_MAX 4 + +/* layer mixer index on dpu_crtc */ +#define LEFT_MIXER 0 +#define RIGHT_MIXER 1 + +#define MISR_BUFF_SIZE 256 + +static inline struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc) +{ + struct msm_drm_private *priv; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid crtc\n"); + return NULL; + } + priv = crtc->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid kms\n"); + return NULL; + } + + return to_dpu_kms(priv->kms); +} + +static inline int _dpu_crtc_power_enable(struct dpu_crtc *dpu_crtc, bool enable) +{ + struct drm_crtc *crtc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!dpu_crtc) { + DPU_ERROR("invalid dpu crtc\n"); + return -EINVAL; + } + + crtc = &dpu_crtc->base; + if (!crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid drm device\n"); + return -EINVAL; + } + + priv = crtc->dev->dev_private; + if (!priv->kms) { + DPU_ERROR("invalid kms\n"); + return -EINVAL; + } + + dpu_kms = to_dpu_kms(priv->kms); + + if (enable) + pm_runtime_get_sync(&dpu_kms->pdev->dev); + else + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + return 0; +} + +/** + * _dpu_crtc_rp_to_crtc - get crtc from resource pool object + * @rp: Pointer to resource pool + * return: Pointer to drm crtc if success; null otherwise + */ +static struct drm_crtc *_dpu_crtc_rp_to_crtc(struct dpu_crtc_respool *rp) +{ + if (!rp) + return NULL; + + return container_of(rp, struct dpu_crtc_state, rp)->base.crtc; +} + +/** + * _dpu_crtc_rp_reclaim - reclaim unused, or all if forced, resources in pool + * @rp: Pointer to resource pool + * @force: True to reclaim all resources; otherwise, reclaim only unused ones + * return: None + */ +static void _dpu_crtc_rp_reclaim(struct dpu_crtc_respool *rp, bool force) +{ + struct dpu_crtc_res *res, *next; + struct drm_crtc *crtc; + + crtc = _dpu_crtc_rp_to_crtc(rp); + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + + DPU_DEBUG("crtc%d.%u %s\n", crtc->base.id, rp->sequence_id, + force ? "destroy" : "free_unused"); + + list_for_each_entry_safe(res, next, &rp->res_list, list) { + if (!force && !(res->flags & DPU_CRTC_RES_FLAG_FREE)) + continue; + DPU_DEBUG("crtc%d.%u reclaim res:0x%x/0x%llx/%pK/%d\n", + crtc->base.id, rp->sequence_id, + res->type, res->tag, res->val, + atomic_read(&res->refcount)); + list_del(&res->list); + if (res->ops.put) + res->ops.put(res->val); + kfree(res); + } +} + +/** + * _dpu_crtc_rp_free_unused - free unused resource in pool + * @rp: Pointer to resource pool + * return: none + */ +static void _dpu_crtc_rp_free_unused(struct dpu_crtc_respool *rp) +{ + mutex_lock(rp->rp_lock); + _dpu_crtc_rp_reclaim(rp, false); + mutex_unlock(rp->rp_lock); +} + +/** + * _dpu_crtc_rp_destroy - destroy resource pool + * @rp: Pointer to resource pool + * return: None + */ +static void _dpu_crtc_rp_destroy(struct dpu_crtc_respool *rp) +{ + mutex_lock(rp->rp_lock); + list_del_init(&rp->rp_list); + _dpu_crtc_rp_reclaim(rp, true); + mutex_unlock(rp->rp_lock); +} + +/** + * _dpu_crtc_hw_blk_get - get callback for hardware block + * @val: Resource handle + * @type: Resource type + * @tag: Search tag for given resource + * return: Resource handle + */ +static void *_dpu_crtc_hw_blk_get(void *val, u32 type, u64 tag) +{ + DPU_DEBUG("res:%d/0x%llx/%pK\n", type, tag, val); + return dpu_hw_blk_get(val, type, tag); +} + +/** + * _dpu_crtc_hw_blk_put - put callback for hardware block + * @val: Resource handle + * return: None + */ +static void _dpu_crtc_hw_blk_put(void *val) +{ + DPU_DEBUG("res://%pK\n", val); + dpu_hw_blk_put(val); +} + +/** + * _dpu_crtc_rp_duplicate - duplicate resource pool and reset reference count + * @rp: Pointer to original resource pool + * @dup_rp: Pointer to duplicated resource pool + * return: None + */ +static void _dpu_crtc_rp_duplicate(struct dpu_crtc_respool *rp, + struct dpu_crtc_respool *dup_rp) +{ + struct dpu_crtc_res *res, *dup_res; + struct drm_crtc *crtc; + + if (!rp || !dup_rp || !rp->rp_head) { + DPU_ERROR("invalid resource pool\n"); + return; + } + + crtc = _dpu_crtc_rp_to_crtc(rp); + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + + DPU_DEBUG("crtc%d.%u duplicate\n", crtc->base.id, rp->sequence_id); + + mutex_lock(rp->rp_lock); + dup_rp->sequence_id = rp->sequence_id + 1; + INIT_LIST_HEAD(&dup_rp->res_list); + dup_rp->ops = rp->ops; + list_for_each_entry(res, &rp->res_list, list) { + dup_res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL); + if (!dup_res) { + mutex_unlock(rp->rp_lock); + return; + } + INIT_LIST_HEAD(&dup_res->list); + atomic_set(&dup_res->refcount, 0); + dup_res->type = res->type; + dup_res->tag = res->tag; + dup_res->val = res->val; + dup_res->ops = res->ops; + dup_res->flags = DPU_CRTC_RES_FLAG_FREE; + DPU_DEBUG("crtc%d.%u dup res:0x%x/0x%llx/%pK/%d\n", + crtc->base.id, dup_rp->sequence_id, + dup_res->type, dup_res->tag, dup_res->val, + atomic_read(&dup_res->refcount)); + list_add_tail(&dup_res->list, &dup_rp->res_list); + if (dup_res->ops.get) + dup_res->ops.get(dup_res->val, 0, -1); + } + + dup_rp->rp_lock = rp->rp_lock; + dup_rp->rp_head = rp->rp_head; + INIT_LIST_HEAD(&dup_rp->rp_list); + list_add_tail(&dup_rp->rp_list, rp->rp_head); + mutex_unlock(rp->rp_lock); +} + +/** + * _dpu_crtc_rp_reset - reset resource pool after allocation + * @rp: Pointer to original resource pool + * @rp_lock: Pointer to serialization resource pool lock + * @rp_head: Pointer to crtc resource pool head + * return: None + */ +static void _dpu_crtc_rp_reset(struct dpu_crtc_respool *rp, + struct mutex *rp_lock, struct list_head *rp_head) +{ + if (!rp || !rp_lock || !rp_head) { + DPU_ERROR("invalid resource pool\n"); + return; + } + + mutex_lock(rp_lock); + rp->rp_lock = rp_lock; + rp->rp_head = rp_head; + INIT_LIST_HEAD(&rp->rp_list); + rp->sequence_id = 0; + INIT_LIST_HEAD(&rp->res_list); + rp->ops.get = _dpu_crtc_hw_blk_get; + rp->ops.put = _dpu_crtc_hw_blk_put; + list_add_tail(&rp->rp_list, rp->rp_head); + mutex_unlock(rp_lock); +} + +static void dpu_crtc_destroy(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + + DPU_DEBUG("\n"); + + if (!crtc) + return; + + dpu_crtc->phandle = NULL; + + drm_crtc_cleanup(crtc); + mutex_destroy(&dpu_crtc->crtc_lock); + kfree(dpu_crtc); +} + +static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer, + struct dpu_plane_state *pstate) +{ + struct dpu_hw_mixer *lm = mixer->hw_lm; + + /* default to opaque blending */ + lm->ops.setup_blend_config(lm, pstate->stage, 0XFF, 0, + DPU_BLEND_FG_ALPHA_FG_CONST | + DPU_BLEND_BG_ALPHA_BG_CONST); +} + +static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *crtc_state; + int lm_idx, lm_horiz_position; + + dpu_crtc = to_dpu_crtc(crtc); + crtc_state = to_dpu_crtc_state(crtc->state); + + lm_horiz_position = 0; + for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) { + const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx]; + struct dpu_hw_mixer *hw_lm = dpu_crtc->mixers[lm_idx].hw_lm; + struct dpu_hw_mixer_cfg cfg; + + if (!lm_roi || !drm_rect_visible(lm_roi)) + continue; + + cfg.out_width = drm_rect_width(lm_roi); + cfg.out_height = drm_rect_height(lm_roi); + cfg.right_mixer = lm_horiz_position++; + cfg.flags = 0; + hw_lm->ops.setup_mixer_out(hw_lm, &cfg); + } +} + +static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, + struct dpu_crtc *dpu_crtc, struct dpu_crtc_mixer *mixer) +{ + struct drm_plane *plane; + struct drm_framebuffer *fb; + struct drm_plane_state *state; + struct dpu_crtc_state *cstate; + struct dpu_plane_state *pstate = NULL; + struct dpu_format *format; + struct dpu_hw_ctl *ctl; + struct dpu_hw_mixer *lm; + struct dpu_hw_stage_cfg *stage_cfg; + + u32 flush_mask; + uint32_t stage_idx, lm_idx; + int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 }; + bool bg_alpha_enable = false; + + if (!dpu_crtc || !mixer) { + DPU_ERROR("invalid dpu_crtc or mixer\n"); + return; + } + + ctl = mixer->hw_ctl; + lm = mixer->hw_lm; + stage_cfg = &dpu_crtc->stage_cfg; + cstate = to_dpu_crtc_state(crtc->state); + + drm_atomic_crtc_for_each_plane(plane, crtc) { + state = plane->state; + if (!state) + continue; + + pstate = to_dpu_plane_state(state); + fb = state->fb; + + dpu_plane_get_ctl_flush(plane, ctl, &flush_mask); + + DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n", + crtc->base.id, + pstate->stage, + plane->base.id, + dpu_plane_pipe(plane) - SSPP_VIG0, + state->fb ? state->fb->base.id : -1); + + format = to_dpu_format(msm_framebuffer_format(pstate->base.fb)); + if (!format) { + DPU_ERROR("invalid format\n"); + return; + } + + if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable) + bg_alpha_enable = true; + + stage_idx = zpos_cnt[pstate->stage]++; + stage_cfg->stage[pstate->stage][stage_idx] = + dpu_plane_pipe(plane); + stage_cfg->multirect_index[pstate->stage][stage_idx] = + pstate->multirect_index; + + trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane), + state, pstate, stage_idx, + dpu_plane_pipe(plane) - SSPP_VIG0, + format->base.pixel_format, + fb ? fb->modifier : 0); + + /* blend config update */ + for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) { + _dpu_crtc_setup_blend_cfg(mixer + lm_idx, pstate); + + mixer[lm_idx].flush_mask |= flush_mask; + + if (bg_alpha_enable && !format->alpha_enable) + mixer[lm_idx].mixer_op_mode = 0; + else + mixer[lm_idx].mixer_op_mode |= + 1 << pstate->stage; + } + } + + _dpu_crtc_program_lm_output_roi(crtc); +} + +/** + * _dpu_crtc_blend_setup - configure crtc mixers + * @crtc: Pointer to drm crtc structure + */ +static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *dpu_crtc_state; + struct dpu_crtc_mixer *mixer; + struct dpu_hw_ctl *ctl; + struct dpu_hw_mixer *lm; + + int i; + + if (!crtc) + return; + + dpu_crtc = to_dpu_crtc(crtc); + dpu_crtc_state = to_dpu_crtc_state(crtc->state); + mixer = dpu_crtc->mixers; + + DPU_DEBUG("%s\n", dpu_crtc->name); + + if (dpu_crtc->num_mixers > CRTC_DUAL_MIXERS) { + DPU_ERROR("invalid number mixers: %d\n", dpu_crtc->num_mixers); + return; + } + + for (i = 0; i < dpu_crtc->num_mixers; i++) { + if (!mixer[i].hw_lm || !mixer[i].hw_ctl) { + DPU_ERROR("invalid lm or ctl assigned to mixer\n"); + return; + } + mixer[i].mixer_op_mode = 0; + mixer[i].flush_mask = 0; + if (mixer[i].hw_ctl->ops.clear_all_blendstages) + mixer[i].hw_ctl->ops.clear_all_blendstages( + mixer[i].hw_ctl); + } + + /* initialize stage cfg */ + memset(&dpu_crtc->stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg)); + + _dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer); + + for (i = 0; i < dpu_crtc->num_mixers; i++) { + ctl = mixer[i].hw_ctl; + lm = mixer[i].hw_lm; + + lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode); + + mixer[i].flush_mask |= ctl->ops.get_bitmask_mixer(ctl, + mixer[i].hw_lm->idx); + + /* stage config flush mask */ + ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask); + + DPU_DEBUG("lm %d, op_mode 0x%X, ctl %d, flush mask 0x%x\n", + mixer[i].hw_lm->idx - LM_0, + mixer[i].mixer_op_mode, + ctl->idx - CTL_0, + mixer[i].flush_mask); + + ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx, + &dpu_crtc->stage_cfg); + } +} + +/** + * _dpu_crtc_complete_flip - signal pending page_flip events + * Any pending vblank events are added to the vblank_event_list + * so that the next vblank interrupt shall signal them. + * However PAGE_FLIP events are not handled through the vblank_event_list. + * This API signals any pending PAGE_FLIP events requested through + * DRM_IOCTL_MODE_PAGE_FLIP and are cached in the dpu_crtc->event. + * @crtc: Pointer to drm crtc structure + */ +static void _dpu_crtc_complete_flip(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct drm_device *dev = crtc->dev; + unsigned long flags; + + spin_lock_irqsave(&dev->event_lock, flags); + if (dpu_crtc->event) { + DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name, + dpu_crtc->event); + trace_dpu_crtc_complete_flip(DRMID(crtc)); + drm_crtc_send_vblank_event(crtc, dpu_crtc->event); + dpu_crtc->event = NULL; + } + spin_unlock_irqrestore(&dev->event_lock, flags); +} + +enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + + if (!crtc || !crtc->dev) { + DPU_ERROR("invalid crtc\n"); + return INTF_MODE_NONE; + } + + drm_for_each_encoder(encoder, crtc->dev) + if (encoder->crtc == crtc) + return dpu_encoder_get_intf_mode(encoder); + + return INTF_MODE_NONE; +} + +static void dpu_crtc_vblank_cb(void *data) +{ + struct drm_crtc *crtc = (struct drm_crtc *)data; + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + + /* keep statistics on vblank callback - with auto reset via debugfs */ + if (ktime_compare(dpu_crtc->vblank_cb_time, ktime_set(0, 0)) == 0) + dpu_crtc->vblank_cb_time = ktime_get(); + else + dpu_crtc->vblank_cb_count++; + _dpu_crtc_complete_flip(crtc); + drm_crtc_handle_vblank(crtc); + trace_dpu_crtc_vblank_cb(DRMID(crtc)); +} + +static void dpu_crtc_frame_event_work(struct kthread_work *work) +{ + struct msm_drm_private *priv; + struct dpu_crtc_frame_event *fevent; + struct drm_crtc *crtc; + struct dpu_crtc *dpu_crtc; + struct dpu_kms *dpu_kms; + unsigned long flags; + bool frame_done = false; + + if (!work) { + DPU_ERROR("invalid work handle\n"); + return; + } + + fevent = container_of(work, struct dpu_crtc_frame_event, work); + if (!fevent->crtc || !fevent->crtc->state) { + DPU_ERROR("invalid crtc\n"); + return; + } + + crtc = fevent->crtc; + dpu_crtc = to_dpu_crtc(crtc); + + dpu_kms = _dpu_crtc_get_kms(crtc); + if (!dpu_kms) { + DPU_ERROR("invalid kms handle\n"); + return; + } + priv = dpu_kms->dev->dev_private; + DPU_ATRACE_BEGIN("crtc_frame_event"); + + DRM_DEBUG_KMS("crtc%d event:%u ts:%lld\n", crtc->base.id, fevent->event, + ktime_to_ns(fevent->ts)); + + if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE + | DPU_ENCODER_FRAME_EVENT_ERROR + | DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) { + + if (atomic_read(&dpu_crtc->frame_pending) < 1) { + /* this should not happen */ + DRM_ERROR("crtc%d ev:%u ts:%lld frame_pending:%d\n", + crtc->base.id, + fevent->event, + ktime_to_ns(fevent->ts), + atomic_read(&dpu_crtc->frame_pending)); + } else if (atomic_dec_return(&dpu_crtc->frame_pending) == 0) { + /* release bandwidth and other resources */ + trace_dpu_crtc_frame_event_done(DRMID(crtc), + fevent->event); + dpu_core_perf_crtc_release_bw(crtc); + } else { + trace_dpu_crtc_frame_event_more_pending(DRMID(crtc), + fevent->event); + } + + if (fevent->event & DPU_ENCODER_FRAME_EVENT_DONE) + dpu_core_perf_crtc_update(crtc, 0, false); + + if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE + | DPU_ENCODER_FRAME_EVENT_ERROR)) + frame_done = true; + } + + if (fevent->event & DPU_ENCODER_FRAME_EVENT_PANEL_DEAD) + DPU_ERROR("crtc%d ts:%lld received panel dead event\n", + crtc->base.id, ktime_to_ns(fevent->ts)); + + if (frame_done) + complete_all(&dpu_crtc->frame_done_comp); + + spin_lock_irqsave(&dpu_crtc->spin_lock, flags); + list_add_tail(&fevent->list, &dpu_crtc->frame_event_list); + spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags); + DPU_ATRACE_END("crtc_frame_event"); +} + +/* + * dpu_crtc_frame_event_cb - crtc frame event callback API. CRTC module + * registers this API to encoder for all frame event callbacks like + * frame_error, frame_done, idle_timeout, etc. Encoder may call different events + * from different context - IRQ, user thread, commit_thread, etc. Each event + * should be carefully reviewed and should be processed in proper task context + * to avoid schedulin delay or properly manage the irq context's bottom half + * processing. + */ +static void dpu_crtc_frame_event_cb(void *data, u32 event) +{ + struct drm_crtc *crtc = (struct drm_crtc *)data; + struct dpu_crtc *dpu_crtc; + struct msm_drm_private *priv; + struct dpu_crtc_frame_event *fevent; + unsigned long flags; + u32 crtc_id; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid parameters\n"); + return; + } + + /* Nothing to do on idle event */ + if (event & DPU_ENCODER_FRAME_EVENT_IDLE) + return; + + dpu_crtc = to_dpu_crtc(crtc); + priv = crtc->dev->dev_private; + crtc_id = drm_crtc_index(crtc); + + trace_dpu_crtc_frame_event_cb(DRMID(crtc), event); + + spin_lock_irqsave(&dpu_crtc->spin_lock, flags); + fevent = list_first_entry_or_null(&dpu_crtc->frame_event_list, + struct dpu_crtc_frame_event, list); + if (fevent) + list_del_init(&fevent->list); + spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags); + + if (!fevent) { + DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event); + return; + } + + fevent->event = event; + fevent->crtc = crtc; + fevent->ts = ktime_get(); + kthread_queue_work(&priv->event_thread[crtc_id].worker, &fevent->work); +} + +void dpu_crtc_complete_commit(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + if (!crtc || !crtc->state) { + DPU_ERROR("invalid crtc\n"); + return; + } + trace_dpu_crtc_complete_commit(DRMID(crtc)); +} + +static void _dpu_crtc_setup_mixer_for_encoder( + struct drm_crtc *crtc, + struct drm_encoder *enc) +{ + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + struct dpu_rm *rm = &dpu_kms->rm; + struct dpu_crtc_mixer *mixer; + struct dpu_hw_ctl *last_valid_ctl = NULL; + int i; + struct dpu_rm_hw_iter lm_iter, ctl_iter; + + dpu_rm_init_hw_iter(&lm_iter, enc->base.id, DPU_HW_BLK_LM); + dpu_rm_init_hw_iter(&ctl_iter, enc->base.id, DPU_HW_BLK_CTL); + + /* Set up all the mixers and ctls reserved by this encoder */ + for (i = dpu_crtc->num_mixers; i < ARRAY_SIZE(dpu_crtc->mixers); i++) { + mixer = &dpu_crtc->mixers[i]; + + if (!dpu_rm_get_hw(rm, &lm_iter)) + break; + mixer->hw_lm = (struct dpu_hw_mixer *)lm_iter.hw; + + /* CTL may be <= LMs, if <, multiple LMs controlled by 1 CTL */ + if (!dpu_rm_get_hw(rm, &ctl_iter)) { + DPU_DEBUG("no ctl assigned to lm %d, using previous\n", + mixer->hw_lm->idx - LM_0); + mixer->hw_ctl = last_valid_ctl; + } else { + mixer->hw_ctl = (struct dpu_hw_ctl *)ctl_iter.hw; + last_valid_ctl = mixer->hw_ctl; + } + + /* Shouldn't happen, mixers are always >= ctls */ + if (!mixer->hw_ctl) { + DPU_ERROR("no valid ctls found for lm %d\n", + mixer->hw_lm->idx - LM_0); + return; + } + + mixer->encoder = enc; + + dpu_crtc->num_mixers++; + DPU_DEBUG("setup mixer %d: lm %d\n", + i, mixer->hw_lm->idx - LM_0); + DPU_DEBUG("setup mixer %d: ctl %d\n", + i, mixer->hw_ctl->idx - CTL_0); + } +} + +static void _dpu_crtc_setup_mixers(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct drm_encoder *enc; + + dpu_crtc->num_mixers = 0; + dpu_crtc->mixers_swapped = false; + memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers)); + + mutex_lock(&dpu_crtc->crtc_lock); + /* Check for mixers on all encoders attached to this crtc */ + list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) { + if (enc->crtc != crtc) + continue; + + _dpu_crtc_setup_mixer_for_encoder(crtc, enc); + } + + mutex_unlock(&dpu_crtc->crtc_lock); +} + +static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc, + struct drm_crtc_state *state) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *cstate; + struct drm_display_mode *adj_mode; + u32 crtc_split_width; + int i; + + if (!crtc || !state) { + DPU_ERROR("invalid args\n"); + return; + } + + dpu_crtc = to_dpu_crtc(crtc); + cstate = to_dpu_crtc_state(state); + + adj_mode = &state->adjusted_mode; + crtc_split_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, adj_mode); + + for (i = 0; i < dpu_crtc->num_mixers; i++) { + struct drm_rect *r = &cstate->lm_bounds[i]; + r->x1 = crtc_split_width * i; + r->y1 = 0; + r->x2 = r->x1 + crtc_split_width; + r->y2 = dpu_crtc_get_mixer_height(dpu_crtc, cstate, adj_mode); + + trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r); + } + + drm_mode_debug_printmodeline(adj_mode); +} + +static void dpu_crtc_atomic_begin(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + struct dpu_crtc *dpu_crtc; + struct drm_encoder *encoder; + struct drm_device *dev; + unsigned long flags; + struct dpu_crtc_smmu_state_data *smmu_state; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + + if (!crtc->state->enable) { + DPU_DEBUG("crtc%d -> enable %d, skip atomic_begin\n", + crtc->base.id, crtc->state->enable); + return; + } + + DPU_DEBUG("crtc%d\n", crtc->base.id); + + dpu_crtc = to_dpu_crtc(crtc); + dev = crtc->dev; + smmu_state = &dpu_crtc->smmu_state; + + if (!dpu_crtc->num_mixers) { + _dpu_crtc_setup_mixers(crtc); + _dpu_crtc_setup_lm_bounds(crtc, crtc->state); + } + + if (dpu_crtc->event) { + WARN_ON(dpu_crtc->event); + } else { + spin_lock_irqsave(&dev->event_lock, flags); + dpu_crtc->event = crtc->state->event; + crtc->state->event = NULL; + spin_unlock_irqrestore(&dev->event_lock, flags); + } + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + if (encoder->crtc != crtc) + continue; + + /* encoder will trigger pending mask now */ + dpu_encoder_trigger_kickoff_pending(encoder); + } + + /* + * If no mixers have been allocated in dpu_crtc_atomic_check(), + * it means we are trying to flush a CRTC whose state is disabled: + * nothing else needs to be done. + */ + if (unlikely(!dpu_crtc->num_mixers)) + return; + + _dpu_crtc_blend_setup(crtc); + + /* + * PP_DONE irq is only used by command mode for now. + * It is better to request pending before FLUSH and START trigger + * to make sure no pp_done irq missed. + * This is safe because no pp_done will happen before SW trigger + * in command mode. + */ +} + +static void dpu_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) +{ + struct dpu_crtc *dpu_crtc; + struct drm_device *dev; + struct drm_plane *plane; + struct msm_drm_private *priv; + struct msm_drm_thread *event_thread; + unsigned long flags; + struct dpu_crtc_state *cstate; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid crtc\n"); + return; + } + + if (!crtc->state->enable) { + DPU_DEBUG("crtc%d -> enable %d, skip atomic_flush\n", + crtc->base.id, crtc->state->enable); + return; + } + + DPU_DEBUG("crtc%d\n", crtc->base.id); + + dpu_crtc = to_dpu_crtc(crtc); + cstate = to_dpu_crtc_state(crtc->state); + dev = crtc->dev; + priv = dev->dev_private; + + if (crtc->index >= ARRAY_SIZE(priv->event_thread)) { + DPU_ERROR("invalid crtc index[%d]\n", crtc->index); + return; + } + + event_thread = &priv->event_thread[crtc->index]; + + if (dpu_crtc->event) { + DPU_DEBUG("already received dpu_crtc->event\n"); + } else { + spin_lock_irqsave(&dev->event_lock, flags); + dpu_crtc->event = crtc->state->event; + crtc->state->event = NULL; + spin_unlock_irqrestore(&dev->event_lock, flags); + } + + /* + * If no mixers has been allocated in dpu_crtc_atomic_check(), + * it means we are trying to flush a CRTC whose state is disabled: + * nothing else needs to be done. + */ + if (unlikely(!dpu_crtc->num_mixers)) + return; + + /* + * For planes without commit update, drm framework will not add + * those planes to current state since hardware update is not + * required. However, if those planes were power collapsed since + * last commit cycle, driver has to restore the hardware state + * of those planes explicitly here prior to plane flush. + */ + drm_atomic_crtc_for_each_plane(plane, crtc) + dpu_plane_restore(plane); + + /* update performance setting before crtc kickoff */ + dpu_core_perf_crtc_update(crtc, 1, false); + + /* + * Final plane updates: Give each plane a chance to complete all + * required writes/flushing before crtc's "flush + * everything" call below. + */ + drm_atomic_crtc_for_each_plane(plane, crtc) { + if (dpu_crtc->smmu_state.transition_error) + dpu_plane_set_error(plane, true); + dpu_plane_flush(plane); + } + + /* Kickoff will be scheduled by outer layer */ +} + +/** + * dpu_crtc_destroy_state - state destroy hook + * @crtc: drm CRTC + * @state: CRTC state object to release + */ +static void dpu_crtc_destroy_state(struct drm_crtc *crtc, + struct drm_crtc_state *state) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *cstate; + + if (!crtc || !state) { + DPU_ERROR("invalid argument(s)\n"); + return; + } + + dpu_crtc = to_dpu_crtc(crtc); + cstate = to_dpu_crtc_state(state); + + DPU_DEBUG("crtc%d\n", crtc->base.id); + + _dpu_crtc_rp_destroy(&cstate->rp); + + __drm_atomic_helper_crtc_destroy_state(state); + + kfree(cstate); +} + +static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + int ret, rc = 0; + + if (!crtc) { + DPU_ERROR("invalid argument\n"); + return -EINVAL; + } + dpu_crtc = to_dpu_crtc(crtc); + + if (!atomic_read(&dpu_crtc->frame_pending)) { + DPU_DEBUG("no frames pending\n"); + return 0; + } + + DPU_ATRACE_BEGIN("frame done completion wait"); + ret = wait_for_completion_timeout(&dpu_crtc->frame_done_comp, + msecs_to_jiffies(DPU_FRAME_DONE_TIMEOUT)); + if (!ret) { + DRM_ERROR("frame done wait timed out, ret:%d\n", ret); + rc = -ETIMEDOUT; + } + DPU_ATRACE_END("frame done completion wait"); + + return rc; +} + +void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + struct drm_device *dev; + struct dpu_crtc *dpu_crtc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + struct dpu_crtc_state *cstate; + int ret; + + if (!crtc) { + DPU_ERROR("invalid argument\n"); + return; + } + dev = crtc->dev; + dpu_crtc = to_dpu_crtc(crtc); + dpu_kms = _dpu_crtc_get_kms(crtc); + + if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) { + DPU_ERROR("invalid argument\n"); + return; + } + + priv = dpu_kms->dev->dev_private; + cstate = to_dpu_crtc_state(crtc->state); + + /* + * If no mixers has been allocated in dpu_crtc_atomic_check(), + * it means we are trying to start a CRTC whose state is disabled: + * nothing else needs to be done. + */ + if (unlikely(!dpu_crtc->num_mixers)) + return; + + DPU_ATRACE_BEGIN("crtc_commit"); + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + struct dpu_encoder_kickoff_params params = { 0 }; + + if (encoder->crtc != crtc) + continue; + + /* + * Encoder will flush/start now, unless it has a tx pending. + * If so, it may delay and flush at an irq event (e.g. ppdone) + */ + dpu_encoder_prepare_for_kickoff(encoder, ¶ms); + } + + /* wait for frame_event_done completion */ + DPU_ATRACE_BEGIN("wait_for_frame_done_event"); + ret = _dpu_crtc_wait_for_frame_done(crtc); + DPU_ATRACE_END("wait_for_frame_done_event"); + if (ret) { + DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n", + crtc->base.id, + atomic_read(&dpu_crtc->frame_pending)); + goto end; + } + + if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) { + /* acquire bandwidth and other resources */ + DPU_DEBUG("crtc%d first commit\n", crtc->base.id); + } else + DPU_DEBUG("crtc%d commit\n", crtc->base.id); + + dpu_crtc->play_count++; + + dpu_vbif_clear_errors(dpu_kms); + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + if (encoder->crtc != crtc) + continue; + + dpu_encoder_kickoff(encoder); + } + +end: + reinit_completion(&dpu_crtc->frame_done_comp); + DPU_ATRACE_END("crtc_commit"); +} + +/** + * _dpu_crtc_vblank_enable_no_lock - update power resource and vblank request + * @dpu_crtc: Pointer to dpu crtc structure + * @enable: Whether to enable/disable vblanks + * + * @Return: error code + */ +static int _dpu_crtc_vblank_enable_no_lock( + struct dpu_crtc *dpu_crtc, bool enable) +{ + struct drm_device *dev; + struct drm_crtc *crtc; + struct drm_encoder *enc; + + if (!dpu_crtc) { + DPU_ERROR("invalid crtc\n"); + return -EINVAL; + } + + crtc = &dpu_crtc->base; + dev = crtc->dev; + + if (enable) { + int ret; + + /* drop lock since power crtc cb may try to re-acquire lock */ + mutex_unlock(&dpu_crtc->crtc_lock); + ret = _dpu_crtc_power_enable(dpu_crtc, true); + mutex_lock(&dpu_crtc->crtc_lock); + if (ret) + return ret; + + list_for_each_entry(enc, &dev->mode_config.encoder_list, head) { + if (enc->crtc != crtc) + continue; + + trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base), + DRMID(enc), enable, + dpu_crtc); + + dpu_encoder_register_vblank_callback(enc, + dpu_crtc_vblank_cb, (void *)crtc); + } + } else { + list_for_each_entry(enc, &dev->mode_config.encoder_list, head) { + if (enc->crtc != crtc) + continue; + + trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base), + DRMID(enc), enable, + dpu_crtc); + + dpu_encoder_register_vblank_callback(enc, NULL, NULL); + } + + /* drop lock since power crtc cb may try to re-acquire lock */ + mutex_unlock(&dpu_crtc->crtc_lock); + _dpu_crtc_power_enable(dpu_crtc, false); + mutex_lock(&dpu_crtc->crtc_lock); + } + + return 0; +} + +/** + * _dpu_crtc_set_suspend - notify crtc of suspend enable/disable + * @crtc: Pointer to drm crtc object + * @enable: true to enable suspend, false to indicate resume + */ +static void _dpu_crtc_set_suspend(struct drm_crtc *crtc, bool enable) +{ + struct dpu_crtc *dpu_crtc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + int ret = 0; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid crtc\n"); + return; + } + dpu_crtc = to_dpu_crtc(crtc); + priv = crtc->dev->dev_private; + + if (!priv->kms) { + DPU_ERROR("invalid crtc kms\n"); + return; + } + dpu_kms = to_dpu_kms(priv->kms); + + DRM_DEBUG_KMS("crtc%d suspend = %d\n", crtc->base.id, enable); + + mutex_lock(&dpu_crtc->crtc_lock); + + /* + * If the vblank is enabled, release a power reference on suspend + * and take it back during resume (if it is still enabled). + */ + trace_dpu_crtc_set_suspend(DRMID(&dpu_crtc->base), enable, dpu_crtc); + if (dpu_crtc->suspend == enable) + DPU_DEBUG("crtc%d suspend already set to %d, ignoring update\n", + crtc->base.id, enable); + else if (dpu_crtc->enabled && dpu_crtc->vblank_requested) { + ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, !enable); + if (ret) + DPU_ERROR("%s vblank enable failed: %d\n", + dpu_crtc->name, ret); + } + + dpu_crtc->suspend = enable; + mutex_unlock(&dpu_crtc->crtc_lock); +} + +/** + * dpu_crtc_duplicate_state - state duplicate hook + * @crtc: Pointer to drm crtc structure + * @Returns: Pointer to new drm_crtc_state structure + */ +static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *cstate, *old_cstate; + + if (!crtc || !crtc->state) { + DPU_ERROR("invalid argument(s)\n"); + return NULL; + } + + dpu_crtc = to_dpu_crtc(crtc); + old_cstate = to_dpu_crtc_state(crtc->state); + cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL); + if (!cstate) { + DPU_ERROR("failed to allocate state\n"); + return NULL; + } + + /* duplicate base helper */ + __drm_atomic_helper_crtc_duplicate_state(crtc, &cstate->base); + + _dpu_crtc_rp_duplicate(&old_cstate->rp, &cstate->rp); + + return &cstate->base; +} + +/** + * dpu_crtc_reset - reset hook for CRTCs + * Resets the atomic state for @crtc by freeing the state pointer (which might + * be NULL, e.g. at driver load time) and allocating a new empty state object. + * @crtc: Pointer to drm crtc structure + */ +static void dpu_crtc_reset(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *cstate; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + + /* revert suspend actions, if necessary */ + if (dpu_kms_is_suspend_state(crtc->dev)) + _dpu_crtc_set_suspend(crtc, false); + + /* remove previous state, if present */ + if (crtc->state) { + dpu_crtc_destroy_state(crtc, crtc->state); + crtc->state = 0; + } + + dpu_crtc = to_dpu_crtc(crtc); + cstate = kzalloc(sizeof(*cstate), GFP_KERNEL); + if (!cstate) { + DPU_ERROR("failed to allocate state\n"); + return; + } + + _dpu_crtc_rp_reset(&cstate->rp, &dpu_crtc->rp_lock, + &dpu_crtc->rp_head); + + cstate->base.crtc = crtc; + crtc->state = &cstate->base; +} + +static void dpu_crtc_handle_power_event(u32 event_type, void *arg) +{ + struct drm_crtc *crtc = arg; + struct dpu_crtc *dpu_crtc; + struct drm_encoder *encoder; + struct dpu_crtc_mixer *m; + u32 i, misr_status; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return; + } + dpu_crtc = to_dpu_crtc(crtc); + + mutex_lock(&dpu_crtc->crtc_lock); + + trace_dpu_crtc_handle_power_event(DRMID(crtc), event_type); + + switch (event_type) { + case DPU_POWER_EVENT_POST_ENABLE: + /* restore encoder; crtc will be programmed during commit */ + drm_for_each_encoder(encoder, crtc->dev) { + if (encoder->crtc != crtc) + continue; + + dpu_encoder_virt_restore(encoder); + } + + for (i = 0; i < dpu_crtc->num_mixers; ++i) { + m = &dpu_crtc->mixers[i]; + if (!m->hw_lm || !m->hw_lm->ops.setup_misr || + !dpu_crtc->misr_enable) + continue; + + m->hw_lm->ops.setup_misr(m->hw_lm, true, + dpu_crtc->misr_frame_count); + } + break; + case DPU_POWER_EVENT_PRE_DISABLE: + for (i = 0; i < dpu_crtc->num_mixers; ++i) { + m = &dpu_crtc->mixers[i]; + if (!m->hw_lm || !m->hw_lm->ops.collect_misr || + !dpu_crtc->misr_enable) + continue; + + misr_status = m->hw_lm->ops.collect_misr(m->hw_lm); + dpu_crtc->misr_data[i] = misr_status ? misr_status : + dpu_crtc->misr_data[i]; + } + break; + case DPU_POWER_EVENT_POST_DISABLE: + /** + * Nothing to do. All the planes on the CRTC will be + * programmed for every frame + */ + break; + default: + DPU_DEBUG("event:%d not handled\n", event_type); + break; + } + + mutex_unlock(&dpu_crtc->crtc_lock); +} + +static void dpu_crtc_disable(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_state *cstate; + struct drm_display_mode *mode; + struct drm_encoder *encoder; + struct msm_drm_private *priv; + int ret; + unsigned long flags; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) { + DPU_ERROR("invalid crtc\n"); + return; + } + dpu_crtc = to_dpu_crtc(crtc); + cstate = to_dpu_crtc_state(crtc->state); + mode = &cstate->base.adjusted_mode; + priv = crtc->dev->dev_private; + + DRM_DEBUG_KMS("crtc%d\n", crtc->base.id); + + if (dpu_kms_is_suspend_state(crtc->dev)) + _dpu_crtc_set_suspend(crtc, true); + + /* Disable/save vblank irq handling */ + drm_crtc_vblank_off(crtc); + + mutex_lock(&dpu_crtc->crtc_lock); + + /* wait for frame_event_done completion */ + if (_dpu_crtc_wait_for_frame_done(crtc)) + DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n", + crtc->base.id, + atomic_read(&dpu_crtc->frame_pending)); + + trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc); + if (dpu_crtc->enabled && !dpu_crtc->suspend && + dpu_crtc->vblank_requested) { + ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, false); + if (ret) + DPU_ERROR("%s vblank enable failed: %d\n", + dpu_crtc->name, ret); + } + dpu_crtc->enabled = false; + + if (atomic_read(&dpu_crtc->frame_pending)) { + trace_dpu_crtc_disable_frame_pending(DRMID(crtc), + atomic_read(&dpu_crtc->frame_pending)); + dpu_core_perf_crtc_release_bw(crtc); + atomic_set(&dpu_crtc->frame_pending, 0); + } + + dpu_core_perf_crtc_update(crtc, 0, true); + + drm_for_each_encoder(encoder, crtc->dev) { + if (encoder->crtc != crtc) + continue; + dpu_encoder_register_frame_event_callback(encoder, NULL, NULL); + } + + if (dpu_crtc->power_event) + dpu_power_handle_unregister_event(dpu_crtc->phandle, + dpu_crtc->power_event); + + memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers)); + dpu_crtc->num_mixers = 0; + dpu_crtc->mixers_swapped = false; + + /* disable clk & bw control until clk & bw properties are set */ + cstate->bw_control = false; + cstate->bw_split_vote = false; + + mutex_unlock(&dpu_crtc->crtc_lock); + + if (crtc->state->event && !crtc->state->active) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, crtc->state->event); + crtc->state->event = NULL; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + } +} + +static void dpu_crtc_enable(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) +{ + struct dpu_crtc *dpu_crtc; + struct drm_encoder *encoder; + struct msm_drm_private *priv; + int ret; + + if (!crtc || !crtc->dev || !crtc->dev->dev_private) { + DPU_ERROR("invalid crtc\n"); + return; + } + priv = crtc->dev->dev_private; + + DRM_DEBUG_KMS("crtc%d\n", crtc->base.id); + dpu_crtc = to_dpu_crtc(crtc); + + drm_for_each_encoder(encoder, crtc->dev) { + if (encoder->crtc != crtc) + continue; + dpu_encoder_register_frame_event_callback(encoder, + dpu_crtc_frame_event_cb, (void *)crtc); + } + + mutex_lock(&dpu_crtc->crtc_lock); + trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc); + if (!dpu_crtc->enabled && !dpu_crtc->suspend && + dpu_crtc->vblank_requested) { + ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, true); + if (ret) + DPU_ERROR("%s vblank enable failed: %d\n", + dpu_crtc->name, ret); + } + dpu_crtc->enabled = true; + + mutex_unlock(&dpu_crtc->crtc_lock); + + /* Enable/restore vblank irq handling */ + drm_crtc_vblank_on(crtc); + + dpu_crtc->power_event = dpu_power_handle_register_event( + dpu_crtc->phandle, + DPU_POWER_EVENT_POST_ENABLE | DPU_POWER_EVENT_POST_DISABLE | + DPU_POWER_EVENT_PRE_DISABLE, + dpu_crtc_handle_power_event, crtc, dpu_crtc->name); + +} + +struct plane_state { + struct dpu_plane_state *dpu_pstate; + const struct drm_plane_state *drm_pstate; + int stage; + u32 pipe_id; +}; + +static int dpu_crtc_atomic_check(struct drm_crtc *crtc, + struct drm_crtc_state *state) +{ + struct dpu_crtc *dpu_crtc; + struct plane_state *pstates; + struct dpu_crtc_state *cstate; + + const struct drm_plane_state *pstate; + struct drm_plane *plane; + struct drm_display_mode *mode; + + int cnt = 0, rc = 0, mixer_width, i, z_pos; + + struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2]; + int multirect_count = 0; + const struct drm_plane_state *pipe_staged[SSPP_MAX]; + int left_zpos_cnt = 0, right_zpos_cnt = 0; + struct drm_rect crtc_rect = { 0 }; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return -EINVAL; + } + + pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL); + + dpu_crtc = to_dpu_crtc(crtc); + cstate = to_dpu_crtc_state(state); + + if (!state->enable || !state->active) { + DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n", + crtc->base.id, state->enable, state->active); + goto end; + } + + mode = &state->adjusted_mode; + DPU_DEBUG("%s: check", dpu_crtc->name); + + /* force a full mode set if active state changed */ + if (state->active_changed) + state->mode_changed = true; + + memset(pipe_staged, 0, sizeof(pipe_staged)); + + mixer_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode); + + _dpu_crtc_setup_lm_bounds(crtc, state); + + crtc_rect.x2 = mode->hdisplay; + crtc_rect.y2 = mode->vdisplay; + + /* get plane state for all drm planes associated with crtc state */ + drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) { + struct drm_rect dst, clip = crtc_rect; + + if (IS_ERR_OR_NULL(pstate)) { + rc = PTR_ERR(pstate); + DPU_ERROR("%s: failed to get plane%d state, %d\n", + dpu_crtc->name, plane->base.id, rc); + goto end; + } + if (cnt >= DPU_STAGE_MAX * 4) + continue; + + pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate); + pstates[cnt].drm_pstate = pstate; + pstates[cnt].stage = pstate->normalized_zpos; + pstates[cnt].pipe_id = dpu_plane_pipe(plane); + + if (pipe_staged[pstates[cnt].pipe_id]) { + multirect_plane[multirect_count].r0 = + pipe_staged[pstates[cnt].pipe_id]; + multirect_plane[multirect_count].r1 = pstate; + multirect_count++; + + pipe_staged[pstates[cnt].pipe_id] = NULL; + } else { + pipe_staged[pstates[cnt].pipe_id] = pstate; + } + + cnt++; + + dst = drm_plane_state_dest(pstate); + if (!drm_rect_intersect(&clip, &dst) || + !drm_rect_equals(&clip, &dst)) { + DPU_ERROR("invalid vertical/horizontal destination\n"); + DPU_ERROR("display: " DRM_RECT_FMT " plane: " + DRM_RECT_FMT "\n", DRM_RECT_ARG(&crtc_rect), + DRM_RECT_ARG(&dst)); + rc = -E2BIG; + goto end; + } + } + + for (i = 1; i < SSPP_MAX; i++) { + if (pipe_staged[i]) { + dpu_plane_clear_multirect(pipe_staged[i]); + + if (is_dpu_plane_virtual(pipe_staged[i]->plane)) { + DPU_ERROR( + "r1 only virt plane:%d not supported\n", + pipe_staged[i]->plane->base.id); + rc = -EINVAL; + goto end; + } + } + } + + z_pos = -1; + for (i = 0; i < cnt; i++) { + /* reset counts at every new blend stage */ + if (pstates[i].stage != z_pos) { + left_zpos_cnt = 0; + right_zpos_cnt = 0; + z_pos = pstates[i].stage; + } + + /* verify z_pos setting before using it */ + if (z_pos >= DPU_STAGE_MAX - DPU_STAGE_0) { + DPU_ERROR("> %d plane stages assigned\n", + DPU_STAGE_MAX - DPU_STAGE_0); + rc = -EINVAL; + goto end; + } else if (pstates[i].drm_pstate->crtc_x < mixer_width) { + if (left_zpos_cnt == 2) { + DPU_ERROR("> 2 planes @ stage %d on left\n", + z_pos); + rc = -EINVAL; + goto end; + } + left_zpos_cnt++; + + } else { + if (right_zpos_cnt == 2) { + DPU_ERROR("> 2 planes @ stage %d on right\n", + z_pos); + rc = -EINVAL; + goto end; + } + right_zpos_cnt++; + } + + pstates[i].dpu_pstate->stage = z_pos + DPU_STAGE_0; + DPU_DEBUG("%s: zpos %d", dpu_crtc->name, z_pos); + } + + for (i = 0; i < multirect_count; i++) { + if (dpu_plane_validate_multirect_v2(&multirect_plane[i])) { + DPU_ERROR( + "multirect validation failed for planes (%d - %d)\n", + multirect_plane[i].r0->plane->base.id, + multirect_plane[i].r1->plane->base.id); + rc = -EINVAL; + goto end; + } + } + + rc = dpu_core_perf_crtc_check(crtc, state); + if (rc) { + DPU_ERROR("crtc%d failed performance check %d\n", + crtc->base.id, rc); + goto end; + } + + /* validate source split: + * use pstates sorted by stage to check planes on same stage + * we assume that all pipes are in source split so its valid to compare + * without taking into account left/right mixer placement + */ + for (i = 1; i < cnt; i++) { + struct plane_state *prv_pstate, *cur_pstate; + struct drm_rect left_rect, right_rect; + int32_t left_pid, right_pid; + int32_t stage; + + prv_pstate = &pstates[i - 1]; + cur_pstate = &pstates[i]; + if (prv_pstate->stage != cur_pstate->stage) + continue; + + stage = cur_pstate->stage; + + left_pid = prv_pstate->dpu_pstate->base.plane->base.id; + left_rect = drm_plane_state_dest(prv_pstate->drm_pstate); + + right_pid = cur_pstate->dpu_pstate->base.plane->base.id; + right_rect = drm_plane_state_dest(cur_pstate->drm_pstate); + + if (right_rect.x1 < left_rect.x1) { + swap(left_pid, right_pid); + swap(left_rect, right_rect); + } + + /** + * - planes are enumerated in pipe-priority order such that + * planes with lower drm_id must be left-most in a shared + * blend-stage when using source split. + * - planes in source split must be contiguous in width + * - planes in source split must have same dest yoff and height + */ + if (right_pid < left_pid) { + DPU_ERROR( + "invalid src split cfg. priority mismatch. stage: %d left: %d right: %d\n", + stage, left_pid, right_pid); + rc = -EINVAL; + goto end; + } else if (right_rect.x1 != drm_rect_width(&left_rect)) { + DPU_ERROR("non-contiguous coordinates for src split. " + "stage: %d left: " DRM_RECT_FMT " right: " + DRM_RECT_FMT "\n", stage, + DRM_RECT_ARG(&left_rect), + DRM_RECT_ARG(&right_rect)); + rc = -EINVAL; + goto end; + } else if (left_rect.y1 != right_rect.y1 || + drm_rect_height(&left_rect) != drm_rect_height(&right_rect)) { + DPU_ERROR("source split at stage: %d. invalid " + "yoff/height: left: " DRM_RECT_FMT " right: " + DRM_RECT_FMT "\n", stage, + DRM_RECT_ARG(&left_rect), + DRM_RECT_ARG(&right_rect)); + rc = -EINVAL; + goto end; + } + } + +end: + _dpu_crtc_rp_free_unused(&cstate->rp); + kfree(pstates); + return rc; +} + +int dpu_crtc_vblank(struct drm_crtc *crtc, bool en) +{ + struct dpu_crtc *dpu_crtc; + int ret; + + if (!crtc) { + DPU_ERROR("invalid crtc\n"); + return -EINVAL; + } + dpu_crtc = to_dpu_crtc(crtc); + + mutex_lock(&dpu_crtc->crtc_lock); + trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc); + if (dpu_crtc->enabled && !dpu_crtc->suspend) { + ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, en); + if (ret) + DPU_ERROR("%s vblank enable failed: %d\n", + dpu_crtc->name, ret); + } + dpu_crtc->vblank_requested = en; + mutex_unlock(&dpu_crtc->crtc_lock); + + return 0; +} + +#ifdef CONFIG_DEBUG_FS +static int _dpu_debugfs_status_show(struct seq_file *s, void *data) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_plane_state *pstate = NULL; + struct dpu_crtc_mixer *m; + + struct drm_crtc *crtc; + struct drm_plane *plane; + struct drm_display_mode *mode; + struct drm_framebuffer *fb; + struct drm_plane_state *state; + struct dpu_crtc_state *cstate; + + int i, out_width; + + if (!s || !s->private) + return -EINVAL; + + dpu_crtc = s->private; + crtc = &dpu_crtc->base; + cstate = to_dpu_crtc_state(crtc->state); + + mutex_lock(&dpu_crtc->crtc_lock); + mode = &crtc->state->adjusted_mode; + out_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode); + + seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id, + mode->hdisplay, mode->vdisplay); + + seq_puts(s, "\n"); + + for (i = 0; i < dpu_crtc->num_mixers; ++i) { + m = &dpu_crtc->mixers[i]; + if (!m->hw_lm) + seq_printf(s, "\tmixer[%d] has no lm\n", i); + else if (!m->hw_ctl) + seq_printf(s, "\tmixer[%d] has no ctl\n", i); + else + seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n", + m->hw_lm->idx - LM_0, m->hw_ctl->idx - CTL_0, + out_width, mode->vdisplay); + } + + seq_puts(s, "\n"); + + drm_atomic_crtc_for_each_plane(plane, crtc) { + pstate = to_dpu_plane_state(plane->state); + state = plane->state; + + if (!pstate || !state) + continue; + + seq_printf(s, "\tplane:%u stage:%d\n", plane->base.id, + pstate->stage); + + if (plane->state->fb) { + fb = plane->state->fb; + + seq_printf(s, "\tfb:%d image format:%4.4s wxh:%ux%u ", + fb->base.id, (char *) &fb->format->format, + fb->width, fb->height); + for (i = 0; i < ARRAY_SIZE(fb->format->cpp); ++i) + seq_printf(s, "cpp[%d]:%u ", + i, fb->format->cpp[i]); + seq_puts(s, "\n\t"); + + seq_printf(s, "modifier:%8llu ", fb->modifier); + seq_puts(s, "\n"); + + seq_puts(s, "\t"); + for (i = 0; i < ARRAY_SIZE(fb->pitches); i++) + seq_printf(s, "pitches[%d]:%8u ", i, + fb->pitches[i]); + seq_puts(s, "\n"); + + seq_puts(s, "\t"); + for (i = 0; i < ARRAY_SIZE(fb->offsets); i++) + seq_printf(s, "offsets[%d]:%8u ", i, + fb->offsets[i]); + seq_puts(s, "\n"); + } + + seq_printf(s, "\tsrc_x:%4d src_y:%4d src_w:%4d src_h:%4d\n", + state->src_x, state->src_y, state->src_w, state->src_h); + + seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n", + state->crtc_x, state->crtc_y, state->crtc_w, + state->crtc_h); + seq_printf(s, "\tmultirect: mode: %d index: %d\n", + pstate->multirect_mode, pstate->multirect_index); + + seq_puts(s, "\n"); + } + if (dpu_crtc->vblank_cb_count) { + ktime_t diff = ktime_sub(ktime_get(), dpu_crtc->vblank_cb_time); + s64 diff_ms = ktime_to_ms(diff); + s64 fps = diff_ms ? div_s64( + dpu_crtc->vblank_cb_count * 1000, diff_ms) : 0; + + seq_printf(s, + "vblank fps:%lld count:%u total:%llums total_framecount:%llu\n", + fps, dpu_crtc->vblank_cb_count, + ktime_to_ms(diff), dpu_crtc->play_count); + + /* reset time & count for next measurement */ + dpu_crtc->vblank_cb_count = 0; + dpu_crtc->vblank_cb_time = ktime_set(0, 0); + } + + seq_printf(s, "vblank_enable:%d\n", dpu_crtc->vblank_requested); + + mutex_unlock(&dpu_crtc->crtc_lock); + + return 0; +} + +static int _dpu_debugfs_status_open(struct inode *inode, struct file *file) +{ + return single_open(file, _dpu_debugfs_status_show, inode->i_private); +} + +static ssize_t _dpu_crtc_misr_setup(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_mixer *m; + int i = 0, rc; + char buf[MISR_BUFF_SIZE + 1]; + u32 frame_count, enable; + size_t buff_copy; + + if (!file || !file->private_data) + return -EINVAL; + + dpu_crtc = file->private_data; + buff_copy = min_t(size_t, count, MISR_BUFF_SIZE); + if (copy_from_user(buf, user_buf, buff_copy)) { + DPU_ERROR("buffer copy failed\n"); + return -EINVAL; + } + + buf[buff_copy] = 0; /* end of string */ + + if (sscanf(buf, "%u %u", &enable, &frame_count) != 2) + return -EINVAL; + + rc = _dpu_crtc_power_enable(dpu_crtc, true); + if (rc) + return rc; + + mutex_lock(&dpu_crtc->crtc_lock); + dpu_crtc->misr_enable = enable; + dpu_crtc->misr_frame_count = frame_count; + for (i = 0; i < dpu_crtc->num_mixers; ++i) { + dpu_crtc->misr_data[i] = 0; + m = &dpu_crtc->mixers[i]; + if (!m->hw_lm || !m->hw_lm->ops.setup_misr) + continue; + + m->hw_lm->ops.setup_misr(m->hw_lm, enable, frame_count); + } + mutex_unlock(&dpu_crtc->crtc_lock); + _dpu_crtc_power_enable(dpu_crtc, false); + + return count; +} + +static ssize_t _dpu_crtc_misr_read(struct file *file, + char __user *user_buff, size_t count, loff_t *ppos) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_crtc_mixer *m; + int i = 0, rc; + u32 misr_status; + ssize_t len = 0; + char buf[MISR_BUFF_SIZE + 1] = {'\0'}; + + if (*ppos) + return 0; + + if (!file || !file->private_data) + return -EINVAL; + + dpu_crtc = file->private_data; + rc = _dpu_crtc_power_enable(dpu_crtc, true); + if (rc) + return rc; + + mutex_lock(&dpu_crtc->crtc_lock); + if (!dpu_crtc->misr_enable) { + len += snprintf(buf + len, MISR_BUFF_SIZE - len, + "disabled\n"); + goto buff_check; + } + + for (i = 0; i < dpu_crtc->num_mixers; ++i) { + m = &dpu_crtc->mixers[i]; + if (!m->hw_lm || !m->hw_lm->ops.collect_misr) + continue; + + misr_status = m->hw_lm->ops.collect_misr(m->hw_lm); + dpu_crtc->misr_data[i] = misr_status ? misr_status : + dpu_crtc->misr_data[i]; + len += snprintf(buf + len, MISR_BUFF_SIZE - len, "lm idx:%d\n", + m->hw_lm->idx - LM_0); + len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n", + dpu_crtc->misr_data[i]); + } + +buff_check: + if (count <= len) { + len = 0; + goto end; + } + + if (copy_to_user(user_buff, buf, len)) { + len = -EFAULT; + goto end; + } + + *ppos += len; /* increase offset */ + +end: + mutex_unlock(&dpu_crtc->crtc_lock); + _dpu_crtc_power_enable(dpu_crtc, false); + return len; +} + +#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ +static int __prefix ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __prefix ## _show, inode->i_private); \ +} \ +static const struct file_operations __prefix ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __prefix ## _open, \ + .release = single_release, \ + .read = seq_read, \ + .llseek = seq_lseek, \ +} + +static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) +{ + struct drm_crtc *crtc = (struct drm_crtc *) s->private; + struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc); + struct dpu_crtc_res *res; + struct dpu_crtc_respool *rp; + int i; + + seq_printf(s, "client type: %d\n", dpu_crtc_get_client_type(crtc)); + seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc)); + seq_printf(s, "core_clk_rate: %llu\n", + dpu_crtc->cur_perf.core_clk_rate); + for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC; + i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) { + seq_printf(s, "bw_ctl[%s]: %llu\n", + dpu_power_handle_get_dbus_name(i), + dpu_crtc->cur_perf.bw_ctl[i]); + seq_printf(s, "max_per_pipe_ib[%s]: %llu\n", + dpu_power_handle_get_dbus_name(i), + dpu_crtc->cur_perf.max_per_pipe_ib[i]); + } + + mutex_lock(&dpu_crtc->rp_lock); + list_for_each_entry(rp, &dpu_crtc->rp_head, rp_list) { + seq_printf(s, "rp.%d: ", rp->sequence_id); + list_for_each_entry(res, &rp->res_list, list) + seq_printf(s, "0x%x/0x%llx/%pK/%d ", + res->type, res->tag, res->val, + atomic_read(&res->refcount)); + seq_puts(s, "\n"); + } + mutex_unlock(&dpu_crtc->rp_lock); + + return 0; +} +DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state); + +static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + struct dpu_kms *dpu_kms; + + static const struct file_operations debugfs_status_fops = { + .open = _dpu_debugfs_status_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + }; + static const struct file_operations debugfs_misr_fops = { + .open = simple_open, + .read = _dpu_crtc_misr_read, + .write = _dpu_crtc_misr_setup, + }; + + if (!crtc) + return -EINVAL; + dpu_crtc = to_dpu_crtc(crtc); + + dpu_kms = _dpu_crtc_get_kms(crtc); + if (!dpu_kms) + return -EINVAL; + + dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name, + crtc->dev->primary->debugfs_root); + if (!dpu_crtc->debugfs_root) + return -ENOMEM; + + /* don't error check these */ + debugfs_create_file("status", 0400, + dpu_crtc->debugfs_root, + dpu_crtc, &debugfs_status_fops); + debugfs_create_file("state", 0600, + dpu_crtc->debugfs_root, + &dpu_crtc->base, + &dpu_crtc_debugfs_state_fops); + debugfs_create_file("misr_data", 0600, dpu_crtc->debugfs_root, + dpu_crtc, &debugfs_misr_fops); + + return 0; +} + +static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + + if (!crtc) + return; + dpu_crtc = to_dpu_crtc(crtc); + debugfs_remove_recursive(dpu_crtc->debugfs_root); +} +#else +static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc) +{ + return 0; +} + +static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc) +{ +} +#endif /* CONFIG_DEBUG_FS */ + +static int dpu_crtc_late_register(struct drm_crtc *crtc) +{ + return _dpu_crtc_init_debugfs(crtc); +} + +static void dpu_crtc_early_unregister(struct drm_crtc *crtc) +{ + _dpu_crtc_destroy_debugfs(crtc); +} + +static const struct drm_crtc_funcs dpu_crtc_funcs = { + .set_config = drm_atomic_helper_set_config, + .destroy = dpu_crtc_destroy, + .page_flip = drm_atomic_helper_page_flip, + .reset = dpu_crtc_reset, + .atomic_duplicate_state = dpu_crtc_duplicate_state, + .atomic_destroy_state = dpu_crtc_destroy_state, + .late_register = dpu_crtc_late_register, + .early_unregister = dpu_crtc_early_unregister, +}; + +static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = { + .disable = dpu_crtc_disable, + .atomic_enable = dpu_crtc_enable, + .atomic_check = dpu_crtc_atomic_check, + .atomic_begin = dpu_crtc_atomic_begin, + .atomic_flush = dpu_crtc_atomic_flush, +}; + +/* initialize crtc */ +struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane) +{ + struct drm_crtc *crtc = NULL; + struct dpu_crtc *dpu_crtc = NULL; + struct msm_drm_private *priv = NULL; + struct dpu_kms *kms = NULL; + int i; + + priv = dev->dev_private; + kms = to_dpu_kms(priv->kms); + + dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL); + if (!dpu_crtc) + return ERR_PTR(-ENOMEM); + + crtc = &dpu_crtc->base; + crtc->dev = dev; + + mutex_init(&dpu_crtc->crtc_lock); + spin_lock_init(&dpu_crtc->spin_lock); + atomic_set(&dpu_crtc->frame_pending, 0); + + mutex_init(&dpu_crtc->rp_lock); + INIT_LIST_HEAD(&dpu_crtc->rp_head); + + init_completion(&dpu_crtc->frame_done_comp); + + INIT_LIST_HEAD(&dpu_crtc->frame_event_list); + + for (i = 0; i < ARRAY_SIZE(dpu_crtc->frame_events); i++) { + INIT_LIST_HEAD(&dpu_crtc->frame_events[i].list); + list_add(&dpu_crtc->frame_events[i].list, + &dpu_crtc->frame_event_list); + kthread_init_work(&dpu_crtc->frame_events[i].work, + dpu_crtc_frame_event_work); + } + + drm_crtc_init_with_planes(dev, crtc, plane, NULL, &dpu_crtc_funcs, + NULL); + + drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs); + plane->crtc = crtc; + + /* save user friendly CRTC name for later */ + snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id); + + /* initialize event handling */ + spin_lock_init(&dpu_crtc->event_lock); + + dpu_crtc->phandle = &kms->phandle; + + DPU_DEBUG("%s: successfully initialized crtc\n", dpu_crtc->name); + return crtc; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h new file mode 100644 index 000000000000..e87109e608e9 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -0,0 +1,423 @@ +/* + * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _DPU_CRTC_H_ +#define _DPU_CRTC_H_ + +#include <linux/kthread.h> +#include <drm/drm_crtc.h> +#include "dpu_kms.h" +#include "dpu_core_perf.h" +#include "dpu_hw_blk.h" + +#define DPU_CRTC_NAME_SIZE 12 + +/* define the maximum number of in-flight frame events */ +#define DPU_CRTC_FRAME_EVENT_SIZE 4 + +/** + * enum dpu_crtc_client_type: crtc client type + * @RT_CLIENT: RealTime client like video/cmd mode display + * voting through apps rsc + * @NRT_CLIENT: Non-RealTime client like WB display + * voting through apps rsc + */ +enum dpu_crtc_client_type { + RT_CLIENT, + NRT_CLIENT, +}; + +/** + * enum dpu_crtc_smmu_state: smmu state + * @ATTACHED: all the context banks are attached. + * @DETACHED: all the context banks are detached. + * @ATTACH_ALL_REQ: transient state of attaching context banks. + * @DETACH_ALL_REQ: transient state of detaching context banks. + */ +enum dpu_crtc_smmu_state { + ATTACHED = 0, + DETACHED, + ATTACH_ALL_REQ, + DETACH_ALL_REQ, +}; + +/** + * enum dpu_crtc_smmu_state_transition_type: state transition type + * @NONE: no pending state transitions + * @PRE_COMMIT: state transitions should be done before processing the commit + * @POST_COMMIT: state transitions to be done after processing the commit. + */ +enum dpu_crtc_smmu_state_transition_type { + NONE, + PRE_COMMIT, + POST_COMMIT +}; + +/** + * struct dpu_crtc_smmu_state_data: stores the smmu state and transition type + * @state: current state of smmu context banks + * @transition_type: transition request type + * @transition_error: whether there is error while transitioning the state + */ +struct dpu_crtc_smmu_state_data { + uint32_t state; + uint32_t transition_type; + uint32_t transition_error; +}; + +/** + * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC + * @hw_lm: LM HW Driver context + * @hw_ctl: CTL Path HW driver context + * @encoder: Encoder attached to this lm & ctl + * @mixer_op_mode: mixer blending operation mode + * @flush_mask: mixer flush mask for ctl, mixer and pipe + */ +struct dpu_crtc_mixer { + struct dpu_hw_mixer *hw_lm; + struct dpu_hw_ctl *hw_ctl; + struct drm_encoder *encoder; + u32 mixer_op_mode; + u32 flush_mask; +}; + +/** + * struct dpu_crtc_frame_event: stores crtc frame event for crtc processing + * @work: base work structure + * @crtc: Pointer to crtc handling this event + * @list: event list + * @ts: timestamp at queue entry + * @event: event identifier + */ +struct dpu_crtc_frame_event { + struct kthread_work work; + struct drm_crtc *crtc; + struct list_head list; + ktime_t ts; + u32 event; +}; + +/* + * Maximum number of free event structures to cache + */ +#define DPU_CRTC_MAX_EVENT_COUNT 16 + +/** + * struct dpu_crtc - virtualized CRTC data structure + * @base : Base drm crtc structure + * @name : ASCII description of this crtc + * @num_ctls : Number of ctl paths in use + * @num_mixers : Number of mixers in use + * @mixers_swapped: Whether the mixers have been swapped for left/right update + * especially in the case of DSC Merge. + * @mixers : List of active mixers + * @event : Pointer to last received drm vblank event. If there is a + * pending vblank event, this will be non-null. + * @vsync_count : Running count of received vsync events + * @drm_requested_vblank : Whether vblanks have been enabled in the encoder + * @property_info : Opaque structure for generic property support + * @property_defaults : Array of default values for generic property support + * @stage_cfg : H/w mixer stage configuration + * @debugfs_root : Parent of debugfs node + * @vblank_cb_count : count of vblank callback since last reset + * @play_count : frame count between crtc enable and disable + * @vblank_cb_time : ktime at vblank count reset + * @vblank_requested : whether the user has requested vblank events + * @suspend : whether or not a suspend operation is in progress + * @enabled : whether the DPU CRTC is currently enabled. updated in the + * commit-thread, not state-swap time which is earlier, so + * safe to make decisions on during VBLANK on/off work + * @feature_list : list of color processing features supported on a crtc + * @active_list : list of color processing features are active + * @dirty_list : list of color processing features are dirty + * @ad_dirty: list containing ad properties that are dirty + * @ad_active: list containing ad properties that are active + * @crtc_lock : crtc lock around create, destroy and access. + * @frame_pending : Whether or not an update is pending + * @frame_events : static allocation of in-flight frame events + * @frame_event_list : available frame event list + * @spin_lock : spin lock for frame event, transaction status, etc... + * @frame_done_comp : for frame_event_done synchronization + * @event_thread : Pointer to event handler thread + * @event_worker : Event worker queue + * @event_lock : Spinlock around event handling code + * @misr_enable : boolean entry indicates misr enable/disable status. + * @misr_frame_count : misr frame count provided by client + * @misr_data : store misr data before turning off the clocks. + * @phandle: Pointer to power handler + * @power_event : registered power event handle + * @cur_perf : current performance committed to clock/bandwidth driver + * @rp_lock : serialization lock for resource pool + * @rp_head : list of active resource pool + * @scl3_cfg_lut : qseed3 lut config + */ +struct dpu_crtc { + struct drm_crtc base; + char name[DPU_CRTC_NAME_SIZE]; + + /* HW Resources reserved for the crtc */ + u32 num_ctls; + u32 num_mixers; + bool mixers_swapped; + struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS]; + struct dpu_hw_scaler3_lut_cfg *scl3_lut_cfg; + + struct drm_pending_vblank_event *event; + u32 vsync_count; + + struct dpu_hw_stage_cfg stage_cfg; + struct dentry *debugfs_root; + + u32 vblank_cb_count; + u64 play_count; + ktime_t vblank_cb_time; + bool vblank_requested; + bool suspend; + bool enabled; + + struct list_head feature_list; + struct list_head active_list; + struct list_head dirty_list; + struct list_head ad_dirty; + struct list_head ad_active; + + struct mutex crtc_lock; + + atomic_t frame_pending; + struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE]; + struct list_head frame_event_list; + spinlock_t spin_lock; + struct completion frame_done_comp; + + /* for handling internal event thread */ + spinlock_t event_lock; + bool misr_enable; + u32 misr_frame_count; + u32 misr_data[CRTC_DUAL_MIXERS]; + + struct dpu_power_handle *phandle; + struct dpu_power_event *power_event; + + struct dpu_core_perf_params cur_perf; + + struct mutex rp_lock; + struct list_head rp_head; + + struct dpu_crtc_smmu_state_data smmu_state; +}; + +#define to_dpu_crtc(x) container_of(x, struct dpu_crtc, base) + +/** + * struct dpu_crtc_res_ops - common operations for crtc resources + * @get: get given resource + * @put: put given resource + */ +struct dpu_crtc_res_ops { + void *(*get)(void *val, u32 type, u64 tag); + void (*put)(void *val); +}; + +#define DPU_CRTC_RES_FLAG_FREE BIT(0) + +/** + * struct dpu_crtc_res - definition of crtc resources + * @list: list of crtc resource + * @type: crtc resource type + * @tag: unique identifier per type + * @refcount: reference/usage count + * @ops: callback operations + * @val: resource handle associated with type/tag + * @flags: customization flags + */ +struct dpu_crtc_res { + struct list_head list; + u32 type; + u64 tag; + atomic_t refcount; + struct dpu_crtc_res_ops ops; + void *val; + u32 flags; +}; + +/** + * dpu_crtc_respool - crtc resource pool + * @rp_lock: pointer to serialization lock + * @rp_head: pointer to head of active resource pools of this crtc + * @rp_list: list of crtc resource pool + * @sequence_id: sequence identifier, incremented per state duplication + * @res_list: list of resource managed by this resource pool + * @ops: resource operations for parent resource pool + */ +struct dpu_crtc_respool { + struct mutex *rp_lock; + struct list_head *rp_head; + struct list_head rp_list; + u32 sequence_id; + struct list_head res_list; + struct dpu_crtc_res_ops ops; +}; + +/** + * struct dpu_crtc_state - dpu container for atomic crtc state + * @base: Base drm crtc state structure + * @is_ppsplit : Whether current topology requires PPSplit special handling + * @bw_control : true if bw/clk controlled by core bw/clk properties + * @bw_split_vote : true if bw controlled by llcc/dram bw properties + * @lm_bounds : LM boundaries based on current mode full resolution, no ROI. + * Origin top left of CRTC. + * @property_state: Local storage for msm_prop properties + * @property_values: Current crtc property values + * @input_fence_timeout_ns : Cached input fence timeout, in ns + * @new_perf: new performance state being requested + */ +struct dpu_crtc_state { + struct drm_crtc_state base; + + bool bw_control; + bool bw_split_vote; + + bool is_ppsplit; + struct drm_rect lm_bounds[CRTC_DUAL_MIXERS]; + + uint64_t input_fence_timeout_ns; + + struct dpu_core_perf_params new_perf; + struct dpu_crtc_respool rp; +}; + +#define to_dpu_crtc_state(x) \ + container_of(x, struct dpu_crtc_state, base) + +/** + * dpu_crtc_get_mixer_width - get the mixer width + * Mixer width will be same as panel width(/2 for split) + */ +static inline int dpu_crtc_get_mixer_width(struct dpu_crtc *dpu_crtc, + struct dpu_crtc_state *cstate, struct drm_display_mode *mode) +{ + u32 mixer_width; + + if (!dpu_crtc || !cstate || !mode) + return 0; + + mixer_width = (dpu_crtc->num_mixers == CRTC_DUAL_MIXERS ? + mode->hdisplay / CRTC_DUAL_MIXERS : mode->hdisplay); + + return mixer_width; +} + +/** + * dpu_crtc_get_mixer_height - get the mixer height + * Mixer height will be same as panel height + */ +static inline int dpu_crtc_get_mixer_height(struct dpu_crtc *dpu_crtc, + struct dpu_crtc_state *cstate, struct drm_display_mode *mode) +{ + if (!dpu_crtc || !cstate || !mode) + return 0; + + return mode->vdisplay; +} + +/** + * dpu_crtc_frame_pending - retun the number of pending frames + * @crtc: Pointer to drm crtc object + */ +static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc) +{ + struct dpu_crtc *dpu_crtc; + + if (!crtc) + return -EINVAL; + + dpu_crtc = to_dpu_crtc(crtc); + return atomic_read(&dpu_crtc->frame_pending); +} + +/** + * dpu_crtc_vblank - enable or disable vblanks for this crtc + * @crtc: Pointer to drm crtc object + * @en: true to enable vblanks, false to disable + */ +int dpu_crtc_vblank(struct drm_crtc *crtc, bool en); + +/** + * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc + * @crtc: Pointer to drm crtc object + */ +void dpu_crtc_commit_kickoff(struct drm_crtc *crtc); + +/** + * dpu_crtc_complete_commit - callback signalling completion of current commit + * @crtc: Pointer to drm crtc object + * @old_state: Pointer to drm crtc old state object + */ +void dpu_crtc_complete_commit(struct drm_crtc *crtc, + struct drm_crtc_state *old_state); + +/** + * dpu_crtc_init - create a new crtc object + * @dev: dpu device + * @plane: base plane + * @Return: new crtc object or error + */ +struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane); + +/** + * dpu_crtc_register_custom_event - api for enabling/disabling crtc event + * @kms: Pointer to dpu_kms + * @crtc_drm: Pointer to crtc object + * @event: Event that client is interested + * @en: Flag to enable/disable the event + */ +int dpu_crtc_register_custom_event(struct dpu_kms *kms, + struct drm_crtc *crtc_drm, u32 event, bool en); + +/** + * dpu_crtc_get_intf_mode - get interface mode of the given crtc + * @crtc: Pointert to crtc + */ +enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc); + +/** + * dpu_crtc_get_client_type - check the crtc type- rt, nrt etc. + * @crtc: Pointer to crtc + */ +static inline enum dpu_crtc_client_type dpu_crtc_get_client_type( + struct drm_crtc *crtc) +{ + struct dpu_crtc_state *cstate = + crtc ? to_dpu_crtc_state(crtc->state) : NULL; + + if (!cstate) + return NRT_CLIENT; + + return RT_CLIENT; +} + +/** + * dpu_crtc_is_enabled - check if dpu crtc is enabled or not + * @crtc: Pointer to crtc + */ +static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc) +{ + return crtc ? crtc->enabled : false; +} + +#endif /* _DPU_CRTC_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c new file mode 100644 index 000000000000..ae2aee7ed9e1 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c @@ -0,0 +1,2393 @@ +/* Copyright (c) 2009-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/ktime.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/dma-buf.h> +#include <linux/slab.h> +#include <linux/list_sort.h> +#include <linux/pm_runtime.h> + +#include "dpu_dbg.h" +#include "disp/dpu1/dpu_hw_catalog.h" + + +#define DEFAULT_DBGBUS_DPU DPU_DBG_DUMP_IN_MEM +#define DEFAULT_DBGBUS_VBIFRT DPU_DBG_DUMP_IN_MEM +#define REG_BASE_NAME_LEN 80 + +#define DBGBUS_FLAGS_DSPP BIT(0) +#define DBGBUS_DSPP_STATUS 0x34C + +#define DBGBUS_NAME_DPU "dpu" +#define DBGBUS_NAME_VBIF_RT "vbif_rt" + +/* offsets from dpu top address for the debug buses */ +#define DBGBUS_SSPP0 0x188 +#define DBGBUS_AXI_INTF 0x194 +#define DBGBUS_SSPP1 0x298 +#define DBGBUS_DSPP 0x348 +#define DBGBUS_PERIPH 0x418 + +#define TEST_MASK(id, tp) ((id << 4) | (tp << 1) | BIT(0)) + +/* following offsets are with respect to MDP VBIF base for DBG BUS access */ +#define MMSS_VBIF_CLKON 0x4 +#define MMSS_VBIF_TEST_BUS_OUT_CTRL 0x210 +#define MMSS_VBIF_TEST_BUS_OUT 0x230 + +/* Vbif error info */ +#define MMSS_VBIF_PND_ERR 0x190 +#define MMSS_VBIF_SRC_ERR 0x194 +#define MMSS_VBIF_XIN_HALT_CTRL1 0x204 +#define MMSS_VBIF_ERR_INFO 0X1a0 +#define MMSS_VBIF_ERR_INFO_1 0x1a4 +#define MMSS_VBIF_CLIENT_NUM 14 + +/** + * struct dpu_dbg_reg_base - register region base. + * may sub-ranges: sub-ranges are used for dumping + * or may not have sub-ranges: dumping is base -> max_offset + * @reg_base_head: head of this node + * @name: register base name + * @base: base pointer + * @off: cached offset of region for manual register dumping + * @cnt: cached range of region for manual register dumping + * @max_offset: length of region + * @buf: buffer used for manual register dumping + * @buf_len: buffer length used for manual register dumping + * @cb: callback for external dump function, null if not defined + * @cb_ptr: private pointer to callback function + */ +struct dpu_dbg_reg_base { + struct list_head reg_base_head; + char name[REG_BASE_NAME_LEN]; + void __iomem *base; + size_t off; + size_t cnt; + size_t max_offset; + char *buf; + size_t buf_len; + void (*cb)(void *ptr); + void *cb_ptr; +}; + +struct dpu_debug_bus_entry { + u32 wr_addr; + u32 block_id; + u32 test_id; + void (*analyzer)(void __iomem *mem_base, + struct dpu_debug_bus_entry *entry, u32 val); +}; + +struct vbif_debug_bus_entry { + u32 disable_bus_addr; + u32 block_bus_addr; + u32 bit_offset; + u32 block_cnt; + u32 test_pnt_start; + u32 test_pnt_cnt; +}; + +struct dpu_dbg_debug_bus_common { + char *name; + u32 enable_mask; + bool include_in_deferred_work; + u32 flags; + u32 entries_size; + u32 *dumped_content; +}; + +struct dpu_dbg_dpu_debug_bus { + struct dpu_dbg_debug_bus_common cmn; + struct dpu_debug_bus_entry *entries; + u32 top_blk_off; +}; + +struct dpu_dbg_vbif_debug_bus { + struct dpu_dbg_debug_bus_common cmn; + struct vbif_debug_bus_entry *entries; +}; + +/** + * struct dpu_dbg_base - global dpu debug base structure + * @reg_base_list: list of register dumping regions + * @dev: device pointer + * @dump_work: work struct for deferring register dump work to separate thread + * @dbgbus_dpu: debug bus structure for the dpu + * @dbgbus_vbif_rt: debug bus structure for the realtime vbif + */ +static struct dpu_dbg_base { + struct list_head reg_base_list; + struct device *dev; + + struct work_struct dump_work; + + struct dpu_dbg_dpu_debug_bus dbgbus_dpu; + struct dpu_dbg_vbif_debug_bus dbgbus_vbif_rt; +} dpu_dbg_base; + +static void _dpu_debug_bus_xbar_dump(void __iomem *mem_base, + struct dpu_debug_bus_entry *entry, u32 val) +{ + dev_err(dpu_dbg_base.dev, "xbar 0x%x %d %d 0x%x\n", + entry->wr_addr, entry->block_id, entry->test_id, val); +} + +static void _dpu_debug_bus_lm_dump(void __iomem *mem_base, + struct dpu_debug_bus_entry *entry, u32 val) +{ + if (!(val & 0xFFF000)) + return; + + dev_err(dpu_dbg_base.dev, "lm 0x%x %d %d 0x%x\n", + entry->wr_addr, entry->block_id, entry->test_id, val); +} + +static void _dpu_debug_bus_ppb0_dump(void __iomem *mem_base, + struct dpu_debug_bus_entry *entry, u32 val) +{ + if (!(val & BIT(15))) + return; + + dev_err(dpu_dbg_base.dev, "ppb0 0x%x %d %d 0x%x\n", + entry->wr_addr, entry->block_id, entry->test_id, val); +} + +static void _dpu_debug_bus_ppb1_dump(void __iomem *mem_base, + struct dpu_debug_bus_entry *entry, u32 val) +{ + if (!(val & BIT(15))) + return; + + dev_err(dpu_dbg_base.dev, "ppb1 0x%x %d %d 0x%x\n", + entry->wr_addr, entry->block_id, entry->test_id, val); +} + +static struct dpu_debug_bus_entry dbg_bus_dpu_8998[] = { + + /* Unpack 0 sspp 0*/ + { DBGBUS_SSPP0, 50, 2 }, + { DBGBUS_SSPP0, 60, 2 }, + { DBGBUS_SSPP0, 70, 2 }, + { DBGBUS_SSPP0, 85, 2 }, + + /* Upack 0 sspp 1*/ + { DBGBUS_SSPP1, 50, 2 }, + { DBGBUS_SSPP1, 60, 2 }, + { DBGBUS_SSPP1, 70, 2 }, + { DBGBUS_SSPP1, 85, 2 }, + + /* scheduler */ + { DBGBUS_DSPP, 130, 0 }, + { DBGBUS_DSPP, 130, 1 }, + { DBGBUS_DSPP, 130, 2 }, + { DBGBUS_DSPP, 130, 3 }, + { DBGBUS_DSPP, 130, 4 }, + { DBGBUS_DSPP, 130, 5 }, + + /* qseed */ + { DBGBUS_SSPP0, 6, 0}, + { DBGBUS_SSPP0, 6, 1}, + { DBGBUS_SSPP0, 26, 0}, + { DBGBUS_SSPP0, 26, 1}, + { DBGBUS_SSPP1, 6, 0}, + { DBGBUS_SSPP1, 6, 1}, + { DBGBUS_SSPP1, 26, 0}, + { DBGBUS_SSPP1, 26, 1}, + + /* scale */ + { DBGBUS_SSPP0, 16, 0}, + { DBGBUS_SSPP0, 16, 1}, + { DBGBUS_SSPP0, 36, 0}, + { DBGBUS_SSPP0, 36, 1}, + { DBGBUS_SSPP1, 16, 0}, + { DBGBUS_SSPP1, 16, 1}, + { DBGBUS_SSPP1, 36, 0}, + { DBGBUS_SSPP1, 36, 1}, + + /* fetch sspp0 */ + + /* vig 0 */ + { DBGBUS_SSPP0, 0, 0 }, + { DBGBUS_SSPP0, 0, 1 }, + { DBGBUS_SSPP0, 0, 2 }, + { DBGBUS_SSPP0, 0, 3 }, + { DBGBUS_SSPP0, 0, 4 }, + { DBGBUS_SSPP0, 0, 5 }, + { DBGBUS_SSPP0, 0, 6 }, + { DBGBUS_SSPP0, 0, 7 }, + + { DBGBUS_SSPP0, 1, 0 }, + { DBGBUS_SSPP0, 1, 1 }, + { DBGBUS_SSPP0, 1, 2 }, + { DBGBUS_SSPP0, 1, 3 }, + { DBGBUS_SSPP0, 1, 4 }, + { DBGBUS_SSPP0, 1, 5 }, + { DBGBUS_SSPP0, 1, 6 }, + { DBGBUS_SSPP0, 1, 7 }, + + { DBGBUS_SSPP0, 2, 0 }, + { DBGBUS_SSPP0, 2, 1 }, + { DBGBUS_SSPP0, 2, 2 }, + { DBGBUS_SSPP0, 2, 3 }, + { DBGBUS_SSPP0, 2, 4 }, + { DBGBUS_SSPP0, 2, 5 }, + { DBGBUS_SSPP0, 2, 6 }, + { DBGBUS_SSPP0, 2, 7 }, + + { DBGBUS_SSPP0, 4, 0 }, + { DBGBUS_SSPP0, 4, 1 }, + { DBGBUS_SSPP0, 4, 2 }, + { DBGBUS_SSPP0, 4, 3 }, + { DBGBUS_SSPP0, 4, 4 }, + { DBGBUS_SSPP0, 4, 5 }, + { DBGBUS_SSPP0, 4, 6 }, + { DBGBUS_SSPP0, 4, 7 }, + + { DBGBUS_SSPP0, 5, 0 }, + { DBGBUS_SSPP0, 5, 1 }, + { DBGBUS_SSPP0, 5, 2 }, + { DBGBUS_SSPP0, 5, 3 }, + { DBGBUS_SSPP0, 5, 4 }, + { DBGBUS_SSPP0, 5, 5 }, + { DBGBUS_SSPP0, 5, 6 }, + { DBGBUS_SSPP0, 5, 7 }, + + /* vig 2 */ + { DBGBUS_SSPP0, 20, 0 }, + { DBGBUS_SSPP0, 20, 1 }, + { DBGBUS_SSPP0, 20, 2 }, + { DBGBUS_SSPP0, 20, 3 }, + { DBGBUS_SSPP0, 20, 4 }, + { DBGBUS_SSPP0, 20, 5 }, + { DBGBUS_SSPP0, 20, 6 }, + { DBGBUS_SSPP0, 20, 7 }, + + { DBGBUS_SSPP0, 21, 0 }, + { DBGBUS_SSPP0, 21, 1 }, + { DBGBUS_SSPP0, 21, 2 }, + { DBGBUS_SSPP0, 21, 3 }, + { DBGBUS_SSPP0, 21, 4 }, + { DBGBUS_SSPP0, 21, 5 }, + { DBGBUS_SSPP0, 21, 6 }, + { DBGBUS_SSPP0, 21, 7 }, + + { DBGBUS_SSPP0, 22, 0 }, + { DBGBUS_SSPP0, 22, 1 }, + { DBGBUS_SSPP0, 22, 2 }, + { DBGBUS_SSPP0, 22, 3 }, + { DBGBUS_SSPP0, 22, 4 }, + { DBGBUS_SSPP0, 22, 5 }, + { DBGBUS_SSPP0, 22, 6 }, + { DBGBUS_SSPP0, 22, 7 }, + + { DBGBUS_SSPP0, 24, 0 }, + { DBGBUS_SSPP0, 24, 1 }, + { DBGBUS_SSPP0, 24, 2 }, + { DBGBUS_SSPP0, 24, 3 }, + { DBGBUS_SSPP0, 24, 4 }, + { DBGBUS_SSPP0, 24, 5 }, + { DBGBUS_SSPP0, 24, 6 }, + { DBGBUS_SSPP0, 24, 7 }, + + { DBGBUS_SSPP0, 25, 0 }, + { DBGBUS_SSPP0, 25, 1 }, + { DBGBUS_SSPP0, 25, 2 }, + { DBGBUS_SSPP0, 25, 3 }, + { DBGBUS_SSPP0, 25, 4 }, + { DBGBUS_SSPP0, 25, 5 }, + { DBGBUS_SSPP0, 25, 6 }, + { DBGBUS_SSPP0, 25, 7 }, + + /* dma 2 */ + { DBGBUS_SSPP0, 30, 0 }, + { DBGBUS_SSPP0, 30, 1 }, + { DBGBUS_SSPP0, 30, 2 }, + { DBGBUS_SSPP0, 30, 3 }, + { DBGBUS_SSPP0, 30, 4 }, + { DBGBUS_SSPP0, 30, 5 }, + { DBGBUS_SSPP0, 30, 6 }, + { DBGBUS_SSPP0, 30, 7 }, + + { DBGBUS_SSPP0, 31, 0 }, + { DBGBUS_SSPP0, 31, 1 }, + { DBGBUS_SSPP0, 31, 2 }, + { DBGBUS_SSPP0, 31, 3 }, + { DBGBUS_SSPP0, 31, 4 }, + { DBGBUS_SSPP0, 31, 5 }, + { DBGBUS_SSPP0, 31, 6 }, + { DBGBUS_SSPP0, 31, 7 }, + + { DBGBUS_SSPP0, 32, 0 }, + { DBGBUS_SSPP0, 32, 1 }, + { DBGBUS_SSPP0, 32, 2 }, + { DBGBUS_SSPP0, 32, 3 }, + { DBGBUS_SSPP0, 32, 4 }, + { DBGBUS_SSPP0, 32, 5 }, + { DBGBUS_SSPP0, 32, 6 }, + { DBGBUS_SSPP0, 32, 7 }, + + { DBGBUS_SSPP0, 33, 0 }, + { DBGBUS_SSPP0, 33, 1 }, + { DBGBUS_SSPP0, 33, 2 }, + { DBGBUS_SSPP0, 33, 3 }, + { DBGBUS_SSPP0, 33, 4 }, + { DBGBUS_SSPP0, 33, 5 }, + { DBGBUS_SSPP0, 33, 6 }, + { DBGBUS_SSPP0, 33, 7 }, + + { DBGBUS_SSPP0, 34, 0 }, + { DBGBUS_SSPP0, 34, 1 }, + { DBGBUS_SSPP0, 34, 2 }, + { DBGBUS_SSPP0, 34, 3 }, + { DBGBUS_SSPP0, 34, 4 }, + { DBGBUS_SSPP0, 34, 5 }, + { DBGBUS_SSPP0, 34, 6 }, + { DBGBUS_SSPP0, 34, 7 }, + + { DBGBUS_SSPP0, 35, 0 }, + { DBGBUS_SSPP0, 35, 1 }, + { DBGBUS_SSPP0, 35, 2 }, + { DBGBUS_SSPP0, 35, 3 }, + + /* dma 0 */ + { DBGBUS_SSPP0, 40, 0 }, + { DBGBUS_SSPP0, 40, 1 }, + { DBGBUS_SSPP0, 40, 2 }, + { DBGBUS_SSPP0, 40, 3 }, + { DBGBUS_SSPP0, 40, 4 }, + { DBGBUS_SSPP0, 40, 5 }, + { DBGBUS_SSPP0, 40, 6 }, + { DBGBUS_SSPP0, 40, 7 }, + + { DBGBUS_SSPP0, 41, 0 }, + { DBGBUS_SSPP0, 41, 1 }, + { DBGBUS_SSPP0, 41, 2 }, + { DBGBUS_SSPP0, 41, 3 }, + { DBGBUS_SSPP0, 41, 4 }, + { DBGBUS_SSPP0, 41, 5 }, + { DBGBUS_SSPP0, 41, 6 }, + { DBGBUS_SSPP0, 41, 7 }, + + { DBGBUS_SSPP0, 42, 0 }, + { DBGBUS_SSPP0, 42, 1 }, + { DBGBUS_SSPP0, 42, 2 }, + { DBGBUS_SSPP0, 42, 3 }, + { DBGBUS_SSPP0, 42, 4 }, + { DBGBUS_SSPP0, 42, 5 }, + { DBGBUS_SSPP0, 42, 6 }, + { DBGBUS_SSPP0, 42, 7 }, + + { DBGBUS_SSPP0, 44, 0 }, + { DBGBUS_SSPP0, 44, 1 }, + { DBGBUS_SSPP0, 44, 2 }, + { DBGBUS_SSPP0, 44, 3 }, + { DBGBUS_SSPP0, 44, 4 }, + { DBGBUS_SSPP0, 44, 5 }, + { DBGBUS_SSPP0, 44, 6 }, + { DBGBUS_SSPP0, 44, 7 }, + + { DBGBUS_SSPP0, 45, 0 }, + { DBGBUS_SSPP0, 45, 1 }, + { DBGBUS_SSPP0, 45, 2 }, + { DBGBUS_SSPP0, 45, 3 }, + { DBGBUS_SSPP0, 45, 4 }, + { DBGBUS_SSPP0, 45, 5 }, + { DBGBUS_SSPP0, 45, 6 }, + { DBGBUS_SSPP0, 45, 7 }, + + /* fetch sspp1 */ + /* vig 1 */ + { DBGBUS_SSPP1, 0, 0 }, + { DBGBUS_SSPP1, 0, 1 }, + { DBGBUS_SSPP1, 0, 2 }, + { DBGBUS_SSPP1, 0, 3 }, + { DBGBUS_SSPP1, 0, 4 }, + { DBGBUS_SSPP1, 0, 5 }, + { DBGBUS_SSPP1, 0, 6 }, + { DBGBUS_SSPP1, 0, 7 }, + + { DBGBUS_SSPP1, 1, 0 }, + { DBGBUS_SSPP1, 1, 1 }, + { DBGBUS_SSPP1, 1, 2 }, + { DBGBUS_SSPP1, 1, 3 }, + { DBGBUS_SSPP1, 1, 4 }, + { DBGBUS_SSPP1, 1, 5 }, + { DBGBUS_SSPP1, 1, 6 }, + { DBGBUS_SSPP1, 1, 7 }, + + { DBGBUS_SSPP1, 2, 0 }, + { DBGBUS_SSPP1, 2, 1 }, + { DBGBUS_SSPP1, 2, 2 }, + { DBGBUS_SSPP1, 2, 3 }, + { DBGBUS_SSPP1, 2, 4 }, + { DBGBUS_SSPP1, 2, 5 }, + { DBGBUS_SSPP1, 2, 6 }, + { DBGBUS_SSPP1, 2, 7 }, + + { DBGBUS_SSPP1, 4, 0 }, + { DBGBUS_SSPP1, 4, 1 }, + { DBGBUS_SSPP1, 4, 2 }, + { DBGBUS_SSPP1, 4, 3 }, + { DBGBUS_SSPP1, 4, 4 }, + { DBGBUS_SSPP1, 4, 5 }, + { DBGBUS_SSPP1, 4, 6 }, + { DBGBUS_SSPP1, 4, 7 }, + + { DBGBUS_SSPP1, 5, 0 }, + { DBGBUS_SSPP1, 5, 1 }, + { DBGBUS_SSPP1, 5, 2 }, + { DBGBUS_SSPP1, 5, 3 }, + { DBGBUS_SSPP1, 5, 4 }, + { DBGBUS_SSPP1, 5, 5 }, + { DBGBUS_SSPP1, 5, 6 }, + { DBGBUS_SSPP1, 5, 7 }, + + /* vig 3 */ + { DBGBUS_SSPP1, 20, 0 }, + { DBGBUS_SSPP1, 20, 1 }, + { DBGBUS_SSPP1, 20, 2 }, + { DBGBUS_SSPP1, 20, 3 }, + { DBGBUS_SSPP1, 20, 4 }, + { DBGBUS_SSPP1, 20, 5 }, + { DBGBUS_SSPP1, 20, 6 }, + { DBGBUS_SSPP1, 20, 7 }, + + { DBGBUS_SSPP1, 21, 0 }, + { DBGBUS_SSPP1, 21, 1 }, + { DBGBUS_SSPP1, 21, 2 }, + { DBGBUS_SSPP1, 21, 3 }, + { DBGBUS_SSPP1, 21, 4 }, + { DBGBUS_SSPP1, 21, 5 }, + { DBGBUS_SSPP1, 21, 6 }, + { DBGBUS_SSPP1, 21, 7 }, + + { DBGBUS_SSPP1, 22, 0 }, + { DBGBUS_SSPP1, 22, 1 }, + { DBGBUS_SSPP1, 22, 2 }, + { DBGBUS_SSPP1, 22, 3 }, + { DBGBUS_SSPP1, 22, 4 }, + { DBGBUS_SSPP1, 22, 5 }, + { DBGBUS_SSPP1, 22, 6 }, + { DBGBUS_SSPP1, 22, 7 }, + + { DBGBUS_SSPP1, 24, 0 }, + { DBGBUS_SSPP1, 24, 1 }, + { DBGBUS_SSPP1, 24, 2 }, + { DBGBUS_SSPP1, 24, 3 }, + { DBGBUS_SSPP1, 24, 4 }, + { DBGBUS_SSPP1, 24, 5 }, + { DBGBUS_SSPP1, 24, 6 }, + { DBGBUS_SSPP1, 24, 7 }, + + { DBGBUS_SSPP1, 25, 0 }, + { DBGBUS_SSPP1, 25, 1 }, + { DBGBUS_SSPP1, 25, 2 }, + { DBGBUS_SSPP1, 25, 3 }, + { DBGBUS_SSPP1, 25, 4 }, + { DBGBUS_SSPP1, 25, 5 }, + { DBGBUS_SSPP1, 25, 6 }, + { DBGBUS_SSPP1, 25, 7 }, + + /* dma 3 */ + { DBGBUS_SSPP1, 30, 0 }, + { DBGBUS_SSPP1, 30, 1 }, + { DBGBUS_SSPP1, 30, 2 }, + { DBGBUS_SSPP1, 30, 3 }, + { DBGBUS_SSPP1, 30, 4 }, + { DBGBUS_SSPP1, 30, 5 }, + { DBGBUS_SSPP1, 30, 6 }, + { DBGBUS_SSPP1, 30, 7 }, + + { DBGBUS_SSPP1, 31, 0 }, + { DBGBUS_SSPP1, 31, 1 }, + { DBGBUS_SSPP1, 31, 2 }, + { DBGBUS_SSPP1, 31, 3 }, + { DBGBUS_SSPP1, 31, 4 }, + { DBGBUS_SSPP1, 31, 5 }, + { DBGBUS_SSPP1, 31, 6 }, + { DBGBUS_SSPP1, 31, 7 }, + + { DBGBUS_SSPP1, 32, 0 }, + { DBGBUS_SSPP1, 32, 1 }, + { DBGBUS_SSPP1, 32, 2 }, + { DBGBUS_SSPP1, 32, 3 }, + { DBGBUS_SSPP1, 32, 4 }, + { DBGBUS_SSPP1, 32, 5 }, + { DBGBUS_SSPP1, 32, 6 }, + { DBGBUS_SSPP1, 32, 7 }, + + { DBGBUS_SSPP1, 33, 0 }, + { DBGBUS_SSPP1, 33, 1 }, + { DBGBUS_SSPP1, 33, 2 }, + { DBGBUS_SSPP1, 33, 3 }, + { DBGBUS_SSPP1, 33, 4 }, + { DBGBUS_SSPP1, 33, 5 }, + { DBGBUS_SSPP1, 33, 6 }, + { DBGBUS_SSPP1, 33, 7 }, + + { DBGBUS_SSPP1, 34, 0 }, + { DBGBUS_SSPP1, 34, 1 }, + { DBGBUS_SSPP1, 34, 2 }, + { DBGBUS_SSPP1, 34, 3 }, + { DBGBUS_SSPP1, 34, 4 }, + { DBGBUS_SSPP1, 34, 5 }, + { DBGBUS_SSPP1, 34, 6 }, + { DBGBUS_SSPP1, 34, 7 }, + + { DBGBUS_SSPP1, 35, 0 }, + { DBGBUS_SSPP1, 35, 1 }, + { DBGBUS_SSPP1, 35, 2 }, + + /* dma 1 */ + { DBGBUS_SSPP1, 40, 0 }, + { DBGBUS_SSPP1, 40, 1 }, + { DBGBUS_SSPP1, 40, 2 }, + { DBGBUS_SSPP1, 40, 3 }, + { DBGBUS_SSPP1, 40, 4 }, + { DBGBUS_SSPP1, 40, 5 }, + { DBGBUS_SSPP1, 40, 6 }, + { DBGBUS_SSPP1, 40, 7 }, + + { DBGBUS_SSPP1, 41, 0 }, + { DBGBUS_SSPP1, 41, 1 }, + { DBGBUS_SSPP1, 41, 2 }, + { DBGBUS_SSPP1, 41, 3 }, + { DBGBUS_SSPP1, 41, 4 }, + { DBGBUS_SSPP1, 41, 5 }, + { DBGBUS_SSPP1, 41, 6 }, + { DBGBUS_SSPP1, 41, 7 }, + + { DBGBUS_SSPP1, 42, 0 }, + { DBGBUS_SSPP1, 42, 1 }, + { DBGBUS_SSPP1, 42, 2 }, + { DBGBUS_SSPP1, 42, 3 }, + { DBGBUS_SSPP1, 42, 4 }, + { DBGBUS_SSPP1, 42, 5 }, + { DBGBUS_SSPP1, 42, 6 }, + { DBGBUS_SSPP1, 42, 7 }, + + { DBGBUS_SSPP1, 44, 0 }, + { DBGBUS_SSPP1, 44, 1 }, + { DBGBUS_SSPP1, 44, 2 }, + { DBGBUS_SSPP1, 44, 3 }, + { DBGBUS_SSPP1, 44, 4 }, + { DBGBUS_SSPP1, 44, 5 }, + { DBGBUS_SSPP1, 44, 6 }, + { DBGBUS_SSPP1, 44, 7 }, + + { DBGBUS_SSPP1, 45, 0 }, + { DBGBUS_SSPP1, 45, 1 }, + { DBGBUS_SSPP1, 45, 2 }, + { DBGBUS_SSPP1, 45, 3 }, + { DBGBUS_SSPP1, 45, 4 }, + { DBGBUS_SSPP1, 45, 5 }, + { DBGBUS_SSPP1, 45, 6 }, + { DBGBUS_SSPP1, 45, 7 }, + + /* cursor 1 */ + { DBGBUS_SSPP1, 80, 0 }, + { DBGBUS_SSPP1, 80, 1 }, + { DBGBUS_SSPP1, 80, 2 }, + { DBGBUS_SSPP1, 80, 3 }, + { DBGBUS_SSPP1, 80, 4 }, + { DBGBUS_SSPP1, 80, 5 }, + { DBGBUS_SSPP1, 80, 6 }, + { DBGBUS_SSPP1, 80, 7 }, + + { DBGBUS_SSPP1, 81, 0 }, + { DBGBUS_SSPP1, 81, 1 }, + { DBGBUS_SSPP1, 81, 2 }, + { DBGBUS_SSPP1, 81, 3 }, + { DBGBUS_SSPP1, 81, 4 }, + { DBGBUS_SSPP1, 81, 5 }, + { DBGBUS_SSPP1, 81, 6 }, + { DBGBUS_SSPP1, 81, 7 }, + + { DBGBUS_SSPP1, 82, 0 }, + { DBGBUS_SSPP1, 82, 1 }, + { DBGBUS_SSPP1, 82, 2 }, + { DBGBUS_SSPP1, 82, 3 }, + { DBGBUS_SSPP1, 82, 4 }, + { DBGBUS_SSPP1, 82, 5 }, + { DBGBUS_SSPP1, 82, 6 }, + { DBGBUS_SSPP1, 82, 7 }, + + { DBGBUS_SSPP1, 83, 0 }, + { DBGBUS_SSPP1, 83, 1 }, + { DBGBUS_SSPP1, 83, 2 }, + { DBGBUS_SSPP1, 83, 3 }, + { DBGBUS_SSPP1, 83, 4 }, + { DBGBUS_SSPP1, 83, 5 }, + { DBGBUS_SSPP1, 83, 6 }, + { DBGBUS_SSPP1, 83, 7 }, + + { DBGBUS_SSPP1, 84, 0 }, + { DBGBUS_SSPP1, 84, 1 }, + { DBGBUS_SSPP1, 84, 2 }, + { DBGBUS_SSPP1, 84, 3 }, + { DBGBUS_SSPP1, 84, 4 }, + { DBGBUS_SSPP1, 84, 5 }, + { DBGBUS_SSPP1, 84, 6 }, + { DBGBUS_SSPP1, 84, 7 }, + + /* dspp */ + { DBGBUS_DSPP, 13, 0 }, + { DBGBUS_DSPP, 19, 0 }, + { DBGBUS_DSPP, 14, 0 }, + { DBGBUS_DSPP, 14, 1 }, + { DBGBUS_DSPP, 14, 3 }, + { DBGBUS_DSPP, 20, 0 }, + { DBGBUS_DSPP, 20, 1 }, + { DBGBUS_DSPP, 20, 3 }, + + /* ppb_0 */ + { DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump }, + + /* ppb_1 */ + { DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump }, + + /* lm_lut */ + { DBGBUS_DSPP, 109, 0 }, + { DBGBUS_DSPP, 105, 0 }, + { DBGBUS_DSPP, 103, 0 }, + + /* tear-check */ + { DBGBUS_PERIPH, 63, 0 }, + { DBGBUS_PERIPH, 64, 0 }, + { DBGBUS_PERIPH, 65, 0 }, + { DBGBUS_PERIPH, 73, 0 }, + { DBGBUS_PERIPH, 74, 0 }, + + /* crossbar */ + { DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump }, + + /* rotator */ + { DBGBUS_DSPP, 9, 0}, + + /* blend */ + /* LM0 */ + { DBGBUS_DSPP, 63, 0}, + { DBGBUS_DSPP, 63, 1}, + { DBGBUS_DSPP, 63, 2}, + { DBGBUS_DSPP, 63, 3}, + { DBGBUS_DSPP, 63, 4}, + { DBGBUS_DSPP, 63, 5}, + { DBGBUS_DSPP, 63, 6}, + { DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 64, 0}, + { DBGBUS_DSPP, 64, 1}, + { DBGBUS_DSPP, 64, 2}, + { DBGBUS_DSPP, 64, 3}, + { DBGBUS_DSPP, 64, 4}, + { DBGBUS_DSPP, 64, 5}, + { DBGBUS_DSPP, 64, 6}, + { DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 65, 0}, + { DBGBUS_DSPP, 65, 1}, + { DBGBUS_DSPP, 65, 2}, + { DBGBUS_DSPP, 65, 3}, + { DBGBUS_DSPP, 65, 4}, + { DBGBUS_DSPP, 65, 5}, + { DBGBUS_DSPP, 65, 6}, + { DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 66, 0}, + { DBGBUS_DSPP, 66, 1}, + { DBGBUS_DSPP, 66, 2}, + { DBGBUS_DSPP, 66, 3}, + { DBGBUS_DSPP, 66, 4}, + { DBGBUS_DSPP, 66, 5}, + { DBGBUS_DSPP, 66, 6}, + { DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 67, 0}, + { DBGBUS_DSPP, 67, 1}, + { DBGBUS_DSPP, 67, 2}, + { DBGBUS_DSPP, 67, 3}, + { DBGBUS_DSPP, 67, 4}, + { DBGBUS_DSPP, 67, 5}, + { DBGBUS_DSPP, 67, 6}, + { DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 68, 0}, + { DBGBUS_DSPP, 68, 1}, + { DBGBUS_DSPP, 68, 2}, + { DBGBUS_DSPP, 68, 3}, + { DBGBUS_DSPP, 68, 4}, + { DBGBUS_DSPP, 68, 5}, + { DBGBUS_DSPP, 68, 6}, + { DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 69, 0}, + { DBGBUS_DSPP, 69, 1}, + { DBGBUS_DSPP, 69, 2}, + { DBGBUS_DSPP, 69, 3}, + { DBGBUS_DSPP, 69, 4}, + { DBGBUS_DSPP, 69, 5}, + { DBGBUS_DSPP, 69, 6}, + { DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump }, + + /* LM1 */ + { DBGBUS_DSPP, 70, 0}, + { DBGBUS_DSPP, 70, 1}, + { DBGBUS_DSPP, 70, 2}, + { DBGBUS_DSPP, 70, 3}, + { DBGBUS_DSPP, 70, 4}, + { DBGBUS_DSPP, 70, 5}, + { DBGBUS_DSPP, 70, 6}, + { DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 71, 0}, + { DBGBUS_DSPP, 71, 1}, + { DBGBUS_DSPP, 71, 2}, + { DBGBUS_DSPP, 71, 3}, + { DBGBUS_DSPP, 71, 4}, + { DBGBUS_DSPP, 71, 5}, + { DBGBUS_DSPP, 71, 6}, + { DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 72, 0}, + { DBGBUS_DSPP, 72, 1}, + { DBGBUS_DSPP, 72, 2}, + { DBGBUS_DSPP, 72, 3}, + { DBGBUS_DSPP, 72, 4}, + { DBGBUS_DSPP, 72, 5}, + { DBGBUS_DSPP, 72, 6}, + { DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 73, 0}, + { DBGBUS_DSPP, 73, 1}, + { DBGBUS_DSPP, 73, 2}, + { DBGBUS_DSPP, 73, 3}, + { DBGBUS_DSPP, 73, 4}, + { DBGBUS_DSPP, 73, 5}, + { DBGBUS_DSPP, 73, 6}, + { DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 74, 0}, + { DBGBUS_DSPP, 74, 1}, + { DBGBUS_DSPP, 74, 2}, + { DBGBUS_DSPP, 74, 3}, + { DBGBUS_DSPP, 74, 4}, + { DBGBUS_DSPP, 74, 5}, + { DBGBUS_DSPP, 74, 6}, + { DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 75, 0}, + { DBGBUS_DSPP, 75, 1}, + { DBGBUS_DSPP, 75, 2}, + { DBGBUS_DSPP, 75, 3}, + { DBGBUS_DSPP, 75, 4}, + { DBGBUS_DSPP, 75, 5}, + { DBGBUS_DSPP, 75, 6}, + { DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 76, 0}, + { DBGBUS_DSPP, 76, 1}, + { DBGBUS_DSPP, 76, 2}, + { DBGBUS_DSPP, 76, 3}, + { DBGBUS_DSPP, 76, 4}, + { DBGBUS_DSPP, 76, 5}, + { DBGBUS_DSPP, 76, 6}, + { DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump }, + + /* LM2 */ + { DBGBUS_DSPP, 77, 0}, + { DBGBUS_DSPP, 77, 1}, + { DBGBUS_DSPP, 77, 2}, + { DBGBUS_DSPP, 77, 3}, + { DBGBUS_DSPP, 77, 4}, + { DBGBUS_DSPP, 77, 5}, + { DBGBUS_DSPP, 77, 6}, + { DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 78, 0}, + { DBGBUS_DSPP, 78, 1}, + { DBGBUS_DSPP, 78, 2}, + { DBGBUS_DSPP, 78, 3}, + { DBGBUS_DSPP, 78, 4}, + { DBGBUS_DSPP, 78, 5}, + { DBGBUS_DSPP, 78, 6}, + { DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 79, 0}, + { DBGBUS_DSPP, 79, 1}, + { DBGBUS_DSPP, 79, 2}, + { DBGBUS_DSPP, 79, 3}, + { DBGBUS_DSPP, 79, 4}, + { DBGBUS_DSPP, 79, 5}, + { DBGBUS_DSPP, 79, 6}, + { DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 80, 0}, + { DBGBUS_DSPP, 80, 1}, + { DBGBUS_DSPP, 80, 2}, + { DBGBUS_DSPP, 80, 3}, + { DBGBUS_DSPP, 80, 4}, + { DBGBUS_DSPP, 80, 5}, + { DBGBUS_DSPP, 80, 6}, + { DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 81, 0}, + { DBGBUS_DSPP, 81, 1}, + { DBGBUS_DSPP, 81, 2}, + { DBGBUS_DSPP, 81, 3}, + { DBGBUS_DSPP, 81, 4}, + { DBGBUS_DSPP, 81, 5}, + { DBGBUS_DSPP, 81, 6}, + { DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 82, 0}, + { DBGBUS_DSPP, 82, 1}, + { DBGBUS_DSPP, 82, 2}, + { DBGBUS_DSPP, 82, 3}, + { DBGBUS_DSPP, 82, 4}, + { DBGBUS_DSPP, 82, 5}, + { DBGBUS_DSPP, 82, 6}, + { DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 83, 0}, + { DBGBUS_DSPP, 83, 1}, + { DBGBUS_DSPP, 83, 2}, + { DBGBUS_DSPP, 83, 3}, + { DBGBUS_DSPP, 83, 4}, + { DBGBUS_DSPP, 83, 5}, + { DBGBUS_DSPP, 83, 6}, + { DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump }, + + /* csc */ + { DBGBUS_SSPP0, 7, 0}, + { DBGBUS_SSPP0, 7, 1}, + { DBGBUS_SSPP0, 27, 0}, + { DBGBUS_SSPP0, 27, 1}, + { DBGBUS_SSPP1, 7, 0}, + { DBGBUS_SSPP1, 7, 1}, + { DBGBUS_SSPP1, 27, 0}, + { DBGBUS_SSPP1, 27, 1}, + + /* pcc */ + { DBGBUS_SSPP0, 3, 3}, + { DBGBUS_SSPP0, 23, 3}, + { DBGBUS_SSPP0, 33, 3}, + { DBGBUS_SSPP0, 43, 3}, + { DBGBUS_SSPP1, 3, 3}, + { DBGBUS_SSPP1, 23, 3}, + { DBGBUS_SSPP1, 33, 3}, + { DBGBUS_SSPP1, 43, 3}, + + /* spa */ + { DBGBUS_SSPP0, 8, 0}, + { DBGBUS_SSPP0, 28, 0}, + { DBGBUS_SSPP1, 8, 0}, + { DBGBUS_SSPP1, 28, 0}, + { DBGBUS_DSPP, 13, 0}, + { DBGBUS_DSPP, 19, 0}, + + /* igc */ + { DBGBUS_SSPP0, 9, 0}, + { DBGBUS_SSPP0, 9, 1}, + { DBGBUS_SSPP0, 9, 3}, + { DBGBUS_SSPP0, 29, 0}, + { DBGBUS_SSPP0, 29, 1}, + { DBGBUS_SSPP0, 29, 3}, + { DBGBUS_SSPP0, 17, 0}, + { DBGBUS_SSPP0, 17, 1}, + { DBGBUS_SSPP0, 17, 3}, + { DBGBUS_SSPP0, 37, 0}, + { DBGBUS_SSPP0, 37, 1}, + { DBGBUS_SSPP0, 37, 3}, + { DBGBUS_SSPP0, 46, 0}, + { DBGBUS_SSPP0, 46, 1}, + { DBGBUS_SSPP0, 46, 3}, + + { DBGBUS_SSPP1, 9, 0}, + { DBGBUS_SSPP1, 9, 1}, + { DBGBUS_SSPP1, 9, 3}, + { DBGBUS_SSPP1, 29, 0}, + { DBGBUS_SSPP1, 29, 1}, + { DBGBUS_SSPP1, 29, 3}, + { DBGBUS_SSPP1, 17, 0}, + { DBGBUS_SSPP1, 17, 1}, + { DBGBUS_SSPP1, 17, 3}, + { DBGBUS_SSPP1, 37, 0}, + { DBGBUS_SSPP1, 37, 1}, + { DBGBUS_SSPP1, 37, 3}, + { DBGBUS_SSPP1, 46, 0}, + { DBGBUS_SSPP1, 46, 1}, + { DBGBUS_SSPP1, 46, 3}, + + { DBGBUS_DSPP, 14, 0}, + { DBGBUS_DSPP, 14, 1}, + { DBGBUS_DSPP, 14, 3}, + { DBGBUS_DSPP, 20, 0}, + { DBGBUS_DSPP, 20, 1}, + { DBGBUS_DSPP, 20, 3}, + + { DBGBUS_PERIPH, 60, 0}, +}; + +static struct dpu_debug_bus_entry dbg_bus_dpu_sdm845[] = { + + /* Unpack 0 sspp 0*/ + { DBGBUS_SSPP0, 50, 2 }, + { DBGBUS_SSPP0, 60, 2 }, + { DBGBUS_SSPP0, 70, 2 }, + + /* Upack 0 sspp 1*/ + { DBGBUS_SSPP1, 50, 2 }, + { DBGBUS_SSPP1, 60, 2 }, + { DBGBUS_SSPP1, 70, 2 }, + + /* scheduler */ + { DBGBUS_DSPP, 130, 0 }, + { DBGBUS_DSPP, 130, 1 }, + { DBGBUS_DSPP, 130, 2 }, + { DBGBUS_DSPP, 130, 3 }, + { DBGBUS_DSPP, 130, 4 }, + { DBGBUS_DSPP, 130, 5 }, + + /* qseed */ + { DBGBUS_SSPP0, 6, 0}, + { DBGBUS_SSPP0, 6, 1}, + { DBGBUS_SSPP0, 26, 0}, + { DBGBUS_SSPP0, 26, 1}, + { DBGBUS_SSPP1, 6, 0}, + { DBGBUS_SSPP1, 6, 1}, + { DBGBUS_SSPP1, 26, 0}, + { DBGBUS_SSPP1, 26, 1}, + + /* scale */ + { DBGBUS_SSPP0, 16, 0}, + { DBGBUS_SSPP0, 16, 1}, + { DBGBUS_SSPP0, 36, 0}, + { DBGBUS_SSPP0, 36, 1}, + { DBGBUS_SSPP1, 16, 0}, + { DBGBUS_SSPP1, 16, 1}, + { DBGBUS_SSPP1, 36, 0}, + { DBGBUS_SSPP1, 36, 1}, + + /* fetch sspp0 */ + + /* vig 0 */ + { DBGBUS_SSPP0, 0, 0 }, + { DBGBUS_SSPP0, 0, 1 }, + { DBGBUS_SSPP0, 0, 2 }, + { DBGBUS_SSPP0, 0, 3 }, + { DBGBUS_SSPP0, 0, 4 }, + { DBGBUS_SSPP0, 0, 5 }, + { DBGBUS_SSPP0, 0, 6 }, + { DBGBUS_SSPP0, 0, 7 }, + + { DBGBUS_SSPP0, 1, 0 }, + { DBGBUS_SSPP0, 1, 1 }, + { DBGBUS_SSPP0, 1, 2 }, + { DBGBUS_SSPP0, 1, 3 }, + { DBGBUS_SSPP0, 1, 4 }, + { DBGBUS_SSPP0, 1, 5 }, + { DBGBUS_SSPP0, 1, 6 }, + { DBGBUS_SSPP0, 1, 7 }, + + { DBGBUS_SSPP0, 2, 0 }, + { DBGBUS_SSPP0, 2, 1 }, + { DBGBUS_SSPP0, 2, 2 }, + { DBGBUS_SSPP0, 2, 3 }, + { DBGBUS_SSPP0, 2, 4 }, + { DBGBUS_SSPP0, 2, 5 }, + { DBGBUS_SSPP0, 2, 6 }, + { DBGBUS_SSPP0, 2, 7 }, + + { DBGBUS_SSPP0, 4, 0 }, + { DBGBUS_SSPP0, 4, 1 }, + { DBGBUS_SSPP0, 4, 2 }, + { DBGBUS_SSPP0, 4, 3 }, + { DBGBUS_SSPP0, 4, 4 }, + { DBGBUS_SSPP0, 4, 5 }, + { DBGBUS_SSPP0, 4, 6 }, + { DBGBUS_SSPP0, 4, 7 }, + + { DBGBUS_SSPP0, 5, 0 }, + { DBGBUS_SSPP0, 5, 1 }, + { DBGBUS_SSPP0, 5, 2 }, + { DBGBUS_SSPP0, 5, 3 }, + { DBGBUS_SSPP0, 5, 4 }, + { DBGBUS_SSPP0, 5, 5 }, + { DBGBUS_SSPP0, 5, 6 }, + { DBGBUS_SSPP0, 5, 7 }, + + /* vig 2 */ + { DBGBUS_SSPP0, 20, 0 }, + { DBGBUS_SSPP0, 20, 1 }, + { DBGBUS_SSPP0, 20, 2 }, + { DBGBUS_SSPP0, 20, 3 }, + { DBGBUS_SSPP0, 20, 4 }, + { DBGBUS_SSPP0, 20, 5 }, + { DBGBUS_SSPP0, 20, 6 }, + { DBGBUS_SSPP0, 20, 7 }, + + { DBGBUS_SSPP0, 21, 0 }, + { DBGBUS_SSPP0, 21, 1 }, + { DBGBUS_SSPP0, 21, 2 }, + { DBGBUS_SSPP0, 21, 3 }, + { DBGBUS_SSPP0, 21, 4 }, + { DBGBUS_SSPP0, 21, 5 }, + { DBGBUS_SSPP0, 21, 6 }, + { DBGBUS_SSPP0, 21, 7 }, + + { DBGBUS_SSPP0, 22, 0 }, + { DBGBUS_SSPP0, 22, 1 }, + { DBGBUS_SSPP0, 22, 2 }, + { DBGBUS_SSPP0, 22, 3 }, + { DBGBUS_SSPP0, 22, 4 }, + { DBGBUS_SSPP0, 22, 5 }, + { DBGBUS_SSPP0, 22, 6 }, + { DBGBUS_SSPP0, 22, 7 }, + + { DBGBUS_SSPP0, 24, 0 }, + { DBGBUS_SSPP0, 24, 1 }, + { DBGBUS_SSPP0, 24, 2 }, + { DBGBUS_SSPP0, 24, 3 }, + { DBGBUS_SSPP0, 24, 4 }, + { DBGBUS_SSPP0, 24, 5 }, + { DBGBUS_SSPP0, 24, 6 }, + { DBGBUS_SSPP0, 24, 7 }, + + { DBGBUS_SSPP0, 25, 0 }, + { DBGBUS_SSPP0, 25, 1 }, + { DBGBUS_SSPP0, 25, 2 }, + { DBGBUS_SSPP0, 25, 3 }, + { DBGBUS_SSPP0, 25, 4 }, + { DBGBUS_SSPP0, 25, 5 }, + { DBGBUS_SSPP0, 25, 6 }, + { DBGBUS_SSPP0, 25, 7 }, + + /* dma 2 */ + { DBGBUS_SSPP0, 30, 0 }, + { DBGBUS_SSPP0, 30, 1 }, + { DBGBUS_SSPP0, 30, 2 }, + { DBGBUS_SSPP0, 30, 3 }, + { DBGBUS_SSPP0, 30, 4 }, + { DBGBUS_SSPP0, 30, 5 }, + { DBGBUS_SSPP0, 30, 6 }, + { DBGBUS_SSPP0, 30, 7 }, + + { DBGBUS_SSPP0, 31, 0 }, + { DBGBUS_SSPP0, 31, 1 }, + { DBGBUS_SSPP0, 31, 2 }, + { DBGBUS_SSPP0, 31, 3 }, + { DBGBUS_SSPP0, 31, 4 }, + { DBGBUS_SSPP0, 31, 5 }, + { DBGBUS_SSPP0, 31, 6 }, + { DBGBUS_SSPP0, 31, 7 }, + + { DBGBUS_SSPP0, 32, 0 }, + { DBGBUS_SSPP0, 32, 1 }, + { DBGBUS_SSPP0, 32, 2 }, + { DBGBUS_SSPP0, 32, 3 }, + { DBGBUS_SSPP0, 32, 4 }, + { DBGBUS_SSPP0, 32, 5 }, + { DBGBUS_SSPP0, 32, 6 }, + { DBGBUS_SSPP0, 32, 7 }, + + { DBGBUS_SSPP0, 33, 0 }, + { DBGBUS_SSPP0, 33, 1 }, + { DBGBUS_SSPP0, 33, 2 }, + { DBGBUS_SSPP0, 33, 3 }, + { DBGBUS_SSPP0, 33, 4 }, + { DBGBUS_SSPP0, 33, 5 }, + { DBGBUS_SSPP0, 33, 6 }, + { DBGBUS_SSPP0, 33, 7 }, + + { DBGBUS_SSPP0, 34, 0 }, + { DBGBUS_SSPP0, 34, 1 }, + { DBGBUS_SSPP0, 34, 2 }, + { DBGBUS_SSPP0, 34, 3 }, + { DBGBUS_SSPP0, 34, 4 }, + { DBGBUS_SSPP0, 34, 5 }, + { DBGBUS_SSPP0, 34, 6 }, + { DBGBUS_SSPP0, 34, 7 }, + + { DBGBUS_SSPP0, 35, 0 }, + { DBGBUS_SSPP0, 35, 1 }, + { DBGBUS_SSPP0, 35, 2 }, + { DBGBUS_SSPP0, 35, 3 }, + + /* dma 0 */ + { DBGBUS_SSPP0, 40, 0 }, + { DBGBUS_SSPP0, 40, 1 }, + { DBGBUS_SSPP0, 40, 2 }, + { DBGBUS_SSPP0, 40, 3 }, + { DBGBUS_SSPP0, 40, 4 }, + { DBGBUS_SSPP0, 40, 5 }, + { DBGBUS_SSPP0, 40, 6 }, + { DBGBUS_SSPP0, 40, 7 }, + + { DBGBUS_SSPP0, 41, 0 }, + { DBGBUS_SSPP0, 41, 1 }, + { DBGBUS_SSPP0, 41, 2 }, + { DBGBUS_SSPP0, 41, 3 }, + { DBGBUS_SSPP0, 41, 4 }, + { DBGBUS_SSPP0, 41, 5 }, + { DBGBUS_SSPP0, 41, 6 }, + { DBGBUS_SSPP0, 41, 7 }, + + { DBGBUS_SSPP0, 42, 0 }, + { DBGBUS_SSPP0, 42, 1 }, + { DBGBUS_SSPP0, 42, 2 }, + { DBGBUS_SSPP0, 42, 3 }, + { DBGBUS_SSPP0, 42, 4 }, + { DBGBUS_SSPP0, 42, 5 }, + { DBGBUS_SSPP0, 42, 6 }, + { DBGBUS_SSPP0, 42, 7 }, + + { DBGBUS_SSPP0, 44, 0 }, + { DBGBUS_SSPP0, 44, 1 }, + { DBGBUS_SSPP0, 44, 2 }, + { DBGBUS_SSPP0, 44, 3 }, + { DBGBUS_SSPP0, 44, 4 }, + { DBGBUS_SSPP0, 44, 5 }, + { DBGBUS_SSPP0, 44, 6 }, + { DBGBUS_SSPP0, 44, 7 }, + + { DBGBUS_SSPP0, 45, 0 }, + { DBGBUS_SSPP0, 45, 1 }, + { DBGBUS_SSPP0, 45, 2 }, + { DBGBUS_SSPP0, 45, 3 }, + { DBGBUS_SSPP0, 45, 4 }, + { DBGBUS_SSPP0, 45, 5 }, + { DBGBUS_SSPP0, 45, 6 }, + { DBGBUS_SSPP0, 45, 7 }, + + /* fetch sspp1 */ + /* vig 1 */ + { DBGBUS_SSPP1, 0, 0 }, + { DBGBUS_SSPP1, 0, 1 }, + { DBGBUS_SSPP1, 0, 2 }, + { DBGBUS_SSPP1, 0, 3 }, + { DBGBUS_SSPP1, 0, 4 }, + { DBGBUS_SSPP1, 0, 5 }, + { DBGBUS_SSPP1, 0, 6 }, + { DBGBUS_SSPP1, 0, 7 }, + + { DBGBUS_SSPP1, 1, 0 }, + { DBGBUS_SSPP1, 1, 1 }, + { DBGBUS_SSPP1, 1, 2 }, + { DBGBUS_SSPP1, 1, 3 }, + { DBGBUS_SSPP1, 1, 4 }, + { DBGBUS_SSPP1, 1, 5 }, + { DBGBUS_SSPP1, 1, 6 }, + { DBGBUS_SSPP1, 1, 7 }, + + { DBGBUS_SSPP1, 2, 0 }, + { DBGBUS_SSPP1, 2, 1 }, + { DBGBUS_SSPP1, 2, 2 }, + { DBGBUS_SSPP1, 2, 3 }, + { DBGBUS_SSPP1, 2, 4 }, + { DBGBUS_SSPP1, 2, 5 }, + { DBGBUS_SSPP1, 2, 6 }, + { DBGBUS_SSPP1, 2, 7 }, + + { DBGBUS_SSPP1, 4, 0 }, + { DBGBUS_SSPP1, 4, 1 }, + { DBGBUS_SSPP1, 4, 2 }, + { DBGBUS_SSPP1, 4, 3 }, + { DBGBUS_SSPP1, 4, 4 }, + { DBGBUS_SSPP1, 4, 5 }, + { DBGBUS_SSPP1, 4, 6 }, + { DBGBUS_SSPP1, 4, 7 }, + + { DBGBUS_SSPP1, 5, 0 }, + { DBGBUS_SSPP1, 5, 1 }, + { DBGBUS_SSPP1, 5, 2 }, + { DBGBUS_SSPP1, 5, 3 }, + { DBGBUS_SSPP1, 5, 4 }, + { DBGBUS_SSPP1, 5, 5 }, + { DBGBUS_SSPP1, 5, 6 }, + { DBGBUS_SSPP1, 5, 7 }, + + /* vig 3 */ + { DBGBUS_SSPP1, 20, 0 }, + { DBGBUS_SSPP1, 20, 1 }, + { DBGBUS_SSPP1, 20, 2 }, + { DBGBUS_SSPP1, 20, 3 }, + { DBGBUS_SSPP1, 20, 4 }, + { DBGBUS_SSPP1, 20, 5 }, + { DBGBUS_SSPP1, 20, 6 }, + { DBGBUS_SSPP1, 20, 7 }, + + { DBGBUS_SSPP1, 21, 0 }, + { DBGBUS_SSPP1, 21, 1 }, + { DBGBUS_SSPP1, 21, 2 }, + { DBGBUS_SSPP1, 21, 3 }, + { DBGBUS_SSPP1, 21, 4 }, + { DBGBUS_SSPP1, 21, 5 }, + { DBGBUS_SSPP1, 21, 6 }, + { DBGBUS_SSPP1, 21, 7 }, + + { DBGBUS_SSPP1, 22, 0 }, + { DBGBUS_SSPP1, 22, 1 }, + { DBGBUS_SSPP1, 22, 2 }, + { DBGBUS_SSPP1, 22, 3 }, + { DBGBUS_SSPP1, 22, 4 }, + { DBGBUS_SSPP1, 22, 5 }, + { DBGBUS_SSPP1, 22, 6 }, + { DBGBUS_SSPP1, 22, 7 }, + + { DBGBUS_SSPP1, 24, 0 }, + { DBGBUS_SSPP1, 24, 1 }, + { DBGBUS_SSPP1, 24, 2 }, + { DBGBUS_SSPP1, 24, 3 }, + { DBGBUS_SSPP1, 24, 4 }, + { DBGBUS_SSPP1, 24, 5 }, + { DBGBUS_SSPP1, 24, 6 }, + { DBGBUS_SSPP1, 24, 7 }, + + { DBGBUS_SSPP1, 25, 0 }, + { DBGBUS_SSPP1, 25, 1 }, + { DBGBUS_SSPP1, 25, 2 }, + { DBGBUS_SSPP1, 25, 3 }, + { DBGBUS_SSPP1, 25, 4 }, + { DBGBUS_SSPP1, 25, 5 }, + { DBGBUS_SSPP1, 25, 6 }, + { DBGBUS_SSPP1, 25, 7 }, + + /* dma 3 */ + { DBGBUS_SSPP1, 30, 0 }, + { DBGBUS_SSPP1, 30, 1 }, + { DBGBUS_SSPP1, 30, 2 }, + { DBGBUS_SSPP1, 30, 3 }, + { DBGBUS_SSPP1, 30, 4 }, + { DBGBUS_SSPP1, 30, 5 }, + { DBGBUS_SSPP1, 30, 6 }, + { DBGBUS_SSPP1, 30, 7 }, + + { DBGBUS_SSPP1, 31, 0 }, + { DBGBUS_SSPP1, 31, 1 }, + { DBGBUS_SSPP1, 31, 2 }, + { DBGBUS_SSPP1, 31, 3 }, + { DBGBUS_SSPP1, 31, 4 }, + { DBGBUS_SSPP1, 31, 5 }, + { DBGBUS_SSPP1, 31, 6 }, + { DBGBUS_SSPP1, 31, 7 }, + + { DBGBUS_SSPP1, 32, 0 }, + { DBGBUS_SSPP1, 32, 1 }, + { DBGBUS_SSPP1, 32, 2 }, + { DBGBUS_SSPP1, 32, 3 }, + { DBGBUS_SSPP1, 32, 4 }, + { DBGBUS_SSPP1, 32, 5 }, + { DBGBUS_SSPP1, 32, 6 }, + { DBGBUS_SSPP1, 32, 7 }, + + { DBGBUS_SSPP1, 33, 0 }, + { DBGBUS_SSPP1, 33, 1 }, + { DBGBUS_SSPP1, 33, 2 }, + { DBGBUS_SSPP1, 33, 3 }, + { DBGBUS_SSPP1, 33, 4 }, + { DBGBUS_SSPP1, 33, 5 }, + { DBGBUS_SSPP1, 33, 6 }, + { DBGBUS_SSPP1, 33, 7 }, + + { DBGBUS_SSPP1, 34, 0 }, + { DBGBUS_SSPP1, 34, 1 }, + { DBGBUS_SSPP1, 34, 2 }, + { DBGBUS_SSPP1, 34, 3 }, + { DBGBUS_SSPP1, 34, 4 }, + { DBGBUS_SSPP1, 34, 5 }, + { DBGBUS_SSPP1, 34, 6 }, + { DBGBUS_SSPP1, 34, 7 }, + + { DBGBUS_SSPP1, 35, 0 }, + { DBGBUS_SSPP1, 35, 1 }, + { DBGBUS_SSPP1, 35, 2 }, + + /* dma 1 */ + { DBGBUS_SSPP1, 40, 0 }, + { DBGBUS_SSPP1, 40, 1 }, + { DBGBUS_SSPP1, 40, 2 }, + { DBGBUS_SSPP1, 40, 3 }, + { DBGBUS_SSPP1, 40, 4 }, + { DBGBUS_SSPP1, 40, 5 }, + { DBGBUS_SSPP1, 40, 6 }, + { DBGBUS_SSPP1, 40, 7 }, + + { DBGBUS_SSPP1, 41, 0 }, + { DBGBUS_SSPP1, 41, 1 }, + { DBGBUS_SSPP1, 41, 2 }, + { DBGBUS_SSPP1, 41, 3 }, + { DBGBUS_SSPP1, 41, 4 }, + { DBGBUS_SSPP1, 41, 5 }, + { DBGBUS_SSPP1, 41, 6 }, + { DBGBUS_SSPP1, 41, 7 }, + + { DBGBUS_SSPP1, 42, 0 }, + { DBGBUS_SSPP1, 42, 1 }, + { DBGBUS_SSPP1, 42, 2 }, + { DBGBUS_SSPP1, 42, 3 }, + { DBGBUS_SSPP1, 42, 4 }, + { DBGBUS_SSPP1, 42, 5 }, + { DBGBUS_SSPP1, 42, 6 }, + { DBGBUS_SSPP1, 42, 7 }, + + { DBGBUS_SSPP1, 44, 0 }, + { DBGBUS_SSPP1, 44, 1 }, + { DBGBUS_SSPP1, 44, 2 }, + { DBGBUS_SSPP1, 44, 3 }, + { DBGBUS_SSPP1, 44, 4 }, + { DBGBUS_SSPP1, 44, 5 }, + { DBGBUS_SSPP1, 44, 6 }, + { DBGBUS_SSPP1, 44, 7 }, + + { DBGBUS_SSPP1, 45, 0 }, + { DBGBUS_SSPP1, 45, 1 }, + { DBGBUS_SSPP1, 45, 2 }, + { DBGBUS_SSPP1, 45, 3 }, + { DBGBUS_SSPP1, 45, 4 }, + { DBGBUS_SSPP1, 45, 5 }, + { DBGBUS_SSPP1, 45, 6 }, + { DBGBUS_SSPP1, 45, 7 }, + + /* dspp */ + { DBGBUS_DSPP, 13, 0 }, + { DBGBUS_DSPP, 19, 0 }, + { DBGBUS_DSPP, 14, 0 }, + { DBGBUS_DSPP, 14, 1 }, + { DBGBUS_DSPP, 14, 3 }, + { DBGBUS_DSPP, 20, 0 }, + { DBGBUS_DSPP, 20, 1 }, + { DBGBUS_DSPP, 20, 3 }, + + /* ppb_0 */ + { DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump }, + { DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump }, + + /* ppb_1 */ + { DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump }, + { DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump }, + + /* lm_lut */ + { DBGBUS_DSPP, 109, 0 }, + { DBGBUS_DSPP, 105, 0 }, + { DBGBUS_DSPP, 103, 0 }, + + /* crossbar */ + { DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump }, + + /* rotator */ + { DBGBUS_DSPP, 9, 0}, + + /* blend */ + /* LM0 */ + { DBGBUS_DSPP, 63, 1}, + { DBGBUS_DSPP, 63, 2}, + { DBGBUS_DSPP, 63, 3}, + { DBGBUS_DSPP, 63, 4}, + { DBGBUS_DSPP, 63, 5}, + { DBGBUS_DSPP, 63, 6}, + { DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 64, 1}, + { DBGBUS_DSPP, 64, 2}, + { DBGBUS_DSPP, 64, 3}, + { DBGBUS_DSPP, 64, 4}, + { DBGBUS_DSPP, 64, 5}, + { DBGBUS_DSPP, 64, 6}, + { DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 65, 1}, + { DBGBUS_DSPP, 65, 2}, + { DBGBUS_DSPP, 65, 3}, + { DBGBUS_DSPP, 65, 4}, + { DBGBUS_DSPP, 65, 5}, + { DBGBUS_DSPP, 65, 6}, + { DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 66, 1}, + { DBGBUS_DSPP, 66, 2}, + { DBGBUS_DSPP, 66, 3}, + { DBGBUS_DSPP, 66, 4}, + { DBGBUS_DSPP, 66, 5}, + { DBGBUS_DSPP, 66, 6}, + { DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 67, 1}, + { DBGBUS_DSPP, 67, 2}, + { DBGBUS_DSPP, 67, 3}, + { DBGBUS_DSPP, 67, 4}, + { DBGBUS_DSPP, 67, 5}, + { DBGBUS_DSPP, 67, 6}, + { DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 68, 1}, + { DBGBUS_DSPP, 68, 2}, + { DBGBUS_DSPP, 68, 3}, + { DBGBUS_DSPP, 68, 4}, + { DBGBUS_DSPP, 68, 5}, + { DBGBUS_DSPP, 68, 6}, + { DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 69, 1}, + { DBGBUS_DSPP, 69, 2}, + { DBGBUS_DSPP, 69, 3}, + { DBGBUS_DSPP, 69, 4}, + { DBGBUS_DSPP, 69, 5}, + { DBGBUS_DSPP, 69, 6}, + { DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 84, 1}, + { DBGBUS_DSPP, 84, 2}, + { DBGBUS_DSPP, 84, 3}, + { DBGBUS_DSPP, 84, 4}, + { DBGBUS_DSPP, 84, 5}, + { DBGBUS_DSPP, 84, 6}, + { DBGBUS_DSPP, 84, 7, _dpu_debug_bus_lm_dump }, + + + { DBGBUS_DSPP, 85, 1}, + { DBGBUS_DSPP, 85, 2}, + { DBGBUS_DSPP, 85, 3}, + { DBGBUS_DSPP, 85, 4}, + { DBGBUS_DSPP, 85, 5}, + { DBGBUS_DSPP, 85, 6}, + { DBGBUS_DSPP, 85, 7, _dpu_debug_bus_lm_dump }, + + + { DBGBUS_DSPP, 86, 1}, + { DBGBUS_DSPP, 86, 2}, + { DBGBUS_DSPP, 86, 3}, + { DBGBUS_DSPP, 86, 4}, + { DBGBUS_DSPP, 86, 5}, + { DBGBUS_DSPP, 86, 6}, + { DBGBUS_DSPP, 86, 7, _dpu_debug_bus_lm_dump }, + + + { DBGBUS_DSPP, 87, 1}, + { DBGBUS_DSPP, 87, 2}, + { DBGBUS_DSPP, 87, 3}, + { DBGBUS_DSPP, 87, 4}, + { DBGBUS_DSPP, 87, 5}, + { DBGBUS_DSPP, 87, 6}, + { DBGBUS_DSPP, 87, 7, _dpu_debug_bus_lm_dump }, + + /* LM1 */ + { DBGBUS_DSPP, 70, 1}, + { DBGBUS_DSPP, 70, 2}, + { DBGBUS_DSPP, 70, 3}, + { DBGBUS_DSPP, 70, 4}, + { DBGBUS_DSPP, 70, 5}, + { DBGBUS_DSPP, 70, 6}, + { DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 71, 1}, + { DBGBUS_DSPP, 71, 2}, + { DBGBUS_DSPP, 71, 3}, + { DBGBUS_DSPP, 71, 4}, + { DBGBUS_DSPP, 71, 5}, + { DBGBUS_DSPP, 71, 6}, + { DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 72, 1}, + { DBGBUS_DSPP, 72, 2}, + { DBGBUS_DSPP, 72, 3}, + { DBGBUS_DSPP, 72, 4}, + { DBGBUS_DSPP, 72, 5}, + { DBGBUS_DSPP, 72, 6}, + { DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 73, 1}, + { DBGBUS_DSPP, 73, 2}, + { DBGBUS_DSPP, 73, 3}, + { DBGBUS_DSPP, 73, 4}, + { DBGBUS_DSPP, 73, 5}, + { DBGBUS_DSPP, 73, 6}, + { DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 74, 1}, + { DBGBUS_DSPP, 74, 2}, + { DBGBUS_DSPP, 74, 3}, + { DBGBUS_DSPP, 74, 4}, + { DBGBUS_DSPP, 74, 5}, + { DBGBUS_DSPP, 74, 6}, + { DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 75, 1}, + { DBGBUS_DSPP, 75, 2}, + { DBGBUS_DSPP, 75, 3}, + { DBGBUS_DSPP, 75, 4}, + { DBGBUS_DSPP, 75, 5}, + { DBGBUS_DSPP, 75, 6}, + { DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 76, 1}, + { DBGBUS_DSPP, 76, 2}, + { DBGBUS_DSPP, 76, 3}, + { DBGBUS_DSPP, 76, 4}, + { DBGBUS_DSPP, 76, 5}, + { DBGBUS_DSPP, 76, 6}, + { DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 88, 1}, + { DBGBUS_DSPP, 88, 2}, + { DBGBUS_DSPP, 88, 3}, + { DBGBUS_DSPP, 88, 4}, + { DBGBUS_DSPP, 88, 5}, + { DBGBUS_DSPP, 88, 6}, + { DBGBUS_DSPP, 88, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 89, 1}, + { DBGBUS_DSPP, 89, 2}, + { DBGBUS_DSPP, 89, 3}, + { DBGBUS_DSPP, 89, 4}, + { DBGBUS_DSPP, 89, 5}, + { DBGBUS_DSPP, 89, 6}, + { DBGBUS_DSPP, 89, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 90, 1}, + { DBGBUS_DSPP, 90, 2}, + { DBGBUS_DSPP, 90, 3}, + { DBGBUS_DSPP, 90, 4}, + { DBGBUS_DSPP, 90, 5}, + { DBGBUS_DSPP, 90, 6}, + { DBGBUS_DSPP, 90, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 91, 1}, + { DBGBUS_DSPP, 91, 2}, + { DBGBUS_DSPP, 91, 3}, + { DBGBUS_DSPP, 91, 4}, + { DBGBUS_DSPP, 91, 5}, + { DBGBUS_DSPP, 91, 6}, + { DBGBUS_DSPP, 91, 7, _dpu_debug_bus_lm_dump }, + + /* LM2 */ + { DBGBUS_DSPP, 77, 0}, + { DBGBUS_DSPP, 77, 1}, + { DBGBUS_DSPP, 77, 2}, + { DBGBUS_DSPP, 77, 3}, + { DBGBUS_DSPP, 77, 4}, + { DBGBUS_DSPP, 77, 5}, + { DBGBUS_DSPP, 77, 6}, + { DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 78, 0}, + { DBGBUS_DSPP, 78, 1}, + { DBGBUS_DSPP, 78, 2}, + { DBGBUS_DSPP, 78, 3}, + { DBGBUS_DSPP, 78, 4}, + { DBGBUS_DSPP, 78, 5}, + { DBGBUS_DSPP, 78, 6}, + { DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 79, 0}, + { DBGBUS_DSPP, 79, 1}, + { DBGBUS_DSPP, 79, 2}, + { DBGBUS_DSPP, 79, 3}, + { DBGBUS_DSPP, 79, 4}, + { DBGBUS_DSPP, 79, 5}, + { DBGBUS_DSPP, 79, 6}, + { DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 80, 0}, + { DBGBUS_DSPP, 80, 1}, + { DBGBUS_DSPP, 80, 2}, + { DBGBUS_DSPP, 80, 3}, + { DBGBUS_DSPP, 80, 4}, + { DBGBUS_DSPP, 80, 5}, + { DBGBUS_DSPP, 80, 6}, + { DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 81, 0}, + { DBGBUS_DSPP, 81, 1}, + { DBGBUS_DSPP, 81, 2}, + { DBGBUS_DSPP, 81, 3}, + { DBGBUS_DSPP, 81, 4}, + { DBGBUS_DSPP, 81, 5}, + { DBGBUS_DSPP, 81, 6}, + { DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 82, 0}, + { DBGBUS_DSPP, 82, 1}, + { DBGBUS_DSPP, 82, 2}, + { DBGBUS_DSPP, 82, 3}, + { DBGBUS_DSPP, 82, 4}, + { DBGBUS_DSPP, 82, 5}, + { DBGBUS_DSPP, 82, 6}, + { DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 83, 0}, + { DBGBUS_DSPP, 83, 1}, + { DBGBUS_DSPP, 83, 2}, + { DBGBUS_DSPP, 83, 3}, + { DBGBUS_DSPP, 83, 4}, + { DBGBUS_DSPP, 83, 5}, + { DBGBUS_DSPP, 83, 6}, + { DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 92, 1}, + { DBGBUS_DSPP, 92, 2}, + { DBGBUS_DSPP, 92, 3}, + { DBGBUS_DSPP, 92, 4}, + { DBGBUS_DSPP, 92, 5}, + { DBGBUS_DSPP, 92, 6}, + { DBGBUS_DSPP, 92, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 93, 1}, + { DBGBUS_DSPP, 93, 2}, + { DBGBUS_DSPP, 93, 3}, + { DBGBUS_DSPP, 93, 4}, + { DBGBUS_DSPP, 93, 5}, + { DBGBUS_DSPP, 93, 6}, + { DBGBUS_DSPP, 93, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 94, 1}, + { DBGBUS_DSPP, 94, 2}, + { DBGBUS_DSPP, 94, 3}, + { DBGBUS_DSPP, 94, 4}, + { DBGBUS_DSPP, 94, 5}, + { DBGBUS_DSPP, 94, 6}, + { DBGBUS_DSPP, 94, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 95, 1}, + { DBGBUS_DSPP, 95, 2}, + { DBGBUS_DSPP, 95, 3}, + { DBGBUS_DSPP, 95, 4}, + { DBGBUS_DSPP, 95, 5}, + { DBGBUS_DSPP, 95, 6}, + { DBGBUS_DSPP, 95, 7, _dpu_debug_bus_lm_dump }, + + /* LM5 */ + { DBGBUS_DSPP, 110, 1}, + { DBGBUS_DSPP, 110, 2}, + { DBGBUS_DSPP, 110, 3}, + { DBGBUS_DSPP, 110, 4}, + { DBGBUS_DSPP, 110, 5}, + { DBGBUS_DSPP, 110, 6}, + { DBGBUS_DSPP, 110, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 111, 1}, + { DBGBUS_DSPP, 111, 2}, + { DBGBUS_DSPP, 111, 3}, + { DBGBUS_DSPP, 111, 4}, + { DBGBUS_DSPP, 111, 5}, + { DBGBUS_DSPP, 111, 6}, + { DBGBUS_DSPP, 111, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 112, 1}, + { DBGBUS_DSPP, 112, 2}, + { DBGBUS_DSPP, 112, 3}, + { DBGBUS_DSPP, 112, 4}, + { DBGBUS_DSPP, 112, 5}, + { DBGBUS_DSPP, 112, 6}, + { DBGBUS_DSPP, 112, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 113, 1}, + { DBGBUS_DSPP, 113, 2}, + { DBGBUS_DSPP, 113, 3}, + { DBGBUS_DSPP, 113, 4}, + { DBGBUS_DSPP, 113, 5}, + { DBGBUS_DSPP, 113, 6}, + { DBGBUS_DSPP, 113, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 114, 1}, + { DBGBUS_DSPP, 114, 2}, + { DBGBUS_DSPP, 114, 3}, + { DBGBUS_DSPP, 114, 4}, + { DBGBUS_DSPP, 114, 5}, + { DBGBUS_DSPP, 114, 6}, + { DBGBUS_DSPP, 114, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 115, 1}, + { DBGBUS_DSPP, 115, 2}, + { DBGBUS_DSPP, 115, 3}, + { DBGBUS_DSPP, 115, 4}, + { DBGBUS_DSPP, 115, 5}, + { DBGBUS_DSPP, 115, 6}, + { DBGBUS_DSPP, 115, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 116, 1}, + { DBGBUS_DSPP, 116, 2}, + { DBGBUS_DSPP, 116, 3}, + { DBGBUS_DSPP, 116, 4}, + { DBGBUS_DSPP, 116, 5}, + { DBGBUS_DSPP, 116, 6}, + { DBGBUS_DSPP, 116, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 117, 1}, + { DBGBUS_DSPP, 117, 2}, + { DBGBUS_DSPP, 117, 3}, + { DBGBUS_DSPP, 117, 4}, + { DBGBUS_DSPP, 117, 5}, + { DBGBUS_DSPP, 117, 6}, + { DBGBUS_DSPP, 117, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 118, 1}, + { DBGBUS_DSPP, 118, 2}, + { DBGBUS_DSPP, 118, 3}, + { DBGBUS_DSPP, 118, 4}, + { DBGBUS_DSPP, 118, 5}, + { DBGBUS_DSPP, 118, 6}, + { DBGBUS_DSPP, 118, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 119, 1}, + { DBGBUS_DSPP, 119, 2}, + { DBGBUS_DSPP, 119, 3}, + { DBGBUS_DSPP, 119, 4}, + { DBGBUS_DSPP, 119, 5}, + { DBGBUS_DSPP, 119, 6}, + { DBGBUS_DSPP, 119, 7, _dpu_debug_bus_lm_dump }, + + { DBGBUS_DSPP, 120, 1}, + { DBGBUS_DSPP, 120, 2}, + { DBGBUS_DSPP, 120, 3}, + { DBGBUS_DSPP, 120, 4}, + { DBGBUS_DSPP, 120, 5}, + { DBGBUS_DSPP, 120, 6}, + { DBGBUS_DSPP, 120, 7, _dpu_debug_bus_lm_dump }, + + /* csc */ + { DBGBUS_SSPP0, 7, 0}, + { DBGBUS_SSPP0, 7, 1}, + { DBGBUS_SSPP0, 27, 0}, + { DBGBUS_SSPP0, 27, 1}, + { DBGBUS_SSPP1, 7, 0}, + { DBGBUS_SSPP1, 7, 1}, + { DBGBUS_SSPP1, 27, 0}, + { DBGBUS_SSPP1, 27, 1}, + + /* pcc */ + { DBGBUS_SSPP0, 3, 3}, + { DBGBUS_SSPP0, 23, 3}, + { DBGBUS_SSPP0, 33, 3}, + { DBGBUS_SSPP0, 43, 3}, + { DBGBUS_SSPP1, 3, 3}, + { DBGBUS_SSPP1, 23, 3}, + { DBGBUS_SSPP1, 33, 3}, + { DBGBUS_SSPP1, 43, 3}, + + /* spa */ + { DBGBUS_SSPP0, 8, 0}, + { DBGBUS_SSPP0, 28, 0}, + { DBGBUS_SSPP1, 8, 0}, + { DBGBUS_SSPP1, 28, 0}, + { DBGBUS_DSPP, 13, 0}, + { DBGBUS_DSPP, 19, 0}, + + /* igc */ + { DBGBUS_SSPP0, 17, 0}, + { DBGBUS_SSPP0, 17, 1}, + { DBGBUS_SSPP0, 17, 3}, + { DBGBUS_SSPP0, 37, 0}, + { DBGBUS_SSPP0, 37, 1}, + { DBGBUS_SSPP0, 37, 3}, + { DBGBUS_SSPP0, 46, 0}, + { DBGBUS_SSPP0, 46, 1}, + { DBGBUS_SSPP0, 46, 3}, + + { DBGBUS_SSPP1, 17, 0}, + { DBGBUS_SSPP1, 17, 1}, + { DBGBUS_SSPP1, 17, 3}, + { DBGBUS_SSPP1, 37, 0}, + { DBGBUS_SSPP1, 37, 1}, + { DBGBUS_SSPP1, 37, 3}, + { DBGBUS_SSPP1, 46, 0}, + { DBGBUS_SSPP1, 46, 1}, + { DBGBUS_SSPP1, 46, 3}, + + { DBGBUS_DSPP, 14, 0}, + { DBGBUS_DSPP, 14, 1}, + { DBGBUS_DSPP, 14, 3}, + { DBGBUS_DSPP, 20, 0}, + { DBGBUS_DSPP, 20, 1}, + { DBGBUS_DSPP, 20, 3}, + + /* intf0-3 */ + { DBGBUS_PERIPH, 0, 0}, + { DBGBUS_PERIPH, 1, 0}, + { DBGBUS_PERIPH, 2, 0}, + { DBGBUS_PERIPH, 3, 0}, + + /* te counter wrapper */ + { DBGBUS_PERIPH, 60, 0}, + + /* dsc0 */ + { DBGBUS_PERIPH, 47, 0}, + { DBGBUS_PERIPH, 47, 1}, + { DBGBUS_PERIPH, 47, 2}, + { DBGBUS_PERIPH, 47, 3}, + { DBGBUS_PERIPH, 47, 4}, + { DBGBUS_PERIPH, 47, 5}, + { DBGBUS_PERIPH, 47, 6}, + { DBGBUS_PERIPH, 47, 7}, + + /* dsc1 */ + { DBGBUS_PERIPH, 48, 0}, + { DBGBUS_PERIPH, 48, 1}, + { DBGBUS_PERIPH, 48, 2}, + { DBGBUS_PERIPH, 48, 3}, + { DBGBUS_PERIPH, 48, 4}, + { DBGBUS_PERIPH, 48, 5}, + { DBGBUS_PERIPH, 48, 6}, + { DBGBUS_PERIPH, 48, 7}, + + /* dsc2 */ + { DBGBUS_PERIPH, 51, 0}, + { DBGBUS_PERIPH, 51, 1}, + { DBGBUS_PERIPH, 51, 2}, + { DBGBUS_PERIPH, 51, 3}, + { DBGBUS_PERIPH, 51, 4}, + { DBGBUS_PERIPH, 51, 5}, + { DBGBUS_PERIPH, 51, 6}, + { DBGBUS_PERIPH, 51, 7}, + + /* dsc3 */ + { DBGBUS_PERIPH, 52, 0}, + { DBGBUS_PERIPH, 52, 1}, + { DBGBUS_PERIPH, 52, 2}, + { DBGBUS_PERIPH, 52, 3}, + { DBGBUS_PERIPH, 52, 4}, + { DBGBUS_PERIPH, 52, 5}, + { DBGBUS_PERIPH, 52, 6}, + { DBGBUS_PERIPH, 52, 7}, + + /* tear-check */ + { DBGBUS_PERIPH, 63, 0 }, + { DBGBUS_PERIPH, 64, 0 }, + { DBGBUS_PERIPH, 65, 0 }, + { DBGBUS_PERIPH, 73, 0 }, + { DBGBUS_PERIPH, 74, 0 }, + + /* cdwn */ + { DBGBUS_PERIPH, 80, 0}, + { DBGBUS_PERIPH, 80, 1}, + { DBGBUS_PERIPH, 80, 2}, + + { DBGBUS_PERIPH, 81, 0}, + { DBGBUS_PERIPH, 81, 1}, + { DBGBUS_PERIPH, 81, 2}, + + { DBGBUS_PERIPH, 82, 0}, + { DBGBUS_PERIPH, 82, 1}, + { DBGBUS_PERIPH, 82, 2}, + { DBGBUS_PERIPH, 82, 3}, + { DBGBUS_PERIPH, 82, 4}, + { DBGBUS_PERIPH, 82, 5}, + { DBGBUS_PERIPH, 82, 6}, + { DBGBUS_PERIPH, 82, 7}, + + /* hdmi */ + { DBGBUS_PERIPH, 68, 0}, + { DBGBUS_PERIPH, 68, 1}, + { DBGBUS_PERIPH, 68, 2}, + { DBGBUS_PERIPH, 68, 3}, + { DBGBUS_PERIPH, 68, 4}, + { DBGBUS_PERIPH, 68, 5}, + + /* edp */ + { DBGBUS_PERIPH, 69, 0}, + { DBGBUS_PERIPH, 69, 1}, + { DBGBUS_PERIPH, 69, 2}, + { DBGBUS_PERIPH, 69, 3}, + { DBGBUS_PERIPH, 69, 4}, + { DBGBUS_PERIPH, 69, 5}, + + /* dsi0 */ + { DBGBUS_PERIPH, 70, 0}, + { DBGBUS_PERIPH, 70, 1}, + { DBGBUS_PERIPH, 70, 2}, + { DBGBUS_PERIPH, 70, 3}, + { DBGBUS_PERIPH, 70, 4}, + { DBGBUS_PERIPH, 70, 5}, + + /* dsi1 */ + { DBGBUS_PERIPH, 71, 0}, + { DBGBUS_PERIPH, 71, 1}, + { DBGBUS_PERIPH, 71, 2}, + { DBGBUS_PERIPH, 71, 3}, + { DBGBUS_PERIPH, 71, 4}, + { DBGBUS_PERIPH, 71, 5}, +}; + +static struct vbif_debug_bus_entry vbif_dbg_bus_msm8998[] = { + {0x214, 0x21c, 16, 2, 0x0, 0xd}, /* arb clients */ + {0x214, 0x21c, 16, 2, 0x80, 0xc0}, /* arb clients */ + {0x214, 0x21c, 16, 2, 0x100, 0x140}, /* arb clients */ + {0x214, 0x21c, 0, 16, 0x0, 0xf}, /* xin blocks - axi side */ + {0x214, 0x21c, 0, 16, 0x80, 0xa4}, /* xin blocks - axi side */ + {0x214, 0x21c, 0, 15, 0x100, 0x124}, /* xin blocks - axi side */ + {0x21c, 0x214, 0, 14, 0, 0xc}, /* xin blocks - clock side */ +}; + +/** + * _dpu_dbg_enable_power - use callback to turn power on for hw register access + * @enable: whether to turn power on or off + */ +static inline void _dpu_dbg_enable_power(int enable) +{ + if (enable) + pm_runtime_get_sync(dpu_dbg_base.dev); + else + pm_runtime_put_sync(dpu_dbg_base.dev); +} + +static void _dpu_dbg_dump_dpu_dbg_bus(struct dpu_dbg_dpu_debug_bus *bus) +{ + bool in_log, in_mem; + u32 **dump_mem = NULL; + u32 *dump_addr = NULL; + u32 status = 0; + struct dpu_debug_bus_entry *head; + phys_addr_t phys = 0; + int list_size; + int i; + u32 offset; + void __iomem *mem_base = NULL; + struct dpu_dbg_reg_base *reg_base; + + if (!bus || !bus->cmn.entries_size) + return; + + list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list, + reg_base_head) + if (strlen(reg_base->name) && + !strcmp(reg_base->name, bus->cmn.name)) + mem_base = reg_base->base + bus->top_blk_off; + + if (!mem_base) { + pr_err("unable to find mem_base for %s\n", bus->cmn.name); + return; + } + + dump_mem = &bus->cmn.dumped_content; + + /* will keep in memory 4 entries of 4 bytes each */ + list_size = (bus->cmn.entries_size * 4 * 4); + + in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG); + in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM); + + if (!in_log && !in_mem) + return; + + dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n", + bus->cmn.name); + + if (in_mem) { + if (!(*dump_mem)) + *dump_mem = dma_alloc_coherent(dpu_dbg_base.dev, + list_size, &phys, GFP_KERNEL); + + if (*dump_mem) { + dump_addr = *dump_mem; + dev_info(dpu_dbg_base.dev, + "%s: start_addr:0x%pK len:0x%x\n", + __func__, dump_addr, list_size); + } else { + in_mem = false; + pr_err("dump_mem: allocation fails\n"); + } + } + + _dpu_dbg_enable_power(true); + for (i = 0; i < bus->cmn.entries_size; i++) { + head = bus->entries + i; + writel_relaxed(TEST_MASK(head->block_id, head->test_id), + mem_base + head->wr_addr); + wmb(); /* make sure test bits were written */ + + if (bus->cmn.flags & DBGBUS_FLAGS_DSPP) { + offset = DBGBUS_DSPP_STATUS; + /* keep DSPP test point enabled */ + if (head->wr_addr != DBGBUS_DSPP) + writel_relaxed(0xF, mem_base + DBGBUS_DSPP); + } else { + offset = head->wr_addr + 0x4; + } + + status = readl_relaxed(mem_base + offset); + + if (in_log) + dev_info(dpu_dbg_base.dev, + "waddr=0x%x blk=%d tst=%d val=0x%x\n", + head->wr_addr, head->block_id, + head->test_id, status); + + if (dump_addr && in_mem) { + dump_addr[i*4] = head->wr_addr; + dump_addr[i*4 + 1] = head->block_id; + dump_addr[i*4 + 2] = head->test_id; + dump_addr[i*4 + 3] = status; + } + + if (head->analyzer) + head->analyzer(mem_base, head, status); + + /* Disable debug bus once we are done */ + writel_relaxed(0, mem_base + head->wr_addr); + if (bus->cmn.flags & DBGBUS_FLAGS_DSPP && + head->wr_addr != DBGBUS_DSPP) + writel_relaxed(0x0, mem_base + DBGBUS_DSPP); + } + _dpu_dbg_enable_power(false); + + dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n", + bus->cmn.name); +} + +static void _dpu_dbg_dump_vbif_debug_bus_entry( + struct vbif_debug_bus_entry *head, void __iomem *mem_base, + u32 *dump_addr, bool in_log) +{ + int i, j; + u32 val; + + if (!dump_addr && !in_log) + return; + + for (i = 0; i < head->block_cnt; i++) { + writel_relaxed(1 << (i + head->bit_offset), + mem_base + head->block_bus_addr); + /* make sure that current bus blcok enable */ + wmb(); + for (j = head->test_pnt_start; j < head->test_pnt_cnt; j++) { + writel_relaxed(j, mem_base + head->block_bus_addr + 4); + /* make sure that test point is enabled */ + wmb(); + val = readl_relaxed(mem_base + MMSS_VBIF_TEST_BUS_OUT); + if (dump_addr) { + *dump_addr++ = head->block_bus_addr; + *dump_addr++ = i; + *dump_addr++ = j; + *dump_addr++ = val; + } + if (in_log) + dev_info(dpu_dbg_base.dev, + "testpoint:%x arb/xin id=%d index=%d val=0x%x\n", + head->block_bus_addr, i, j, val); + } + } +} + +static void _dpu_dbg_dump_vbif_dbg_bus(struct dpu_dbg_vbif_debug_bus *bus) +{ + bool in_log, in_mem; + u32 **dump_mem = NULL; + u32 *dump_addr = NULL; + u32 value, d0, d1; + unsigned long reg, reg1, reg2; + struct vbif_debug_bus_entry *head; + phys_addr_t phys = 0; + int i, list_size = 0; + void __iomem *mem_base = NULL; + struct vbif_debug_bus_entry *dbg_bus; + u32 bus_size; + struct dpu_dbg_reg_base *reg_base; + + if (!bus || !bus->cmn.entries_size) + return; + + list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list, + reg_base_head) + if (strlen(reg_base->name) && + !strcmp(reg_base->name, bus->cmn.name)) + mem_base = reg_base->base; + + if (!mem_base) { + pr_err("unable to find mem_base for %s\n", bus->cmn.name); + return; + } + + dbg_bus = bus->entries; + bus_size = bus->cmn.entries_size; + list_size = bus->cmn.entries_size; + dump_mem = &bus->cmn.dumped_content; + + dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n", + bus->cmn.name); + + if (!dump_mem || !dbg_bus || !bus_size || !list_size) + return; + + /* allocate memory for each test point */ + for (i = 0; i < bus_size; i++) { + head = dbg_bus + i; + list_size += (head->block_cnt * head->test_pnt_cnt); + } + + /* 4 bytes * 4 entries for each test point*/ + list_size *= 16; + + in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG); + in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM); + + if (!in_log && !in_mem) + return; + + if (in_mem) { + if (!(*dump_mem)) + *dump_mem = dma_alloc_coherent(dpu_dbg_base.dev, + list_size, &phys, GFP_KERNEL); + + if (*dump_mem) { + dump_addr = *dump_mem; + dev_info(dpu_dbg_base.dev, + "%s: start_addr:0x%pK len:0x%x\n", + __func__, dump_addr, list_size); + } else { + in_mem = false; + pr_err("dump_mem: allocation fails\n"); + } + } + + _dpu_dbg_enable_power(true); + + value = readl_relaxed(mem_base + MMSS_VBIF_CLKON); + writel_relaxed(value | BIT(1), mem_base + MMSS_VBIF_CLKON); + + /* make sure that vbif core is on */ + wmb(); + + /** + * Extract VBIF error info based on XIN halt and error status. + * If the XIN client is not in HALT state, or an error is detected, + * then retrieve the VBIF error info for it. + */ + reg = readl_relaxed(mem_base + MMSS_VBIF_XIN_HALT_CTRL1); + reg1 = readl_relaxed(mem_base + MMSS_VBIF_PND_ERR); + reg2 = readl_relaxed(mem_base + MMSS_VBIF_SRC_ERR); + dev_err(dpu_dbg_base.dev, + "XIN HALT:0x%lX, PND ERR:0x%lX, SRC ERR:0x%lX\n", + reg, reg1, reg2); + reg >>= 16; + reg &= ~(reg1 | reg2); + for (i = 0; i < MMSS_VBIF_CLIENT_NUM; i++) { + if (!test_bit(0, ®)) { + writel_relaxed(i, mem_base + MMSS_VBIF_ERR_INFO); + /* make sure reg write goes through */ + wmb(); + + d0 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO); + d1 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO_1); + + dev_err(dpu_dbg_base.dev, + "Client:%d, errinfo=0x%X, errinfo1=0x%X\n", + i, d0, d1); + } + reg >>= 1; + } + + for (i = 0; i < bus_size; i++) { + head = dbg_bus + i; + + writel_relaxed(0, mem_base + head->disable_bus_addr); + writel_relaxed(BIT(0), mem_base + MMSS_VBIF_TEST_BUS_OUT_CTRL); + /* make sure that other bus is off */ + wmb(); + + _dpu_dbg_dump_vbif_debug_bus_entry(head, mem_base, dump_addr, + in_log); + if (dump_addr) + dump_addr += (head->block_cnt * head->test_pnt_cnt * 4); + } + + _dpu_dbg_enable_power(false); + + dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n", + bus->cmn.name); +} + +/** + * _dpu_dump_array - dump array of register bases + * @name: string indicating origin of dump + * @dump_dbgbus_dpu: whether to dump the dpu debug bus + * @dump_dbgbus_vbif_rt: whether to dump the vbif rt debug bus + */ +static void _dpu_dump_array(const char *name, bool dump_dbgbus_dpu, + bool dump_dbgbus_vbif_rt) +{ + if (dump_dbgbus_dpu) + _dpu_dbg_dump_dpu_dbg_bus(&dpu_dbg_base.dbgbus_dpu); + + if (dump_dbgbus_vbif_rt) + _dpu_dbg_dump_vbif_dbg_bus(&dpu_dbg_base.dbgbus_vbif_rt); +} + +/** + * _dpu_dump_work - deferred dump work function + * @work: work structure + */ +static void _dpu_dump_work(struct work_struct *work) +{ + _dpu_dump_array("dpudump_workitem", + dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work, + dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work); +} + +void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu, + bool dump_dbgbus_vbif_rt) +{ + if (queue_work && work_pending(&dpu_dbg_base.dump_work)) + return; + + if (!queue_work) { + _dpu_dump_array(name, dump_dbgbus_dpu, dump_dbgbus_vbif_rt); + return; + } + + /* schedule work to dump later */ + dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work = dump_dbgbus_dpu; + dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work = + dump_dbgbus_vbif_rt; + schedule_work(&dpu_dbg_base.dump_work); +} + +/* + * dpu_dbg_debugfs_open - debugfs open handler for debug dump + * @inode: debugfs inode + * @file: file handle + */ +static int dpu_dbg_debugfs_open(struct inode *inode, struct file *file) +{ + /* non-seekable */ + file->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + file->private_data = inode->i_private; + return 0; +} + +/** + * dpu_dbg_dump_write - debugfs write handler for debug dump + * @file: file handler + * @user_buf: user buffer content from debugfs + * @count: size of user buffer + * @ppos: position offset of user buffer + */ +static ssize_t dpu_dbg_dump_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + _dpu_dump_array("dump_debugfs", true, true); + return count; +} + +static const struct file_operations dpu_dbg_dump_fops = { + .open = dpu_dbg_debugfs_open, + .write = dpu_dbg_dump_write, +}; + +int dpu_dbg_debugfs_register(struct dentry *debugfs_root) +{ + static struct dpu_dbg_base *dbg = &dpu_dbg_base; + char debug_name[80] = ""; + + if (!debugfs_root) + return -EINVAL; + + debugfs_create_file("dump", 0600, debugfs_root, NULL, + &dpu_dbg_dump_fops); + + if (dbg->dbgbus_dpu.entries) { + dbg->dbgbus_dpu.cmn.name = DBGBUS_NAME_DPU; + snprintf(debug_name, sizeof(debug_name), "%s_dbgbus", + dbg->dbgbus_dpu.cmn.name); + dbg->dbgbus_dpu.cmn.enable_mask = DEFAULT_DBGBUS_DPU; + debugfs_create_u32(debug_name, 0600, debugfs_root, + &dbg->dbgbus_dpu.cmn.enable_mask); + } + + if (dbg->dbgbus_vbif_rt.entries) { + dbg->dbgbus_vbif_rt.cmn.name = DBGBUS_NAME_VBIF_RT; + snprintf(debug_name, sizeof(debug_name), "%s_dbgbus", + dbg->dbgbus_vbif_rt.cmn.name); + dbg->dbgbus_vbif_rt.cmn.enable_mask = DEFAULT_DBGBUS_VBIFRT; + debugfs_create_u32(debug_name, 0600, debugfs_root, + &dbg->dbgbus_vbif_rt.cmn.enable_mask); + } + + return 0; +} + +static void _dpu_dbg_debugfs_destroy(void) +{ +} + +void dpu_dbg_init_dbg_buses(u32 hwversion) +{ + static struct dpu_dbg_base *dbg = &dpu_dbg_base; + + memset(&dbg->dbgbus_dpu, 0, sizeof(dbg->dbgbus_dpu)); + memset(&dbg->dbgbus_vbif_rt, 0, sizeof(dbg->dbgbus_vbif_rt)); + + if (IS_MSM8998_TARGET(hwversion)) { + dbg->dbgbus_dpu.entries = dbg_bus_dpu_8998; + dbg->dbgbus_dpu.cmn.entries_size = ARRAY_SIZE(dbg_bus_dpu_8998); + dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP; + + dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998; + dbg->dbgbus_vbif_rt.cmn.entries_size = + ARRAY_SIZE(vbif_dbg_bus_msm8998); + } else if (IS_SDM845_TARGET(hwversion) || IS_SDM670_TARGET(hwversion)) { + dbg->dbgbus_dpu.entries = dbg_bus_dpu_sdm845; + dbg->dbgbus_dpu.cmn.entries_size = + ARRAY_SIZE(dbg_bus_dpu_sdm845); + dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP; + + /* vbif is unchanged vs 8998 */ + dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998; + dbg->dbgbus_vbif_rt.cmn.entries_size = + ARRAY_SIZE(vbif_dbg_bus_msm8998); + } else { + pr_err("unsupported chipset id %X\n", hwversion); + } +} + +int dpu_dbg_init(struct device *dev) +{ + if (!dev) { + pr_err("invalid params\n"); + return -EINVAL; + } + + INIT_LIST_HEAD(&dpu_dbg_base.reg_base_list); + dpu_dbg_base.dev = dev; + + INIT_WORK(&dpu_dbg_base.dump_work, _dpu_dump_work); + + return 0; +} + +/** + * dpu_dbg_destroy - destroy dpu debug facilities + */ +void dpu_dbg_destroy(void) +{ + _dpu_dbg_debugfs_destroy(); +} + +void dpu_dbg_set_dpu_top_offset(u32 blk_off) +{ + dpu_dbg_base.dbgbus_dpu.top_blk_off = blk_off; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h new file mode 100644 index 000000000000..1e6fa945f98b --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h @@ -0,0 +1,103 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef DPU_DBG_H_ +#define DPU_DBG_H_ + +#include <stdarg.h> +#include <linux/debugfs.h> +#include <linux/list.h> + +enum dpu_dbg_dump_flag { + DPU_DBG_DUMP_IN_LOG = BIT(0), + DPU_DBG_DUMP_IN_MEM = BIT(1), +}; + +#if defined(CONFIG_DEBUG_FS) + +/** + * dpu_dbg_init_dbg_buses - initialize debug bus dumping support for the chipset + * @hwversion: Chipset revision + */ +void dpu_dbg_init_dbg_buses(u32 hwversion); + +/** + * dpu_dbg_init - initialize global dpu debug facilities: regdump + * @dev: device handle + * Returns: 0 or -ERROR + */ +int dpu_dbg_init(struct device *dev); + +/** + * dpu_dbg_debugfs_register - register entries at the given debugfs dir + * @debugfs_root: debugfs root in which to create dpu debug entries + * Returns: 0 or -ERROR + */ +int dpu_dbg_debugfs_register(struct dentry *debugfs_root); + +/** + * dpu_dbg_destroy - destroy the global dpu debug facilities + * Returns: none + */ +void dpu_dbg_destroy(void); + +/** + * dpu_dbg_dump - trigger dumping of all dpu_dbg facilities + * @queue_work: whether to queue the dumping work to the work_struct + * @name: string indicating origin of dump + * @dump_dbgbus: dump the dpu debug bus + * @dump_vbif_rt: dump the vbif rt bus + * Returns: none + */ +void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu, + bool dump_dbgbus_vbif_rt); + +/** + * dpu_dbg_set_dpu_top_offset - set the target specific offset from mdss base + * address of the top registers. Used for accessing debug bus controls. + * @blk_off: offset from mdss base of the top block + */ +void dpu_dbg_set_dpu_top_offset(u32 blk_off); + +#else + +static inline void dpu_dbg_init_dbg_buses(u32 hwversion) +{ +} + +static inline int dpu_dbg_init(struct device *dev) +{ + return 0; +} + +static inline int dpu_dbg_debugfs_register(struct dentry *debugfs_root) +{ + return 0; +} + +static inline void dpu_dbg_destroy(void) +{ +} + +static inline void dpu_dbg_dump(bool queue_work, const char *name, + bool dump_dbgbus_dpu, bool dump_dbgbus_vbif_rt) +{ +} + +static inline void dpu_dbg_set_dpu_top_offset(u32 blk_off) +{ +} + +#endif /* defined(CONFIG_DEBUG_FS) */ + + +#endif /* DPU_DBG_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c new file mode 100644 index 000000000000..0bd3eda93e22 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -0,0 +1,2498 @@ +/* + * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include <linux/kthread.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +#include "msm_drv.h" +#include "dpu_kms.h" +#include <drm/drm_crtc.h> +#include <drm/drm_crtc_helper.h> +#include "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_intf.h" +#include "dpu_hw_ctl.h" +#include "dpu_formats.h" +#include "dpu_encoder_phys.h" +#include "dpu_crtc.h" +#include "dpu_trace.h" +#include "dpu_core_irq.h" + +#define DPU_DEBUG_ENC(e, fmt, ...) DPU_DEBUG("enc%d " fmt,\ + (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) + +#define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\ + (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) + +#define DPU_DEBUG_PHYS(p, fmt, ...) DPU_DEBUG("enc%d intf%d pp%d " fmt,\ + (p) ? (p)->parent->base.id : -1, \ + (p) ? (p)->intf_idx - INTF_0 : -1, \ + (p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \ + ##__VA_ARGS__) + +#define DPU_ERROR_PHYS(p, fmt, ...) DPU_ERROR("enc%d intf%d pp%d " fmt,\ + (p) ? (p)->parent->base.id : -1, \ + (p) ? (p)->intf_idx - INTF_0 : -1, \ + (p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \ + ##__VA_ARGS__) + +/* + * Two to anticipate panels that can do cmd/vid dynamic switching + * plan is to create all possible physical encoder types, and switch between + * them at runtime + */ +#define NUM_PHYS_ENCODER_TYPES 2 + +#define MAX_PHYS_ENCODERS_PER_VIRTUAL \ + (MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES) + +#define MAX_CHANNELS_PER_ENC 2 + +#define MISR_BUFF_SIZE 256 + +#define IDLE_SHORT_TIMEOUT 1 + +#define MAX_VDISPLAY_SPLIT 1080 + +/** + * enum dpu_enc_rc_events - events for resource control state machine + * @DPU_ENC_RC_EVENT_KICKOFF: + * This event happens at NORMAL priority. + * Event that signals the start of the transfer. When this event is + * received, enable MDP/DSI core clocks. Regardless of the previous + * state, the resource should be in ON state at the end of this event. + * @DPU_ENC_RC_EVENT_FRAME_DONE: + * This event happens at INTERRUPT level. + * Event signals the end of the data transfer after the PP FRAME_DONE + * event. At the end of this event, a delayed work is scheduled to go to + * IDLE_PC state after IDLE_TIMEOUT time. + * @DPU_ENC_RC_EVENT_PRE_STOP: + * This event happens at NORMAL priority. + * This event, when received during the ON state, leave the RC STATE + * in the PRE_OFF state. It should be followed by the STOP event as + * part of encoder disable. + * If received during IDLE or OFF states, it will do nothing. + * @DPU_ENC_RC_EVENT_STOP: + * This event happens at NORMAL priority. + * When this event is received, disable all the MDP/DSI core clocks, and + * disable IRQs. It should be called from the PRE_OFF or IDLE states. + * IDLE is expected when IDLE_PC has run, and PRE_OFF did nothing. + * PRE_OFF is expected when PRE_STOP was executed during the ON state. + * Resource state should be in OFF at the end of the event. + * @DPU_ENC_RC_EVENT_ENTER_IDLE: + * This event happens at NORMAL priority from a work item. + * Event signals that there were no frame updates for IDLE_TIMEOUT time. + * This would disable MDP/DSI core clocks and change the resource state + * to IDLE. + */ +enum dpu_enc_rc_events { + DPU_ENC_RC_EVENT_KICKOFF = 1, + DPU_ENC_RC_EVENT_FRAME_DONE, + DPU_ENC_RC_EVENT_PRE_STOP, + DPU_ENC_RC_EVENT_STOP, + DPU_ENC_RC_EVENT_ENTER_IDLE +}; + +/* + * enum dpu_enc_rc_states - states that the resource control maintains + * @DPU_ENC_RC_STATE_OFF: Resource is in OFF state + * @DPU_ENC_RC_STATE_PRE_OFF: Resource is transitioning to OFF state + * @DPU_ENC_RC_STATE_ON: Resource is in ON state + * @DPU_ENC_RC_STATE_MODESET: Resource is in modeset state + * @DPU_ENC_RC_STATE_IDLE: Resource is in IDLE state + */ +enum dpu_enc_rc_states { + DPU_ENC_RC_STATE_OFF, + DPU_ENC_RC_STATE_PRE_OFF, + DPU_ENC_RC_STATE_ON, + DPU_ENC_RC_STATE_IDLE +}; + +/** + * struct dpu_encoder_virt - virtual encoder. Container of one or more physical + * encoders. Virtual encoder manages one "logical" display. Physical + * encoders manage one intf block, tied to a specific panel/sub-panel. + * Virtual encoder defers as much as possible to the physical encoders. + * Virtual encoder registers itself with the DRM Framework as the encoder. + * @base: drm_encoder base class for registration with DRM + * @enc_spin_lock: Virtual-Encoder-Wide Spin Lock for IRQ purposes + * @bus_scaling_client: Client handle to the bus scaling interface + * @num_phys_encs: Actual number of physical encoders contained. + * @phys_encs: Container of physical encoders managed. + * @cur_master: Pointer to the current master in this mode. Optimization + * Only valid after enable. Cleared as disable. + * @hw_pp Handle to the pingpong blocks used for the display. No. + * pingpong blocks can be different than num_phys_encs. + * @intfs_swapped Whether or not the phys_enc interfaces have been swapped + * for partial update right-only cases, such as pingpong + * split where virtual pingpong does not generate IRQs + * @crtc_vblank_cb: Callback into the upper layer / CRTC for + * notification of the VBLANK + * @crtc_vblank_cb_data: Data from upper layer for VBLANK notification + * @crtc_kickoff_cb: Callback into CRTC that will flush & start + * all CTL paths + * @crtc_kickoff_cb_data: Opaque user data given to crtc_kickoff_cb + * @debugfs_root: Debug file system root file node + * @enc_lock: Lock around physical encoder create/destroy and + access. + * @frame_busy_mask: Bitmask tracking which phys_enc we are still + * busy processing current command. + * Bit0 = phys_encs[0] etc. + * @crtc_frame_event_cb: callback handler for frame event + * @crtc_frame_event_cb_data: callback handler private data + * @frame_done_timeout: frame done timeout in Hz + * @frame_done_timer: watchdog timer for frame done event + * @vsync_event_timer: vsync timer + * @disp_info: local copy of msm_display_info struct + * @misr_enable: misr enable/disable status + * @misr_frame_count: misr frame count before start capturing the data + * @idle_pc_supported: indicate if idle power collaps is supported + * @rc_lock: resource control mutex lock to protect + * virt encoder over various state changes + * @rc_state: resource controller state + * @delayed_off_work: delayed worker to schedule disabling of + * clks and resources after IDLE_TIMEOUT time. + * @vsync_event_work: worker to handle vsync event for autorefresh + * @topology: topology of the display + * @mode_set_complete: flag to indicate modeset completion + * @idle_timeout: idle timeout duration in milliseconds + */ +struct dpu_encoder_virt { + struct drm_encoder base; + spinlock_t enc_spinlock; + uint32_t bus_scaling_client; + + uint32_t display_num_of_h_tiles; + + unsigned int num_phys_encs; + struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL]; + struct dpu_encoder_phys *cur_master; + struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC]; + + bool intfs_swapped; + + void (*crtc_vblank_cb)(void *); + void *crtc_vblank_cb_data; + + struct dentry *debugfs_root; + struct mutex enc_lock; + DECLARE_BITMAP(frame_busy_mask, MAX_PHYS_ENCODERS_PER_VIRTUAL); + void (*crtc_frame_event_cb)(void *, u32 event); + void *crtc_frame_event_cb_data; + + atomic_t frame_done_timeout; + struct timer_list frame_done_timer; + struct timer_list vsync_event_timer; + + struct msm_display_info disp_info; + bool misr_enable; + u32 misr_frame_count; + + bool idle_pc_supported; + struct mutex rc_lock; + enum dpu_enc_rc_states rc_state; + struct kthread_delayed_work delayed_off_work; + struct kthread_work vsync_event_work; + struct msm_display_topology topology; + bool mode_set_complete; + + u32 idle_timeout; +}; + +#define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base) +static inline int _dpu_encoder_power_enable(struct dpu_encoder_virt *dpu_enc, + bool enable) +{ + struct drm_encoder *drm_enc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!dpu_enc) { + DPU_ERROR("invalid dpu enc\n"); + return -EINVAL; + } + + drm_enc = &dpu_enc->base; + if (!drm_enc->dev || !drm_enc->dev->dev_private) { + DPU_ERROR("drm device invalid\n"); + return -EINVAL; + } + + priv = drm_enc->dev->dev_private; + if (!priv->kms) { + DPU_ERROR("invalid kms\n"); + return -EINVAL; + } + + dpu_kms = to_dpu_kms(priv->kms); + + if (enable) + pm_runtime_get_sync(&dpu_kms->pdev->dev); + else + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + return 0; +} + +void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx) +{ + DRM_ERROR("irq timeout id=%u, intf=%d, pp=%d, intr=%d\n", + DRMID(phys_enc->parent), phys_enc->intf_idx - INTF_0, + phys_enc->hw_pp->idx - PINGPONG_0, intr_idx); + + if (phys_enc->parent_ops->handle_frame_done) + phys_enc->parent_ops->handle_frame_done( + phys_enc->parent, phys_enc, + DPU_ENCODER_FRAME_EVENT_ERROR); +} + +static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id, + int32_t hw_id, struct dpu_encoder_wait_info *info); + +int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx, + struct dpu_encoder_wait_info *wait_info) +{ + struct dpu_encoder_irq *irq; + u32 irq_status; + int ret; + + if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + irq = &phys_enc->irq[intr_idx]; + + /* note: do master / slave checking outside */ + + /* return EWOULDBLOCK since we know the wait isn't necessary */ + if (phys_enc->enable_state == DPU_ENC_DISABLED) { + DRM_ERROR("encoder is disabled id=%u, intr=%d, hw=%d, irq=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx); + return -EWOULDBLOCK; + } + + if (irq->irq_idx < 0) { + DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, hw=%d, irq=%s", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->name); + return 0; + } + + DRM_DEBUG_KMS("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, pending_cnt=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx, phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(wait_info->atomic_cnt)); + + ret = dpu_encoder_helper_wait_event_timeout( + DRMID(phys_enc->parent), + irq->hw_idx, + wait_info); + + if (ret <= 0) { + irq_status = dpu_core_irq_read(phys_enc->dpu_kms, + irq->irq_idx, true); + if (irq_status) { + unsigned long flags; + + DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, " + "hw=%d, irq=%d, pp=%d, atomic_cnt=%d", + DRMID(phys_enc->parent), intr_idx, + irq->hw_idx, irq->irq_idx, + phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(wait_info->atomic_cnt)); + local_irq_save(flags); + irq->cb.func(phys_enc, irq->irq_idx); + local_irq_restore(flags); + ret = 0; + } else { + ret = -ETIMEDOUT; + DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, " + "hw=%d, irq=%d, pp=%d, atomic_cnt=%d", + DRMID(phys_enc->parent), intr_idx, + irq->hw_idx, irq->irq_idx, + phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(wait_info->atomic_cnt)); + } + } else { + ret = 0; + trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent), + intr_idx, irq->hw_idx, irq->irq_idx, + phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(wait_info->atomic_cnt)); + } + + return ret; +} + +int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx) +{ + struct dpu_encoder_irq *irq; + int ret = 0; + + if (!phys_enc || intr_idx >= INTR_IDX_MAX) { + DPU_ERROR("invalid params\n"); + return -EINVAL; + } + irq = &phys_enc->irq[intr_idx]; + + if (irq->irq_idx >= 0) { + DPU_DEBUG_PHYS(phys_enc, + "skipping already registered irq %s type %d\n", + irq->name, irq->intr_type); + return 0; + } + + irq->irq_idx = dpu_core_irq_idx_lookup(phys_enc->dpu_kms, + irq->intr_type, irq->hw_idx); + if (irq->irq_idx < 0) { + DPU_ERROR_PHYS(phys_enc, + "failed to lookup IRQ index for %s type:%d\n", + irq->name, irq->intr_type); + return -EINVAL; + } + + ret = dpu_core_irq_register_callback(phys_enc->dpu_kms, irq->irq_idx, + &irq->cb); + if (ret) { + DPU_ERROR_PHYS(phys_enc, + "failed to register IRQ callback for %s\n", + irq->name); + irq->irq_idx = -EINVAL; + return ret; + } + + ret = dpu_core_irq_enable(phys_enc->dpu_kms, &irq->irq_idx, 1); + if (ret) { + DRM_ERROR("enable failed id=%u, intr=%d, hw=%d, irq=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx); + dpu_core_irq_unregister_callback(phys_enc->dpu_kms, + irq->irq_idx, &irq->cb); + irq->irq_idx = -EINVAL; + return ret; + } + + trace_dpu_enc_irq_register_success(DRMID(phys_enc->parent), intr_idx, + irq->hw_idx, irq->irq_idx); + + return ret; +} + +int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx) +{ + struct dpu_encoder_irq *irq; + int ret; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + irq = &phys_enc->irq[intr_idx]; + + /* silently skip irqs that weren't registered */ + if (irq->irq_idx < 0) { + DRM_ERROR("duplicate unregister id=%u, intr=%d, hw=%d, irq=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx); + return 0; + } + + ret = dpu_core_irq_disable(phys_enc->dpu_kms, &irq->irq_idx, 1); + if (ret) { + DRM_ERROR("diable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx, ret); + } + + ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms, irq->irq_idx, + &irq->cb); + if (ret) { + DRM_ERROR("unreg cb fail id=%u, intr=%d, hw=%d, irq=%d ret=%d", + DRMID(phys_enc->parent), intr_idx, irq->hw_idx, + irq->irq_idx, ret); + } + + trace_dpu_enc_irq_unregister_success(DRMID(phys_enc->parent), intr_idx, + irq->hw_idx, irq->irq_idx); + + irq->irq_idx = -EINVAL; + + return 0; +} + +void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc, + struct dpu_encoder_hw_resources *hw_res, + struct drm_connector_state *conn_state) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i = 0; + + if (!hw_res || !drm_enc || !conn_state) { + DPU_ERROR("invalid argument(s), drm_enc %d, res %d, state %d\n", + drm_enc != 0, hw_res != 0, conn_state != 0); + return; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + /* Query resources used by phys encs, expected to be without overlap */ + memset(hw_res, 0, sizeof(*hw_res)); + hw_res->display_num_of_h_tiles = dpu_enc->display_num_of_h_tiles; + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.get_hw_resources) + phys->ops.get_hw_resources(phys, hw_res, conn_state); + } +} + +static void dpu_encoder_destroy(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i = 0; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + mutex_lock(&dpu_enc->enc_lock); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.destroy) { + phys->ops.destroy(phys); + --dpu_enc->num_phys_encs; + dpu_enc->phys_encs[i] = NULL; + } + } + + if (dpu_enc->num_phys_encs) + DPU_ERROR_ENC(dpu_enc, "expected 0 num_phys_encs not %d\n", + dpu_enc->num_phys_encs); + dpu_enc->num_phys_encs = 0; + mutex_unlock(&dpu_enc->enc_lock); + + drm_encoder_cleanup(drm_enc); + mutex_destroy(&dpu_enc->enc_lock); + + kfree(dpu_enc); +} + +void dpu_encoder_helper_split_config( + struct dpu_encoder_phys *phys_enc, + enum dpu_intf interface) +{ + struct dpu_encoder_virt *dpu_enc; + struct split_pipe_cfg cfg = { 0 }; + struct dpu_hw_mdp *hw_mdptop; + struct msm_display_info *disp_info; + + if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) { + DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0); + return; + } + + dpu_enc = to_dpu_encoder_virt(phys_enc->parent); + hw_mdptop = phys_enc->hw_mdptop; + disp_info = &dpu_enc->disp_info; + + if (disp_info->intf_type != DRM_MODE_CONNECTOR_DSI) + return; + + /** + * disable split modes since encoder will be operating in as the only + * encoder, either for the entire use case in the case of, for example, + * single DSI, or for this frame in the case of left/right only partial + * update. + */ + if (phys_enc->split_role == ENC_ROLE_SOLO) { + if (hw_mdptop->ops.setup_split_pipe) + hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg); + return; + } + + cfg.en = true; + cfg.mode = phys_enc->intf_mode; + cfg.intf = interface; + + if (cfg.en && phys_enc->ops.needs_single_flush && + phys_enc->ops.needs_single_flush(phys_enc)) + cfg.split_flush_en = true; + + if (phys_enc->split_role == ENC_ROLE_MASTER) { + DPU_DEBUG_ENC(dpu_enc, "enable %d\n", cfg.en); + + if (hw_mdptop->ops.setup_split_pipe) + hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg); + } +} + +static void _dpu_encoder_adjust_mode(struct drm_connector *connector, + struct drm_display_mode *adj_mode) +{ + struct drm_display_mode *cur_mode; + + if (!connector || !adj_mode) + return; + + list_for_each_entry(cur_mode, &connector->modes, head) { + if (cur_mode->vdisplay == adj_mode->vdisplay && + cur_mode->hdisplay == adj_mode->hdisplay && + cur_mode->vrefresh == adj_mode->vrefresh) { + adj_mode->private = cur_mode->private; + adj_mode->private_flags |= cur_mode->private_flags; + } + } +} + +static struct msm_display_topology dpu_encoder_get_topology( + struct dpu_encoder_virt *dpu_enc, + struct dpu_kms *dpu_kms, + struct drm_display_mode *mode) +{ + struct msm_display_topology topology; + int i, intf_count = 0; + + for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++) + if (dpu_enc->phys_encs[i]) + intf_count++; + + /* User split topology for width > 1080 */ + topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1; + topology.num_enc = 0; + topology.num_intf = intf_count; + + return topology; +} +static int dpu_encoder_virt_atomic_check( + struct drm_encoder *drm_enc, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct dpu_encoder_virt *dpu_enc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + const struct drm_display_mode *mode; + struct drm_display_mode *adj_mode; + struct msm_display_topology topology; + int i = 0; + int ret = 0; + + if (!drm_enc || !crtc_state || !conn_state) { + DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n", + drm_enc != 0, crtc_state != 0, conn_state != 0); + return -EINVAL; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + mode = &crtc_state->mode; + adj_mode = &crtc_state->adjusted_mode; + trace_dpu_enc_atomic_check(DRMID(drm_enc)); + + /* + * display drivers may populate private fields of the drm display mode + * structure while registering possible modes of a connector with DRM. + * These private fields are not populated back while DRM invokes + * the mode_set callbacks. This module retrieves and populates the + * private fields of the given mode. + */ + _dpu_encoder_adjust_mode(conn_state->connector, adj_mode); + + /* perform atomic check on the first physical encoder (master) */ + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.atomic_check) + ret = phys->ops.atomic_check(phys, crtc_state, + conn_state); + else if (phys && phys->ops.mode_fixup) + if (!phys->ops.mode_fixup(phys, mode, adj_mode)) + ret = -EINVAL; + + if (ret) { + DPU_ERROR_ENC(dpu_enc, + "mode unsupported, phys idx %d\n", i); + break; + } + } + + topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode); + + /* Reserve dynamic resources now. Indicating AtomicTest phase */ + if (!ret) { + /* + * Avoid reserving resources when mode set is pending. Topology + * info may not be available to complete reservation. + */ + if (drm_atomic_crtc_needs_modeset(crtc_state) + && dpu_enc->mode_set_complete) { + ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state, + conn_state, topology, true); + dpu_enc->mode_set_complete = false; + } + } + + if (!ret) + drm_mode_set_crtcinfo(adj_mode, 0); + + trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags, + adj_mode->private_flags); + + return ret; +} + +static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc, + struct msm_display_info *disp_info) +{ + struct dpu_vsync_source_cfg vsync_cfg = { 0 }; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + struct dpu_hw_mdp *hw_mdptop; + struct drm_encoder *drm_enc; + int i; + + if (!dpu_enc || !disp_info) { + DPU_ERROR("invalid param dpu_enc:%d or disp_info:%d\n", + dpu_enc != NULL, disp_info != NULL); + return; + } else if (dpu_enc->num_phys_encs > ARRAY_SIZE(dpu_enc->hw_pp)) { + DPU_ERROR("invalid num phys enc %d/%d\n", + dpu_enc->num_phys_encs, + (int) ARRAY_SIZE(dpu_enc->hw_pp)); + return; + } + + drm_enc = &dpu_enc->base; + /* this pointers are checked in virt_enable_helper */ + priv = drm_enc->dev->dev_private; + + dpu_kms = to_dpu_kms(priv->kms); + if (!dpu_kms) { + DPU_ERROR("invalid dpu_kms\n"); + return; + } + + hw_mdptop = dpu_kms->hw_mdp; + if (!hw_mdptop) { + DPU_ERROR("invalid mdptop\n"); + return; + } + + if (hw_mdptop->ops.setup_vsync_source && + disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) { + for (i = 0; i < dpu_enc->num_phys_encs; i++) + vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx; + + vsync_cfg.pp_count = dpu_enc->num_phys_encs; + if (disp_info->is_te_using_watchdog_timer) + vsync_cfg.vsync_source = DPU_VSYNC_SOURCE_WD_TIMER_0; + else + vsync_cfg.vsync_source = DPU_VSYNC0_SOURCE_GPIO; + + hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg); + } +} + +static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable) +{ + struct dpu_encoder_virt *dpu_enc; + int i; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + + DPU_DEBUG_ENC(dpu_enc, "enable:%d\n", enable); + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.irq_control) + phys->ops.irq_control(phys, enable); + } + +} + +static void _dpu_encoder_resource_control_helper(struct drm_encoder *drm_enc, + bool enable) +{ + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + struct dpu_encoder_virt *dpu_enc; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + + trace_dpu_enc_rc_helper(DRMID(drm_enc), enable); + + if (!dpu_enc->cur_master) { + DPU_ERROR("encoder master not set\n"); + return; + } + + if (enable) { + /* enable DPU core clks */ + pm_runtime_get_sync(&dpu_kms->pdev->dev); + + /* enable all the irq */ + _dpu_encoder_irq_control(drm_enc, true); + + } else { + /* disable all the irq */ + _dpu_encoder_irq_control(drm_enc, false); + + /* disable DPU core clks */ + pm_runtime_put_sync(&dpu_kms->pdev->dev); + } + +} + +static int dpu_encoder_resource_control(struct drm_encoder *drm_enc, + u32 sw_event) +{ + struct dpu_encoder_virt *dpu_enc; + struct msm_drm_private *priv; + struct msm_drm_thread *disp_thread; + bool is_vid_mode = false; + + if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private || + !drm_enc->crtc) { + DPU_ERROR("invalid parameters\n"); + return -EINVAL; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + priv = drm_enc->dev->dev_private; + is_vid_mode = dpu_enc->disp_info.capabilities & + MSM_DISPLAY_CAP_VID_MODE; + + if (drm_enc->crtc->index >= ARRAY_SIZE(priv->disp_thread)) { + DPU_ERROR("invalid crtc index\n"); + return -EINVAL; + } + disp_thread = &priv->disp_thread[drm_enc->crtc->index]; + + /* + * when idle_pc is not supported, process only KICKOFF, STOP and MODESET + * events and return early for other events (ie wb display). + */ + if (!dpu_enc->idle_pc_supported && + (sw_event != DPU_ENC_RC_EVENT_KICKOFF && + sw_event != DPU_ENC_RC_EVENT_STOP && + sw_event != DPU_ENC_RC_EVENT_PRE_STOP)) + return 0; + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, dpu_enc->idle_pc_supported, + dpu_enc->rc_state, "begin"); + + switch (sw_event) { + case DPU_ENC_RC_EVENT_KICKOFF: + /* cancel delayed off work, if any */ + if (kthread_cancel_delayed_work_sync( + &dpu_enc->delayed_off_work)) + DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n", + sw_event); + + mutex_lock(&dpu_enc->rc_lock); + + /* return if the resource control is already in ON state */ + if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) { + DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in ON state\n", + DRMID(drm_enc), sw_event); + mutex_unlock(&dpu_enc->rc_lock); + return 0; + } else if (dpu_enc->rc_state != DPU_ENC_RC_STATE_OFF && + dpu_enc->rc_state != DPU_ENC_RC_STATE_IDLE) { + DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in state %d\n", + DRMID(drm_enc), sw_event, + dpu_enc->rc_state); + mutex_unlock(&dpu_enc->rc_lock); + return -EINVAL; + } + + if (is_vid_mode && dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) + _dpu_encoder_irq_control(drm_enc, true); + else + _dpu_encoder_resource_control_helper(drm_enc, true); + + dpu_enc->rc_state = DPU_ENC_RC_STATE_ON; + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "kickoff"); + + mutex_unlock(&dpu_enc->rc_lock); + break; + + case DPU_ENC_RC_EVENT_FRAME_DONE: + /* + * mutex lock is not used as this event happens at interrupt + * context. And locking is not required as, the other events + * like KICKOFF and STOP does a wait-for-idle before executing + * the resource_control + */ + if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) { + DRM_DEBUG_KMS("id:%d, sw_event:%d,rc:%d-unexpected\n", + DRMID(drm_enc), sw_event, + dpu_enc->rc_state); + return -EINVAL; + } + + /* + * schedule off work item only when there are no + * frames pending + */ + if (dpu_crtc_frame_pending(drm_enc->crtc) > 1) { + DRM_DEBUG_KMS("id:%d skip schedule work\n", + DRMID(drm_enc)); + return 0; + } + + kthread_queue_delayed_work( + &disp_thread->worker, + &dpu_enc->delayed_off_work, + msecs_to_jiffies(dpu_enc->idle_timeout)); + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "frame done"); + break; + + case DPU_ENC_RC_EVENT_PRE_STOP: + /* cancel delayed off work, if any */ + if (kthread_cancel_delayed_work_sync( + &dpu_enc->delayed_off_work)) + DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n", + sw_event); + + mutex_lock(&dpu_enc->rc_lock); + + if (is_vid_mode && + dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) { + _dpu_encoder_irq_control(drm_enc, true); + } + /* skip if is already OFF or IDLE, resources are off already */ + else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF || + dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) { + DRM_DEBUG_KMS("id:%u, sw_event:%d, rc in %d state\n", + DRMID(drm_enc), sw_event, + dpu_enc->rc_state); + mutex_unlock(&dpu_enc->rc_lock); + return 0; + } + + dpu_enc->rc_state = DPU_ENC_RC_STATE_PRE_OFF; + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "pre stop"); + + mutex_unlock(&dpu_enc->rc_lock); + break; + + case DPU_ENC_RC_EVENT_STOP: + mutex_lock(&dpu_enc->rc_lock); + + /* return if the resource control is already in OFF state */ + if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF) { + DRM_DEBUG_KMS("id: %u, sw_event:%d, rc in OFF state\n", + DRMID(drm_enc), sw_event); + mutex_unlock(&dpu_enc->rc_lock); + return 0; + } else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) { + DRM_ERROR("id: %u, sw_event:%d, rc in state %d\n", + DRMID(drm_enc), sw_event, dpu_enc->rc_state); + mutex_unlock(&dpu_enc->rc_lock); + return -EINVAL; + } + + /** + * expect to arrive here only if in either idle state or pre-off + * and in IDLE state the resources are already disabled + */ + if (dpu_enc->rc_state == DPU_ENC_RC_STATE_PRE_OFF) + _dpu_encoder_resource_control_helper(drm_enc, false); + + dpu_enc->rc_state = DPU_ENC_RC_STATE_OFF; + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "stop"); + + mutex_unlock(&dpu_enc->rc_lock); + break; + + case DPU_ENC_RC_EVENT_ENTER_IDLE: + mutex_lock(&dpu_enc->rc_lock); + + if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) { + DRM_ERROR("id: %u, sw_event:%d, rc:%d !ON state\n", + DRMID(drm_enc), sw_event, dpu_enc->rc_state); + mutex_unlock(&dpu_enc->rc_lock); + return 0; + } + + /* + * if we are in ON but a frame was just kicked off, + * ignore the IDLE event, it's probably a stale timer event + */ + if (dpu_enc->frame_busy_mask[0]) { + DRM_ERROR("id:%u, sw_event:%d, rc:%d frame pending\n", + DRMID(drm_enc), sw_event, dpu_enc->rc_state); + mutex_unlock(&dpu_enc->rc_lock); + return 0; + } + + if (is_vid_mode) + _dpu_encoder_irq_control(drm_enc, false); + else + _dpu_encoder_resource_control_helper(drm_enc, false); + + dpu_enc->rc_state = DPU_ENC_RC_STATE_IDLE; + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "idle"); + + mutex_unlock(&dpu_enc->rc_lock); + break; + + default: + DRM_ERROR("id:%u, unexpected sw_event: %d\n", DRMID(drm_enc), + sw_event); + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "error"); + break; + } + + trace_dpu_enc_rc(DRMID(drm_enc), sw_event, + dpu_enc->idle_pc_supported, dpu_enc->rc_state, + "end"); + return 0; +} + +static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + struct dpu_encoder_virt *dpu_enc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + struct list_head *connector_list; + struct drm_connector *conn = NULL, *conn_iter; + struct dpu_rm_hw_iter pp_iter; + struct msm_display_topology topology; + enum dpu_rm_topology_name topology_name; + int i = 0, ret; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + connector_list = &dpu_kms->dev->mode_config.connector_list; + + trace_dpu_enc_mode_set(DRMID(drm_enc)); + + list_for_each_entry(conn_iter, connector_list, head) + if (conn_iter->encoder == drm_enc) + conn = conn_iter; + + if (!conn) { + DPU_ERROR_ENC(dpu_enc, "failed to find attached connector\n"); + return; + } else if (!conn->state) { + DPU_ERROR_ENC(dpu_enc, "invalid connector state\n"); + return; + } + + topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode); + + /* Reserve dynamic resources now. Indicating non-AtomicTest phase */ + ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_enc->crtc->state, + conn->state, topology, false); + if (ret) { + DPU_ERROR_ENC(dpu_enc, + "failed to reserve hw resources, %d\n", ret); + return; + } + + dpu_rm_init_hw_iter(&pp_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG); + for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + dpu_enc->hw_pp[i] = NULL; + if (!dpu_rm_get_hw(&dpu_kms->rm, &pp_iter)) + break; + dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) pp_iter.hw; + } + + topology_name = dpu_rm_get_topology_name(topology); + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys) { + if (!dpu_enc->hw_pp[i]) { + DPU_ERROR_ENC(dpu_enc, + "invalid pingpong block for the encoder\n"); + return; + } + phys->hw_pp = dpu_enc->hw_pp[i]; + phys->connector = conn->state->connector; + phys->topology_name = topology_name; + if (phys->ops.mode_set) + phys->ops.mode_set(phys, mode, adj_mode); + } + } + + dpu_enc->mode_set_complete = true; +} + +static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) { + DPU_ERROR("invalid parameters\n"); + return; + } + + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + if (!dpu_kms) { + DPU_ERROR("invalid dpu_kms\n"); + return; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + if (!dpu_enc || !dpu_enc->cur_master) { + DPU_ERROR("invalid dpu encoder/master\n"); + return; + } + + if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort && + dpu_enc->cur_master->hw_mdptop && + dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select) + dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select( + dpu_enc->cur_master->hw_mdptop); + + if (dpu_enc->cur_master->hw_mdptop && + dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc) + dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc( + dpu_enc->cur_master->hw_mdptop, + dpu_kms->catalog); + + _dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info); +} + +void dpu_encoder_virt_restore(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && (phys != dpu_enc->cur_master) && phys->ops.restore) + phys->ops.restore(phys); + } + + if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore) + dpu_enc->cur_master->ops.restore(dpu_enc->cur_master); + + _dpu_encoder_virt_enable_helper(drm_enc); +} + +static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i, ret = 0; + struct drm_display_mode *cur_mode = NULL; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + cur_mode = &dpu_enc->base.crtc->state->adjusted_mode; + + trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay, + cur_mode->vdisplay); + + dpu_enc->cur_master = NULL; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.is_master && phys->ops.is_master(phys)) { + DPU_DEBUG_ENC(dpu_enc, "master is now idx %d\n", i); + dpu_enc->cur_master = phys; + break; + } + } + + if (!dpu_enc->cur_master) { + DPU_ERROR("virt encoder has no master! num_phys %d\n", i); + return; + } + + ret = dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF); + if (ret) { + DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n", + ret); + return; + } + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (!phys) + continue; + + if (phys != dpu_enc->cur_master) { + if (phys->ops.enable) + phys->ops.enable(phys); + } + + if (dpu_enc->misr_enable && (dpu_enc->disp_info.capabilities & + MSM_DISPLAY_CAP_VID_MODE) && phys->ops.setup_misr) + phys->ops.setup_misr(phys, true, + dpu_enc->misr_frame_count); + } + + if (dpu_enc->cur_master->ops.enable) + dpu_enc->cur_master->ops.enable(dpu_enc->cur_master); + + _dpu_encoder_virt_enable_helper(drm_enc); +} + +static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + struct drm_display_mode *mode; + int i = 0; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } else if (!drm_enc->dev) { + DPU_ERROR("invalid dev\n"); + return; + } else if (!drm_enc->dev->dev_private) { + DPU_ERROR("invalid dev_private\n"); + return; + } + + mode = &drm_enc->crtc->state->adjusted_mode; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + + trace_dpu_enc_disable(DRMID(drm_enc)); + + /* wait for idle */ + dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE); + + dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.disable) + phys->ops.disable(phys); + } + + /* after phys waits for frame-done, should be no more frames pending */ + if (atomic_xchg(&dpu_enc->frame_done_timeout, 0)) { + DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id); + del_timer_sync(&dpu_enc->frame_done_timer); + } + + dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + if (dpu_enc->phys_encs[i]) + dpu_enc->phys_encs[i]->connector = NULL; + } + + dpu_enc->cur_master = NULL; + + DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); + + dpu_rm_release(&dpu_kms->rm, drm_enc); +} + +static enum dpu_intf dpu_encoder_get_intf(struct dpu_mdss_cfg *catalog, + enum dpu_intf_type type, u32 controller_id) +{ + int i = 0; + + for (i = 0; i < catalog->intf_count; i++) { + if (catalog->intf[i].type == type + && catalog->intf[i].controller_id == controller_id) { + return catalog->intf[i].id; + } + } + + return INTF_MAX; +} + +static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc, + struct dpu_encoder_phys *phy_enc) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + unsigned long lock_flags; + + if (!drm_enc || !phy_enc) + return; + + DPU_ATRACE_BEGIN("encoder_vblank_callback"); + dpu_enc = to_dpu_encoder_virt(drm_enc); + + spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags); + if (dpu_enc->crtc_vblank_cb) + dpu_enc->crtc_vblank_cb(dpu_enc->crtc_vblank_cb_data); + spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags); + + atomic_inc(&phy_enc->vsync_cnt); + DPU_ATRACE_END("encoder_vblank_callback"); +} + +static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc, + struct dpu_encoder_phys *phy_enc) +{ + if (!phy_enc) + return; + + DPU_ATRACE_BEGIN("encoder_underrun_callback"); + atomic_inc(&phy_enc->underrun_cnt); + trace_dpu_enc_underrun_cb(DRMID(drm_enc), + atomic_read(&phy_enc->underrun_cnt)); + DPU_ATRACE_END("encoder_underrun_callback"); +} + +void dpu_encoder_register_vblank_callback(struct drm_encoder *drm_enc, + void (*vbl_cb)(void *), void *vbl_data) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + unsigned long lock_flags; + bool enable; + int i; + + enable = vbl_cb ? true : false; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable); + + spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags); + dpu_enc->crtc_vblank_cb = vbl_cb; + dpu_enc->crtc_vblank_cb_data = vbl_data; + spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys && phys->ops.control_vblank_irq) + phys->ops.control_vblank_irq(phys, enable); + } +} + +void dpu_encoder_register_frame_event_callback(struct drm_encoder *drm_enc, + void (*frame_event_cb)(void *, u32 event), + void *frame_event_cb_data) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + unsigned long lock_flags; + bool enable; + + enable = frame_event_cb ? true : false; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + trace_dpu_enc_frame_event_cb(DRMID(drm_enc), enable); + + spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags); + dpu_enc->crtc_frame_event_cb = frame_event_cb; + dpu_enc->crtc_frame_event_cb_data = frame_event_cb_data; + spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags); +} + +static void dpu_encoder_frame_done_callback( + struct drm_encoder *drm_enc, + struct dpu_encoder_phys *ready_phys, u32 event) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + unsigned int i; + + if (event & (DPU_ENCODER_FRAME_EVENT_DONE + | DPU_ENCODER_FRAME_EVENT_ERROR + | DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) { + + if (!dpu_enc->frame_busy_mask[0]) { + /** + * suppress frame_done without waiter, + * likely autorefresh + */ + trace_dpu_enc_frame_done_cb_not_busy(DRMID(drm_enc), + event, ready_phys->intf_idx); + return; + } + + /* One of the physical encoders has become idle */ + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + if (dpu_enc->phys_encs[i] == ready_phys) { + clear_bit(i, dpu_enc->frame_busy_mask); + trace_dpu_enc_frame_done_cb(DRMID(drm_enc), i, + dpu_enc->frame_busy_mask[0]); + } + } + + if (!dpu_enc->frame_busy_mask[0]) { + atomic_set(&dpu_enc->frame_done_timeout, 0); + del_timer(&dpu_enc->frame_done_timer); + + dpu_encoder_resource_control(drm_enc, + DPU_ENC_RC_EVENT_FRAME_DONE); + + if (dpu_enc->crtc_frame_event_cb) + dpu_enc->crtc_frame_event_cb( + dpu_enc->crtc_frame_event_cb_data, + event); + } + } else { + if (dpu_enc->crtc_frame_event_cb) + dpu_enc->crtc_frame_event_cb( + dpu_enc->crtc_frame_event_cb_data, event); + } +} + +static void dpu_encoder_off_work(struct kthread_work *work) +{ + struct dpu_encoder_virt *dpu_enc = container_of(work, + struct dpu_encoder_virt, delayed_off_work.work); + + if (!dpu_enc) { + DPU_ERROR("invalid dpu encoder\n"); + return; + } + + dpu_encoder_resource_control(&dpu_enc->base, + DPU_ENC_RC_EVENT_ENTER_IDLE); + + dpu_encoder_frame_done_callback(&dpu_enc->base, NULL, + DPU_ENCODER_FRAME_EVENT_IDLE); +} + +/** + * _dpu_encoder_trigger_flush - trigger flush for a physical encoder + * drm_enc: Pointer to drm encoder structure + * phys: Pointer to physical encoder structure + * extra_flush_bits: Additional bit mask to include in flush trigger + */ +static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, + struct dpu_encoder_phys *phys, uint32_t extra_flush_bits) +{ + struct dpu_hw_ctl *ctl; + int pending_kickoff_cnt; + u32 ret = UINT_MAX; + + if (!drm_enc || !phys) { + DPU_ERROR("invalid argument(s), drm_enc %d, phys_enc %d\n", + drm_enc != 0, phys != 0); + return; + } + + if (!phys->hw_pp) { + DPU_ERROR("invalid pingpong hw\n"); + return; + } + + ctl = phys->hw_ctl; + if (!ctl || !ctl->ops.trigger_flush) { + DPU_ERROR("missing trigger cb\n"); + return; + } + + pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys); + + if (extra_flush_bits && ctl->ops.update_pending_flush) + ctl->ops.update_pending_flush(ctl, extra_flush_bits); + + ctl->ops.trigger_flush(ctl); + + if (ctl->ops.get_pending_flush) + ret = ctl->ops.get_pending_flush(ctl); + + trace_dpu_enc_trigger_flush(DRMID(drm_enc), phys->intf_idx, + pending_kickoff_cnt, ctl->idx, ret); +} + +/** + * _dpu_encoder_trigger_start - trigger start for a physical encoder + * phys: Pointer to physical encoder structure + */ +static inline void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) +{ + if (!phys) { + DPU_ERROR("invalid argument(s)\n"); + return; + } + + if (!phys->hw_pp) { + DPU_ERROR("invalid pingpong hw\n"); + return; + } + + if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED) + phys->ops.trigger_start(phys); +} + +void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_hw_ctl *ctl; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + ctl = phys_enc->hw_ctl; + if (ctl && ctl->ops.trigger_start) { + ctl->ops.trigger_start(ctl); + trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx); + } +} + +static int dpu_encoder_helper_wait_event_timeout( + int32_t drm_id, + int32_t hw_id, + struct dpu_encoder_wait_info *info) +{ + int rc = 0; + s64 expected_time = ktime_to_ms(ktime_get()) + info->timeout_ms; + s64 jiffies = msecs_to_jiffies(info->timeout_ms); + s64 time; + + do { + rc = wait_event_timeout(*(info->wq), + atomic_read(info->atomic_cnt) == 0, jiffies); + time = ktime_to_ms(ktime_get()); + + trace_dpu_enc_wait_event_timeout(drm_id, hw_id, rc, time, + expected_time, + atomic_read(info->atomic_cnt)); + /* If we timed out, counter is valid and time is less, wait again */ + } while (atomic_read(info->atomic_cnt) && (rc == 0) && + (time < expected_time)); + + return rc; +} + +void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_hw_ctl *ctl; + int rc; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(phys_enc->parent); + ctl = phys_enc->hw_ctl; + + if (!ctl || !ctl->ops.reset) + return; + + DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent), + ctl->idx); + + rc = ctl->ops.reset(ctl); + if (rc) { + DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n", ctl->idx); + dpu_dbg_dump(false, __func__, true, true); + } + + phys_enc->enable_state = DPU_ENC_ENABLED; +} + +/** + * _dpu_encoder_kickoff_phys - handle physical encoder kickoff + * Iterate through the physical encoders and perform consolidated flush + * and/or control start triggering as needed. This is done in the virtual + * encoder rather than the individual physical ones in order to handle + * use cases that require visibility into multiple physical encoders at + * a time. + * dpu_enc: Pointer to virtual encoder structure + */ +static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc) +{ + struct dpu_hw_ctl *ctl; + uint32_t i, pending_flush; + unsigned long lock_flags; + + if (!dpu_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + pending_flush = 0x0; + + /* update pending counts and trigger kickoff ctl flush atomically */ + spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags); + + /* don't perform flush/start operations for slave encoders */ + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (!phys || phys->enable_state == DPU_ENC_DISABLED) + continue; + + ctl = phys->hw_ctl; + if (!ctl) + continue; + + if (phys->split_role != ENC_ROLE_SLAVE) + set_bit(i, dpu_enc->frame_busy_mask); + if (!phys->ops.needs_single_flush || + !phys->ops.needs_single_flush(phys)) + _dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0); + else if (ctl->ops.get_pending_flush) + pending_flush |= ctl->ops.get_pending_flush(ctl); + } + + /* for split flush, combine pending flush masks and send to master */ + if (pending_flush && dpu_enc->cur_master) { + _dpu_encoder_trigger_flush( + &dpu_enc->base, + dpu_enc->cur_master, + pending_flush); + } + + _dpu_encoder_trigger_start(dpu_enc->cur_master); + + spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags); +} + +void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + unsigned int i; + struct dpu_hw_ctl *ctl; + struct msm_display_info *disp_info; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + disp_info = &dpu_enc->disp_info; + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys = dpu_enc->phys_encs[i]; + + if (phys && phys->hw_ctl) { + ctl = phys->hw_ctl; + if (ctl->ops.clear_pending_flush) + ctl->ops.clear_pending_flush(ctl); + + /* update only for command mode primary ctl */ + if ((phys == dpu_enc->cur_master) && + (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) + && ctl->ops.trigger_pending) + ctl->ops.trigger_pending(ctl); + } + } +} + +static u32 _dpu_encoder_calculate_linetime(struct dpu_encoder_virt *dpu_enc, + struct drm_display_mode *mode) +{ + u64 pclk_rate; + u32 pclk_period; + u32 line_time; + + /* + * For linetime calculation, only operate on master encoder. + */ + if (!dpu_enc->cur_master) + return 0; + + if (!dpu_enc->cur_master->ops.get_line_count) { + DPU_ERROR("get_line_count function not defined\n"); + return 0; + } + + pclk_rate = mode->clock; /* pixel clock in kHz */ + if (pclk_rate == 0) { + DPU_ERROR("pclk is 0, cannot calculate line time\n"); + return 0; + } + + pclk_period = DIV_ROUND_UP_ULL(1000000000ull, pclk_rate); + if (pclk_period == 0) { + DPU_ERROR("pclk period is 0\n"); + return 0; + } + + /* + * Line time calculation based on Pixel clock and HTOTAL. + * Final unit is in ns. + */ + line_time = (pclk_period * mode->htotal) / 1000; + if (line_time == 0) { + DPU_ERROR("line time calculation is 0\n"); + return 0; + } + + DPU_DEBUG_ENC(dpu_enc, + "clk_rate=%lldkHz, clk_period=%d, linetime=%dns\n", + pclk_rate, pclk_period, line_time); + + return line_time; +} + +static int _dpu_encoder_wakeup_time(struct drm_encoder *drm_enc, + ktime_t *wakeup_time) +{ + struct drm_display_mode *mode; + struct dpu_encoder_virt *dpu_enc; + u32 cur_line; + u32 line_time; + u32 vtotal, time_to_vsync; + ktime_t cur_time; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + + if (!drm_enc->crtc || !drm_enc->crtc->state) { + DPU_ERROR("crtc/crtc state object is NULL\n"); + return -EINVAL; + } + mode = &drm_enc->crtc->state->adjusted_mode; + + line_time = _dpu_encoder_calculate_linetime(dpu_enc, mode); + if (!line_time) + return -EINVAL; + + cur_line = dpu_enc->cur_master->ops.get_line_count(dpu_enc->cur_master); + + vtotal = mode->vtotal; + if (cur_line >= vtotal) + time_to_vsync = line_time * vtotal; + else + time_to_vsync = line_time * (vtotal - cur_line); + + if (time_to_vsync == 0) { + DPU_ERROR("time to vsync should not be zero, vtotal=%d\n", + vtotal); + return -EINVAL; + } + + cur_time = ktime_get(); + *wakeup_time = ktime_add_ns(cur_time, time_to_vsync); + + DPU_DEBUG_ENC(dpu_enc, + "cur_line=%u vtotal=%u time_to_vsync=%u, cur_time=%lld, wakeup_time=%lld\n", + cur_line, vtotal, time_to_vsync, + ktime_to_ms(cur_time), + ktime_to_ms(*wakeup_time)); + return 0; +} + +static void dpu_encoder_vsync_event_handler(struct timer_list *t) +{ + struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t, + vsync_event_timer); + struct drm_encoder *drm_enc = &dpu_enc->base; + struct msm_drm_private *priv; + struct msm_drm_thread *event_thread; + + if (!drm_enc->dev || !drm_enc->dev->dev_private || + !drm_enc->crtc) { + DPU_ERROR("invalid parameters\n"); + return; + } + + priv = drm_enc->dev->dev_private; + + if (drm_enc->crtc->index >= ARRAY_SIZE(priv->event_thread)) { + DPU_ERROR("invalid crtc index\n"); + return; + } + event_thread = &priv->event_thread[drm_enc->crtc->index]; + if (!event_thread) { + DPU_ERROR("event_thread not found for crtc:%d\n", + drm_enc->crtc->index); + return; + } + + del_timer(&dpu_enc->vsync_event_timer); +} + +static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work) +{ + struct dpu_encoder_virt *dpu_enc = container_of(work, + struct dpu_encoder_virt, vsync_event_work); + ktime_t wakeup_time; + + if (!dpu_enc) { + DPU_ERROR("invalid dpu encoder\n"); + return; + } + + if (_dpu_encoder_wakeup_time(&dpu_enc->base, &wakeup_time)) + return; + + trace_dpu_enc_vsync_event_work(DRMID(&dpu_enc->base), wakeup_time); + mod_timer(&dpu_enc->vsync_event_timer, + nsecs_to_jiffies(ktime_to_ns(wakeup_time))); +} + +void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc, + struct dpu_encoder_kickoff_params *params) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + bool needs_hw_reset = false; + unsigned int i; + + if (!drm_enc || !params) { + DPU_ERROR("invalid args\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + + trace_dpu_enc_prepare_kickoff(DRMID(drm_enc)); + + /* prepare for next kickoff, may include waiting on previous kickoff */ + DPU_ATRACE_BEGIN("enc_prepare_for_kickoff"); + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys = dpu_enc->phys_encs[i]; + if (phys) { + if (phys->ops.prepare_for_kickoff) + phys->ops.prepare_for_kickoff(phys, params); + if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET) + needs_hw_reset = true; + } + } + DPU_ATRACE_END("enc_prepare_for_kickoff"); + + dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF); + + /* if any phys needs reset, reset all phys, in-order */ + if (needs_hw_reset) { + trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc)); + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys = dpu_enc->phys_encs[i]; + if (phys && phys->ops.hw_reset) + phys->ops.hw_reset(phys); + } + } +} + +void dpu_encoder_kickoff(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + ktime_t wakeup_time; + unsigned int i; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + DPU_ATRACE_BEGIN("encoder_kickoff"); + dpu_enc = to_dpu_encoder_virt(drm_enc); + + trace_dpu_enc_kickoff(DRMID(drm_enc)); + + atomic_set(&dpu_enc->frame_done_timeout, + DPU_FRAME_DONE_TIMEOUT * 1000 / + drm_enc->crtc->state->adjusted_mode.vrefresh); + mod_timer(&dpu_enc->frame_done_timer, jiffies + + ((atomic_read(&dpu_enc->frame_done_timeout) * HZ) / 1000)); + + /* All phys encs are ready to go, trigger the kickoff */ + _dpu_encoder_kickoff_phys(dpu_enc); + + /* allow phys encs to handle any post-kickoff business */ + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys = dpu_enc->phys_encs[i]; + if (phys && phys->ops.handle_post_kickoff) + phys->ops.handle_post_kickoff(phys); + } + + if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DSI && + !_dpu_encoder_wakeup_time(drm_enc, &wakeup_time)) { + trace_dpu_enc_early_kickoff(DRMID(drm_enc), + ktime_to_ms(wakeup_time)); + mod_timer(&dpu_enc->vsync_event_timer, + nsecs_to_jiffies(ktime_to_ns(wakeup_time))); + } + + DPU_ATRACE_END("encoder_kickoff"); +} + +void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + int i; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + phys = dpu_enc->phys_encs[i]; + if (phys && phys->ops.prepare_commit) + phys->ops.prepare_commit(phys); + } +} + +#ifdef CONFIG_DEBUG_FS +static int _dpu_encoder_status_show(struct seq_file *s, void *data) +{ + struct dpu_encoder_virt *dpu_enc; + int i; + + if (!s || !s->private) + return -EINVAL; + + dpu_enc = s->private; + + mutex_lock(&dpu_enc->enc_lock); + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (!phys) + continue; + + seq_printf(s, "intf:%d vsync:%8d underrun:%8d ", + phys->intf_idx - INTF_0, + atomic_read(&phys->vsync_cnt), + atomic_read(&phys->underrun_cnt)); + + switch (phys->intf_mode) { + case INTF_MODE_VIDEO: + seq_puts(s, "mode: video\n"); + break; + case INTF_MODE_CMD: + seq_puts(s, "mode: command\n"); + break; + default: + seq_puts(s, "mode: ???\n"); + break; + } + } + mutex_unlock(&dpu_enc->enc_lock); + + return 0; +} + +static int _dpu_encoder_debugfs_status_open(struct inode *inode, + struct file *file) +{ + return single_open(file, _dpu_encoder_status_show, inode->i_private); +} + +static ssize_t _dpu_encoder_misr_setup(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + struct dpu_encoder_virt *dpu_enc; + int i = 0, rc; + char buf[MISR_BUFF_SIZE + 1]; + size_t buff_copy; + u32 frame_count, enable; + + if (!file || !file->private_data) + return -EINVAL; + + dpu_enc = file->private_data; + + buff_copy = min_t(size_t, count, MISR_BUFF_SIZE); + if (copy_from_user(buf, user_buf, buff_copy)) + return -EINVAL; + + buf[buff_copy] = 0; /* end of string */ + + if (sscanf(buf, "%u %u", &enable, &frame_count) != 2) + return -EINVAL; + + rc = _dpu_encoder_power_enable(dpu_enc, true); + if (rc) + return rc; + + mutex_lock(&dpu_enc->enc_lock); + dpu_enc->misr_enable = enable; + dpu_enc->misr_frame_count = frame_count; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (!phys || !phys->ops.setup_misr) + continue; + + phys->ops.setup_misr(phys, enable, frame_count); + } + mutex_unlock(&dpu_enc->enc_lock); + _dpu_encoder_power_enable(dpu_enc, false); + + return count; +} + +static ssize_t _dpu_encoder_misr_read(struct file *file, + char __user *user_buff, size_t count, loff_t *ppos) +{ + struct dpu_encoder_virt *dpu_enc; + int i = 0, len = 0; + char buf[MISR_BUFF_SIZE + 1] = {'\0'}; + int rc; + + if (*ppos) + return 0; + + if (!file || !file->private_data) + return -EINVAL; + + dpu_enc = file->private_data; + + rc = _dpu_encoder_power_enable(dpu_enc, true); + if (rc) + return rc; + + mutex_lock(&dpu_enc->enc_lock); + if (!dpu_enc->misr_enable) { + len += snprintf(buf + len, MISR_BUFF_SIZE - len, + "disabled\n"); + goto buff_check; + } else if (dpu_enc->disp_info.capabilities & + ~MSM_DISPLAY_CAP_VID_MODE) { + len += snprintf(buf + len, MISR_BUFF_SIZE - len, + "unsupported\n"); + goto buff_check; + } + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (!phys || !phys->ops.collect_misr) + continue; + + len += snprintf(buf + len, MISR_BUFF_SIZE - len, + "Intf idx:%d\n", phys->intf_idx - INTF_0); + len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n", + phys->ops.collect_misr(phys)); + } + +buff_check: + if (count <= len) { + len = 0; + goto end; + } + + if (copy_to_user(user_buff, buf, len)) { + len = -EFAULT; + goto end; + } + + *ppos += len; /* increase offset */ + +end: + mutex_unlock(&dpu_enc->enc_lock); + _dpu_encoder_power_enable(dpu_enc, false); + return len; +} + +static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + int i; + + static const struct file_operations debugfs_status_fops = { + .open = _dpu_encoder_debugfs_status_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + }; + + static const struct file_operations debugfs_misr_fops = { + .open = simple_open, + .read = _dpu_encoder_misr_read, + .write = _dpu_encoder_misr_setup, + }; + + char name[DPU_NAME_SIZE]; + + if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) { + DPU_ERROR("invalid encoder or kms\n"); + return -EINVAL; + } + + dpu_enc = to_dpu_encoder_virt(drm_enc); + priv = drm_enc->dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + + snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id); + + /* create overall sub-directory for the encoder */ + dpu_enc->debugfs_root = debugfs_create_dir(name, + drm_enc->dev->primary->debugfs_root); + if (!dpu_enc->debugfs_root) + return -ENOMEM; + + /* don't error check these */ + debugfs_create_file("status", 0600, + dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops); + + debugfs_create_file("misr_data", 0600, + dpu_enc->debugfs_root, dpu_enc, &debugfs_misr_fops); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) + if (dpu_enc->phys_encs[i] && + dpu_enc->phys_encs[i]->ops.late_register) + dpu_enc->phys_encs[i]->ops.late_register( + dpu_enc->phys_encs[i], + dpu_enc->debugfs_root); + + return 0; +} + +static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + + if (!drm_enc) + return; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + debugfs_remove_recursive(dpu_enc->debugfs_root); +} +#else +static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc) +{ + return 0; +} + +static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc) +{ +} +#endif + +static int dpu_encoder_late_register(struct drm_encoder *encoder) +{ + return _dpu_encoder_init_debugfs(encoder); +} + +static void dpu_encoder_early_unregister(struct drm_encoder *encoder) +{ + _dpu_encoder_destroy_debugfs(encoder); +} + +static int dpu_encoder_virt_add_phys_encs( + u32 display_caps, + struct dpu_encoder_virt *dpu_enc, + struct dpu_enc_phys_init_params *params) +{ + struct dpu_encoder_phys *enc = NULL; + + DPU_DEBUG_ENC(dpu_enc, "\n"); + + /* + * We may create up to NUM_PHYS_ENCODER_TYPES physical encoder types + * in this function, check up-front. + */ + if (dpu_enc->num_phys_encs + NUM_PHYS_ENCODER_TYPES >= + ARRAY_SIZE(dpu_enc->phys_encs)) { + DPU_ERROR_ENC(dpu_enc, "too many physical encoders %d\n", + dpu_enc->num_phys_encs); + return -EINVAL; + } + + if (display_caps & MSM_DISPLAY_CAP_VID_MODE) { + enc = dpu_encoder_phys_vid_init(params); + + if (IS_ERR_OR_NULL(enc)) { + DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n", + PTR_ERR(enc)); + return enc == 0 ? -EINVAL : PTR_ERR(enc); + } + + dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; + ++dpu_enc->num_phys_encs; + } + + if (display_caps & MSM_DISPLAY_CAP_CMD_MODE) { + enc = dpu_encoder_phys_cmd_init(params); + + if (IS_ERR_OR_NULL(enc)) { + DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n", + PTR_ERR(enc)); + return enc == 0 ? -EINVAL : PTR_ERR(enc); + } + + dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc; + ++dpu_enc->num_phys_encs; + } + + return 0; +} + +static const struct dpu_encoder_virt_ops dpu_encoder_parent_ops = { + .handle_vblank_virt = dpu_encoder_vblank_callback, + .handle_underrun_virt = dpu_encoder_underrun_callback, + .handle_frame_done = dpu_encoder_frame_done_callback, +}; + +static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, + struct dpu_kms *dpu_kms, + struct msm_display_info *disp_info, + int *drm_enc_mode) +{ + int ret = 0; + int i = 0; + enum dpu_intf_type intf_type; + struct dpu_enc_phys_init_params phys_params; + + if (!dpu_enc || !dpu_kms) { + DPU_ERROR("invalid arg(s), enc %d kms %d\n", + dpu_enc != 0, dpu_kms != 0); + return -EINVAL; + } + + memset(&phys_params, 0, sizeof(phys_params)); + phys_params.dpu_kms = dpu_kms; + phys_params.parent = &dpu_enc->base; + phys_params.parent_ops = &dpu_encoder_parent_ops; + phys_params.enc_spinlock = &dpu_enc->enc_spinlock; + + DPU_DEBUG("\n"); + + if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI) { + *drm_enc_mode = DRM_MODE_ENCODER_DSI; + intf_type = INTF_DSI; + } else if (disp_info->intf_type == DRM_MODE_CONNECTOR_HDMIA) { + *drm_enc_mode = DRM_MODE_ENCODER_TMDS; + intf_type = INTF_HDMI; + } else if (disp_info->intf_type == DRM_MODE_CONNECTOR_DisplayPort) { + *drm_enc_mode = DRM_MODE_ENCODER_TMDS; + intf_type = INTF_DP; + } else { + DPU_ERROR_ENC(dpu_enc, "unsupported display interface type\n"); + return -EINVAL; + } + + WARN_ON(disp_info->num_of_h_tiles < 1); + + dpu_enc->display_num_of_h_tiles = disp_info->num_of_h_tiles; + + DPU_DEBUG("dsi_info->num_of_h_tiles %d\n", disp_info->num_of_h_tiles); + + if ((disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) || + (disp_info->capabilities & MSM_DISPLAY_CAP_VID_MODE)) + dpu_enc->idle_pc_supported = + dpu_kms->catalog->caps->has_idle_pc; + + mutex_lock(&dpu_enc->enc_lock); + for (i = 0; i < disp_info->num_of_h_tiles && !ret; i++) { + /* + * Left-most tile is at index 0, content is controller id + * h_tile_instance_ids[2] = {0, 1}; DSI0 = left, DSI1 = right + * h_tile_instance_ids[2] = {1, 0}; DSI1 = left, DSI0 = right + */ + u32 controller_id = disp_info->h_tile_instance[i]; + + if (disp_info->num_of_h_tiles > 1) { + if (i == 0) + phys_params.split_role = ENC_ROLE_MASTER; + else + phys_params.split_role = ENC_ROLE_SLAVE; + } else { + phys_params.split_role = ENC_ROLE_SOLO; + } + + DPU_DEBUG("h_tile_instance %d = %d, split_role %d\n", + i, controller_id, phys_params.split_role); + + phys_params.intf_idx = dpu_encoder_get_intf(dpu_kms->catalog, + intf_type, + controller_id); + if (phys_params.intf_idx == INTF_MAX) { + DPU_ERROR_ENC(dpu_enc, "could not get intf: type %d, id %d\n", + intf_type, controller_id); + ret = -EINVAL; + } + + if (!ret) { + ret = dpu_encoder_virt_add_phys_encs(disp_info->capabilities, + dpu_enc, + &phys_params); + if (ret) + DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n"); + } + } + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys) { + atomic_set(&phys->vsync_cnt, 0); + atomic_set(&phys->underrun_cnt, 0); + } + } + mutex_unlock(&dpu_enc->enc_lock); + + return ret; +} + +static void dpu_encoder_frame_done_timeout(struct timer_list *t) +{ + struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t, + frame_done_timer); + struct drm_encoder *drm_enc = &dpu_enc->base; + struct msm_drm_private *priv; + u32 event; + + if (!drm_enc->dev || !drm_enc->dev->dev_private) { + DPU_ERROR("invalid parameters\n"); + return; + } + priv = drm_enc->dev->dev_private; + + if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) { + DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n", + DRMID(drm_enc), dpu_enc->frame_busy_mask[0]); + return; + } else if (!atomic_xchg(&dpu_enc->frame_done_timeout, 0)) { + DRM_DEBUG_KMS("id:%u invalid timeout\n", DRMID(drm_enc)); + return; + } + + DPU_ERROR_ENC(dpu_enc, "frame done timeout\n"); + + event = DPU_ENCODER_FRAME_EVENT_ERROR; + trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event); + dpu_enc->crtc_frame_event_cb(dpu_enc->crtc_frame_event_cb_data, event); +} + +static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = { + .mode_set = dpu_encoder_virt_mode_set, + .disable = dpu_encoder_virt_disable, + .enable = dpu_kms_encoder_enable, + .atomic_check = dpu_encoder_virt_atomic_check, + + /* This is called by dpu_kms_encoder_enable */ + .commit = dpu_encoder_virt_enable, +}; + +static const struct drm_encoder_funcs dpu_encoder_funcs = { + .destroy = dpu_encoder_destroy, + .late_register = dpu_encoder_late_register, + .early_unregister = dpu_encoder_early_unregister, +}; + +int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, + struct msm_display_info *disp_info) +{ + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); + struct drm_encoder *drm_enc = NULL; + struct dpu_encoder_virt *dpu_enc = NULL; + int drm_enc_mode = DRM_MODE_ENCODER_NONE; + int ret = 0; + + dpu_enc = to_dpu_encoder_virt(enc); + + mutex_init(&dpu_enc->enc_lock); + ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info, + &drm_enc_mode); + if (ret) + goto fail; + + dpu_enc->cur_master = NULL; + spin_lock_init(&dpu_enc->enc_spinlock); + + atomic_set(&dpu_enc->frame_done_timeout, 0); + timer_setup(&dpu_enc->frame_done_timer, + dpu_encoder_frame_done_timeout, 0); + + if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI) + timer_setup(&dpu_enc->vsync_event_timer, + dpu_encoder_vsync_event_handler, + 0); + + + mutex_init(&dpu_enc->rc_lock); + kthread_init_delayed_work(&dpu_enc->delayed_off_work, + dpu_encoder_off_work); + dpu_enc->idle_timeout = IDLE_TIMEOUT; + + kthread_init_work(&dpu_enc->vsync_event_work, + dpu_encoder_vsync_event_work_handler); + + memcpy(&dpu_enc->disp_info, disp_info, sizeof(*disp_info)); + + DPU_DEBUG_ENC(dpu_enc, "created\n"); + + return ret; + +fail: + DPU_ERROR("failed to create encoder\n"); + if (drm_enc) + dpu_encoder_destroy(drm_enc); + + return ret; + + +} + +struct drm_encoder *dpu_encoder_init(struct drm_device *dev, + int drm_enc_mode) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int rc = 0; + + dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL); + if (!dpu_enc) + return ERR_PTR(ENOMEM); + + rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs, + drm_enc_mode, NULL); + if (rc) { + devm_kfree(dev->dev, dpu_enc); + return ERR_PTR(rc); + } + + drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs); + + return &dpu_enc->base; +} + +int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc, + enum msm_event_wait event) +{ + int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL; + struct dpu_encoder_virt *dpu_enc = NULL; + int i, ret = 0; + + if (!drm_enc) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + dpu_enc = to_dpu_encoder_virt(drm_enc); + DPU_DEBUG_ENC(dpu_enc, "\n"); + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + switch (event) { + case MSM_ENC_COMMIT_DONE: + fn_wait = phys->ops.wait_for_commit_done; + break; + case MSM_ENC_TX_COMPLETE: + fn_wait = phys->ops.wait_for_tx_complete; + break; + case MSM_ENC_VBLANK: + fn_wait = phys->ops.wait_for_vblank; + break; + default: + DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n", + event); + return -EINVAL; + }; + + if (phys && fn_wait) { + DPU_ATRACE_BEGIN("wait_for_completion_event"); + ret = fn_wait(phys); + DPU_ATRACE_END("wait_for_completion_event"); + if (ret) + return ret; + } + } + + return ret; +} + +enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder) +{ + struct dpu_encoder_virt *dpu_enc = NULL; + int i; + + if (!encoder) { + DPU_ERROR("invalid encoder\n"); + return INTF_MODE_NONE; + } + dpu_enc = to_dpu_encoder_virt(encoder); + + if (dpu_enc->cur_master) + return dpu_enc->cur_master->intf_mode; + + for (i = 0; i < dpu_enc->num_phys_encs; i++) { + struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + + if (phys) + return phys->intf_mode; + } + + return INTF_MODE_NONE; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h new file mode 100644 index 000000000000..60f809fc7c13 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -0,0 +1,177 @@ +/* + * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __DPU_ENCODER_H__ +#define __DPU_ENCODER_H__ + +#include <drm/drm_crtc.h> +#include "dpu_hw_mdss.h" + +#define DPU_ENCODER_FRAME_EVENT_DONE BIT(0) +#define DPU_ENCODER_FRAME_EVENT_ERROR BIT(1) +#define DPU_ENCODER_FRAME_EVENT_PANEL_DEAD BIT(2) +#define DPU_ENCODER_FRAME_EVENT_IDLE BIT(3) + +#define IDLE_TIMEOUT (66 - 16/2) + +/** + * Encoder functions and data types + * @intfs: Interfaces this encoder is using, INTF_MODE_NONE if unused + * @needs_cdm: Encoder requests a CDM based on pixel format conversion needs + * @display_num_of_h_tiles: Number of horizontal tiles in case of split + * interface + * @topology: Topology of the display + */ +struct dpu_encoder_hw_resources { + enum dpu_intf_mode intfs[INTF_MAX]; + bool needs_cdm; + u32 display_num_of_h_tiles; +}; + +/** + * dpu_encoder_kickoff_params - info encoder requires at kickoff + * @affected_displays: bitmask, bit set means the ROI of the commit lies within + * the bounds of the physical display at the bit index + */ +struct dpu_encoder_kickoff_params { + unsigned long affected_displays; +}; + +/** + * dpu_encoder_get_hw_resources - Populate table of required hardware resources + * @encoder: encoder pointer + * @hw_res: resource table to populate with encoder required resources + * @conn_state: report hw reqs based on this proposed connector state + */ +void dpu_encoder_get_hw_resources(struct drm_encoder *encoder, + struct dpu_encoder_hw_resources *hw_res, + struct drm_connector_state *conn_state); + +/** + * dpu_encoder_register_vblank_callback - provide callback to encoder that + * will be called on the next vblank. + * @encoder: encoder pointer + * @cb: callback pointer, provide NULL to deregister and disable IRQs + * @data: user data provided to callback + */ +void dpu_encoder_register_vblank_callback(struct drm_encoder *encoder, + void (*cb)(void *), void *data); + +/** + * dpu_encoder_register_frame_event_callback - provide callback to encoder that + * will be called after the request is complete, or other events. + * @encoder: encoder pointer + * @cb: callback pointer, provide NULL to deregister + * @data: user data provided to callback + */ +void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder, + void (*cb)(void *, u32), void *data); + +/** + * dpu_encoder_prepare_for_kickoff - schedule double buffer flip of the ctl + * path (i.e. ctl flush and start) at next appropriate time. + * Immediately: if no previous commit is outstanding. + * Delayed: Block until next trigger can be issued. + * @encoder: encoder pointer + * @params: kickoff time parameters + */ +void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder, + struct dpu_encoder_kickoff_params *params); + +/** + * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous + * kickoff and trigger the ctl prepare progress for command mode display. + * @encoder: encoder pointer + */ +void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder); + +/** + * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path + * (i.e. ctl flush and start) immediately. + * @encoder: encoder pointer + */ +void dpu_encoder_kickoff(struct drm_encoder *encoder); + +/** + * dpu_encoder_wait_for_event - Waits for encoder events + * @encoder: encoder pointer + * @event: event to wait for + * MSM_ENC_COMMIT_DONE - Wait for hardware to have flushed the current pending + * frames to hardware at a vblank or ctl_start + * Encoders will map this differently depending on the + * panel type. + * vid mode -> vsync_irq + * cmd mode -> ctl_start + * MSM_ENC_TX_COMPLETE - Wait for the hardware to transfer all the pixels to + * the panel. Encoders will map this differently + * depending on the panel type. + * vid mode -> vsync_irq + * cmd mode -> pp_done + * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise + */ +int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder, + enum msm_event_wait event); + +/* + * dpu_encoder_get_intf_mode - get interface mode of the given encoder + * @encoder: Pointer to drm encoder object + */ +enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder); + +/** + * dpu_encoder_virt_restore - restore the encoder configs + * @encoder: encoder pointer + */ +void dpu_encoder_virt_restore(struct drm_encoder *encoder); + +/** + * dpu_encoder_init - initialize virtual encoder object + * @dev: Pointer to drm device structure + * @disp_info: Pointer to display information structure + * Returns: Pointer to newly created drm encoder + */ +struct drm_encoder *dpu_encoder_init( + struct drm_device *dev, + int drm_enc_mode); + +/** + * dpu_encoder_setup - setup dpu_encoder for the display probed + * @dev: Pointer to drm device structure + * @enc: Pointer to the drm_encoder + * @disp_info: Pointer to the display info + */ +int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, + struct msm_display_info *disp_info); + +/** + * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an + * atomic commit, before any registers are written + * @drm_enc: Pointer to previously created drm encoder structure + */ +void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc); + +/** + * dpu_encoder_set_idle_timeout - set the idle timeout for video + * and command mode encoders. + * @drm_enc: Pointer to previously created drm encoder structure + * @idle_timeout: idle timeout duration in milliseconds + */ +void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc, + u32 idle_timeout); + +#endif /* __DPU_ENCODER_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h new file mode 100644 index 000000000000..c7df8aad6613 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -0,0 +1,430 @@ +/* + * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#ifndef __DPU_ENCODER_PHYS_H__ +#define __DPU_ENCODER_PHYS_H__ + +#include <linux/jiffies.h> + +#include "dpu_kms.h" +#include "dpu_hw_intf.h" +#include "dpu_hw_pingpong.h" +#include "dpu_hw_ctl.h" +#include "dpu_hw_top.h" +#include "dpu_hw_cdm.h" +#include "dpu_encoder.h" + +#define DPU_ENCODER_NAME_MAX 16 + +/* wait for at most 2 vsync for lowest refresh rate (24hz) */ +#define KICKOFF_TIMEOUT_MS 84 +#define KICKOFF_TIMEOUT_JIFFIES msecs_to_jiffies(KICKOFF_TIMEOUT_MS) + +/** + * enum dpu_enc_split_role - Role this physical encoder will play in a + * split-panel configuration, where one panel is master, and others slaves. + * Masters have extra responsibilities, like managing the VBLANK IRQ. + * @ENC_ROLE_SOLO: This is the one and only panel. This encoder is master. + * @ENC_ROLE_MASTER: This encoder is the master of a split panel config. + * @ENC_ROLE_SLAVE: This encoder is not the master of a split panel config. + */ +enum dpu_enc_split_role { + ENC_ROLE_SOLO, + ENC_ROLE_MASTER, + ENC_ROLE_SLAVE, +}; + +/** + * enum dpu_enc_enable_state - current enabled state of the physical encoder + * @DPU_ENC_DISABLING: Encoder transitioning to disable state + * Events bounding transition are encoder type specific + * @DPU_ENC_DISABLED: Encoder is disabled + * @DPU_ENC_ENABLING: Encoder transitioning to enabled + * Events bounding transition are encoder type specific + * @DPU_ENC_ENABLED: Encoder is enabled + * @DPU_ENC_ERR_NEEDS_HW_RESET: Encoder is enabled, but requires a hw_reset + * to recover from a previous error + */ +enum dpu_enc_enable_state { + DPU_ENC_DISABLING, + DPU_ENC_DISABLED, + DPU_ENC_ENABLING, + DPU_ENC_ENABLED, + DPU_ENC_ERR_NEEDS_HW_RESET +}; + +struct dpu_encoder_phys; + +/** + * struct dpu_encoder_virt_ops - Interface the containing virtual encoder + * provides for the physical encoders to use to callback. + * @handle_vblank_virt: Notify virtual encoder of vblank IRQ reception + * Note: This is called from IRQ handler context. + * @handle_underrun_virt: Notify virtual encoder of underrun IRQ reception + * Note: This is called from IRQ handler context. + * @handle_frame_done: Notify virtual encoder that this phys encoder + * completes last request frame. + */ +struct dpu_encoder_virt_ops { + void (*handle_vblank_virt)(struct drm_encoder *, + struct dpu_encoder_phys *phys); + void (*handle_underrun_virt)(struct drm_encoder *, + struct dpu_encoder_phys *phys); + void (*handle_frame_done)(struct drm_encoder *, + struct dpu_encoder_phys *phys, u32 event); +}; + +/** + * struct dpu_encoder_phys_ops - Interface the physical encoders provide to + * the containing virtual encoder. + * @late_register: DRM Call. Add Userspace interfaces, debugfs. + * @prepare_commit: MSM Atomic Call, start of atomic commit sequence + * @is_master: Whether this phys_enc is the current master + * encoder. Can be switched at enable time. Based + * on split_role and current mode (CMD/VID). + * @mode_fixup: DRM Call. Fixup a DRM mode. + * @mode_set: DRM Call. Set a DRM mode. + * This likely caches the mode, for use at enable. + * @enable: DRM Call. Enable a DRM mode. + * @disable: DRM Call. Disable mode. + * @atomic_check: DRM Call. Atomic check new DRM state. + * @destroy: DRM Call. Destroy and release resources. + * @get_hw_resources: Populate the structure with the hardware + * resources that this phys_enc is using. + * Expect no overlap between phys_encs. + * @control_vblank_irq Register/Deregister for VBLANK IRQ + * @wait_for_commit_done: Wait for hardware to have flushed the + * current pending frames to hardware + * @wait_for_tx_complete: Wait for hardware to transfer the pixels + * to the panel + * @wait_for_vblank: Wait for VBLANK, for sub-driver internal use + * @prepare_for_kickoff: Do any work necessary prior to a kickoff + * For CMD encoder, may wait for previous tx done + * @handle_post_kickoff: Do any work necessary post-kickoff work + * @trigger_start: Process start event on physical encoder + * @needs_single_flush: Whether encoder slaves need to be flushed + * @setup_misr: Sets up MISR, enable and disables based on sysfs + * @collect_misr: Collects MISR data on frame update + * @hw_reset: Issue HW recovery such as CTL reset and clear + * DPU_ENC_ERR_NEEDS_HW_RESET state + * @irq_control: Handler to enable/disable all the encoder IRQs + * @prepare_idle_pc: phys encoder can update the vsync_enable status + * on idle power collapse prepare + * @restore: Restore all the encoder configs. + * @get_line_count: Obtain current vertical line count + */ + +struct dpu_encoder_phys_ops { + int (*late_register)(struct dpu_encoder_phys *encoder, + struct dentry *debugfs_root); + void (*prepare_commit)(struct dpu_encoder_phys *encoder); + bool (*is_master)(struct dpu_encoder_phys *encoder); + bool (*mode_fixup)(struct dpu_encoder_phys *encoder, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); + void (*mode_set)(struct dpu_encoder_phys *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); + void (*enable)(struct dpu_encoder_phys *encoder); + void (*disable)(struct dpu_encoder_phys *encoder); + int (*atomic_check)(struct dpu_encoder_phys *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state); + void (*destroy)(struct dpu_encoder_phys *encoder); + void (*get_hw_resources)(struct dpu_encoder_phys *encoder, + struct dpu_encoder_hw_resources *hw_res, + struct drm_connector_state *conn_state); + int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable); + int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc); + int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc); + int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc); + void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc, + struct dpu_encoder_kickoff_params *params); + void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc); + void (*trigger_start)(struct dpu_encoder_phys *phys_enc); + bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc); + + void (*setup_misr)(struct dpu_encoder_phys *phys_encs, + bool enable, u32 frame_count); + u32 (*collect_misr)(struct dpu_encoder_phys *phys_enc); + void (*hw_reset)(struct dpu_encoder_phys *phys_enc); + void (*irq_control)(struct dpu_encoder_phys *phys, bool enable); + void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc); + void (*restore)(struct dpu_encoder_phys *phys); + int (*get_line_count)(struct dpu_encoder_phys *phys); +}; + +/** + * enum dpu_intr_idx - dpu encoder interrupt index + * @INTR_IDX_VSYNC: Vsync interrupt for video mode panel + * @INTR_IDX_PINGPONG: Pingpong done unterrupt for cmd mode panel + * @INTR_IDX_UNDERRUN: Underrun unterrupt for video and cmd mode panel + * @INTR_IDX_RDPTR: Readpointer done unterrupt for cmd mode panel + */ +enum dpu_intr_idx { + INTR_IDX_VSYNC, + INTR_IDX_PINGPONG, + INTR_IDX_UNDERRUN, + INTR_IDX_CTL_START, + INTR_IDX_RDPTR, + INTR_IDX_MAX, +}; + +/** + * dpu_encoder_irq - tracking structure for interrupts + * @name: string name of interrupt + * @intr_type: Encoder interrupt type + * @intr_idx: Encoder interrupt enumeration + * @hw_idx: HW Block ID + * @irq_idx: IRQ interface lookup index from DPU IRQ framework + * will be -EINVAL if IRQ is not registered + * @irq_cb: interrupt callback + */ +struct dpu_encoder_irq { + const char *name; + enum dpu_intr_type intr_type; + enum dpu_intr_idx intr_idx; + int hw_idx; + int irq_idx; + struct dpu_irq_callback cb; +}; + +/** + * struct dpu_encoder_phys - physical encoder that drives a single INTF block + * tied to a specific panel / sub-panel. Abstract type, sub-classed by + * phys_vid or phys_cmd for video mode or command mode encs respectively. + * @parent: Pointer to the containing virtual encoder + * @connector: If a mode is set, cached pointer to the active connector + * @ops: Operations exposed to the virtual encoder + * @parent_ops: Callbacks exposed by the parent to the phys_enc + * @hw_mdptop: Hardware interface to the top registers + * @hw_ctl: Hardware interface to the ctl registers + * @hw_cdm: Hardware interface to the cdm registers + * @cdm_cfg: Chroma-down hardware configuration + * @hw_pp: Hardware interface to the ping pong registers + * @dpu_kms: Pointer to the dpu_kms top level + * @cached_mode: DRM mode cached at mode_set time, acted on in enable + * @enabled: Whether the encoder has enabled and running a mode + * @split_role: Role to play in a split-panel configuration + * @intf_mode: Interface mode + * @intf_idx: Interface index on dpu hardware + * @topology_name: topology selected for the display + * @enc_spinlock: Virtual-Encoder-Wide Spin Lock for IRQ purposes + * @enable_state: Enable state tracking + * @vblank_refcount: Reference count of vblank request + * @vsync_cnt: Vsync count for the physical encoder + * @underrun_cnt: Underrun count for the physical encoder + * @pending_kickoff_cnt: Atomic counter tracking the number of kickoffs + * vs. the number of done/vblank irqs. Should hover + * between 0-2 Incremented when a new kickoff is + * scheduled. Decremented in irq handler + * @pending_ctlstart_cnt: Atomic counter tracking the number of ctl start + * pending. + * @pending_kickoff_wq: Wait queue for blocking until kickoff completes + * @irq: IRQ tracking structures + */ +struct dpu_encoder_phys { + struct drm_encoder *parent; + struct drm_connector *connector; + struct dpu_encoder_phys_ops ops; + const struct dpu_encoder_virt_ops *parent_ops; + struct dpu_hw_mdp *hw_mdptop; + struct dpu_hw_ctl *hw_ctl; + struct dpu_hw_cdm *hw_cdm; + struct dpu_hw_cdm_cfg cdm_cfg; + struct dpu_hw_pingpong *hw_pp; + struct dpu_kms *dpu_kms; + struct drm_display_mode cached_mode; + enum dpu_enc_split_role split_role; + enum dpu_intf_mode intf_mode; + enum dpu_intf intf_idx; + enum dpu_rm_topology_name topology_name; + spinlock_t *enc_spinlock; + enum dpu_enc_enable_state enable_state; + atomic_t vblank_refcount; + atomic_t vsync_cnt; + atomic_t underrun_cnt; + atomic_t pending_ctlstart_cnt; + atomic_t pending_kickoff_cnt; + wait_queue_head_t pending_kickoff_wq; + struct dpu_encoder_irq irq[INTR_IDX_MAX]; +}; + +static inline int dpu_encoder_phys_inc_pending(struct dpu_encoder_phys *phys) +{ + atomic_inc_return(&phys->pending_ctlstart_cnt); + return atomic_inc_return(&phys->pending_kickoff_cnt); +} + +/** + * struct dpu_encoder_phys_vid - sub-class of dpu_encoder_phys to handle video + * mode specific operations + * @base: Baseclass physical encoder structure + * @hw_intf: Hardware interface to the intf registers + * @timing_params: Current timing parameter + */ +struct dpu_encoder_phys_vid { + struct dpu_encoder_phys base; + struct dpu_hw_intf *hw_intf; + struct intf_timing_params timing_params; +}; + +/** + * struct dpu_encoder_phys_cmd - sub-class of dpu_encoder_phys to handle command + * mode specific operations + * @base: Baseclass physical encoder structure + * @intf_idx: Intf Block index used by this phys encoder + * @stream_sel: Stream selection for multi-stream interfaces + * @serialize_wait4pp: serialize wait4pp feature waits for pp_done interrupt + * after ctl_start instead of before next frame kickoff + * @pp_timeout_report_cnt: number of pingpong done irq timeout errors + * @pending_vblank_cnt: Atomic counter tracking pending wait for VBLANK + * @pending_vblank_wq: Wait queue for blocking until VBLANK received + */ +struct dpu_encoder_phys_cmd { + struct dpu_encoder_phys base; + int stream_sel; + bool serialize_wait4pp; + int pp_timeout_report_cnt; + atomic_t pending_vblank_cnt; + wait_queue_head_t pending_vblank_wq; +}; + +/** + * struct dpu_enc_phys_init_params - initialization parameters for phys encs + * @dpu_kms: Pointer to the dpu_kms top level + * @parent: Pointer to the containing virtual encoder + * @parent_ops: Callbacks exposed by the parent to the phys_enc + * @split_role: Role to play in a split-panel configuration + * @intf_idx: Interface index this phys_enc will control + * @enc_spinlock: Virtual-Encoder-Wide Spin Lock for IRQ purposes + */ +struct dpu_enc_phys_init_params { + struct dpu_kms *dpu_kms; + struct drm_encoder *parent; + const struct dpu_encoder_virt_ops *parent_ops; + enum dpu_enc_split_role split_role; + enum dpu_intf intf_idx; + spinlock_t *enc_spinlock; +}; + +/** + * dpu_encoder_wait_info - container for passing arguments to irq wait functions + * @wq: wait queue structure + * @atomic_cnt: wait until atomic_cnt equals zero + * @timeout_ms: timeout value in milliseconds + */ +struct dpu_encoder_wait_info { + wait_queue_head_t *wq; + atomic_t *atomic_cnt; + s64 timeout_ms; +}; + +/** + * dpu_encoder_phys_vid_init - Construct a new video mode physical encoder + * @p: Pointer to init params structure + * Return: Error code or newly allocated encoder + */ +struct dpu_encoder_phys *dpu_encoder_phys_vid_init( + struct dpu_enc_phys_init_params *p); + +/** + * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder + * @p: Pointer to init params structure + * Return: Error code or newly allocated encoder + */ +struct dpu_encoder_phys *dpu_encoder_phys_cmd_init( + struct dpu_enc_phys_init_params *p); + +/** + * dpu_encoder_helper_trigger_start - control start helper function + * This helper function may be optionally specified by physical + * encoders if they require ctl_start triggering. + * @phys_enc: Pointer to physical encoder structure + */ +void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc); + +/** + * dpu_encoder_helper_hw_reset - issue ctl hw reset + * This helper function may be optionally specified by physical + * encoders if they require ctl hw reset. If state is currently + * DPU_ENC_ERR_NEEDS_HW_RESET, it is set back to DPU_ENC_ENABLED. + * @phys_enc: Pointer to physical encoder structure + */ +void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc); + +static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( + struct dpu_encoder_phys *phys_enc) +{ + if (!phys_enc || phys_enc->enable_state == DPU_ENC_DISABLING) + return BLEND_3D_NONE; + + if (phys_enc->split_role == ENC_ROLE_SOLO && + phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE) + return BLEND_3D_H_ROW_INT; + + return BLEND_3D_NONE; +} + +/** + * dpu_encoder_helper_split_config - split display configuration helper function + * This helper function may be used by physical encoders to configure + * the split display related registers. + * @phys_enc: Pointer to physical encoder structure + * @interface: enum dpu_intf setting + */ +void dpu_encoder_helper_split_config( + struct dpu_encoder_phys *phys_enc, + enum dpu_intf interface); + +/** + * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has + * timed out, including reporting frame error event to crtc and debug dump + * @phys_enc: Pointer to physical encoder structure + * @intr_idx: Failing interrupt index + */ +void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx); + +/** + * dpu_encoder_helper_wait_for_irq - utility to wait on an irq. + * note: will call dpu_encoder_helper_wait_for_irq on timeout + * @phys_enc: Pointer to physical encoder structure + * @intr_idx: encoder interrupt index + * @wait_info: wait info struct + * @Return: 0 or -ERROR + */ +int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx, + struct dpu_encoder_wait_info *wait_info); + +/** + * dpu_encoder_helper_register_irq - register and enable an irq + * @phys_enc: Pointer to physical encoder structure + * @intr_idx: encoder interrupt index + * @Return: 0 or -ERROR + */ +int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx); + +/** + * dpu_encoder_helper_unregister_irq - unregister and disable an irq + * @phys_enc: Pointer to physical encoder structure + * @intr_idx: encoder interrupt index + * @Return: 0 or -ERROR + */ +int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc, + enum dpu_intr_idx intr_idx); + +#endif /* __dpu_encoder_phys_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c new file mode 100644 index 000000000000..3084675ed425 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -0,0 +1,905 @@ +/* + * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include "dpu_encoder_phys.h" +#include "dpu_hw_interrupts.h" +#include "dpu_core_irq.h" +#include "dpu_formats.h" +#include "dpu_trace.h" + +#define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \ + (e) && (e)->base.parent ? \ + (e)->base.parent->base.id : -1, \ + (e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__) + +#define DPU_ERROR_CMDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \ + (e) && (e)->base.parent ? \ + (e)->base.parent->base.id : -1, \ + (e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__) + +#define to_dpu_encoder_phys_cmd(x) \ + container_of(x, struct dpu_encoder_phys_cmd, base) + +#define PP_TIMEOUT_MAX_TRIALS 10 + +/* + * Tearcheck sync start and continue thresholds are empirically found + * based on common panels In the future, may want to allow panels to override + * these default values + */ +#define DEFAULT_TEARCHECK_SYNC_THRESH_START 4 +#define DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE 4 + +#define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000 + +static inline int _dpu_encoder_phys_cmd_get_idle_timeout( + struct dpu_encoder_phys_cmd *cmd_enc) +{ + return KICKOFF_TIMEOUT_MS; +} + +static inline bool dpu_encoder_phys_cmd_is_master( + struct dpu_encoder_phys *phys_enc) +{ + return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false; +} + +static bool dpu_encoder_phys_cmd_mode_fixup( + struct dpu_encoder_phys *phys_enc, + const struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + if (phys_enc) + DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n"); + return true; +} + +static void _dpu_encoder_phys_cmd_update_intf_cfg( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + struct dpu_hw_ctl *ctl; + struct dpu_hw_intf_cfg intf_cfg = { 0 }; + + if (!phys_enc) + return; + + ctl = phys_enc->hw_ctl; + if (!ctl || !ctl->ops.setup_intf_cfg) + return; + + intf_cfg.intf = phys_enc->intf_idx; + intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD; + intf_cfg.stream_sel = cmd_enc->stream_sel; + intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); + ctl->ops.setup_intf_cfg(ctl, &intf_cfg); +} + +static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + unsigned long lock_flags; + int new_cnt; + u32 event = DPU_ENCODER_FRAME_EVENT_DONE; + + if (!phys_enc || !phys_enc->hw_pp) + return; + + DPU_ATRACE_BEGIN("pp_done_irq"); + /* notify all synchronous clients first, then asynchronous clients */ + if (phys_enc->parent_ops->handle_frame_done) + phys_enc->parent_ops->handle_frame_done(phys_enc->parent, + phys_enc, event); + + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); + + trace_dpu_enc_phys_cmd_pp_tx_done(DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + new_cnt, event); + + /* Signal any waiting atomic commit thread */ + wake_up_all(&phys_enc->pending_kickoff_wq); + DPU_ATRACE_END("pp_done_irq"); +} + +static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + struct dpu_encoder_phys_cmd *cmd_enc; + + if (!phys_enc || !phys_enc->hw_pp) + return; + + DPU_ATRACE_BEGIN("rd_ptr_irq"); + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + if (phys_enc->parent_ops->handle_vblank_virt) + phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent, + phys_enc); + + atomic_add_unless(&cmd_enc->pending_vblank_cnt, -1, 0); + wake_up_all(&cmd_enc->pending_vblank_wq); + DPU_ATRACE_END("rd_ptr_irq"); +} + +static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + struct dpu_encoder_phys_cmd *cmd_enc; + + if (!phys_enc || !phys_enc->hw_ctl) + return; + + DPU_ATRACE_BEGIN("ctl_start_irq"); + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0); + + /* Signal any waiting ctl start interrupt */ + wake_up_all(&phys_enc->pending_kickoff_wq); + DPU_ATRACE_END("ctl_start_irq"); +} + +static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + + if (!phys_enc) + return; + + if (phys_enc->parent_ops->handle_underrun_virt) + phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent, + phys_enc); +} + +static void _dpu_encoder_phys_cmd_setup_irq_hw_idx( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_irq *irq; + + irq = &phys_enc->irq[INTR_IDX_CTL_START]; + irq->hw_idx = phys_enc->hw_ctl->idx; + irq->irq_idx = -EINVAL; + + irq = &phys_enc->irq[INTR_IDX_PINGPONG]; + irq->hw_idx = phys_enc->hw_pp->idx; + irq->irq_idx = -EINVAL; + + irq = &phys_enc->irq[INTR_IDX_RDPTR]; + irq->hw_idx = phys_enc->hw_pp->idx; + irq->irq_idx = -EINVAL; + + irq = &phys_enc->irq[INTR_IDX_UNDERRUN]; + irq->hw_idx = phys_enc->intf_idx; + irq->irq_idx = -EINVAL; +} + +static void dpu_encoder_phys_cmd_mode_set( + struct dpu_encoder_phys *phys_enc, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + struct dpu_rm *rm = &phys_enc->dpu_kms->rm; + struct dpu_rm_hw_iter iter; + int i, instance; + + if (!phys_enc || !mode || !adj_mode) { + DPU_ERROR("invalid args\n"); + return; + } + phys_enc->cached_mode = *adj_mode; + DPU_DEBUG_CMDENC(cmd_enc, "caching mode:\n"); + drm_mode_debug_printmodeline(adj_mode); + + instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0; + + /* Retrieve previously allocated HW Resources. Shouldn't fail */ + dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL); + for (i = 0; i <= instance; i++) { + if (dpu_rm_get_hw(rm, &iter)) + phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw; + } + + if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) { + DPU_ERROR_CMDENC(cmd_enc, "failed to init ctl: %ld\n", + PTR_ERR(phys_enc->hw_ctl)); + phys_enc->hw_ctl = NULL; + return; + } + + _dpu_encoder_phys_cmd_setup_irq_hw_idx(phys_enc); +} + +static int _dpu_encoder_phys_cmd_handle_ppdone_timeout( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR; + bool do_log = false; + + if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl) + return -EINVAL; + + cmd_enc->pp_timeout_report_cnt++; + if (cmd_enc->pp_timeout_report_cnt == PP_TIMEOUT_MAX_TRIALS) { + frame_event |= DPU_ENCODER_FRAME_EVENT_PANEL_DEAD; + do_log = true; + } else if (cmd_enc->pp_timeout_report_cnt == 1) { + do_log = true; + } + + trace_dpu_enc_phys_cmd_pdone_timeout(DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + cmd_enc->pp_timeout_report_cnt, + atomic_read(&phys_enc->pending_kickoff_cnt), + frame_event); + + /* to avoid flooding, only log first time, and "dead" time */ + if (do_log) { + DRM_ERROR("id:%d pp:%d kickoff timeout %d cnt %d koff_cnt %d\n", + DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + phys_enc->hw_ctl->idx - CTL_0, + cmd_enc->pp_timeout_report_cnt, + atomic_read(&phys_enc->pending_kickoff_cnt)); + + dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_RDPTR); + dpu_dbg_dump(false, __func__, true, true); + } + + atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0); + + /* request a ctl reset before the next kickoff */ + phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET; + + if (phys_enc->parent_ops->handle_frame_done) + phys_enc->parent_ops->handle_frame_done( + phys_enc->parent, phys_enc, frame_event); + + return -ETIMEDOUT; +} + +static int _dpu_encoder_phys_cmd_wait_for_idle( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + struct dpu_encoder_wait_info wait_info; + int ret; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + + wait_info.wq = &phys_enc->pending_kickoff_wq; + wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt; + wait_info.timeout_ms = KICKOFF_TIMEOUT_MS; + + ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_PINGPONG, + &wait_info); + if (ret == -ETIMEDOUT) + _dpu_encoder_phys_cmd_handle_ppdone_timeout(phys_enc); + else if (!ret) + cmd_enc->pp_timeout_report_cnt = 0; + + return ret; +} + +static int dpu_encoder_phys_cmd_control_vblank_irq( + struct dpu_encoder_phys *phys_enc, + bool enable) +{ + int ret = 0; + int refcount; + + if (!phys_enc || !phys_enc->hw_pp) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + + refcount = atomic_read(&phys_enc->vblank_refcount); + + /* Slave encoders don't report vblank */ + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + goto end; + + /* protect against negative */ + if (!enable && refcount == 0) { + ret = -EINVAL; + goto end; + } + + DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + enable ? "true" : "false", refcount); + + if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1) + ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_RDPTR); + else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0) + ret = dpu_encoder_helper_unregister_irq(phys_enc, + INTR_IDX_RDPTR); + +end: + if (ret) { + DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n", + DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, ret, + enable ? "true" : "false", refcount); + } + + return ret; +} + +static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc, + bool enable) +{ + struct dpu_encoder_phys_cmd *cmd_enc; + + if (!phys_enc) + return; + + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + enable, atomic_read(&phys_enc->vblank_refcount)); + + if (enable) { + dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_PINGPONG); + dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN); + dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, true); + + if (dpu_encoder_phys_cmd_is_master(phys_enc)) + dpu_encoder_helper_register_irq(phys_enc, + INTR_IDX_CTL_START); + } else { + if (dpu_encoder_phys_cmd_is_master(phys_enc)) + dpu_encoder_helper_unregister_irq(phys_enc, + INTR_IDX_CTL_START); + + dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN); + dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false); + dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_PINGPONG); + } +} + +static void dpu_encoder_phys_cmd_tearcheck_config( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + struct dpu_hw_tear_check tc_cfg = { 0 }; + struct drm_display_mode *mode; + bool tc_enable = true; + u32 vsync_hz; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!phys_enc || !phys_enc->hw_pp) { + DPU_ERROR("invalid encoder\n"); + return; + } + mode = &phys_enc->cached_mode; + + DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0); + + if (!phys_enc->hw_pp->ops.setup_tearcheck || + !phys_enc->hw_pp->ops.enable_tearcheck) { + DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n"); + return; + } + + dpu_kms = phys_enc->dpu_kms; + if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) { + DPU_ERROR("invalid device\n"); + return; + } + priv = dpu_kms->dev->dev_private; + + /* + * TE default: dsi byte clock calculated base on 70 fps; + * around 14 ms to complete a kickoff cycle if te disabled; + * vclk_line base on 60 fps; write is faster than read; + * init == start == rdptr; + * + * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel + * frequency divided by the no. of rows (lines) in the LCDpanel. + */ + vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync"); + if (vsync_hz <= 0) { + DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n", + vsync_hz); + return; + } + + tc_cfg.vsync_count = vsync_hz / (mode->vtotal * mode->vrefresh); + + /* enable external TE after kickoff to avoid premature autorefresh */ + tc_cfg.hw_vsync_mode = 0; + + /* + * By setting sync_cfg_height to near max register value, we essentially + * disable dpu hw generated TE signal, since hw TE will arrive first. + * Only caveat is if due to error, we hit wrap-around. + */ + tc_cfg.sync_cfg_height = 0xFFF0; + tc_cfg.vsync_init_val = mode->vdisplay; + tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START; + tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE; + tc_cfg.start_pos = mode->vdisplay; + tc_cfg.rd_ptr_irq = mode->vdisplay + 1; + + DPU_DEBUG_CMDENC(cmd_enc, + "tc %d vsync_clk_speed_hz %u vtotal %u vrefresh %u\n", + phys_enc->hw_pp->idx - PINGPONG_0, vsync_hz, + mode->vtotal, mode->vrefresh); + DPU_DEBUG_CMDENC(cmd_enc, + "tc %d enable %u start_pos %u rd_ptr_irq %u\n", + phys_enc->hw_pp->idx - PINGPONG_0, tc_enable, tc_cfg.start_pos, + tc_cfg.rd_ptr_irq); + DPU_DEBUG_CMDENC(cmd_enc, + "tc %d hw_vsync_mode %u vsync_count %u vsync_init_val %u\n", + phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.hw_vsync_mode, + tc_cfg.vsync_count, tc_cfg.vsync_init_val); + DPU_DEBUG_CMDENC(cmd_enc, + "tc %d cfgheight %u thresh_start %u thresh_cont %u\n", + phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.sync_cfg_height, + tc_cfg.sync_threshold_start, tc_cfg.sync_threshold_continue); + + phys_enc->hw_pp->ops.setup_tearcheck(phys_enc->hw_pp, &tc_cfg); + phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, tc_enable); +} + +static void _dpu_encoder_phys_cmd_pingpong_config( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + + if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp + || !phys_enc->hw_ctl->ops.setup_intf_cfg) { + DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0); + return; + } + + DPU_DEBUG_CMDENC(cmd_enc, "pp %d, enabling mode:\n", + phys_enc->hw_pp->idx - PINGPONG_0); + drm_mode_debug_printmodeline(&phys_enc->cached_mode); + + _dpu_encoder_phys_cmd_update_intf_cfg(phys_enc); + dpu_encoder_phys_cmd_tearcheck_config(phys_enc); +} + +static bool dpu_encoder_phys_cmd_needs_single_flush( + struct dpu_encoder_phys *phys_enc) +{ + /** + * we do separate flush for each CTL and let + * CTL_START synchronize them + */ + return false; +} + +static void dpu_encoder_phys_cmd_enable_helper( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_hw_ctl *ctl; + u32 flush_mask = 0; + + if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) { + DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0); + return; + } + + dpu_encoder_helper_split_config(phys_enc, phys_enc->intf_idx); + + _dpu_encoder_phys_cmd_pingpong_config(phys_enc); + + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + goto skip_flush; + + ctl = phys_enc->hw_ctl; + ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->intf_idx); + ctl->ops.update_pending_flush(ctl, flush_mask); + +skip_flush: + return; +} + +static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + + if (!phys_enc || !phys_enc->hw_pp) { + DPU_ERROR("invalid phys encoder\n"); + return; + } + + DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0); + + if (phys_enc->enable_state == DPU_ENC_ENABLED) { + DPU_ERROR("already enabled\n"); + return; + } + + dpu_encoder_phys_cmd_enable_helper(phys_enc); + phys_enc->enable_state = DPU_ENC_ENABLED; +} + +static void _dpu_encoder_phys_cmd_connect_te( + struct dpu_encoder_phys *phys_enc, bool enable) +{ + if (!phys_enc || !phys_enc->hw_pp || + !phys_enc->hw_pp->ops.connect_external_te) + return; + + trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable); + phys_enc->hw_pp->ops.connect_external_te(phys_enc->hw_pp, enable); +} + +static void dpu_encoder_phys_cmd_prepare_idle_pc( + struct dpu_encoder_phys *phys_enc) +{ + _dpu_encoder_phys_cmd_connect_te(phys_enc, false); +} + +static int dpu_encoder_phys_cmd_get_line_count( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_hw_pingpong *hw_pp; + + if (!phys_enc || !phys_enc->hw_pp) + return -EINVAL; + + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + return -EINVAL; + + hw_pp = phys_enc->hw_pp; + if (!hw_pp->ops.get_line_count) + return -EINVAL; + + return hw_pp->ops.get_line_count(hw_pp); +} + +static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + + if (!phys_enc || !phys_enc->hw_pp) { + DPU_ERROR("invalid encoder\n"); + return; + } + DRM_DEBUG_KMS("id:%u pp:%d state:%d\n", DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + phys_enc->enable_state); + + if (phys_enc->enable_state == DPU_ENC_DISABLED) { + DPU_ERROR_CMDENC(cmd_enc, "already disabled\n"); + return; + } + + if (phys_enc->hw_pp->ops.enable_tearcheck) + phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, false); + phys_enc->enable_state = DPU_ENC_DISABLED; +} + +static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + kfree(cmd_enc); +} + +static void dpu_encoder_phys_cmd_get_hw_resources( + struct dpu_encoder_phys *phys_enc, + struct dpu_encoder_hw_resources *hw_res, + struct drm_connector_state *conn_state) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + if ((phys_enc->intf_idx - INTF_0) >= INTF_MAX) { + DPU_ERROR("invalid intf idx:%d\n", phys_enc->intf_idx); + return; + } + + DPU_DEBUG_CMDENC(cmd_enc, "\n"); + hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_CMD; +} + +static void dpu_encoder_phys_cmd_prepare_for_kickoff( + struct dpu_encoder_phys *phys_enc, + struct dpu_encoder_kickoff_params *params) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + int ret; + + if (!phys_enc || !phys_enc->hw_pp) { + DPU_ERROR("invalid encoder\n"); + return; + } + DRM_DEBUG_KMS("id:%u pp:%d pending_cnt:%d\n", DRMID(phys_enc->parent), + phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(&phys_enc->pending_kickoff_cnt)); + + /* + * Mark kickoff request as outstanding. If there are more than one, + * outstanding, then we have to wait for the previous one to complete + */ + ret = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc); + if (ret) { + /* force pending_kickoff_cnt 0 to discard failed kickoff */ + atomic_set(&phys_enc->pending_kickoff_cnt, 0); + DRM_ERROR("failed wait_for_idle: id:%u ret:%d pp:%d\n", + DRMID(phys_enc->parent), ret, + phys_enc->hw_pp->idx - PINGPONG_0); + } + + DPU_DEBUG_CMDENC(cmd_enc, "pp:%d pending_cnt %d\n", + phys_enc->hw_pp->idx - PINGPONG_0, + atomic_read(&phys_enc->pending_kickoff_cnt)); +} + +static int _dpu_encoder_phys_cmd_wait_for_ctl_start( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_cmd *cmd_enc = + to_dpu_encoder_phys_cmd(phys_enc); + struct dpu_encoder_wait_info wait_info; + int ret; + + if (!phys_enc || !phys_enc->hw_ctl) { + DPU_ERROR("invalid argument(s)\n"); + return -EINVAL; + } + + wait_info.wq = &phys_enc->pending_kickoff_wq; + wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt; + wait_info.timeout_ms = KICKOFF_TIMEOUT_MS; + + ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_CTL_START, + &wait_info); + if (ret == -ETIMEDOUT) { + DPU_ERROR_CMDENC(cmd_enc, "ctl start interrupt wait failed\n"); + ret = -EINVAL; + } else if (!ret) + ret = 0; + + return ret; +} + +static int dpu_encoder_phys_cmd_wait_for_tx_complete( + struct dpu_encoder_phys *phys_enc) +{ + int rc; + struct dpu_encoder_phys_cmd *cmd_enc; + + if (!phys_enc) + return -EINVAL; + + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc); + if (rc) { + DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n", + DRMID(phys_enc->parent), rc, + phys_enc->intf_idx - INTF_0); + } + + return rc; +} + +static int dpu_encoder_phys_cmd_wait_for_commit_done( + struct dpu_encoder_phys *phys_enc) +{ + int rc = 0; + struct dpu_encoder_phys_cmd *cmd_enc; + + if (!phys_enc) + return -EINVAL; + + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + /* only required for master controller */ + if (dpu_encoder_phys_cmd_is_master(phys_enc)) + rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc); + + /* required for both controllers */ + if (!rc && cmd_enc->serialize_wait4pp) + dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc, NULL); + + return rc; +} + +static int dpu_encoder_phys_cmd_wait_for_vblank( + struct dpu_encoder_phys *phys_enc) +{ + int rc = 0; + struct dpu_encoder_phys_cmd *cmd_enc; + struct dpu_encoder_wait_info wait_info; + + if (!phys_enc) + return -EINVAL; + + cmd_enc = to_dpu_encoder_phys_cmd(phys_enc); + + /* only required for master controller */ + if (!dpu_encoder_phys_cmd_is_master(phys_enc)) + return rc; + + wait_info.wq = &cmd_enc->pending_vblank_wq; + wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt; + wait_info.timeout_ms = _dpu_encoder_phys_cmd_get_idle_timeout(cmd_enc); + + atomic_inc(&cmd_enc->pending_vblank_cnt); + + rc = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_RDPTR, + &wait_info); + + return rc; +} + +static void dpu_encoder_phys_cmd_handle_post_kickoff( + struct dpu_encoder_phys *phys_enc) +{ + if (!phys_enc) + return; + + /** + * re-enable external TE, either for the first time after enabling + * or if disabled for Autorefresh + */ + _dpu_encoder_phys_cmd_connect_te(phys_enc, true); +} + +static void dpu_encoder_phys_cmd_trigger_start( + struct dpu_encoder_phys *phys_enc) +{ + if (!phys_enc) + return; + + dpu_encoder_helper_trigger_start(phys_enc); +} + +static void dpu_encoder_phys_cmd_init_ops( + struct dpu_encoder_phys_ops *ops) +{ + ops->is_master = dpu_encoder_phys_cmd_is_master; + ops->mode_set = dpu_encoder_phys_cmd_mode_set; + ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup; + ops->enable = dpu_encoder_phys_cmd_enable; + ops->disable = dpu_encoder_phys_cmd_disable; + ops->destroy = dpu_encoder_phys_cmd_destroy; + ops->get_hw_resources = dpu_encoder_phys_cmd_get_hw_resources; + ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq; + ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done; + ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff; + ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete; + ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank; + ops->trigger_start = dpu_encoder_phys_cmd_trigger_start; + ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush; + ops->hw_reset = dpu_encoder_helper_hw_reset; + ops->irq_control = dpu_encoder_phys_cmd_irq_control; + ops->restore = dpu_encoder_phys_cmd_enable_helper; + ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc; + ops->handle_post_kickoff = dpu_encoder_phys_cmd_handle_post_kickoff; + ops->get_line_count = dpu_encoder_phys_cmd_get_line_count; +} + +struct dpu_encoder_phys *dpu_encoder_phys_cmd_init( + struct dpu_enc_phys_init_params *p) +{ + struct dpu_encoder_phys *phys_enc = NULL; + struct dpu_encoder_phys_cmd *cmd_enc = NULL; + struct dpu_hw_mdp *hw_mdp; + struct dpu_encoder_irq *irq; + int i, ret = 0; + + DPU_DEBUG("intf %d\n", p->intf_idx - INTF_0); + + cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL); + if (!cmd_enc) { + ret = -ENOMEM; + DPU_ERROR("failed to allocate\n"); + goto fail; + } + phys_enc = &cmd_enc->base; + + hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm); + if (IS_ERR_OR_NULL(hw_mdp)) { + ret = PTR_ERR(hw_mdp); + DPU_ERROR("failed to get mdptop\n"); + goto fail_mdp_init; + } + phys_enc->hw_mdptop = hw_mdp; + phys_enc->intf_idx = p->intf_idx; + + dpu_encoder_phys_cmd_init_ops(&phys_enc->ops); + phys_enc->parent = p->parent; + phys_enc->parent_ops = p->parent_ops; + phys_enc->dpu_kms = p->dpu_kms; + phys_enc->split_role = p->split_role; + phys_enc->intf_mode = INTF_MODE_CMD; + phys_enc->enc_spinlock = p->enc_spinlock; + cmd_enc->stream_sel = 0; + phys_enc->enable_state = DPU_ENC_DISABLED; + for (i = 0; i < INTR_IDX_MAX; i++) { + irq = &phys_enc->irq[i]; + INIT_LIST_HEAD(&irq->cb.list); + irq->irq_idx = -EINVAL; + irq->hw_idx = -EINVAL; + irq->cb.arg = phys_enc; + } + + irq = &phys_enc->irq[INTR_IDX_CTL_START]; + irq->name = "ctl_start"; + irq->intr_type = DPU_IRQ_TYPE_CTL_START; + irq->intr_idx = INTR_IDX_CTL_START; + irq->cb.func = dpu_encoder_phys_cmd_ctl_start_irq; + + irq = &phys_enc->irq[INTR_IDX_PINGPONG]; + irq->name = "pp_done"; + irq->intr_type = DPU_IRQ_TYPE_PING_PONG_COMP; + irq->intr_idx = INTR_IDX_PINGPONG; + irq->cb.func = dpu_encoder_phys_cmd_pp_tx_done_irq; + + irq = &phys_enc->irq[INTR_IDX_RDPTR]; + irq->name = "pp_rd_ptr"; + irq->intr_type = DPU_IRQ_TYPE_PING_PONG_RD_PTR; + irq->intr_idx = INTR_IDX_RDPTR; + irq->cb.func = dpu_encoder_phys_cmd_pp_rd_ptr_irq; + + irq = &phys_enc->irq[INTR_IDX_UNDERRUN]; + irq->name = "underrun"; + irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN; + irq->intr_idx = INTR_IDX_UNDERRUN; + irq->cb.func = dpu_encoder_phys_cmd_underrun_irq; + + atomic_set(&phys_enc->vblank_refcount, 0); + atomic_set(&phys_enc->pending_kickoff_cnt, 0); + atomic_set(&phys_enc->pending_ctlstart_cnt, 0); + atomic_set(&cmd_enc->pending_vblank_cnt, 0); + init_waitqueue_head(&phys_enc->pending_kickoff_wq); + init_waitqueue_head(&cmd_enc->pending_vblank_wq); + + DPU_DEBUG_CMDENC(cmd_enc, "created\n"); + + return phys_enc; + +fail_mdp_init: + kfree(cmd_enc); +fail: + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c new file mode 100644 index 000000000000..14fc7c2a6bb7 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -0,0 +1,922 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include "dpu_encoder_phys.h" +#include "dpu_hw_interrupts.h" +#include "dpu_core_irq.h" +#include "dpu_formats.h" +#include "dpu_trace.h" + +#define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \ + (e) && (e)->base.parent ? \ + (e)->base.parent->base.id : -1, \ + (e) && (e)->hw_intf ? \ + (e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__) + +#define DPU_ERROR_VIDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \ + (e) && (e)->base.parent ? \ + (e)->base.parent->base.id : -1, \ + (e) && (e)->hw_intf ? \ + (e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__) + +#define to_dpu_encoder_phys_vid(x) \ + container_of(x, struct dpu_encoder_phys_vid, base) + +static bool dpu_encoder_phys_vid_is_master( + struct dpu_encoder_phys *phys_enc) +{ + bool ret = false; + + if (phys_enc->split_role != ENC_ROLE_SLAVE) + ret = true; + + return ret; +} + +static void drm_mode_to_intf_timing_params( + const struct dpu_encoder_phys_vid *vid_enc, + const struct drm_display_mode *mode, + struct intf_timing_params *timing) +{ + memset(timing, 0, sizeof(*timing)); + + if ((mode->htotal < mode->hsync_end) + || (mode->hsync_start < mode->hdisplay) + || (mode->vtotal < mode->vsync_end) + || (mode->vsync_start < mode->vdisplay) + || (mode->hsync_end < mode->hsync_start) + || (mode->vsync_end < mode->vsync_start)) { + DPU_ERROR( + "invalid params - hstart:%d,hend:%d,htot:%d,hdisplay:%d\n", + mode->hsync_start, mode->hsync_end, + mode->htotal, mode->hdisplay); + DPU_ERROR("vstart:%d,vend:%d,vtot:%d,vdisplay:%d\n", + mode->vsync_start, mode->vsync_end, + mode->vtotal, mode->vdisplay); + return; + } + + /* + * https://www.kernel.org/doc/htmldocs/drm/ch02s05.html + * Active Region Front Porch Sync Back Porch + * <-----------------><------------><-----><-----------> + * <- [hv]display ---> + * <--------- [hv]sync_start ------> + * <----------------- [hv]sync_end -------> + * <---------------------------- [hv]total -------------> + */ + timing->width = mode->hdisplay; /* active width */ + timing->height = mode->vdisplay; /* active height */ + timing->xres = timing->width; + timing->yres = timing->height; + timing->h_back_porch = mode->htotal - mode->hsync_end; + timing->h_front_porch = mode->hsync_start - mode->hdisplay; + timing->v_back_porch = mode->vtotal - mode->vsync_end; + timing->v_front_porch = mode->vsync_start - mode->vdisplay; + timing->hsync_pulse_width = mode->hsync_end - mode->hsync_start; + timing->vsync_pulse_width = mode->vsync_end - mode->vsync_start; + timing->hsync_polarity = (mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0; + timing->vsync_polarity = (mode->flags & DRM_MODE_FLAG_NVSYNC) ? 1 : 0; + timing->border_clr = 0; + timing->underflow_clr = 0xff; + timing->hsync_skew = mode->hskew; + + /* DSI controller cannot handle active-low sync signals. */ + if (vid_enc->hw_intf->cap->type == INTF_DSI) { + timing->hsync_polarity = 0; + timing->vsync_polarity = 0; + } + + /* + * For edp only: + * DISPLAY_V_START = (VBP * HCYCLE) + HBP + * DISPLAY_V_END = (VBP + VACTIVE) * HCYCLE - 1 - HFP + */ + /* + * if (vid_enc->hw->cap->type == INTF_EDP) { + * display_v_start += mode->htotal - mode->hsync_start; + * display_v_end -= mode->hsync_start - mode->hdisplay; + * } + */ +} + +static inline u32 get_horizontal_total(const struct intf_timing_params *timing) +{ + u32 active = timing->xres; + u32 inactive = + timing->h_back_porch + timing->h_front_porch + + timing->hsync_pulse_width; + return active + inactive; +} + +static inline u32 get_vertical_total(const struct intf_timing_params *timing) +{ + u32 active = timing->yres; + u32 inactive = + timing->v_back_porch + timing->v_front_porch + + timing->vsync_pulse_width; + return active + inactive; +} + +/* + * programmable_fetch_get_num_lines: + * Number of fetch lines in vertical front porch + * @timing: Pointer to the intf timing information for the requested mode + * + * Returns the number of fetch lines in vertical front porch at which mdp + * can start fetching the next frame. + * + * Number of needed prefetch lines is anything that cannot be absorbed in the + * start of frame time (back porch + vsync pulse width). + * + * Some panels have very large VFP, however we only need a total number of + * lines based on the chip worst case latencies. + */ +static u32 programmable_fetch_get_num_lines( + struct dpu_encoder_phys_vid *vid_enc, + const struct intf_timing_params *timing) +{ + u32 worst_case_needed_lines = + vid_enc->hw_intf->cap->prog_fetch_lines_worst_case; + u32 start_of_frame_lines = + timing->v_back_porch + timing->vsync_pulse_width; + u32 needed_vfp_lines = worst_case_needed_lines - start_of_frame_lines; + u32 actual_vfp_lines = 0; + + /* Fetch must be outside active lines, otherwise undefined. */ + if (start_of_frame_lines >= worst_case_needed_lines) { + DPU_DEBUG_VIDENC(vid_enc, + "prog fetch is not needed, large vbp+vsw\n"); + actual_vfp_lines = 0; + } else if (timing->v_front_porch < needed_vfp_lines) { + /* Warn fetch needed, but not enough porch in panel config */ + pr_warn_once + ("low vbp+vfp may lead to perf issues in some cases\n"); + DPU_DEBUG_VIDENC(vid_enc, + "less vfp than fetch req, using entire vfp\n"); + actual_vfp_lines = timing->v_front_porch; + } else { + DPU_DEBUG_VIDENC(vid_enc, "room in vfp for needed prefetch\n"); + actual_vfp_lines = needed_vfp_lines; + } + + DPU_DEBUG_VIDENC(vid_enc, + "v_front_porch %u v_back_porch %u vsync_pulse_width %u\n", + timing->v_front_porch, timing->v_back_porch, + timing->vsync_pulse_width); + DPU_DEBUG_VIDENC(vid_enc, + "wc_lines %u needed_vfp_lines %u actual_vfp_lines %u\n", + worst_case_needed_lines, needed_vfp_lines, actual_vfp_lines); + + return actual_vfp_lines; +} + +/* + * programmable_fetch_config: Programs HW to prefetch lines by offsetting + * the start of fetch into the vertical front porch for cases where the + * vsync pulse width and vertical back porch time is insufficient + * + * Gets # of lines to pre-fetch, then calculate VSYNC counter value. + * HW layer requires VSYNC counter of first pixel of tgt VFP line. + * + * @timing: Pointer to the intf timing information for the requested mode + */ +static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc, + const struct intf_timing_params *timing) +{ + struct dpu_encoder_phys_vid *vid_enc = + to_dpu_encoder_phys_vid(phys_enc); + struct intf_prog_fetch f = { 0 }; + u32 vfp_fetch_lines = 0; + u32 horiz_total = 0; + u32 vert_total = 0; + u32 vfp_fetch_start_vsync_counter = 0; + unsigned long lock_flags; + + if (WARN_ON_ONCE(!vid_enc->hw_intf->ops.setup_prg_fetch)) + return; + + vfp_fetch_lines = programmable_fetch_get_num_lines(vid_enc, timing); + if (vfp_fetch_lines) { + vert_total = get_vertical_total(timing); + horiz_total = get_horizontal_total(timing); + vfp_fetch_start_vsync_counter = + (vert_total - vfp_fetch_lines) * horiz_total + 1; + f.enable = 1; + f.fetch_start = vfp_fetch_start_vsync_counter; + } + + DPU_DEBUG_VIDENC(vid_enc, + "vfp_fetch_lines %u vfp_fetch_start_vsync_counter %u\n", + vfp_fetch_lines, vfp_fetch_start_vsync_counter); + + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + vid_enc->hw_intf->ops.setup_prg_fetch(vid_enc->hw_intf, &f); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); +} + +static bool dpu_encoder_phys_vid_mode_fixup( + struct dpu_encoder_phys *phys_enc, + const struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + if (phys_enc) + DPU_DEBUG_VIDENC(to_dpu_encoder_phys_vid(phys_enc), "\n"); + + /* + * Modifying mode has consequences when the mode comes back to us + */ + return true; +} + +static void dpu_encoder_phys_vid_setup_timing_engine( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_vid *vid_enc; + struct drm_display_mode mode; + struct intf_timing_params timing_params = { 0 }; + const struct dpu_format *fmt = NULL; + u32 fmt_fourcc = DRM_FORMAT_RGB888; + unsigned long lock_flags; + struct dpu_hw_intf_cfg intf_cfg = { 0 }; + + if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) { + DPU_ERROR("invalid encoder %d\n", phys_enc != 0); + return; + } + + mode = phys_enc->cached_mode; + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + if (!vid_enc->hw_intf->ops.setup_timing_gen) { + DPU_ERROR("timing engine setup is not supported\n"); + return; + } + + DPU_DEBUG_VIDENC(vid_enc, "enabling mode:\n"); + drm_mode_debug_printmodeline(&mode); + + if (phys_enc->split_role != ENC_ROLE_SOLO) { + mode.hdisplay >>= 1; + mode.htotal >>= 1; + mode.hsync_start >>= 1; + mode.hsync_end >>= 1; + + DPU_DEBUG_VIDENC(vid_enc, + "split_role %d, halve horizontal %d %d %d %d\n", + phys_enc->split_role, + mode.hdisplay, mode.htotal, + mode.hsync_start, mode.hsync_end); + } + + drm_mode_to_intf_timing_params(vid_enc, &mode, &timing_params); + + fmt = dpu_get_dpu_format(fmt_fourcc); + DPU_DEBUG_VIDENC(vid_enc, "fmt_fourcc 0x%X\n", fmt_fourcc); + + intf_cfg.intf = vid_enc->hw_intf->idx; + intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID; + intf_cfg.stream_sel = 0; /* Don't care value for video mode */ + intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); + + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + vid_enc->hw_intf->ops.setup_timing_gen(vid_enc->hw_intf, + &timing_params, fmt); + phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); + + programmable_fetch_config(phys_enc, &timing_params); + + vid_enc->timing_params = timing_params; +} + +static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + struct dpu_hw_ctl *hw_ctl; + unsigned long lock_flags; + u32 flush_register = 0; + int new_cnt = -1, old_cnt = -1; + + if (!phys_enc) + return; + + hw_ctl = phys_enc->hw_ctl; + if (!hw_ctl) + return; + + DPU_ATRACE_BEGIN("vblank_irq"); + + if (phys_enc->parent_ops->handle_vblank_virt) + phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent, + phys_enc); + + old_cnt = atomic_read(&phys_enc->pending_kickoff_cnt); + + /* + * only decrement the pending flush count if we've actually flushed + * hardware. due to sw irq latency, vblank may have already happened + * so we need to double-check with hw that it accepted the flush bits + */ + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + if (hw_ctl && hw_ctl->ops.get_flush_register) + flush_register = hw_ctl->ops.get_flush_register(hw_ctl); + + if (flush_register == 0) + new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, + -1, 0); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); + + /* Signal any waiting atomic commit thread */ + wake_up_all(&phys_enc->pending_kickoff_wq); + DPU_ATRACE_END("vblank_irq"); +} + +static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx) +{ + struct dpu_encoder_phys *phys_enc = arg; + + if (!phys_enc) + return; + + if (phys_enc->parent_ops->handle_underrun_virt) + phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent, + phys_enc); +} + +static bool _dpu_encoder_phys_is_dual_ctl(struct dpu_encoder_phys *phys_enc) +{ + if (!phys_enc) + return false; + + if (phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE) + return true; + + return false; +} + +static bool dpu_encoder_phys_vid_needs_single_flush( + struct dpu_encoder_phys *phys_enc) +{ + return (phys_enc && _dpu_encoder_phys_is_dual_ctl(phys_enc)); +} + +static void _dpu_encoder_phys_vid_setup_irq_hw_idx( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_irq *irq; + + /* + * Initialize irq->hw_idx only when irq is not registered. + * Prevent invalidating irq->irq_idx as modeset may be + * called many times during dfps. + */ + + irq = &phys_enc->irq[INTR_IDX_VSYNC]; + if (irq->irq_idx < 0) + irq->hw_idx = phys_enc->intf_idx; + + irq = &phys_enc->irq[INTR_IDX_UNDERRUN]; + if (irq->irq_idx < 0) + irq->hw_idx = phys_enc->intf_idx; +} + +static void dpu_encoder_phys_vid_mode_set( + struct dpu_encoder_phys *phys_enc, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + struct dpu_rm *rm; + struct dpu_rm_hw_iter iter; + int i, instance; + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc || !phys_enc->dpu_kms) { + DPU_ERROR("invalid encoder/kms\n"); + return; + } + + rm = &phys_enc->dpu_kms->rm; + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + if (adj_mode) { + phys_enc->cached_mode = *adj_mode; + drm_mode_debug_printmodeline(adj_mode); + DPU_DEBUG_VIDENC(vid_enc, "caching mode:\n"); + } + + instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0; + + /* Retrieve previously allocated HW Resources. Shouldn't fail */ + dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL); + for (i = 0; i <= instance; i++) { + if (dpu_rm_get_hw(rm, &iter)) + phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw; + } + if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) { + DPU_ERROR_VIDENC(vid_enc, "failed to init ctl, %ld\n", + PTR_ERR(phys_enc->hw_ctl)); + phys_enc->hw_ctl = NULL; + return; + } + + _dpu_encoder_phys_vid_setup_irq_hw_idx(phys_enc); +} + +static int dpu_encoder_phys_vid_control_vblank_irq( + struct dpu_encoder_phys *phys_enc, + bool enable) +{ + int ret = 0; + struct dpu_encoder_phys_vid *vid_enc; + int refcount; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return -EINVAL; + } + + refcount = atomic_read(&phys_enc->vblank_refcount); + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + /* Slave encoders don't report vblank */ + if (!dpu_encoder_phys_vid_is_master(phys_enc)) + goto end; + + /* protect against negative */ + if (!enable && refcount == 0) { + ret = -EINVAL; + goto end; + } + + DRM_DEBUG_KMS("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable, + atomic_read(&phys_enc->vblank_refcount)); + + if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1) + ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_VSYNC); + else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0) + ret = dpu_encoder_helper_unregister_irq(phys_enc, + INTR_IDX_VSYNC); + +end: + if (ret) { + DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n", + DRMID(phys_enc->parent), + vid_enc->hw_intf->idx - INTF_0, ret, enable, + refcount); + } + return ret; +} + +static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc) +{ + struct msm_drm_private *priv; + struct dpu_encoder_phys_vid *vid_enc; + struct dpu_hw_intf *intf; + struct dpu_hw_ctl *ctl; + u32 flush_mask = 0; + + if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev || + !phys_enc->parent->dev->dev_private) { + DPU_ERROR("invalid encoder/device\n"); + return; + } + priv = phys_enc->parent->dev->dev_private; + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + intf = vid_enc->hw_intf; + ctl = phys_enc->hw_ctl; + if (!vid_enc->hw_intf || !phys_enc->hw_ctl) { + DPU_ERROR("invalid hw_intf %d hw_ctl %d\n", + vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0); + return; + } + + DPU_DEBUG_VIDENC(vid_enc, "\n"); + + if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing)) + return; + + dpu_encoder_helper_split_config(phys_enc, vid_enc->hw_intf->idx); + + dpu_encoder_phys_vid_setup_timing_engine(phys_enc); + + /* + * For single flush cases (dual-ctl or pp-split), skip setting the + * flush bit for the slave intf, since both intfs use same ctl + * and HW will only flush the master. + */ + if (dpu_encoder_phys_vid_needs_single_flush(phys_enc) && + !dpu_encoder_phys_vid_is_master(phys_enc)) + goto skip_flush; + + ctl->ops.get_bitmask_intf(ctl, &flush_mask, intf->idx); + ctl->ops.update_pending_flush(ctl, flush_mask); + +skip_flush: + DPU_DEBUG_VIDENC(vid_enc, "update pending flush ctl %d flush_mask %x\n", + ctl->idx - CTL_0, flush_mask); + + /* ctl_flush & timing engine enable will be triggered by framework */ + if (phys_enc->enable_state == DPU_ENC_DISABLED) + phys_enc->enable_state = DPU_ENC_ENABLING; +} + +static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + DPU_DEBUG_VIDENC(vid_enc, "\n"); + kfree(vid_enc); +} + +static void dpu_encoder_phys_vid_get_hw_resources( + struct dpu_encoder_phys *phys_enc, + struct dpu_encoder_hw_resources *hw_res, + struct drm_connector_state *conn_state) +{ + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc || !hw_res) { + DPU_ERROR("invalid arg(s), enc %d hw_res %d conn_state %d\n", + phys_enc != 0, hw_res != 0, conn_state != 0); + return; + } + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + if (!vid_enc->hw_intf) { + DPU_ERROR("invalid arg(s), hw_intf\n"); + return; + } + + DPU_DEBUG_VIDENC(vid_enc, "\n"); + hw_res->intfs[vid_enc->hw_intf->idx - INTF_0] = INTF_MODE_VIDEO; +} + +static int _dpu_encoder_phys_vid_wait_for_vblank( + struct dpu_encoder_phys *phys_enc, bool notify) +{ + struct dpu_encoder_wait_info wait_info; + int ret; + + if (!phys_enc) { + pr_err("invalid encoder\n"); + return -EINVAL; + } + + wait_info.wq = &phys_enc->pending_kickoff_wq; + wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt; + wait_info.timeout_ms = KICKOFF_TIMEOUT_MS; + + if (!dpu_encoder_phys_vid_is_master(phys_enc)) { + if (notify && phys_enc->parent_ops->handle_frame_done) + phys_enc->parent_ops->handle_frame_done( + phys_enc->parent, phys_enc, + DPU_ENCODER_FRAME_EVENT_DONE); + return 0; + } + + /* Wait for kickoff to complete */ + ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_VSYNC, + &wait_info); + + if (ret == -ETIMEDOUT) { + dpu_encoder_helper_report_irq_timeout(phys_enc, INTR_IDX_VSYNC); + } else if (!ret && notify && phys_enc->parent_ops->handle_frame_done) + phys_enc->parent_ops->handle_frame_done( + phys_enc->parent, phys_enc, + DPU_ENCODER_FRAME_EVENT_DONE); + + return ret; +} + +static int dpu_encoder_phys_vid_wait_for_vblank( + struct dpu_encoder_phys *phys_enc) +{ + return _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, true); +} + +static void dpu_encoder_phys_vid_prepare_for_kickoff( + struct dpu_encoder_phys *phys_enc, + struct dpu_encoder_kickoff_params *params) +{ + struct dpu_encoder_phys_vid *vid_enc; + struct dpu_hw_ctl *ctl; + int rc; + + if (!phys_enc || !params) { + DPU_ERROR("invalid encoder/parameters\n"); + return; + } + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + ctl = phys_enc->hw_ctl; + if (!ctl || !ctl->ops.wait_reset_status) + return; + + /* + * hw supports hardware initiated ctl reset, so before we kickoff a new + * frame, need to check and wait for hw initiated ctl reset completion + */ + rc = ctl->ops.wait_reset_status(ctl); + if (rc) { + DPU_ERROR_VIDENC(vid_enc, "ctl %d reset failure: %d\n", + ctl->idx, rc); + dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_VSYNC); + dpu_dbg_dump(false, __func__, true, true); + } +} + +static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc) +{ + struct msm_drm_private *priv; + struct dpu_encoder_phys_vid *vid_enc; + unsigned long lock_flags; + int ret; + + if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev || + !phys_enc->parent->dev->dev_private) { + DPU_ERROR("invalid encoder/device\n"); + return; + } + priv = phys_enc->parent->dev->dev_private; + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + if (!vid_enc->hw_intf || !phys_enc->hw_ctl) { + DPU_ERROR("invalid hw_intf %d hw_ctl %d\n", + vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0); + return; + } + + DPU_DEBUG_VIDENC(vid_enc, "\n"); + + if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing)) + return; + + if (phys_enc->enable_state == DPU_ENC_DISABLED) { + DPU_ERROR("already disabled\n"); + return; + } + + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 0); + if (dpu_encoder_phys_vid_is_master(phys_enc)) + dpu_encoder_phys_inc_pending(phys_enc); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); + + /* + * Wait for a vsync so we know the ENABLE=0 latched before + * the (connector) source of the vsync's gets disabled, + * otherwise we end up in a funny state if we re-enable + * before the disable latches, which results that some of + * the settings changes for the new modeset (like new + * scanout buffer) don't latch properly.. + */ + if (dpu_encoder_phys_vid_is_master(phys_enc)) { + ret = _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, false); + if (ret) { + atomic_set(&phys_enc->pending_kickoff_cnt, 0); + DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n", + DRMID(phys_enc->parent), + vid_enc->hw_intf->idx - INTF_0, ret); + } + } + + phys_enc->enable_state = DPU_ENC_DISABLED; +} + +static void dpu_encoder_phys_vid_handle_post_kickoff( + struct dpu_encoder_phys *phys_enc) +{ + unsigned long lock_flags; + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc) { + DPU_ERROR("invalid encoder\n"); + return; + } + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + DPU_DEBUG_VIDENC(vid_enc, "enable_state %d\n", phys_enc->enable_state); + + /* + * Video mode must flush CTL before enabling timing engine + * Video encoders need to turn on their interfaces now + */ + if (phys_enc->enable_state == DPU_ENC_ENABLING) { + trace_dpu_enc_phys_vid_post_kickoff(DRMID(phys_enc->parent), + vid_enc->hw_intf->idx - INTF_0); + spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); + vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 1); + spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags); + phys_enc->enable_state = DPU_ENC_ENABLED; + } +} + +static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc, + bool enable) +{ + struct dpu_encoder_phys_vid *vid_enc; + int ret; + + if (!phys_enc) + return; + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent), + vid_enc->hw_intf->idx - INTF_0, + enable, + atomic_read(&phys_enc->vblank_refcount)); + + if (enable) { + ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true); + if (ret) + return; + + dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN); + } else { + dpu_encoder_phys_vid_control_vblank_irq(phys_enc, false); + dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN); + } +} + +static void dpu_encoder_phys_vid_setup_misr(struct dpu_encoder_phys *phys_enc, + bool enable, u32 frame_count) +{ + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc) + return; + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + if (vid_enc->hw_intf && vid_enc->hw_intf->ops.setup_misr) + vid_enc->hw_intf->ops.setup_misr(vid_enc->hw_intf, + enable, frame_count); +} + +static u32 dpu_encoder_phys_vid_collect_misr(struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc) + return 0; + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + + return vid_enc->hw_intf && vid_enc->hw_intf->ops.collect_misr ? + vid_enc->hw_intf->ops.collect_misr(vid_enc->hw_intf) : 0; +} + +static int dpu_encoder_phys_vid_get_line_count( + struct dpu_encoder_phys *phys_enc) +{ + struct dpu_encoder_phys_vid *vid_enc; + + if (!phys_enc) + return -EINVAL; + + if (!dpu_encoder_phys_vid_is_master(phys_enc)) + return -EINVAL; + + vid_enc = to_dpu_encoder_phys_vid(phys_enc); + if (!vid_enc->hw_intf || !vid_enc->hw_intf->ops.get_line_count) + return -EINVAL; + + return vid_enc->hw_intf->ops.get_line_count(vid_enc->hw_intf); +} + +static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) +{ + ops->is_master = dpu_encoder_phys_vid_is_master; + ops->mode_set = dpu_encoder_phys_vid_mode_set; + ops->mode_fixup = dpu_encoder_phys_vid_mode_fixup; + ops->enable = dpu_encoder_phys_vid_enable; + ops->disable = dpu_encoder_phys_vid_disable; + ops->destroy = dpu_encoder_phys_vid_destroy; + ops->get_hw_resources = dpu_encoder_phys_vid_get_hw_resources; + ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq; + ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_vblank; + ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank; + ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank; + ops->irq_control = dpu_encoder_phys_vid_irq_control; + ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff; + ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff; + ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush; + ops->setup_misr = dpu_encoder_phys_vid_setup_misr; + ops->collect_misr = dpu_encoder_phys_vid_collect_misr; + ops->hw_reset = dpu_encoder_helper_hw_reset; + ops->get_line_count = dpu_encoder_phys_vid_get_line_count; +} + +struct dpu_encoder_phys *dpu_encoder_phys_vid_init( + struct dpu_enc_phys_init_params *p) +{ + struct dpu_encoder_phys *phys_enc = NULL; + struct dpu_encoder_phys_vid *vid_enc = NULL; + struct dpu_rm_hw_iter iter; + struct dpu_hw_mdp *hw_mdp; + struct dpu_encoder_irq *irq; + int i, ret = 0; + + if (!p) { + ret = -EINVAL; + goto fail; + } + + vid_enc = kzalloc(sizeof(*vid_enc), GFP_KERNEL); + if (!vid_enc) { + ret = -ENOMEM; + goto fail; + } + + phys_enc = &vid_enc->base; + + hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm); + if (IS_ERR_OR_NULL(hw_mdp)) { + ret = PTR_ERR(hw_mdp); + DPU_ERROR("failed to get mdptop\n"); + goto fail; + } + phys_enc->hw_mdptop = hw_mdp; + phys_enc->intf_idx = p->intf_idx; + + /** + * hw_intf resource permanently assigned to this encoder + * Other resources allocated at atomic commit time by use case + */ + dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_INTF); + while (dpu_rm_get_hw(&p->dpu_kms->rm, &iter)) { + struct dpu_hw_intf *hw_intf = (struct dpu_hw_intf *)iter.hw; + + if (hw_intf->idx == p->intf_idx) { + vid_enc->hw_intf = hw_intf; + break; + } + } + + if (!vid_enc->hw_intf) { + ret = -EINVAL; + DPU_ERROR("failed to get hw_intf\n"); + goto fail; + } + + DPU_DEBUG_VIDENC(vid_enc, "\n"); + + dpu_encoder_phys_vid_init_ops(&phys_enc->ops); + phys_enc->parent = p->parent; + phys_enc->parent_ops = p->parent_ops; + phys_enc->dpu_kms = p->dpu_kms; + phys_enc->split_role = p->split_role; + phys_enc->intf_mode = INTF_MODE_VIDEO; + phys_enc->enc_spinlock = p->enc_spinlock; + for (i = 0; i < INTR_IDX_MAX; i++) { + irq = &phys_enc->irq[i]; + INIT_LIST_HEAD(&irq->cb.list); + irq->irq_idx = -EINVAL; + irq->hw_idx = -EINVAL; + irq->cb.arg = phys_enc; + } + + irq = &phys_enc->irq[INTR_IDX_VSYNC]; + irq->name = "vsync_irq"; + irq->intr_type = DPU_IRQ_TYPE_INTF_VSYNC; + irq->intr_idx = INTR_IDX_VSYNC; + irq->cb.func = dpu_encoder_phys_vid_vblank_irq; + + irq = &phys_enc->irq[INTR_IDX_UNDERRUN]; + irq->name = "underrun"; + irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN; + irq->intr_idx = INTR_IDX_UNDERRUN; + irq->cb.func = dpu_encoder_phys_vid_underrun_irq; + + atomic_set(&phys_enc->vblank_refcount, 0); + atomic_set(&phys_enc->pending_kickoff_cnt, 0); + init_waitqueue_head(&phys_enc->pending_kickoff_wq); + phys_enc->enable_state = DPU_ENC_DISABLED; + + DPU_DEBUG_VIDENC(vid_enc, "created intf idx:%d\n", p->intf_idx); + + return phys_enc; + +fail: + DPU_ERROR("failed to create encoder\n"); + if (vid_enc) + dpu_encoder_phys_vid_destroy(phys_enc); + + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c new file mode 100644 index 000000000000..bfcd165e96df --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c @@ -0,0 +1,1173 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <uapi/drm/drm_fourcc.h> + +#include "msm_media_info.h" +#include "dpu_kms.h" +#include "dpu_formats.h" + +#define DPU_UBWC_META_MACRO_W_H 16 +#define DPU_UBWC_META_BLOCK_SIZE 256 +#define DPU_UBWC_PLANE_SIZE_ALIGNMENT 4096 + +#define DPU_TILE_HEIGHT_DEFAULT 1 +#define DPU_TILE_HEIGHT_TILED 4 +#define DPU_TILE_HEIGHT_UBWC 4 +#define DPU_TILE_HEIGHT_NV12 8 + +#define DPU_MAX_IMG_WIDTH 0x3FFF +#define DPU_MAX_IMG_HEIGHT 0x3FFF + +/** + * DPU supported format packing, bpp, and other format + * information. + * DPU currently only supports interleaved RGB formats + * UBWC support for a pixel format is indicated by the flag, + * there is additional meta data plane for such formats + */ + +#define INTERLEAVED_RGB_FMT(fmt, a, r, g, b, e0, e1, e2, e3, uc, alpha, \ +bp, flg, fm, np) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_INTERLEAVED, \ + .alpha_enable = alpha, \ + .element = { (e0), (e1), (e2), (e3) }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = DPU_CHROMA_RGB, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = uc, \ + .bpp = bp, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = DPU_TILE_HEIGHT_DEFAULT \ +} + +#define INTERLEAVED_RGB_FMT_TILED(fmt, a, r, g, b, e0, e1, e2, e3, uc, \ +alpha, bp, flg, fm, np, th) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_INTERLEAVED, \ + .alpha_enable = alpha, \ + .element = { (e0), (e1), (e2), (e3) }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = DPU_CHROMA_RGB, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = uc, \ + .bpp = bp, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = th \ +} + + +#define INTERLEAVED_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, e3, \ +alpha, chroma, count, bp, flg, fm, np) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_INTERLEAVED, \ + .alpha_enable = alpha, \ + .element = { (e0), (e1), (e2), (e3)}, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = count, \ + .bpp = bp, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = DPU_TILE_HEIGHT_DEFAULT \ +} + +#define PSEUDO_YUV_FMT(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_PSEUDO_PLANAR, \ + .alpha_enable = false, \ + .element = { (e0), (e1), 0, 0 }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = 2, \ + .bpp = 2, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = DPU_TILE_HEIGHT_DEFAULT \ +} + +#define PSEUDO_YUV_FMT_TILED(fmt, a, r, g, b, e0, e1, chroma, \ +flg, fm, np, th) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_PSEUDO_PLANAR, \ + .alpha_enable = false, \ + .element = { (e0), (e1), 0, 0 }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = 2, \ + .bpp = 2, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = th \ +} + +#define PSEUDO_YUV_FMT_LOOSE(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)\ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_PSEUDO_PLANAR, \ + .alpha_enable = false, \ + .element = { (e0), (e1), 0, 0 }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 1, \ + .unpack_tight = 0, \ + .unpack_count = 2, \ + .bpp = 2, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = DPU_TILE_HEIGHT_DEFAULT \ +} + +#define PSEUDO_YUV_FMT_LOOSE_TILED(fmt, a, r, g, b, e0, e1, chroma, \ +flg, fm, np, th) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_PSEUDO_PLANAR, \ + .alpha_enable = false, \ + .element = { (e0), (e1), 0, 0 }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 1, \ + .unpack_tight = 0, \ + .unpack_count = 2, \ + .bpp = 2, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = th \ +} + + +#define PLANAR_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, alpha, chroma, bp, \ +flg, fm, np) \ +{ \ + .base.pixel_format = DRM_FORMAT_ ## fmt, \ + .fetch_planes = DPU_PLANE_PLANAR, \ + .alpha_enable = alpha, \ + .element = { (e0), (e1), (e2), 0 }, \ + .bits = { g, b, r, a }, \ + .chroma_sample = chroma, \ + .unpack_align_msb = 0, \ + .unpack_tight = 1, \ + .unpack_count = 1, \ + .bpp = bp, \ + .fetch_mode = fm, \ + .flag = {(flg)}, \ + .num_planes = np, \ + .tile_height = DPU_TILE_HEIGHT_DEFAULT \ +} + +/* + * struct dpu_media_color_map - maps drm format to media format + * @format: DRM base pixel format + * @color: Media API color related to DRM format + */ +struct dpu_media_color_map { + uint32_t format; + uint32_t color; +}; + +static const struct dpu_format dpu_format_map[] = { + INTERLEAVED_RGB_FMT(ARGB8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + true, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ABGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XBGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBA8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + true, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRA8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + true, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRX8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + false, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XRGB8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + false, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBX8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + false, 4, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGB888, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, + false, 3, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGR888, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + false, 3, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGB565, + 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGR565, + 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ARGB1555, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ABGR1555, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBA5551, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRA5551, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XRGB1555, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XBGR1555, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBX5551, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRX5551, + COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ARGB4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ABGR4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBA4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRA4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + true, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XRGB4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XBGR4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBX4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRX4444, + COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + false, 2, 0, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRA1010102, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBA1010102, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ABGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(ARGB2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XRGB2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + false, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(BGRX1010102, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + false, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(XBGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + INTERLEAVED_RGB_FMT(RGBX1010102, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + false, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_LINEAR, 1), + + PSEUDO_YUV_FMT(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + PSEUDO_YUV_FMT(NV21, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C1_B_Cb, + DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + PSEUDO_YUV_FMT(NV16, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + PSEUDO_YUV_FMT(NV61, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C1_B_Cb, + DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + INTERLEAVED_YUV_FMT(VYUY, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y, + false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + INTERLEAVED_YUV_FMT(UYVY, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y, + false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + INTERLEAVED_YUV_FMT(YUYV, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr, + false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + INTERLEAVED_YUV_FMT(YVYU, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb, + false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 2), + + PLANAR_YUV_FMT(YUV420, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C1_B_Cb, C0_G_Y, + false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 3), + + PLANAR_YUV_FMT(YVU420, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, C0_G_Y, + false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_LINEAR, 3), +}; + +/* + * A5x tile formats tables: + * These tables hold the A5x tile formats supported. + */ +static const struct dpu_format dpu_format_map_tile[] = { + INTERLEAVED_RGB_FMT_TILED(BGR565, + 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + false, 2, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(ARGB8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + true, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(ABGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4, + true, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(XBGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(RGBA8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(BGRA8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + true, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(BGRX8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4, + false, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(XRGB8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4, + false, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(RGBX8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 4, 0, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(ABGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + INTERLEAVED_RGB_FMT_TILED(XBGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX, + DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED), + + PSEUDO_YUV_FMT_TILED(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12), + + PSEUDO_YUV_FMT_TILED(NV21, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C1_B_Cb, + DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12), +}; + +/* + * UBWC formats table: + * This table holds the UBWC formats supported. + * If a compression ratio needs to be used for this or any other format, + * the data will be passed by user-space. + */ +static const struct dpu_format dpu_format_map_ubwc[] = { + INTERLEAVED_RGB_FMT_TILED(BGR565, + 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + false, 2, DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + + INTERLEAVED_RGB_FMT_TILED(ABGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + + INTERLEAVED_RGB_FMT_TILED(XBGR8888, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + false, 4, DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + + INTERLEAVED_RGB_FMT_TILED(ABGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + + INTERLEAVED_RGB_FMT_TILED(XBGR2101010, + COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4, + true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC), + + PSEUDO_YUV_FMT_TILED(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV | + DPU_FORMAT_FLAG_COMPRESSED, + DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12), +}; + +static const struct dpu_format dpu_format_map_p010[] = { + PSEUDO_YUV_FMT_LOOSE(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX), + DPU_FETCH_LINEAR, 2), +}; + +static const struct dpu_format dpu_format_map_p010_ubwc[] = { + PSEUDO_YUV_FMT_LOOSE_TILED(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX | + DPU_FORMAT_FLAG_COMPRESSED), + DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12), +}; + +static const struct dpu_format dpu_format_map_tp10_ubwc[] = { + PSEUDO_YUV_FMT_TILED(NV12, + 0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, + C1_B_Cb, C2_R_Cr, + DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX | + DPU_FORMAT_FLAG_COMPRESSED), + DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12), +}; + +/* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support + * Note: Not using the drm_format_*_subsampling since we have formats + */ +static void _dpu_get_v_h_subsample_rate( + enum dpu_chroma_samp_type chroma_sample, + uint32_t *v_sample, + uint32_t *h_sample) +{ + if (!v_sample || !h_sample) + return; + + switch (chroma_sample) { + case DPU_CHROMA_H2V1: + *v_sample = 1; + *h_sample = 2; + break; + case DPU_CHROMA_H1V2: + *v_sample = 2; + *h_sample = 1; + break; + case DPU_CHROMA_420: + *v_sample = 2; + *h_sample = 2; + break; + default: + *v_sample = 1; + *h_sample = 1; + break; + } +} + +static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt) +{ + static const struct dpu_media_color_map dpu_media_ubwc_map[] = { + {DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC}, + {DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC}, + {DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC}, + {DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC}, + {DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC}, + }; + int color_fmt = -1; + int i; + + if (fmt->base.pixel_format == DRM_FORMAT_NV12) { + if (DPU_FORMAT_IS_DX(fmt)) { + if (fmt->unpack_tight) + color_fmt = COLOR_FMT_NV12_BPP10_UBWC; + else + color_fmt = COLOR_FMT_P010_UBWC; + } else + color_fmt = COLOR_FMT_NV12_UBWC; + return color_fmt; + } + + for (i = 0; i < ARRAY_SIZE(dpu_media_ubwc_map); ++i) + if (fmt->base.pixel_format == dpu_media_ubwc_map[i].format) { + color_fmt = dpu_media_ubwc_map[i].color; + break; + } + return color_fmt; +} + +static int _dpu_format_get_plane_sizes_ubwc( + const struct dpu_format *fmt, + const uint32_t width, + const uint32_t height, + struct dpu_hw_fmt_layout *layout) +{ + int i; + int color; + bool meta = DPU_FORMAT_IS_UBWC(fmt); + + memset(layout, 0, sizeof(struct dpu_hw_fmt_layout)); + layout->format = fmt; + layout->width = width; + layout->height = height; + layout->num_planes = fmt->num_planes; + + color = _dpu_format_get_media_color_ubwc(fmt); + if (color < 0) { + DRM_ERROR("UBWC format not supported for fmt: %4.4s\n", + (char *)&fmt->base.pixel_format); + return -EINVAL; + } + + if (DPU_FORMAT_IS_YUV(layout->format)) { + uint32_t y_sclines, uv_sclines; + uint32_t y_meta_scanlines = 0; + uint32_t uv_meta_scanlines = 0; + + layout->num_planes = 2; + layout->plane_pitch[0] = VENUS_Y_STRIDE(color, width); + y_sclines = VENUS_Y_SCANLINES(color, height); + layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] * + y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + + layout->plane_pitch[1] = VENUS_UV_STRIDE(color, width); + uv_sclines = VENUS_UV_SCANLINES(color, height); + layout->plane_size[1] = MSM_MEDIA_ALIGN(layout->plane_pitch[1] * + uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + + if (!meta) + goto done; + + layout->num_planes += 2; + layout->plane_pitch[2] = VENUS_Y_META_STRIDE(color, width); + y_meta_scanlines = VENUS_Y_META_SCANLINES(color, height); + layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] * + y_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + + layout->plane_pitch[3] = VENUS_UV_META_STRIDE(color, width); + uv_meta_scanlines = VENUS_UV_META_SCANLINES(color, height); + layout->plane_size[3] = MSM_MEDIA_ALIGN(layout->plane_pitch[3] * + uv_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + + } else { + uint32_t rgb_scanlines, rgb_meta_scanlines; + + layout->num_planes = 1; + + layout->plane_pitch[0] = VENUS_RGB_STRIDE(color, width); + rgb_scanlines = VENUS_RGB_SCANLINES(color, height); + layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] * + rgb_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + + if (!meta) + goto done; + layout->num_planes += 2; + layout->plane_pitch[2] = VENUS_RGB_META_STRIDE(color, width); + rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color, height); + layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] * + rgb_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT); + } + +done: + for (i = 0; i < DPU_MAX_PLANES; i++) + layout->total_size += layout->plane_size[i]; + + return 0; +} + +static int _dpu_format_get_plane_sizes_linear( + const struct dpu_format *fmt, + const uint32_t width, + const uint32_t height, + struct dpu_hw_fmt_layout *layout, + const uint32_t *pitches) +{ + int i; + + memset(layout, 0, sizeof(struct dpu_hw_fmt_layout)); + layout->format = fmt; + layout->width = width; + layout->height = height; + layout->num_planes = fmt->num_planes; + + /* Due to memset above, only need to set planes of interest */ + if (fmt->fetch_planes == DPU_PLANE_INTERLEAVED) { + layout->num_planes = 1; + layout->plane_size[0] = width * height * layout->format->bpp; + layout->plane_pitch[0] = width * layout->format->bpp; + } else { + uint32_t v_subsample, h_subsample; + uint32_t chroma_samp; + uint32_t bpp = 1; + + chroma_samp = fmt->chroma_sample; + _dpu_get_v_h_subsample_rate(chroma_samp, &v_subsample, + &h_subsample); + + if (width % h_subsample || height % v_subsample) { + DRM_ERROR("mismatch in subsample vs dimensions\n"); + return -EINVAL; + } + + if ((fmt->base.pixel_format == DRM_FORMAT_NV12) && + (DPU_FORMAT_IS_DX(fmt))) + bpp = 2; + layout->plane_pitch[0] = width * bpp; + layout->plane_pitch[1] = layout->plane_pitch[0] / h_subsample; + layout->plane_size[0] = layout->plane_pitch[0] * height; + layout->plane_size[1] = layout->plane_pitch[1] * + (height / v_subsample); + + if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) { + layout->num_planes = 2; + layout->plane_size[1] *= 2; + layout->plane_pitch[1] *= 2; + } else { + /* planar */ + layout->num_planes = 3; + layout->plane_size[2] = layout->plane_size[1]; + layout->plane_pitch[2] = layout->plane_pitch[1]; + } + } + + /* + * linear format: allow user allocated pitches if they are greater than + * the requirement. + * ubwc format: pitch values are computed uniformly across + * all the components based on ubwc specifications. + */ + for (i = 0; i < layout->num_planes && i < DPU_MAX_PLANES; ++i) { + if (pitches && layout->plane_pitch[i] < pitches[i]) + layout->plane_pitch[i] = pitches[i]; + } + + for (i = 0; i < DPU_MAX_PLANES; i++) + layout->total_size += layout->plane_size[i]; + + return 0; +} + +static int dpu_format_get_plane_sizes( + const struct dpu_format *fmt, + const uint32_t w, + const uint32_t h, + struct dpu_hw_fmt_layout *layout, + const uint32_t *pitches) +{ + if (!layout || !fmt) { + DRM_ERROR("invalid pointer\n"); + return -EINVAL; + } + + if ((w > DPU_MAX_IMG_WIDTH) || (h > DPU_MAX_IMG_HEIGHT)) { + DRM_ERROR("image dimensions outside max range\n"); + return -ERANGE; + } + + if (DPU_FORMAT_IS_UBWC(fmt) || DPU_FORMAT_IS_TILE(fmt)) + return _dpu_format_get_plane_sizes_ubwc(fmt, w, h, layout); + + return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches); +} + +static int _dpu_format_populate_addrs_ubwc( + struct msm_gem_address_space *aspace, + struct drm_framebuffer *fb, + struct dpu_hw_fmt_layout *layout) +{ + uint32_t base_addr = 0; + bool meta; + + if (!fb || !layout) { + DRM_ERROR("invalid pointers\n"); + return -EINVAL; + } + + if (aspace) + base_addr = msm_framebuffer_iova(fb, aspace, 0); + if (!base_addr) { + DRM_ERROR("failed to retrieve base addr\n"); + return -EFAULT; + } + + meta = DPU_FORMAT_IS_UBWC(layout->format); + + /* Per-format logic for verifying active planes */ + if (DPU_FORMAT_IS_YUV(layout->format)) { + /************************************************/ + /* UBWC ** */ + /* buffer ** DPU PLANE */ + /* format ** */ + /************************************************/ + /* ------------------- ** -------------------- */ + /* | Y meta | ** | Y bitstream | */ + /* | data | ** | plane | */ + /* ------------------- ** -------------------- */ + /* | Y bitstream | ** | CbCr bitstream | */ + /* | data | ** | plane | */ + /* ------------------- ** -------------------- */ + /* | Cbcr metadata | ** | Y meta | */ + /* | data | ** | plane | */ + /* ------------------- ** -------------------- */ + /* | CbCr bitstream | ** | CbCr meta | */ + /* | data | ** | plane | */ + /* ------------------- ** -------------------- */ + /************************************************/ + + /* configure Y bitstream plane */ + layout->plane_addr[0] = base_addr + layout->plane_size[2]; + + /* configure CbCr bitstream plane */ + layout->plane_addr[1] = base_addr + layout->plane_size[0] + + layout->plane_size[2] + layout->plane_size[3]; + + if (!meta) + goto done; + + /* configure Y metadata plane */ + layout->plane_addr[2] = base_addr; + + /* configure CbCr metadata plane */ + layout->plane_addr[3] = base_addr + layout->plane_size[0] + + layout->plane_size[2]; + + } else { + /************************************************/ + /* UBWC ** */ + /* buffer ** DPU PLANE */ + /* format ** */ + /************************************************/ + /* ------------------- ** -------------------- */ + /* | RGB meta | ** | RGB bitstream | */ + /* | data | ** | plane | */ + /* ------------------- ** -------------------- */ + /* | RGB bitstream | ** | NONE | */ + /* | data | ** | | */ + /* ------------------- ** -------------------- */ + /* ** | RGB meta | */ + /* ** | plane | */ + /* ** -------------------- */ + /************************************************/ + + layout->plane_addr[0] = base_addr + layout->plane_size[2]; + layout->plane_addr[1] = 0; + + if (!meta) + goto done; + + layout->plane_addr[2] = base_addr; + layout->plane_addr[3] = 0; + } +done: + return 0; +} + +static int _dpu_format_populate_addrs_linear( + struct msm_gem_address_space *aspace, + struct drm_framebuffer *fb, + struct dpu_hw_fmt_layout *layout) +{ + unsigned int i; + + /* Can now check the pitches given vs pitches expected */ + for (i = 0; i < layout->num_planes; ++i) { + if (layout->plane_pitch[i] > fb->pitches[i]) { + DRM_ERROR("plane %u expected pitch %u, fb %u\n", + i, layout->plane_pitch[i], fb->pitches[i]); + return -EINVAL; + } + } + + /* Populate addresses for simple formats here */ + for (i = 0; i < layout->num_planes; ++i) { + if (aspace) + layout->plane_addr[i] = + msm_framebuffer_iova(fb, aspace, i); + if (!layout->plane_addr[i]) { + DRM_ERROR("failed to retrieve base addr\n"); + return -EFAULT; + } + } + + return 0; +} + +int dpu_format_populate_layout( + struct msm_gem_address_space *aspace, + struct drm_framebuffer *fb, + struct dpu_hw_fmt_layout *layout) +{ + uint32_t plane_addr[DPU_MAX_PLANES]; + int i, ret; + + if (!fb || !layout) { + DRM_ERROR("invalid arguments\n"); + return -EINVAL; + } + + if ((fb->width > DPU_MAX_IMG_WIDTH) || + (fb->height > DPU_MAX_IMG_HEIGHT)) { + DRM_ERROR("image dimensions outside max range\n"); + return -ERANGE; + } + + layout->format = to_dpu_format(msm_framebuffer_format(fb)); + + /* Populate the plane sizes etc via get_format */ + ret = dpu_format_get_plane_sizes(layout->format, fb->width, fb->height, + layout, fb->pitches); + if (ret) + return ret; + + for (i = 0; i < DPU_MAX_PLANES; ++i) + plane_addr[i] = layout->plane_addr[i]; + + /* Populate the addresses given the fb */ + if (DPU_FORMAT_IS_UBWC(layout->format) || + DPU_FORMAT_IS_TILE(layout->format)) + ret = _dpu_format_populate_addrs_ubwc(aspace, fb, layout); + else + ret = _dpu_format_populate_addrs_linear(aspace, fb, layout); + + /* check if anything changed */ + if (!ret && !memcmp(plane_addr, layout->plane_addr, sizeof(plane_addr))) + ret = -EAGAIN; + + return ret; +} + +int dpu_format_check_modified_format( + const struct msm_kms *kms, + const struct msm_format *msm_fmt, + const struct drm_mode_fb_cmd2 *cmd, + struct drm_gem_object **bos) +{ + int ret, i, num_base_fmt_planes; + const struct dpu_format *fmt; + struct dpu_hw_fmt_layout layout; + uint32_t bos_total_size = 0; + + if (!msm_fmt || !cmd || !bos) { + DRM_ERROR("invalid arguments\n"); + return -EINVAL; + } + + fmt = to_dpu_format(msm_fmt); + num_base_fmt_planes = drm_format_num_planes(fmt->base.pixel_format); + + ret = dpu_format_get_plane_sizes(fmt, cmd->width, cmd->height, + &layout, cmd->pitches); + if (ret) + return ret; + + for (i = 0; i < num_base_fmt_planes; i++) { + if (!bos[i]) { + DRM_ERROR("invalid handle for plane %d\n", i); + return -EINVAL; + } + if ((i == 0) || (bos[i] != bos[0])) + bos_total_size += bos[i]->size; + } + + if (bos_total_size < layout.total_size) { + DRM_ERROR("buffers total size too small %u expected %u\n", + bos_total_size, layout.total_size); + return -EINVAL; + } + + return 0; +} + +const struct dpu_format *dpu_get_dpu_format_ext( + const uint32_t format, + const uint64_t modifier) +{ + uint32_t i = 0; + const struct dpu_format *fmt = NULL; + const struct dpu_format *map = NULL; + ssize_t map_size = 0; + + /* + * Currently only support exactly zero or one modifier. + * All planes use the same modifier. + */ + DPU_DEBUG("plane format modifier 0x%llX\n", modifier); + + switch (modifier) { + case 0: + map = dpu_format_map; + map_size = ARRAY_SIZE(dpu_format_map); + break; + case DRM_FORMAT_MOD_QCOM_COMPRESSED: + map = dpu_format_map_ubwc; + map_size = ARRAY_SIZE(dpu_format_map_ubwc); + DPU_DEBUG("found fmt: %4.4s DRM_FORMAT_MOD_QCOM_COMPRESSED\n", + (char *)&format); + break; + default: + DPU_ERROR("unsupported format modifier %llX\n", modifier); + return NULL; + } + + for (i = 0; i < map_size; i++) { + if (format == map[i].base.pixel_format) { + fmt = &map[i]; + break; + } + } + + if (fmt == NULL) + DPU_ERROR("unsupported fmt: %4.4s modifier 0x%llX\n", + (char *)&format, modifier); + else + DPU_DEBUG("fmt %4.4s mod 0x%llX ubwc %d yuv %d\n", + (char *)&format, modifier, + DPU_FORMAT_IS_UBWC(fmt), + DPU_FORMAT_IS_YUV(fmt)); + + return fmt; +} + +const struct msm_format *dpu_get_msm_format( + struct msm_kms *kms, + const uint32_t format, + const uint64_t modifiers) +{ + const struct dpu_format *fmt = dpu_get_dpu_format_ext(format, + modifiers); + if (fmt) + return &fmt->base; + return NULL; +} + +uint32_t dpu_populate_formats( + const struct dpu_format_extended *format_list, + uint32_t *pixel_formats, + uint64_t *pixel_modifiers, + uint32_t pixel_formats_max) +{ + uint32_t i, fourcc_format; + + if (!format_list || !pixel_formats) + return 0; + + for (i = 0, fourcc_format = 0; + format_list->fourcc_format && i < pixel_formats_max; + ++format_list) { + /* verify if listed format is in dpu_format_map? */ + + /* optionally return modified formats */ + if (pixel_modifiers) { + /* assume same modifier for all fb planes */ + pixel_formats[i] = format_list->fourcc_format; + pixel_modifiers[i++] = format_list->modifier; + } else { + /* assume base formats grouped together */ + if (fourcc_format != format_list->fourcc_format) { + fourcc_format = format_list->fourcc_format; + pixel_formats[i++] = fourcc_format; + } + } + } + + return i; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h new file mode 100644 index 000000000000..a54451d8d011 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h @@ -0,0 +1,88 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_FORMATS_H +#define _DPU_FORMATS_H + +#include <drm/drm_fourcc.h> +#include "msm_gem.h" +#include "dpu_hw_mdss.h" + +/** + * dpu_get_dpu_format_ext() - Returns dpu format structure pointer. + * @format: DRM FourCC Code + * @modifiers: format modifier array from client, one per plane + */ +const struct dpu_format *dpu_get_dpu_format_ext( + const uint32_t format, + const uint64_t modifier); + +#define dpu_get_dpu_format(f) dpu_get_dpu_format_ext(f, 0) + +/** + * dpu_get_msm_format - get an dpu_format by its msm_format base + * callback function registers with the msm_kms layer + * @kms: kms driver + * @format: DRM FourCC Code + * @modifiers: data layout modifier + */ +const struct msm_format *dpu_get_msm_format( + struct msm_kms *kms, + const uint32_t format, + const uint64_t modifiers); + +/** + * dpu_populate_formats - populate the given array with fourcc codes supported + * @format_list: pointer to list of possible formats + * @pixel_formats: array to populate with fourcc codes + * @pixel_modifiers: array to populate with drm modifiers, can be NULL + * @pixel_formats_max: length of pixel formats array + * Return: number of elements populated + */ +uint32_t dpu_populate_formats( + const struct dpu_format_extended *format_list, + uint32_t *pixel_formats, + uint64_t *pixel_modifiers, + uint32_t pixel_formats_max); + +/** + * dpu_format_check_modified_format - validate format and buffers for + * dpu non-standard, i.e. modified format + * @kms: kms driver + * @msm_fmt: pointer to the msm_fmt base pointer of an dpu_format + * @cmd: fb_cmd2 structure user request + * @bos: gem buffer object list + * + * Return: error code on failure, 0 on success + */ +int dpu_format_check_modified_format( + const struct msm_kms *kms, + const struct msm_format *msm_fmt, + const struct drm_mode_fb_cmd2 *cmd, + struct drm_gem_object **bos); + +/** + * dpu_format_populate_layout - populate the given format layout based on + * mmu, fb, and format found in the fb + * @aspace: address space pointer + * @fb: framebuffer pointer + * @fmtl: format layout structure to populate + * + * Return: error code on failure, -EAGAIN if success but the addresses + * are the same as before or 0 if new addresses were populated + */ +int dpu_format_populate_layout( + struct msm_gem_address_space *aspace, + struct drm_framebuffer *fb, + struct dpu_hw_fmt_layout *fmtl); + +#endif /*_DPU_FORMATS_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c new file mode 100644 index 000000000000..58d29e43faef --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c @@ -0,0 +1,155 @@ +/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/mutex.h> +#include <linux/errno.h> +#include <linux/slab.h> + +#include "dpu_hw_mdss.h" +#include "dpu_hw_blk.h" + +/* Serialization lock for dpu_hw_blk_list */ +static DEFINE_MUTEX(dpu_hw_blk_lock); + +/* List of all hw block objects */ +static LIST_HEAD(dpu_hw_blk_list); + +/** + * dpu_hw_blk_init - initialize hw block object + * @type: hw block type - enum dpu_hw_blk_type + * @id: instance id of the hw block + * @ops: Pointer to block operations + * return: 0 if success; error code otherwise + */ +int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id, + struct dpu_hw_blk_ops *ops) +{ + if (!hw_blk) { + pr_err("invalid parameters\n"); + return -EINVAL; + } + + INIT_LIST_HEAD(&hw_blk->list); + hw_blk->type = type; + hw_blk->id = id; + atomic_set(&hw_blk->refcount, 0); + + if (ops) + hw_blk->ops = *ops; + + mutex_lock(&dpu_hw_blk_lock); + list_add(&hw_blk->list, &dpu_hw_blk_list); + mutex_unlock(&dpu_hw_blk_lock); + + return 0; +} + +/** + * dpu_hw_blk_destroy - destroy hw block object. + * @hw_blk: pointer to hw block object + * return: none + */ +void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk) +{ + if (!hw_blk) { + pr_err("invalid parameters\n"); + return; + } + + if (atomic_read(&hw_blk->refcount)) + pr_err("hw_blk:%d.%d invalid refcount\n", hw_blk->type, + hw_blk->id); + + mutex_lock(&dpu_hw_blk_lock); + list_del(&hw_blk->list); + mutex_unlock(&dpu_hw_blk_lock); +} + +/** + * dpu_hw_blk_get - get hw_blk from free pool + * @hw_blk: if specified, increment reference count only + * @type: if hw_blk is not specified, allocate the next available of this type + * @id: if specified (>= 0), allocate the given instance of the above type + * return: pointer to hw block object + */ +struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id) +{ + struct dpu_hw_blk *curr; + int rc, refcount; + + if (!hw_blk) { + mutex_lock(&dpu_hw_blk_lock); + list_for_each_entry(curr, &dpu_hw_blk_list, list) { + if ((curr->type != type) || + (id >= 0 && curr->id != id) || + (id < 0 && + atomic_read(&curr->refcount))) + continue; + + hw_blk = curr; + break; + } + mutex_unlock(&dpu_hw_blk_lock); + } + + if (!hw_blk) { + pr_debug("no hw_blk:%d\n", type); + return NULL; + } + + refcount = atomic_inc_return(&hw_blk->refcount); + + if (refcount == 1 && hw_blk->ops.start) { + rc = hw_blk->ops.start(hw_blk); + if (rc) { + pr_err("failed to start hw_blk:%d rc:%d\n", type, rc); + goto error_start; + } + } + + pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type, + hw_blk->id, refcount); + return hw_blk; + +error_start: + dpu_hw_blk_put(hw_blk); + return ERR_PTR(rc); +} + +/** + * dpu_hw_blk_put - put hw_blk to free pool if decremented refcount is zero + * @hw_blk: hw block to be freed + * @free_blk: function to be called when reference count goes to zero + */ +void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk) +{ + if (!hw_blk) { + pr_err("invalid parameters\n"); + return; + } + + pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type, hw_blk->id, + atomic_read(&hw_blk->refcount)); + + if (!atomic_read(&hw_blk->refcount)) { + pr_err("hw_blk:%d.%d invalid put\n", hw_blk->type, hw_blk->id); + return; + } + + if (atomic_dec_return(&hw_blk->refcount)) + return; + + if (hw_blk->ops.stop) + hw_blk->ops.stop(hw_blk); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h new file mode 100644 index 000000000000..0f4ca8af1ec5 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h @@ -0,0 +1,53 @@ +/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_BLK_H +#define _DPU_HW_BLK_H + +#include <linux/types.h> +#include <linux/list.h> +#include <linux/atomic.h> + +struct dpu_hw_blk; + +/** + * struct dpu_hw_blk_ops - common hardware block operations + * @start: start operation on first get + * @stop: stop operation on last put + */ +struct dpu_hw_blk_ops { + int (*start)(struct dpu_hw_blk *); + void (*stop)(struct dpu_hw_blk *); +}; + +/** + * struct dpu_hw_blk - definition of hardware block object + * @list: list of hardware blocks + * @type: hardware block type + * @id: instance id + * @refcount: reference/usage count + */ +struct dpu_hw_blk { + struct list_head list; + u32 type; + int id; + atomic_t refcount; + struct dpu_hw_blk_ops ops; +}; + +int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id, + struct dpu_hw_blk_ops *ops); +void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk); + +struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id); +void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk); +#endif /*_DPU_HW_BLK_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c new file mode 100644 index 000000000000..44ee06398b1d --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -0,0 +1,511 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ +#include <linux/slab.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include "dpu_hw_mdss.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_catalog_format.h" +#include "dpu_kms.h" + +#define VIG_SDM845_MASK \ + (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_SCALER_QSEED3) | BIT(DPU_SSPP_QOS) |\ + BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\ + BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT)) + +#define DMA_SDM845_MASK \ + (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\ + BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\ + BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT)) + +#define MIXER_SDM845_MASK \ + (BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER)) + +#define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER) + +#define PINGPONG_SDM845_SPLIT_MASK \ + (PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2)) + +#define DEFAULT_PIXEL_RAM_SIZE (50 * 1024) +#define DEFAULT_DPU_LINE_WIDTH 2048 +#define DEFAULT_DPU_OUTPUT_LINE_WIDTH 2560 + +#define MAX_HORZ_DECIMATION 4 +#define MAX_VERT_DECIMATION 4 + +#define MAX_UPSCALE_RATIO 20 +#define MAX_DOWNSCALE_RATIO 4 +#define SSPP_UNITY_SCALE 1 + +#define STRCAT(X, Y) (X Y) + +/************************************************************* + * DPU sub blocks config + *************************************************************/ +/* DPU top level caps */ +static const struct dpu_caps sdm845_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0xb, + .qseed_type = DPU_SSPP_SCALER_QSEED3, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, + .ubwc_version = DPU_HW_UBWC_VER_20, + .has_src_split = true, + .has_dim_layer = true, + .has_idle_pc = true, +}; + +static struct dpu_mdp_cfg sdm845_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x45C, + .features = 0, + .highest_bank_bit = 0x2, + .has_dest_scaler = true, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2AC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG1] = { + .reg_off = 0x2B4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG2] = { + .reg_off = 0x2BC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_VIG3] = { + .reg_off = 0x2C4, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2AC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_DMA1] = { + .reg_off = 0x2B4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .reg_off = 0x2BC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .reg_off = 0x2C4, .bit_off = 8}, + }, +}; + +/************************************************************* + * CTL sub blocks config + *************************************************************/ +static struct dpu_ctl_cfg sdm845_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x1000, .len = 0xE4, + .features = BIT(DPU_CTL_SPLIT_DISPLAY) + }, + { + .name = "ctl_1", .id = CTL_1, + .base = 0x1200, .len = 0xE4, + .features = BIT(DPU_CTL_SPLIT_DISPLAY) + }, + { + .name = "ctl_2", .id = CTL_2, + .base = 0x1400, .len = 0xE4, + .features = 0 + }, + { + .name = "ctl_3", .id = CTL_3, + .base = 0x1600, .len = 0xE4, + .features = 0 + }, + { + .name = "ctl_4", .id = CTL_4, + .base = 0x1800, .len = 0xE4, + .features = 0 + }, +}; + +/************************************************************* + * SSPP sub blocks config + *************************************************************/ + +/* SSPP common configuration */ +static const struct dpu_sspp_blks_common sdm845_sspp_common = { + .maxlinewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, + .maxhdeciexp = MAX_HORZ_DECIMATION, + .maxvdeciexp = MAX_VERT_DECIMATION, +}; + +#define _VIG_SBLK(num, sdma_pri) \ + { \ + .common = &sdm845_sspp_common, \ + .maxdwnscale = MAX_DOWNSCALE_RATIO, \ + .maxupscale = MAX_UPSCALE_RATIO, \ + .smart_dma_priority = sdma_pri, \ + .src_blk = {.name = STRCAT("sspp_src_", num), \ + .id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \ + .scaler_blk = {.name = STRCAT("sspp_scaler", num), \ + .id = DPU_SSPP_SCALER_QSEED3, \ + .base = 0xa00, .len = 0xa0,}, \ + .csc_blk = {.name = STRCAT("sspp_csc", num), \ + .id = DPU_SSPP_CSC_10BIT, \ + .base = 0x1a00, .len = 0x100,}, \ + .format_list = plane_formats_yuv, \ + .virt_format_list = plane_formats, \ + } + +#define _DMA_SBLK(num, sdma_pri) \ + { \ + .common = &sdm845_sspp_common, \ + .maxdwnscale = SSPP_UNITY_SCALE, \ + .maxupscale = SSPP_UNITY_SCALE, \ + .smart_dma_priority = sdma_pri, \ + .src_blk = {.name = STRCAT("sspp_src_", num), \ + .id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \ + .format_list = plane_formats, \ + .virt_format_list = plane_formats, \ + } + +static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5); +static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = _VIG_SBLK("1", 6); +static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = _VIG_SBLK("2", 7); +static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = _VIG_SBLK("3", 8); + +static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1); +static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2); +static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK("10", 3); +static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4); + +#define SSPP_VIG_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \ + { \ + .name = _name, .id = _id, \ + .base = _base, .len = 0x1c8, \ + .features = VIG_SDM845_MASK, \ + .sblk = &_sblk, \ + .xin_id = _xinid, \ + .type = SSPP_TYPE_VIG, \ + .clk_ctrl = _clkctrl \ + } + +#define SSPP_DMA_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \ + { \ + .name = _name, .id = _id, \ + .base = _base, .len = 0x1c8, \ + .features = DMA_SDM845_MASK, \ + .sblk = &_sblk, \ + .xin_id = _xinid, \ + .type = SSPP_TYPE_DMA, \ + .clk_ctrl = _clkctrl \ + } + +static struct dpu_sspp_cfg sdm845_sspp[] = { + SSPP_VIG_BLK("sspp_0", SSPP_VIG0, 0x4000, + sdm845_vig_sblk_0, 0, DPU_CLK_CTRL_VIG0), + SSPP_VIG_BLK("sspp_1", SSPP_VIG1, 0x6000, + sdm845_vig_sblk_1, 4, DPU_CLK_CTRL_VIG1), + SSPP_VIG_BLK("sspp_2", SSPP_VIG2, 0x8000, + sdm845_vig_sblk_2, 8, DPU_CLK_CTRL_VIG2), + SSPP_VIG_BLK("sspp_3", SSPP_VIG3, 0xa000, + sdm845_vig_sblk_3, 12, DPU_CLK_CTRL_VIG3), + SSPP_DMA_BLK("sspp_8", SSPP_DMA0, 0x24000, + sdm845_dma_sblk_0, 1, DPU_CLK_CTRL_DMA0), + SSPP_DMA_BLK("sspp_9", SSPP_DMA1, 0x26000, + sdm845_dma_sblk_1, 5, DPU_CLK_CTRL_DMA1), + SSPP_DMA_BLK("sspp_10", SSPP_DMA2, 0x28000, + sdm845_dma_sblk_2, 9, DPU_CLK_CTRL_CURSOR0), + SSPP_DMA_BLK("sspp_11", SSPP_DMA3, 0x2a000, + sdm845_dma_sblk_3, 13, DPU_CLK_CTRL_CURSOR1), +}; + +/************************************************************* + * MIXER sub blocks config + *************************************************************/ +static const struct dpu_lm_sub_blks sdm845_lm_sblk = { + .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxblendstages = 11, /* excluding base layer */ + .blendstage_base = { /* offsets relative to mixer base */ + 0x20, 0x38, 0x50, 0x68, 0x80, 0x98, + 0xb0, 0xc8, 0xe0, 0xf8, 0x110 + }, +}; + +#define LM_BLK(_name, _id, _base, _ds, _pp, _lmpair) \ + { \ + .name = _name, .id = _id, \ + .base = _base, .len = 0x320, \ + .features = MIXER_SDM845_MASK, \ + .sblk = &sdm845_lm_sblk, \ + .ds = _ds, \ + .pingpong = _pp, \ + .lm_pair_mask = (1 << _lmpair) \ + } + +static struct dpu_lm_cfg sdm845_lm[] = { + LM_BLK("lm_0", LM_0, 0x44000, DS_0, PINGPONG_0, LM_1), + LM_BLK("lm_1", LM_1, 0x45000, DS_1, PINGPONG_1, LM_0), + LM_BLK("lm_2", LM_2, 0x46000, DS_MAX, PINGPONG_2, LM_5), + LM_BLK("lm_3", LM_3, 0x0, DS_MAX, PINGPONG_MAX, 0), + LM_BLK("lm_4", LM_4, 0x0, DS_MAX, PINGPONG_MAX, 0), + LM_BLK("lm_5", LM_5, 0x49000, DS_MAX, PINGPONG_3, LM_2), +}; + +/************************************************************* + * DS sub blocks config + *************************************************************/ +static const struct dpu_ds_top_cfg sdm845_ds_top = { + .name = "ds_top_0", .id = DS_TOP, + .base = 0x60000, .len = 0xc, + .maxinputwidth = DEFAULT_DPU_LINE_WIDTH, + .maxoutputwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .maxupscale = MAX_UPSCALE_RATIO, +}; + +#define DS_BLK(_name, _id, _base) \ + {\ + .name = _name, .id = _id, \ + .base = _base, .len = 0x800, \ + .features = DPU_SSPP_SCALER_QSEED3, \ + .top = &sdm845_ds_top \ + } + +static struct dpu_ds_cfg sdm845_ds[] = { + DS_BLK("ds_0", DS_0, 0x800), + DS_BLK("ds_1", DS_1, 0x1000), +}; + +/************************************************************* + * PINGPONG sub blocks config + *************************************************************/ +static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = { + .te2 = {.id = DPU_PINGPONG_TE2, .base = 0x2000, .len = 0x0, + .version = 0x1}, + .dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0, + .len = 0x20, .version = 0x10000}, +}; + +static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = { + .dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0, + .len = 0x20, .version = 0x10000}, +}; + +#define PP_BLK_TE(_name, _id, _base) \ + {\ + .name = _name, .id = _id, \ + .base = _base, .len = 0xd4, \ + .features = PINGPONG_SDM845_SPLIT_MASK, \ + .sblk = &sdm845_pp_sblk_te \ + } +#define PP_BLK(_name, _id, _base) \ + {\ + .name = _name, .id = _id, \ + .base = _base, .len = 0xd4, \ + .features = PINGPONG_SDM845_MASK, \ + .sblk = &sdm845_pp_sblk \ + } + +static struct dpu_pingpong_cfg sdm845_pp[] = { + PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000), + PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800), + PP_BLK("pingpong_2", PINGPONG_2, 0x71000), + PP_BLK("pingpong_3", PINGPONG_3, 0x71800), +}; + +/************************************************************* + * INTF sub blocks config + *************************************************************/ +#define INTF_BLK(_name, _id, _base, _type, _ctrl_id) \ + {\ + .name = _name, .id = _id, \ + .base = _base, .len = 0x280, \ + .type = _type, \ + .controller_id = _ctrl_id, \ + .prog_fetch_lines_worst_case = 24 \ + } + +static struct dpu_intf_cfg sdm845_intf[] = { + INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0), + INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0), + INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1), + INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1), +}; + +/************************************************************* + * CDM sub blocks config + *************************************************************/ +static struct dpu_cdm_cfg sdm845_cdm[] = { + { + .name = "cdm_0", .id = CDM_0, + .base = 0x79200, .len = 0x224, + .features = 0, + .intf_connect = BIT(INTF_3), + }, +}; + +/************************************************************* + * VBIF sub blocks config + *************************************************************/ +/* VBIF QOS remap */ +static u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6}; +static u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; + +static struct dpu_vbif_cfg sdm845_vbif[] = { + { + .name = "vbif_0", .id = VBIF_0, + .base = 0, .len = 0x1040, + .features = BIT(DPU_VBIF_QOS_REMAP), + .xin_halt_timeout = 0x4000, + .qos_rt_tbl = { + .npriority_lvl = ARRAY_SIZE(sdm845_rt_pri_lvl), + .priority_lvl = sdm845_rt_pri_lvl, + }, + .qos_nrt_tbl = { + .npriority_lvl = ARRAY_SIZE(sdm845_nrt_pri_lvl), + .priority_lvl = sdm845_nrt_pri_lvl, + }, + .memtype_count = 14, + .memtype = {3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3}, + }, +}; + +static struct dpu_reg_dma_cfg sdm845_regdma = { + .base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c +}; + +/************************************************************* + * PERF data config + *************************************************************/ + +/* SSPP QOS LUTs */ +static struct dpu_qos_lut_entry sdm845_qos_linear[] = { + {.fl = 4, .lut = 0x357}, + {.fl = 5, .lut = 0x3357}, + {.fl = 6, .lut = 0x23357}, + {.fl = 7, .lut = 0x223357}, + {.fl = 8, .lut = 0x2223357}, + {.fl = 9, .lut = 0x22223357}, + {.fl = 10, .lut = 0x222223357}, + {.fl = 11, .lut = 0x2222223357}, + {.fl = 12, .lut = 0x22222223357}, + {.fl = 13, .lut = 0x222222223357}, + {.fl = 14, .lut = 0x1222222223357}, + {.fl = 0, .lut = 0x11222222223357} +}; + +static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = { + {.fl = 10, .lut = 0x344556677}, + {.fl = 11, .lut = 0x3344556677}, + {.fl = 12, .lut = 0x23344556677}, + {.fl = 13, .lut = 0x223344556677}, + {.fl = 14, .lut = 0x1223344556677}, + {.fl = 0, .lut = 0x112233344556677}, +}; + +static struct dpu_qos_lut_entry sdm845_qos_nrt[] = { + {.fl = 0, .lut = 0x0}, +}; + +static struct dpu_perf_cfg sdm845_perf_data = { + .max_bw_low = 6800000, + .max_bw_high = 6800000, + .min_core_ib = 2400000, + .min_llcc_ib = 800000, + .min_dram_ib = 800000, + .core_ib_ff = "6.0", + .core_clk_ff = "1.0", + .comp_ratio_rt = + "NV12/5/1/1.23 AB24/5/1/1.23 XB24/5/1/1.23", + .comp_ratio_nrt = + "NV12/5/1/1.25 AB24/5/1/1.25 XB24/5/1/1.25", + .undersized_prefill_lines = 2, + .xtra_prefill_lines = 2, + .dest_scale_prefill_lines = 3, + .macrotile_prefill_lines = 4, + .yuv_nv12_prefill_lines = 8, + .linear_prefill_lines = 1, + .downscaling_prefill_lines = 1, + .amortizable_threshold = 25, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sdm845_qos_linear), + .entries = sdm845_qos_linear + }, + {.nentry = ARRAY_SIZE(sdm845_qos_macrotile), + .entries = sdm845_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sdm845_qos_nrt), + .entries = sdm845_qos_nrt + }, + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, +}; + +/************************************************************* + * Hardware catalog init + *************************************************************/ + +/* + * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets + * and instance counts. + */ +static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg) +{ + *dpu_cfg = (struct dpu_mdss_cfg){ + .caps = &sdm845_dpu_caps, + .mdp_count = ARRAY_SIZE(sdm845_mdp), + .mdp = sdm845_mdp, + .ctl_count = ARRAY_SIZE(sdm845_ctl), + .ctl = sdm845_ctl, + .sspp_count = ARRAY_SIZE(sdm845_sspp), + .sspp = sdm845_sspp, + .mixer_count = ARRAY_SIZE(sdm845_lm), + .mixer = sdm845_lm, + .ds_count = ARRAY_SIZE(sdm845_ds), + .ds = sdm845_ds, + .pingpong_count = ARRAY_SIZE(sdm845_pp), + .pingpong = sdm845_pp, + .cdm_count = ARRAY_SIZE(sdm845_cdm), + .cdm = sdm845_cdm, + .intf_count = ARRAY_SIZE(sdm845_intf), + .intf = sdm845_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .reg_dma_count = 1, + .dma_cfg = sdm845_regdma, + .perf = sdm845_perf_data, + }; +} + +static struct dpu_mdss_hw_cfg_handler cfg_handler[] = { + { .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init}, + { .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init}, +}; + +void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg) +{ + kfree(dpu_cfg); +} + +struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev) +{ + int i; + struct dpu_mdss_cfg *dpu_cfg; + + dpu_cfg = kzalloc(sizeof(*dpu_cfg), GFP_KERNEL); + if (!dpu_cfg) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) { + if (cfg_handler[i].hw_rev == hw_rev) { + cfg_handler[i].cfg_init(dpu_cfg); + dpu_cfg->hwversion = hw_rev; + return dpu_cfg; + } + } + + DPU_ERROR("unsupported chipset id:%X\n", hw_rev); + dpu_hw_catalog_deinit(dpu_cfg); + return ERR_PTR(-ENODEV); +} + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h new file mode 100644 index 000000000000..f0cb0d4fc80e --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -0,0 +1,804 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_CATALOG_H +#define _DPU_HW_CATALOG_H + +#include <linux/kernel.h> +#include <linux/bug.h> +#include <linux/bitmap.h> +#include <linux/err.h> +#include <drm/drmP.h> + +/** + * Max hardware block count: For ex: max 12 SSPP pipes or + * 5 ctl paths. In all cases, it can have max 12 hardware blocks + * based on current design + */ +#define MAX_BLOCKS 12 + +#define DPU_HW_VER(MAJOR, MINOR, STEP) (((MAJOR & 0xF) << 28) |\ + ((MINOR & 0xFFF) << 16) |\ + (STEP & 0xFFFF)) + +#define DPU_HW_MAJOR(rev) ((rev) >> 28) +#define DPU_HW_MINOR(rev) (((rev) >> 16) & 0xFFF) +#define DPU_HW_STEP(rev) ((rev) & 0xFFFF) +#define DPU_HW_MAJOR_MINOR(rev) ((rev) >> 16) + +#define IS_DPU_MAJOR_MINOR_SAME(rev1, rev2) \ + (DPU_HW_MAJOR_MINOR((rev1)) == DPU_HW_MAJOR_MINOR((rev2))) + +#define DPU_HW_VER_170 DPU_HW_VER(1, 7, 0) /* 8996 v1.0 */ +#define DPU_HW_VER_171 DPU_HW_VER(1, 7, 1) /* 8996 v2.0 */ +#define DPU_HW_VER_172 DPU_HW_VER(1, 7, 2) /* 8996 v3.0 */ +#define DPU_HW_VER_300 DPU_HW_VER(3, 0, 0) /* 8998 v1.0 */ +#define DPU_HW_VER_301 DPU_HW_VER(3, 0, 1) /* 8998 v1.1 */ +#define DPU_HW_VER_400 DPU_HW_VER(4, 0, 0) /* sdm845 v1.0 */ +#define DPU_HW_VER_401 DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */ +#define DPU_HW_VER_410 DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */ +#define DPU_HW_VER_500 DPU_HW_VER(5, 0, 0) /* sdm855 v1.0 */ + + +#define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170) +#define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300) +#define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400) +#define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410) +#define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500) + + +#define DPU_HW_BLK_NAME_LEN 16 + +#define MAX_IMG_WIDTH 0x3fff +#define MAX_IMG_HEIGHT 0x3fff + +#define CRTC_DUAL_MIXERS 2 + +#define MAX_XIN_COUNT 16 + +/** + * Supported UBWC feature versions + */ +enum { + DPU_HW_UBWC_VER_10 = 0x100, + DPU_HW_UBWC_VER_20 = 0x200, + DPU_HW_UBWC_VER_30 = 0x300, +}; + +#define IS_UBWC_20_SUPPORTED(rev) ((rev) >= DPU_HW_UBWC_VER_20) + +/** + * MDP TOP BLOCK features + * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be be done per pipe + * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats + * @DPU_MDP_BWC, MDSS HW supports Bandwidth compression. + * @DPU_MDP_UBWC_1_0, This chipsets supports Universal Bandwidth + * compression initial revision + * @DPU_MDP_UBWC_1_5, Universal Bandwidth compression version 1.5 + * @DPU_MDP_MAX Maximum value + + */ +enum { + DPU_MDP_PANIC_PER_PIPE = 0x1, + DPU_MDP_10BIT_SUPPORT, + DPU_MDP_BWC, + DPU_MDP_UBWC_1_0, + DPU_MDP_UBWC_1_5, + DPU_MDP_MAX +}; + +/** + * SSPP sub-blocks/features + * @DPU_SSPP_SRC Src and fetch part of the pipes, + * @DPU_SSPP_SCALER_QSEED2, QSEED2 algorithm support + * @DPU_SSPP_SCALER_QSEED3, QSEED3 alogorithm support + * @DPU_SSPP_SCALER_RGB, RGB Scaler, supported by RGB pipes + * @DPU_SSPP_CSC, Support of Color space converion + * @DPU_SSPP_CSC_10BIT, Support of 10-bit Color space conversion + * @DPU_SSPP_CURSOR, SSPP can be used as a cursor layer + * @DPU_SSPP_QOS, SSPP support QoS control, danger/safe/creq + * @DPU_SSPP_QOS_8LVL, SSPP support 8-level QoS control + * @DPU_SSPP_EXCL_RECT, SSPP supports exclusion rect + * @DPU_SSPP_SMART_DMA_V1, SmartDMA 1.0 support + * @DPU_SSPP_SMART_DMA_V2, SmartDMA 2.0 support + * @DPU_SSPP_TS_PREFILL Supports prefill with traffic shaper + * @DPU_SSPP_TS_PREFILL_REC1 Supports prefill with traffic shaper multirec + * @DPU_SSPP_CDP Supports client driven prefetch + * @DPU_SSPP_MAX maximum value + */ +enum { + DPU_SSPP_SRC = 0x1, + DPU_SSPP_SCALER_QSEED2, + DPU_SSPP_SCALER_QSEED3, + DPU_SSPP_SCALER_RGB, + DPU_SSPP_CSC, + DPU_SSPP_CSC_10BIT, + DPU_SSPP_CURSOR, + DPU_SSPP_QOS, + DPU_SSPP_QOS_8LVL, + DPU_SSPP_EXCL_RECT, + DPU_SSPP_SMART_DMA_V1, + DPU_SSPP_SMART_DMA_V2, + DPU_SSPP_TS_PREFILL, + DPU_SSPP_TS_PREFILL_REC1, + DPU_SSPP_CDP, + DPU_SSPP_MAX +}; + +/* + * MIXER sub-blocks/features + * @DPU_MIXER_LAYER Layer mixer layer blend configuration, + * @DPU_MIXER_SOURCESPLIT Layer mixer supports source-split configuration + * @DPU_MIXER_GC Gamma correction block + * @DPU_DIM_LAYER Layer mixer supports dim layer + * @DPU_MIXER_MAX maximum value + */ +enum { + DPU_MIXER_LAYER = 0x1, + DPU_MIXER_SOURCESPLIT, + DPU_MIXER_GC, + DPU_DIM_LAYER, + DPU_MIXER_MAX +}; + +/** + * PINGPONG sub-blocks + * @DPU_PINGPONG_TE Tear check block + * @DPU_PINGPONG_TE2 Additional tear check block for split pipes + * @DPU_PINGPONG_SPLIT PP block supports split fifo + * @DPU_PINGPONG_SLAVE PP block is a suitable slave for split fifo + * @DPU_PINGPONG_DITHER, Dither blocks + * @DPU_PINGPONG_MAX + */ +enum { + DPU_PINGPONG_TE = 0x1, + DPU_PINGPONG_TE2, + DPU_PINGPONG_SPLIT, + DPU_PINGPONG_SLAVE, + DPU_PINGPONG_DITHER, + DPU_PINGPONG_MAX +}; + +/** + * CTL sub-blocks + * @DPU_CTL_SPLIT_DISPLAY CTL supports video mode split display + * @DPU_CTL_MAX + */ +enum { + DPU_CTL_SPLIT_DISPLAY = 0x1, + DPU_CTL_MAX +}; + +/** + * VBIF sub-blocks and features + * @DPU_VBIF_QOS_OTLIM VBIF supports OT Limit + * @DPU_VBIF_QOS_REMAP VBIF supports QoS priority remap + * @DPU_VBIF_MAX maximum value + */ +enum { + DPU_VBIF_QOS_OTLIM = 0x1, + DPU_VBIF_QOS_REMAP, + DPU_VBIF_MAX +}; + +/** + * MACRO DPU_HW_BLK_INFO - information of HW blocks inside DPU + * @name: string name for debug purposes + * @id: enum identifying this block + * @base: register base offset to mdss + * @len: length of hardware block + * @features bit mask identifying sub-blocks/features + */ +#define DPU_HW_BLK_INFO \ + char name[DPU_HW_BLK_NAME_LEN]; \ + u32 id; \ + u32 base; \ + u32 len; \ + unsigned long features + +/** + * MACRO DPU_HW_SUBBLK_INFO - information of HW sub-block inside DPU + * @name: string name for debug purposes + * @id: enum identifying this sub-block + * @base: offset of this sub-block relative to the block + * offset + * @len register block length of this sub-block + */ +#define DPU_HW_SUBBLK_INFO \ + char name[DPU_HW_BLK_NAME_LEN]; \ + u32 id; \ + u32 base; \ + u32 len + +/** + * struct dpu_src_blk: SSPP part of the source pipes + * @info: HW register and features supported by this sub-blk + */ +struct dpu_src_blk { + DPU_HW_SUBBLK_INFO; +}; + +/** + * struct dpu_scaler_blk: Scaler information + * @info: HW register and features supported by this sub-blk + * @version: qseed block revision + */ +struct dpu_scaler_blk { + DPU_HW_SUBBLK_INFO; + u32 version; +}; + +struct dpu_csc_blk { + DPU_HW_SUBBLK_INFO; +}; + +/** + * struct dpu_pp_blk : Pixel processing sub-blk information + * @info: HW register and features supported by this sub-blk + * @version: HW Algorithm version + */ +struct dpu_pp_blk { + DPU_HW_SUBBLK_INFO; + u32 version; +}; + +/** + * struct dpu_format_extended - define dpu specific pixel format+modifier + * @fourcc_format: Base FOURCC pixel format code + * @modifier: 64-bit drm format modifier, same modifier must be applied to all + * framebuffer planes + */ +struct dpu_format_extended { + uint32_t fourcc_format; + uint64_t modifier; +}; + +/** + * enum dpu_qos_lut_usage - define QoS LUT use cases + */ +enum dpu_qos_lut_usage { + DPU_QOS_LUT_USAGE_LINEAR, + DPU_QOS_LUT_USAGE_MACROTILE, + DPU_QOS_LUT_USAGE_NRT, + DPU_QOS_LUT_USAGE_MAX, +}; + +/** + * struct dpu_qos_lut_entry - define QoS LUT table entry + * @fl: fill level, or zero on last entry to indicate default lut + * @lut: lut to use if equal to or less than fill level + */ +struct dpu_qos_lut_entry { + u32 fl; + u64 lut; +}; + +/** + * struct dpu_qos_lut_tbl - define QoS LUT table + * @nentry: number of entry in this table + * @entries: Pointer to table entries + */ +struct dpu_qos_lut_tbl { + u32 nentry; + struct dpu_qos_lut_entry *entries; +}; + +/** + * struct dpu_caps - define DPU capabilities + * @max_mixer_width max layer mixer line width support. + * @max_mixer_blendstages max layer mixer blend stages or + * supported z order + * @qseed_type qseed2 or qseed3 support. + * @smart_dma_rev Supported version of SmartDMA feature. + * @ubwc_version UBWC feature version (0x0 for not supported) + * @has_src_split source split feature status + * @has_dim_layer dim layer feature status + * @has_idle_pc indicate if idle power collapse feature is supported + */ +struct dpu_caps { + u32 max_mixer_width; + u32 max_mixer_blendstages; + u32 qseed_type; + u32 smart_dma_rev; + u32 ubwc_version; + bool has_src_split; + bool has_dim_layer; + bool has_idle_pc; +}; + +/** + * struct dpu_sspp_blks_common : SSPP sub-blocks common configuration + * @maxwidth: max pixelwidth supported by this pipe + * @pixel_ram_size: size of latency hiding and de-tiling buffer in bytes + * @maxhdeciexp: max horizontal decimation supported by this pipe + * (max is 2^value) + * @maxvdeciexp: max vertical decimation supported by this pipe + * (max is 2^value) + */ +struct dpu_sspp_blks_common { + u32 maxlinewidth; + u32 pixel_ram_size; + u32 maxhdeciexp; + u32 maxvdeciexp; +}; + +/** + * struct dpu_sspp_sub_blks : SSPP sub-blocks + * common: Pointer to common configurations shared by sub blocks + * @creq_vblank: creq priority during vertical blanking + * @danger_vblank: danger priority during vertical blanking + * @maxdwnscale: max downscale ratio supported(without DECIMATION) + * @maxupscale: maxupscale ratio supported + * @smart_dma_priority: hw priority of rect1 of multirect pipe + * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps + * @src_blk: + * @scaler_blk: + * @csc_blk: + * @hsic: + * @memcolor: + * @pcc_blk: + * @igc_blk: + * @format_list: Pointer to list of supported formats + * @virt_format_list: Pointer to list of supported formats for virtual planes + */ +struct dpu_sspp_sub_blks { + const struct dpu_sspp_blks_common *common; + u32 creq_vblank; + u32 danger_vblank; + u32 maxdwnscale; + u32 maxupscale; + u32 smart_dma_priority; + u32 max_per_pipe_bw; + struct dpu_src_blk src_blk; + struct dpu_scaler_blk scaler_blk; + struct dpu_pp_blk csc_blk; + struct dpu_pp_blk hsic_blk; + struct dpu_pp_blk memcolor_blk; + struct dpu_pp_blk pcc_blk; + struct dpu_pp_blk igc_blk; + + const struct dpu_format_extended *format_list; + const struct dpu_format_extended *virt_format_list; +}; + +/** + * struct dpu_lm_sub_blks: information of mixer block + * @maxwidth: Max pixel width supported by this mixer + * @maxblendstages: Max number of blend-stages supported + * @blendstage_base: Blend-stage register base offset + * @gc: gamma correction block + */ +struct dpu_lm_sub_blks { + u32 maxwidth; + u32 maxblendstages; + u32 blendstage_base[MAX_BLOCKS]; + struct dpu_pp_blk gc; +}; + +struct dpu_pingpong_sub_blks { + struct dpu_pp_blk te; + struct dpu_pp_blk te2; + struct dpu_pp_blk dither; +}; + +/** + * dpu_clk_ctrl_type - Defines top level clock control signals + */ +enum dpu_clk_ctrl_type { + DPU_CLK_CTRL_NONE, + DPU_CLK_CTRL_VIG0, + DPU_CLK_CTRL_VIG1, + DPU_CLK_CTRL_VIG2, + DPU_CLK_CTRL_VIG3, + DPU_CLK_CTRL_VIG4, + DPU_CLK_CTRL_RGB0, + DPU_CLK_CTRL_RGB1, + DPU_CLK_CTRL_RGB2, + DPU_CLK_CTRL_RGB3, + DPU_CLK_CTRL_DMA0, + DPU_CLK_CTRL_DMA1, + DPU_CLK_CTRL_CURSOR0, + DPU_CLK_CTRL_CURSOR1, + DPU_CLK_CTRL_INLINE_ROT0_SSPP, + DPU_CLK_CTRL_MAX, +}; + +/* struct dpu_clk_ctrl_reg : Clock control register + * @reg_off: register offset + * @bit_off: bit offset + */ +struct dpu_clk_ctrl_reg { + u32 reg_off; + u32 bit_off; +}; + +/* struct dpu_mdp_cfg : MDP TOP-BLK instance info + * @id: index identifying this block + * @base: register base offset to mdss + * @features bit mask identifying sub-blocks/features + * @highest_bank_bit: UBWC parameter + * @ubwc_static: ubwc static configuration + * @ubwc_swizzle: ubwc default swizzle setting + * @has_dest_scaler: indicates support of destination scaler + * @clk_ctrls clock control register definition + */ +struct dpu_mdp_cfg { + DPU_HW_BLK_INFO; + u32 highest_bank_bit; + u32 ubwc_static; + u32 ubwc_swizzle; + bool has_dest_scaler; + struct dpu_clk_ctrl_reg clk_ctrls[DPU_CLK_CTRL_MAX]; +}; + +/* struct dpu_mdp_cfg : MDP TOP-BLK instance info + * @id: index identifying this block + * @base: register base offset to mdss + * @features bit mask identifying sub-blocks/features + */ +struct dpu_ctl_cfg { + DPU_HW_BLK_INFO; +}; + +/** + * struct dpu_sspp_cfg - information of source pipes + * @id: index identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @sblk: SSPP sub-blocks information + * @xin_id: bus client identifier + * @clk_ctrl clock control identifier + * @type sspp type identifier + */ +struct dpu_sspp_cfg { + DPU_HW_BLK_INFO; + const struct dpu_sspp_sub_blks *sblk; + u32 xin_id; + enum dpu_clk_ctrl_type clk_ctrl; + u32 type; +}; + +/** + * struct dpu_lm_cfg - information of layer mixer blocks + * @id: index identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @sblk: LM Sub-blocks information + * @pingpong: ID of connected PingPong, PINGPONG_MAX if unsupported + * @ds: ID of connected DS, DS_MAX if unsupported + * @lm_pair_mask: Bitmask of LMs that can be controlled by same CTL + */ +struct dpu_lm_cfg { + DPU_HW_BLK_INFO; + const struct dpu_lm_sub_blks *sblk; + u32 pingpong; + u32 ds; + unsigned long lm_pair_mask; +}; + +/** + * struct dpu_ds_top_cfg - information of dest scaler top + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying features + * @version hw version of dest scaler + * @maxinputwidth maximum input line width + * @maxoutputwidth maximum output line width + * @maxupscale maximum upscale ratio + */ +struct dpu_ds_top_cfg { + DPU_HW_BLK_INFO; + u32 version; + u32 maxinputwidth; + u32 maxoutputwidth; + u32 maxupscale; +}; + +/** + * struct dpu_ds_cfg - information of dest scaler blocks + * @id enum identifying this block + * @base register offset wrt DS top offset + * @features bit mask identifying features + * @version hw version of the qseed block + * @top DS top information + */ +struct dpu_ds_cfg { + DPU_HW_BLK_INFO; + u32 version; + const struct dpu_ds_top_cfg *top; +}; + +/** + * struct dpu_pingpong_cfg - information of PING-PONG blocks + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @sblk sub-blocks information + */ +struct dpu_pingpong_cfg { + DPU_HW_BLK_INFO; + const struct dpu_pingpong_sub_blks *sblk; +}; + +/** + * struct dpu_cdm_cfg - information of chroma down blocks + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @intf_connect Bitmask of INTF IDs this CDM can connect to + */ +struct dpu_cdm_cfg { + DPU_HW_BLK_INFO; + unsigned long intf_connect; +}; + +/** + * struct dpu_intf_cfg - information of timing engine blocks + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @type: Interface type(DSI, DP, HDMI) + * @controller_id: Controller Instance ID in case of multiple of intf type + * @prog_fetch_lines_worst_case Worst case latency num lines needed to prefetch + */ +struct dpu_intf_cfg { + DPU_HW_BLK_INFO; + u32 type; /* interface type*/ + u32 controller_id; + u32 prog_fetch_lines_worst_case; +}; + +/** + * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting + * @pps pixel per seconds + * @ot_limit OT limit to use up to specified pixel per second + */ +struct dpu_vbif_dynamic_ot_cfg { + u64 pps; + u32 ot_limit; +}; + +/** + * struct dpu_vbif_dynamic_ot_tbl - dynamic OT setting table + * @count length of cfg + * @cfg pointer to array of configuration settings with + * ascending requirements + */ +struct dpu_vbif_dynamic_ot_tbl { + u32 count; + struct dpu_vbif_dynamic_ot_cfg *cfg; +}; + +/** + * struct dpu_vbif_qos_tbl - QoS priority table + * @npriority_lvl num of priority level + * @priority_lvl pointer to array of priority level in ascending order + */ +struct dpu_vbif_qos_tbl { + u32 npriority_lvl; + u32 *priority_lvl; +}; + +/** + * struct dpu_vbif_cfg - information of VBIF blocks + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @ot_rd_limit default OT read limit + * @ot_wr_limit default OT write limit + * @xin_halt_timeout maximum time (in usec) for xin to halt + * @dynamic_ot_rd_tbl dynamic OT read configuration table + * @dynamic_ot_wr_tbl dynamic OT write configuration table + * @qos_rt_tbl real-time QoS priority table + * @qos_nrt_tbl non-real-time QoS priority table + * @memtype_count number of defined memtypes + * @memtype array of xin memtype definitions + */ +struct dpu_vbif_cfg { + DPU_HW_BLK_INFO; + u32 default_ot_rd_limit; + u32 default_ot_wr_limit; + u32 xin_halt_timeout; + struct dpu_vbif_dynamic_ot_tbl dynamic_ot_rd_tbl; + struct dpu_vbif_dynamic_ot_tbl dynamic_ot_wr_tbl; + struct dpu_vbif_qos_tbl qos_rt_tbl; + struct dpu_vbif_qos_tbl qos_nrt_tbl; + u32 memtype_count; + u32 memtype[MAX_XIN_COUNT]; +}; +/** + * struct dpu_reg_dma_cfg - information of lut dma blocks + * @id enum identifying this block + * @base register offset of this block + * @features bit mask identifying sub-blocks/features + * @version version of lutdma hw block + * @trigger_sel_off offset to trigger select registers of lutdma + */ +struct dpu_reg_dma_cfg { + DPU_HW_BLK_INFO; + u32 version; + u32 trigger_sel_off; +}; + +/** + * Define CDP use cases + * @DPU_PERF_CDP_UDAGE_RT: real-time use cases + * @DPU_PERF_CDP_USAGE_NRT: non real-time use cases such as WFD + */ +enum { + DPU_PERF_CDP_USAGE_RT, + DPU_PERF_CDP_USAGE_NRT, + DPU_PERF_CDP_USAGE_MAX +}; + +/** + * struct dpu_perf_cdp_cfg - define CDP use case configuration + * @rd_enable: true if read pipe CDP is enabled + * @wr_enable: true if write pipe CDP is enabled + */ +struct dpu_perf_cdp_cfg { + bool rd_enable; + bool wr_enable; +}; + +/** + * struct dpu_perf_cfg - performance control settings + * @max_bw_low low threshold of maximum bandwidth (kbps) + * @max_bw_high high threshold of maximum bandwidth (kbps) + * @min_core_ib minimum bandwidth for core (kbps) + * @min_core_ib minimum mnoc ib vote in kbps + * @min_llcc_ib minimum llcc ib vote in kbps + * @min_dram_ib minimum dram ib vote in kbps + * @core_ib_ff core instantaneous bandwidth fudge factor + * @core_clk_ff core clock fudge factor + * @comp_ratio_rt string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio> + * @comp_ratio_nrt string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio> + * @undersized_prefill_lines undersized prefill in lines + * @xtra_prefill_lines extra prefill latency in lines + * @dest_scale_prefill_lines destination scaler latency in lines + * @macrotile_perfill_lines macrotile latency in lines + * @yuv_nv12_prefill_lines yuv_nv12 latency in lines + * @linear_prefill_lines linear latency in lines + * @downscaling_prefill_lines downscaling latency in lines + * @amortizable_theshold minimum y position for traffic shaping prefill + * @min_prefill_lines minimum pipeline latency in lines + * @safe_lut_tbl: LUT tables for safe signals + * @danger_lut_tbl: LUT tables for danger signals + * @qos_lut_tbl: LUT tables for QoS signals + * @cdp_cfg cdp use case configurations + */ +struct dpu_perf_cfg { + u32 max_bw_low; + u32 max_bw_high; + u32 min_core_ib; + u32 min_llcc_ib; + u32 min_dram_ib; + const char *core_ib_ff; + const char *core_clk_ff; + const char *comp_ratio_rt; + const char *comp_ratio_nrt; + u32 undersized_prefill_lines; + u32 xtra_prefill_lines; + u32 dest_scale_prefill_lines; + u32 macrotile_prefill_lines; + u32 yuv_nv12_prefill_lines; + u32 linear_prefill_lines; + u32 downscaling_prefill_lines; + u32 amortizable_threshold; + u32 min_prefill_lines; + u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; + u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; + struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX]; + struct dpu_perf_cdp_cfg cdp_cfg[DPU_PERF_CDP_USAGE_MAX]; +}; + +/** + * struct dpu_mdss_cfg - information of MDSS HW + * This is the main catalog data structure representing + * this HW version. Contains number of instances, + * register offsets, capabilities of the all MDSS HW sub-blocks. + * + * @dma_formats Supported formats for dma pipe + * @cursor_formats Supported formats for cursor pipe + * @vig_formats Supported formats for vig pipe + */ +struct dpu_mdss_cfg { + u32 hwversion; + + const struct dpu_caps *caps; + + u32 mdp_count; + struct dpu_mdp_cfg *mdp; + + u32 ctl_count; + struct dpu_ctl_cfg *ctl; + + u32 sspp_count; + struct dpu_sspp_cfg *sspp; + + u32 mixer_count; + struct dpu_lm_cfg *mixer; + + u32 ds_count; + struct dpu_ds_cfg *ds; + + u32 pingpong_count; + struct dpu_pingpong_cfg *pingpong; + + u32 cdm_count; + struct dpu_cdm_cfg *cdm; + + u32 intf_count; + struct dpu_intf_cfg *intf; + + u32 vbif_count; + struct dpu_vbif_cfg *vbif; + + u32 reg_dma_count; + struct dpu_reg_dma_cfg dma_cfg; + + u32 ad_count; + + /* Add additional block data structures here */ + + struct dpu_perf_cfg perf; + struct dpu_format_extended *dma_formats; + struct dpu_format_extended *cursor_formats; + struct dpu_format_extended *vig_formats; +}; + +struct dpu_mdss_hw_cfg_handler { + u32 hw_rev; + void (*cfg_init)(struct dpu_mdss_cfg *dpu_cfg); +}; + +/* + * Access Macros + */ +#define BLK_MDP(s) ((s)->mdp) +#define BLK_CTL(s) ((s)->ctl) +#define BLK_VIG(s) ((s)->vig) +#define BLK_RGB(s) ((s)->rgb) +#define BLK_DMA(s) ((s)->dma) +#define BLK_CURSOR(s) ((s)->cursor) +#define BLK_MIXER(s) ((s)->mixer) +#define BLK_DS(s) ((s)->ds) +#define BLK_PINGPONG(s) ((s)->pingpong) +#define BLK_CDM(s) ((s)->cdm) +#define BLK_INTF(s) ((s)->intf) +#define BLK_AD(s) ((s)->ad) + +/** + * dpu_hw_catalog_init - dpu hardware catalog init API retrieves + * hardcoded target specific catalog information in config structure + * @hw_rev: caller needs provide the hardware revision. + * + * Return: dpu config structure + */ +struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev); + +/** + * dpu_hw_catalog_deinit - dpu hardware catalog cleanup + * @dpu_cfg: pointer returned from init function + */ +void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg); + +/** + * dpu_hw_sspp_multirect_enabled - check multirect enabled for the sspp + * @cfg: pointer to sspp cfg + */ +static inline bool dpu_hw_sspp_multirect_enabled(const struct dpu_sspp_cfg *cfg) +{ + return test_bit(DPU_SSPP_SMART_DMA_V1, &cfg->features) || + test_bit(DPU_SSPP_SMART_DMA_V2, &cfg->features); +} +#endif /* _DPU_HW_CATALOG_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h new file mode 100644 index 000000000000..3c9f028628ef --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h @@ -0,0 +1,168 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hw_mdss.h" + +static const struct dpu_format_extended plane_formats[] = { + {DRM_FORMAT_ARGB8888, 0}, + {DRM_FORMAT_ABGR8888, 0}, + {DRM_FORMAT_RGBA8888, 0}, + {DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_BGRA8888, 0}, + {DRM_FORMAT_XRGB8888, 0}, + {DRM_FORMAT_RGBX8888, 0}, + {DRM_FORMAT_BGRX8888, 0}, + {DRM_FORMAT_XBGR8888, 0}, + {DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_RGB888, 0}, + {DRM_FORMAT_BGR888, 0}, + {DRM_FORMAT_RGB565, 0}, + {DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_BGR565, 0}, + {DRM_FORMAT_ARGB1555, 0}, + {DRM_FORMAT_ABGR1555, 0}, + {DRM_FORMAT_RGBA5551, 0}, + {DRM_FORMAT_BGRA5551, 0}, + {DRM_FORMAT_XRGB1555, 0}, + {DRM_FORMAT_XBGR1555, 0}, + {DRM_FORMAT_RGBX5551, 0}, + {DRM_FORMAT_BGRX5551, 0}, + {DRM_FORMAT_ARGB4444, 0}, + {DRM_FORMAT_ABGR4444, 0}, + {DRM_FORMAT_RGBA4444, 0}, + {DRM_FORMAT_BGRA4444, 0}, + {DRM_FORMAT_XRGB4444, 0}, + {DRM_FORMAT_XBGR4444, 0}, + {DRM_FORMAT_RGBX4444, 0}, + {DRM_FORMAT_BGRX4444, 0}, + {0, 0}, +}; + +static const struct dpu_format_extended plane_formats_yuv[] = { + {DRM_FORMAT_ARGB8888, 0}, + {DRM_FORMAT_ABGR8888, 0}, + {DRM_FORMAT_RGBA8888, 0}, + {DRM_FORMAT_BGRX8888, 0}, + {DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_BGRA8888, 0}, + {DRM_FORMAT_XRGB8888, 0}, + {DRM_FORMAT_XBGR8888, 0}, + {DRM_FORMAT_RGBX8888, 0}, + {DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_RGB888, 0}, + {DRM_FORMAT_BGR888, 0}, + {DRM_FORMAT_RGB565, 0}, + {DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_BGR565, 0}, + {DRM_FORMAT_ARGB1555, 0}, + {DRM_FORMAT_ABGR1555, 0}, + {DRM_FORMAT_RGBA5551, 0}, + {DRM_FORMAT_BGRA5551, 0}, + {DRM_FORMAT_XRGB1555, 0}, + {DRM_FORMAT_XBGR1555, 0}, + {DRM_FORMAT_RGBX5551, 0}, + {DRM_FORMAT_BGRX5551, 0}, + {DRM_FORMAT_ARGB4444, 0}, + {DRM_FORMAT_ABGR4444, 0}, + {DRM_FORMAT_RGBA4444, 0}, + {DRM_FORMAT_BGRA4444, 0}, + {DRM_FORMAT_XRGB4444, 0}, + {DRM_FORMAT_XBGR4444, 0}, + {DRM_FORMAT_RGBX4444, 0}, + {DRM_FORMAT_BGRX4444, 0}, + + {DRM_FORMAT_NV12, 0}, + {DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_NV21, 0}, + {DRM_FORMAT_NV16, 0}, + {DRM_FORMAT_NV61, 0}, + {DRM_FORMAT_VYUY, 0}, + {DRM_FORMAT_UYVY, 0}, + {DRM_FORMAT_YUYV, 0}, + {DRM_FORMAT_YVYU, 0}, + {DRM_FORMAT_YUV420, 0}, + {DRM_FORMAT_YVU420, 0}, + {0, 0}, +}; + +static const struct dpu_format_extended cursor_formats[] = { + {DRM_FORMAT_ARGB8888, 0}, + {DRM_FORMAT_ABGR8888, 0}, + {DRM_FORMAT_RGBA8888, 0}, + {DRM_FORMAT_BGRA8888, 0}, + {DRM_FORMAT_XRGB8888, 0}, + {DRM_FORMAT_ARGB1555, 0}, + {DRM_FORMAT_ABGR1555, 0}, + {DRM_FORMAT_RGBA5551, 0}, + {DRM_FORMAT_BGRA5551, 0}, + {DRM_FORMAT_ARGB4444, 0}, + {DRM_FORMAT_ABGR4444, 0}, + {DRM_FORMAT_RGBA4444, 0}, + {DRM_FORMAT_BGRA4444, 0}, + {0, 0}, +}; + +static const struct dpu_format_extended wb2_formats[] = { + {DRM_FORMAT_RGB565, 0}, + {DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_RGB888, 0}, + {DRM_FORMAT_ARGB8888, 0}, + {DRM_FORMAT_RGBA8888, 0}, + {DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_XRGB8888, 0}, + {DRM_FORMAT_RGBX8888, 0}, + {DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_ARGB1555, 0}, + {DRM_FORMAT_RGBA5551, 0}, + {DRM_FORMAT_XRGB1555, 0}, + {DRM_FORMAT_RGBX5551, 0}, + {DRM_FORMAT_ARGB4444, 0}, + {DRM_FORMAT_RGBA4444, 0}, + {DRM_FORMAT_RGBX4444, 0}, + {DRM_FORMAT_XRGB4444, 0}, + + {DRM_FORMAT_BGR565, 0}, + {DRM_FORMAT_BGR888, 0}, + {DRM_FORMAT_ABGR8888, 0}, + {DRM_FORMAT_BGRA8888, 0}, + {DRM_FORMAT_BGRX8888, 0}, + {DRM_FORMAT_XBGR8888, 0}, + {DRM_FORMAT_ABGR1555, 0}, + {DRM_FORMAT_BGRA5551, 0}, + {DRM_FORMAT_XBGR1555, 0}, + {DRM_FORMAT_BGRX5551, 0}, + {DRM_FORMAT_ABGR4444, 0}, + {DRM_FORMAT_BGRA4444, 0}, + {DRM_FORMAT_BGRX4444, 0}, + {DRM_FORMAT_XBGR4444, 0}, + + {DRM_FORMAT_YUV420, 0}, + {DRM_FORMAT_NV12, 0}, + {DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_NV16, 0}, + {DRM_FORMAT_YUYV, 0}, + + {0, 0}, +}; + +static const struct dpu_format_extended rgb_10bit_formats[] = { + {DRM_FORMAT_BGRA1010102, 0}, + {DRM_FORMAT_BGRX1010102, 0}, + {DRM_FORMAT_RGBA1010102, 0}, + {DRM_FORMAT_RGBX1010102, 0}, + {DRM_FORMAT_ABGR2101010, 0}, + {DRM_FORMAT_ABGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_XBGR2101010, 0}, + {DRM_FORMAT_XBGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED}, + {DRM_FORMAT_ARGB2101010, 0}, + {DRM_FORMAT_XRGB2101010, 0}, +}; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c new file mode 100644 index 000000000000..554874ba0c3b --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c @@ -0,0 +1,323 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hw_mdss.h" +#include "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_cdm.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define CDM_CSC_10_OPMODE 0x000 +#define CDM_CSC_10_BASE 0x004 + +#define CDM_CDWN2_OP_MODE 0x100 +#define CDM_CDWN2_CLAMP_OUT 0x104 +#define CDM_CDWN2_PARAMS_3D_0 0x108 +#define CDM_CDWN2_PARAMS_3D_1 0x10C +#define CDM_CDWN2_COEFF_COSITE_H_0 0x110 +#define CDM_CDWN2_COEFF_COSITE_H_1 0x114 +#define CDM_CDWN2_COEFF_COSITE_H_2 0x118 +#define CDM_CDWN2_COEFF_OFFSITE_H_0 0x11C +#define CDM_CDWN2_COEFF_OFFSITE_H_1 0x120 +#define CDM_CDWN2_COEFF_OFFSITE_H_2 0x124 +#define CDM_CDWN2_COEFF_COSITE_V 0x128 +#define CDM_CDWN2_COEFF_OFFSITE_V 0x12C +#define CDM_CDWN2_OUT_SIZE 0x130 + +#define CDM_HDMI_PACK_OP_MODE 0x200 +#define CDM_CSC_10_MATRIX_COEFF_0 0x004 + +/** + * Horizontal coefficients for cosite chroma downscale + * s13 representation of coefficients + */ +static u32 cosite_h_coeff[] = {0x00000016, 0x000001cc, 0x0100009e}; + +/** + * Horizontal coefficients for offsite chroma downscale + */ +static u32 offsite_h_coeff[] = {0x000b0005, 0x01db01eb, 0x00e40046}; + +/** + * Vertical coefficients for cosite chroma downscale + */ +static u32 cosite_v_coeff[] = {0x00080004}; +/** + * Vertical coefficients for offsite chroma downscale + */ +static u32 offsite_v_coeff[] = {0x00060002}; + +/* Limited Range rgb2yuv coeff with clamp and bias values for CSC 10 module */ +static struct dpu_csc_cfg rgb2yuv_cfg = { + { + 0x0083, 0x0102, 0x0032, + 0x1fb5, 0x1f6c, 0x00e1, + 0x00e1, 0x1f45, 0x1fdc + }, + { 0x00, 0x00, 0x00 }, + { 0x0040, 0x0200, 0x0200 }, + { 0x000, 0x3ff, 0x000, 0x3ff, 0x000, 0x3ff }, + { 0x040, 0x3ac, 0x040, 0x3c0, 0x040, 0x3c0 }, +}; + +static struct dpu_cdm_cfg *_cdm_offset(enum dpu_cdm cdm, + struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->cdm_count; i++) { + if (cdm == m->cdm[i].id) { + b->base_off = addr; + b->blk_off = m->cdm[i].base; + b->length = m->cdm[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_CDM; + return &m->cdm[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +static int dpu_hw_cdm_setup_csc_10bit(struct dpu_hw_cdm *ctx, + struct dpu_csc_cfg *data) +{ + dpu_hw_csc_setup(&ctx->hw, CDM_CSC_10_MATRIX_COEFF_0, data, true); + + return 0; +} + +static int dpu_hw_cdm_setup_cdwn(struct dpu_hw_cdm *ctx, + struct dpu_hw_cdm_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 opmode = 0; + u32 out_size = 0; + + if (cfg->output_bit_depth == CDM_CDWN_OUTPUT_10BIT) + opmode &= ~BIT(7); + else + opmode |= BIT(7); + + /* ENABLE DWNS_H bit */ + opmode |= BIT(1); + + switch (cfg->h_cdwn_type) { + case CDM_CDWN_DISABLE: + /* CLEAR METHOD_H field */ + opmode &= ~(0x18); + /* CLEAR DWNS_H bit */ + opmode &= ~BIT(1); + break; + case CDM_CDWN_PIXEL_DROP: + /* Clear METHOD_H field (pixel drop is 0) */ + opmode &= ~(0x18); + break; + case CDM_CDWN_AVG: + /* Clear METHOD_H field (Average is 0x1) */ + opmode &= ~(0x18); + opmode |= (0x1 << 0x3); + break; + case CDM_CDWN_COSITE: + /* Clear METHOD_H field (Average is 0x2) */ + opmode &= ~(0x18); + opmode |= (0x2 << 0x3); + /* Co-site horizontal coefficients */ + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_0, + cosite_h_coeff[0]); + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_1, + cosite_h_coeff[1]); + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_2, + cosite_h_coeff[2]); + break; + case CDM_CDWN_OFFSITE: + /* Clear METHOD_H field (Average is 0x3) */ + opmode &= ~(0x18); + opmode |= (0x3 << 0x3); + + /* Off-site horizontal coefficients */ + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_0, + offsite_h_coeff[0]); + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_1, + offsite_h_coeff[1]); + DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_2, + offsite_h_coeff[2]); + break; + default: + pr_err("%s invalid horz down sampling type\n", __func__); + return -EINVAL; + } + + /* ENABLE DWNS_V bit */ + opmode |= BIT(2); + + switch (cfg->v_cdwn_type) { + case CDM_CDWN_DISABLE: + /* CLEAR METHOD_V field */ + opmode &= ~(0x60); + /* CLEAR DWNS_V bit */ + opmode &= ~BIT(2); + break; + case CDM_CDWN_PIXEL_DROP: + /* Clear METHOD_V field (pixel drop is 0) */ + opmode &= ~(0x60); + break; + case CDM_CDWN_AVG: + /* Clear METHOD_V field (Average is 0x1) */ + opmode &= ~(0x60); + opmode |= (0x1 << 0x5); + break; + case CDM_CDWN_COSITE: + /* Clear METHOD_V field (Average is 0x2) */ + opmode &= ~(0x60); + opmode |= (0x2 << 0x5); + /* Co-site vertical coefficients */ + DPU_REG_WRITE(c, + CDM_CDWN2_COEFF_COSITE_V, + cosite_v_coeff[0]); + break; + case CDM_CDWN_OFFSITE: + /* Clear METHOD_V field (Average is 0x3) */ + opmode &= ~(0x60); + opmode |= (0x3 << 0x5); + + /* Off-site vertical coefficients */ + DPU_REG_WRITE(c, + CDM_CDWN2_COEFF_OFFSITE_V, + offsite_v_coeff[0]); + break; + default: + return -EINVAL; + } + + if (cfg->v_cdwn_type || cfg->h_cdwn_type) + opmode |= BIT(0); /* EN CDWN module */ + else + opmode &= ~BIT(0); + + out_size = (cfg->output_width & 0xFFFF) | + ((cfg->output_height & 0xFFFF) << 16); + DPU_REG_WRITE(c, CDM_CDWN2_OUT_SIZE, out_size); + DPU_REG_WRITE(c, CDM_CDWN2_OP_MODE, opmode); + DPU_REG_WRITE(c, CDM_CDWN2_CLAMP_OUT, + ((0x3FF << 16) | 0x0)); + + return 0; +} + +static int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx, + struct dpu_hw_cdm_cfg *cdm) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + const struct dpu_format *fmt = cdm->output_fmt; + struct cdm_output_cfg cdm_cfg = { 0 }; + u32 opmode = 0; + u32 csc = 0; + + if (!DPU_FORMAT_IS_YUV(fmt)) + return -EINVAL; + + if (cdm->output_type == CDM_CDWN_OUTPUT_HDMI) { + if (fmt->chroma_sample != DPU_CHROMA_H1V2) + return -EINVAL; /*unsupported format */ + opmode = BIT(0); + opmode |= (fmt->chroma_sample << 1); + cdm_cfg.intf_en = true; + } + + csc |= BIT(2); + csc &= ~BIT(1); + csc |= BIT(0); + + if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output) + ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg); + + DPU_REG_WRITE(c, CDM_CSC_10_OPMODE, csc); + DPU_REG_WRITE(c, CDM_HDMI_PACK_OP_MODE, opmode); + return 0; +} + +static void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx) +{ + struct cdm_output_cfg cdm_cfg = { 0 }; + + if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output) + ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg); +} + +static void _setup_cdm_ops(struct dpu_hw_cdm_ops *ops, + unsigned long features) +{ + ops->setup_csc_data = dpu_hw_cdm_setup_csc_10bit; + ops->setup_cdwn = dpu_hw_cdm_setup_cdwn; + ops->enable = dpu_hw_cdm_enable; + ops->disable = dpu_hw_cdm_disable; +} + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx, + void __iomem *addr, + struct dpu_mdss_cfg *m, + struct dpu_hw_mdp *hw_mdp) +{ + struct dpu_hw_cdm *c; + struct dpu_cdm_cfg *cfg; + int rc; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _cdm_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + return ERR_PTR(-EINVAL); + } + + c->idx = idx; + c->caps = cfg; + _setup_cdm_ops(&c->ops, c->caps->features); + c->hw_mdp = hw_mdp; + + rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CDM, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + /* + * Perform any default initialization for the chroma down module + * @setup default csc coefficients + */ + dpu_hw_cdm_setup_csc_10bit(c, &rgb2yuv_cfg); + + return c; + +blk_init_error: + kzfree(c); + + return ERR_PTR(rc); +} + +void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm) +{ + if (cdm) + dpu_hw_blk_destroy(&cdm->base); + kfree(cdm); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h new file mode 100644 index 000000000000..5cceb1ecb8e0 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h @@ -0,0 +1,139 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_CDM_H +#define _DPU_HW_CDM_H + +#include "dpu_hw_mdss.h" +#include "dpu_hw_top.h" +#include "dpu_hw_blk.h" + +struct dpu_hw_cdm; + +struct dpu_hw_cdm_cfg { + u32 output_width; + u32 output_height; + u32 output_bit_depth; + u32 h_cdwn_type; + u32 v_cdwn_type; + const struct dpu_format *output_fmt; + u32 output_type; + int flags; +}; + +enum dpu_hw_cdwn_type { + CDM_CDWN_DISABLE, + CDM_CDWN_PIXEL_DROP, + CDM_CDWN_AVG, + CDM_CDWN_COSITE, + CDM_CDWN_OFFSITE, +}; + +enum dpu_hw_cdwn_output_type { + CDM_CDWN_OUTPUT_HDMI, + CDM_CDWN_OUTPUT_WB, +}; + +enum dpu_hw_cdwn_output_bit_depth { + CDM_CDWN_OUTPUT_8BIT, + CDM_CDWN_OUTPUT_10BIT, +}; + +/** + * struct dpu_hw_cdm_ops : Interface to the chroma down Hw driver functions + * Assumption is these functions will be called after + * clocks are enabled + * @setup_csc: Programs the csc matrix + * @setup_cdwn: Sets up the chroma down sub module + * @enable: Enables the output to interface and programs the + * output packer + * @disable: Puts the cdm in bypass mode + */ +struct dpu_hw_cdm_ops { + /** + * Programs the CSC matrix for conversion from RGB space to YUV space, + * it is optional to call this function as this matrix is automatically + * set during initialization, user should call this if it wants + * to program a different matrix than default matrix. + * @cdm: Pointer to the chroma down context structure + * @data Pointer to CSC configuration data + * return: 0 if success; error code otherwise + */ + int (*setup_csc_data)(struct dpu_hw_cdm *cdm, + struct dpu_csc_cfg *data); + + /** + * Programs the Chroma downsample part. + * @cdm Pointer to chroma down context + */ + int (*setup_cdwn)(struct dpu_hw_cdm *cdm, + struct dpu_hw_cdm_cfg *cfg); + + /** + * Enable the CDM module + * @cdm Pointer to chroma down context + */ + int (*enable)(struct dpu_hw_cdm *cdm, + struct dpu_hw_cdm_cfg *cfg); + + /** + * Disable the CDM module + * @cdm Pointer to chroma down context + */ + void (*disable)(struct dpu_hw_cdm *cdm); +}; + +struct dpu_hw_cdm { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* chroma down */ + const struct dpu_cdm_cfg *caps; + enum dpu_cdm idx; + + /* mdp top hw driver */ + struct dpu_hw_mdp *hw_mdp; + + /* ops */ + struct dpu_hw_cdm_ops ops; +}; + +/** + * dpu_hw_cdm - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_cdm *to_dpu_hw_cdm(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_cdm, base); +} + +/** + * dpu_hw_cdm_init - initializes the cdm hw driver object. + * should be called once before accessing every cdm. + * @idx: cdm index for which driver object is required + * @addr: mapped register io address of MDP + * @m : pointer to mdss catalog data + * @hw_mdp: pointer to mdp top hw driver object + */ +struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx, + void __iomem *addr, + struct dpu_mdss_cfg *m, + struct dpu_hw_mdp *hw_mdp); + +/** + * dpu_hw_cdm_destroy - destroys CDM driver context + * @cdm: pointer to CDM driver context + */ +void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm); + +#endif /*_DPU_HW_CDM_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c new file mode 100644 index 000000000000..06be7cf7ce50 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -0,0 +1,540 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/delay.h> +#include "dpu_hwio.h" +#include "dpu_hw_ctl.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define CTL_LAYER(lm) \ + (((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004)) +#define CTL_LAYER_EXT(lm) \ + (0x40 + (((lm) - LM_0) * 0x004)) +#define CTL_LAYER_EXT2(lm) \ + (0x70 + (((lm) - LM_0) * 0x004)) +#define CTL_LAYER_EXT3(lm) \ + (0xA0 + (((lm) - LM_0) * 0x004)) +#define CTL_TOP 0x014 +#define CTL_FLUSH 0x018 +#define CTL_START 0x01C +#define CTL_PREPARE 0x0d0 +#define CTL_SW_RESET 0x030 +#define CTL_LAYER_EXTN_OFFSET 0x40 + +#define CTL_MIXER_BORDER_OUT BIT(24) +#define CTL_FLUSH_MASK_CTL BIT(17) + +#define DPU_REG_RESET_TIMEOUT_US 2000 + +static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl, + struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->ctl_count; i++) { + if (ctl == m->ctl[i].id) { + b->base_off = addr; + b->blk_off = m->ctl[i].base; + b->length = m->ctl[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_CTL; + return &m->ctl[i]; + } + } + return ERR_PTR(-ENOMEM); +} + +static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count, + enum dpu_lm lm) +{ + int i; + int stages = -EINVAL; + + for (i = 0; i < count; i++) { + if (lm == mixer[i].id) { + stages = mixer[i].sblk->maxblendstages; + break; + } + } + + return stages; +} + +static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx) +{ + DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1); +} + +static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx) +{ + DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1); +} + +static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx) +{ + ctx->pending_flush_mask = 0x0; +} + +static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx, + u32 flushbits) +{ + ctx->pending_flush_mask |= flushbits; +} + +static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx) +{ + if (!ctx) + return 0x0; + + return ctx->pending_flush_mask; +} + +static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx) +{ + + DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask); +} + +static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + + return DPU_REG_READ(c, CTL_FLUSH); +} + +static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx, + enum dpu_sspp sspp) +{ + uint32_t flushbits = 0; + + switch (sspp) { + case SSPP_VIG0: + flushbits = BIT(0); + break; + case SSPP_VIG1: + flushbits = BIT(1); + break; + case SSPP_VIG2: + flushbits = BIT(2); + break; + case SSPP_VIG3: + flushbits = BIT(18); + break; + case SSPP_RGB0: + flushbits = BIT(3); + break; + case SSPP_RGB1: + flushbits = BIT(4); + break; + case SSPP_RGB2: + flushbits = BIT(5); + break; + case SSPP_RGB3: + flushbits = BIT(19); + break; + case SSPP_DMA0: + flushbits = BIT(11); + break; + case SSPP_DMA1: + flushbits = BIT(12); + break; + case SSPP_DMA2: + flushbits = BIT(24); + break; + case SSPP_DMA3: + flushbits = BIT(25); + break; + case SSPP_CURSOR0: + flushbits = BIT(22); + break; + case SSPP_CURSOR1: + flushbits = BIT(23); + break; + default: + break; + } + + return flushbits; +} + +static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx, + enum dpu_lm lm) +{ + uint32_t flushbits = 0; + + switch (lm) { + case LM_0: + flushbits = BIT(6); + break; + case LM_1: + flushbits = BIT(7); + break; + case LM_2: + flushbits = BIT(8); + break; + case LM_3: + flushbits = BIT(9); + break; + case LM_4: + flushbits = BIT(10); + break; + case LM_5: + flushbits = BIT(20); + break; + default: + return -EINVAL; + } + + flushbits |= CTL_FLUSH_MASK_CTL; + + return flushbits; +} + +static inline int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx, + u32 *flushbits, enum dpu_intf intf) +{ + switch (intf) { + case INTF_0: + *flushbits |= BIT(31); + break; + case INTF_1: + *flushbits |= BIT(30); + break; + case INTF_2: + *flushbits |= BIT(29); + break; + case INTF_3: + *flushbits |= BIT(28); + break; + default: + return -EINVAL; + } + return 0; +} + +static inline int dpu_hw_ctl_get_bitmask_cdm(struct dpu_hw_ctl *ctx, + u32 *flushbits, enum dpu_cdm cdm) +{ + switch (cdm) { + case CDM_0: + *flushbits |= BIT(26); + break; + default: + return -EINVAL; + } + return 0; +} + +static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + ktime_t timeout; + u32 status; + + timeout = ktime_add_us(ktime_get(), timeout_us); + + /* + * it takes around 30us to have mdp finish resetting its ctl path + * poll every 50us so that reset should be completed at 1st poll + */ + do { + status = DPU_REG_READ(c, CTL_SW_RESET); + status &= 0x1; + if (status) + usleep_range(20, 50); + } while (status && ktime_compare_safe(ktime_get(), timeout) < 0); + + return status; +} + +static int dpu_hw_ctl_reset_control(struct dpu_hw_ctl *ctx) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + + pr_debug("issuing hw ctl reset for ctl:%d\n", ctx->idx); + DPU_REG_WRITE(c, CTL_SW_RESET, 0x1); + if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) + return -EINVAL; + + return 0; +} + +static int dpu_hw_ctl_wait_reset_status(struct dpu_hw_ctl *ctx) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 status; + + status = DPU_REG_READ(c, CTL_SW_RESET); + status &= 0x01; + if (!status) + return 0; + + pr_debug("hw ctl reset is set for ctl:%d\n", ctx->idx); + if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) { + pr_err("hw recovery is not complete for ctl:%d\n", ctx->idx); + return -EINVAL; + } + + return 0; +} + +static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int i; + + for (i = 0; i < ctx->mixer_count; i++) { + DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0); + DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0); + DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0); + DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0); + } +} + +static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx, + enum dpu_lm lm, struct dpu_hw_stage_cfg *stage_cfg) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 mixercfg = 0, mixercfg_ext = 0, mix, ext; + u32 mixercfg_ext2 = 0, mixercfg_ext3 = 0; + int i, j; + u8 stages; + int pipes_per_stage; + + stages = _mixer_stages(ctx->mixer_hw_caps, ctx->mixer_count, lm); + if (stages < 0) + return; + + if (test_bit(DPU_MIXER_SOURCESPLIT, + &ctx->mixer_hw_caps->features)) + pipes_per_stage = PIPES_PER_STAGE; + else + pipes_per_stage = 1; + + mixercfg = CTL_MIXER_BORDER_OUT; /* always set BORDER_OUT */ + + if (!stage_cfg) + goto exit; + + for (i = 0; i <= stages; i++) { + /* overflow to ext register if 'i + 1 > 7' */ + mix = (i + 1) & 0x7; + ext = i >= 7; + + for (j = 0 ; j < pipes_per_stage; j++) { + enum dpu_sspp_multirect_index rect_index = + stage_cfg->multirect_index[i][j]; + + switch (stage_cfg->stage[i][j]) { + case SSPP_VIG0: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext3 |= ((i + 1) & 0xF) << 0; + } else { + mixercfg |= mix << 0; + mixercfg_ext |= ext << 0; + } + break; + case SSPP_VIG1: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext3 |= ((i + 1) & 0xF) << 4; + } else { + mixercfg |= mix << 3; + mixercfg_ext |= ext << 2; + } + break; + case SSPP_VIG2: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext3 |= ((i + 1) & 0xF) << 8; + } else { + mixercfg |= mix << 6; + mixercfg_ext |= ext << 4; + } + break; + case SSPP_VIG3: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext3 |= ((i + 1) & 0xF) << 12; + } else { + mixercfg |= mix << 26; + mixercfg_ext |= ext << 6; + } + break; + case SSPP_RGB0: + mixercfg |= mix << 9; + mixercfg_ext |= ext << 8; + break; + case SSPP_RGB1: + mixercfg |= mix << 12; + mixercfg_ext |= ext << 10; + break; + case SSPP_RGB2: + mixercfg |= mix << 15; + mixercfg_ext |= ext << 12; + break; + case SSPP_RGB3: + mixercfg |= mix << 29; + mixercfg_ext |= ext << 14; + break; + case SSPP_DMA0: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext2 |= ((i + 1) & 0xF) << 8; + } else { + mixercfg |= mix << 18; + mixercfg_ext |= ext << 16; + } + break; + case SSPP_DMA1: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext2 |= ((i + 1) & 0xF) << 12; + } else { + mixercfg |= mix << 21; + mixercfg_ext |= ext << 18; + } + break; + case SSPP_DMA2: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext2 |= ((i + 1) & 0xF) << 16; + } else { + mix |= (i + 1) & 0xF; + mixercfg_ext2 |= mix << 0; + } + break; + case SSPP_DMA3: + if (rect_index == DPU_SSPP_RECT_1) { + mixercfg_ext2 |= ((i + 1) & 0xF) << 20; + } else { + mix |= (i + 1) & 0xF; + mixercfg_ext2 |= mix << 4; + } + break; + case SSPP_CURSOR0: + mixercfg_ext |= ((i + 1) & 0xF) << 20; + break; + case SSPP_CURSOR1: + mixercfg_ext |= ((i + 1) & 0xF) << 26; + break; + default: + break; + } + } + } + +exit: + DPU_REG_WRITE(c, CTL_LAYER(lm), mixercfg); + DPU_REG_WRITE(c, CTL_LAYER_EXT(lm), mixercfg_ext); + DPU_REG_WRITE(c, CTL_LAYER_EXT2(lm), mixercfg_ext2); + DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3); +} + +static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx, + struct dpu_hw_intf_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 intf_cfg = 0; + + intf_cfg |= (cfg->intf & 0xF) << 4; + + if (cfg->mode_3d) { + intf_cfg |= BIT(19); + intf_cfg |= (cfg->mode_3d - 0x1) << 20; + } + + switch (cfg->intf_mode_sel) { + case DPU_CTL_MODE_SEL_VID: + intf_cfg &= ~BIT(17); + intf_cfg &= ~(0x3 << 15); + break; + case DPU_CTL_MODE_SEL_CMD: + intf_cfg |= BIT(17); + intf_cfg |= ((cfg->stream_sel & 0x3) << 15); + break; + default: + pr_err("unknown interface type %d\n", cfg->intf_mode_sel); + return; + } + + DPU_REG_WRITE(c, CTL_TOP, intf_cfg); +} + +static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, + unsigned long cap) +{ + ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush; + ops->update_pending_flush = dpu_hw_ctl_update_pending_flush; + ops->get_pending_flush = dpu_hw_ctl_get_pending_flush; + ops->trigger_flush = dpu_hw_ctl_trigger_flush; + ops->get_flush_register = dpu_hw_ctl_get_flush_register; + ops->trigger_start = dpu_hw_ctl_trigger_start; + ops->trigger_pending = dpu_hw_ctl_trigger_pending; + ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg; + ops->reset = dpu_hw_ctl_reset_control; + ops->wait_reset_status = dpu_hw_ctl_wait_reset_status; + ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages; + ops->setup_blendstage = dpu_hw_ctl_setup_blendstage; + ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp; + ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer; + ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf; + ops->get_bitmask_cdm = dpu_hw_ctl_get_bitmask_cdm; +}; + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx, + void __iomem *addr, + struct dpu_mdss_cfg *m) +{ + struct dpu_hw_ctl *c; + struct dpu_ctl_cfg *cfg; + int rc; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _ctl_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + pr_err("failed to create dpu_hw_ctl %d\n", idx); + return ERR_PTR(-EINVAL); + } + + c->caps = cfg; + _setup_ctl_ops(&c->ops, c->caps->features); + c->idx = idx; + c->mixer_count = m->mixer_count; + c->mixer_hw_caps = m->mixer; + + rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + return c; + +blk_init_error: + kzfree(c); + + return ERR_PTR(rc); +} + +void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx) +{ + if (ctx) + dpu_hw_blk_destroy(&ctx->base); + kfree(ctx); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h new file mode 100644 index 000000000000..c66a71f8b839 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -0,0 +1,218 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_CTL_H +#define _DPU_HW_CTL_H + +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_sspp.h" +#include "dpu_hw_blk.h" + +/** + * dpu_ctl_mode_sel: Interface mode selection + * DPU_CTL_MODE_SEL_VID: Video mode interface + * DPU_CTL_MODE_SEL_CMD: Command mode interface + */ +enum dpu_ctl_mode_sel { + DPU_CTL_MODE_SEL_VID = 0, + DPU_CTL_MODE_SEL_CMD +}; + +struct dpu_hw_ctl; +/** + * struct dpu_hw_stage_cfg - blending stage cfg + * @stage : SSPP_ID at each stage + * @multirect_index: index of the rectangle of SSPP. + */ +struct dpu_hw_stage_cfg { + enum dpu_sspp stage[DPU_STAGE_MAX][PIPES_PER_STAGE]; + enum dpu_sspp_multirect_index multirect_index + [DPU_STAGE_MAX][PIPES_PER_STAGE]; +}; + +/** + * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface + * @intf : Interface id + * @mode_3d: 3d mux configuration + * @intf_mode_sel: Interface mode, cmd / vid + * @stream_sel: Stream selection for multi-stream interfaces + */ +struct dpu_hw_intf_cfg { + enum dpu_intf intf; + enum dpu_3d_blend_mode mode_3d; + enum dpu_ctl_mode_sel intf_mode_sel; + int stream_sel; +}; + +/** + * struct dpu_hw_ctl_ops - Interface to the wb Hw driver functions + * Assumption is these functions will be called after clocks are enabled + */ +struct dpu_hw_ctl_ops { + /** + * kickoff hw operation for Sw controlled interfaces + * DSI cmd mode and WB interface are SW controlled + * @ctx : ctl path ctx pointer + */ + void (*trigger_start)(struct dpu_hw_ctl *ctx); + + /** + * kickoff prepare is in progress hw operation for sw + * controlled interfaces: DSI cmd mode and WB interface + * are SW controlled + * @ctx : ctl path ctx pointer + */ + void (*trigger_pending)(struct dpu_hw_ctl *ctx); + + /** + * Clear the value of the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + */ + void (*clear_pending_flush)(struct dpu_hw_ctl *ctx); + + /** + * Query the value of the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + */ + u32 (*get_pending_flush)(struct dpu_hw_ctl *ctx); + + /** + * OR in the given flushbits to the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @flushbits : module flushmask + */ + void (*update_pending_flush)(struct dpu_hw_ctl *ctx, + u32 flushbits); + + /** + * Write the value of the pending_flush_mask to hardware + * @ctx : ctl path ctx pointer + */ + void (*trigger_flush)(struct dpu_hw_ctl *ctx); + + /** + * Read the value of the flush register + * @ctx : ctl path ctx pointer + * @Return: value of the ctl flush register. + */ + u32 (*get_flush_register)(struct dpu_hw_ctl *ctx); + + /** + * Setup ctl_path interface config + * @ctx + * @cfg : interface config structure pointer + */ + void (*setup_intf_cfg)(struct dpu_hw_ctl *ctx, + struct dpu_hw_intf_cfg *cfg); + + int (*reset)(struct dpu_hw_ctl *c); + + /* + * wait_reset_status - checks ctl reset status + * @ctx : ctl path ctx pointer + * + * This function checks the ctl reset status bit. + * If the reset bit is set, it keeps polling the status till the hw + * reset is complete. + * Returns: 0 on success or -error if reset incomplete within interval + */ + int (*wait_reset_status)(struct dpu_hw_ctl *ctx); + + uint32_t (*get_bitmask_sspp)(struct dpu_hw_ctl *ctx, + enum dpu_sspp blk); + + uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx, + enum dpu_lm blk); + + int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx, + u32 *flushbits, + enum dpu_intf blk); + + int (*get_bitmask_cdm)(struct dpu_hw_ctl *ctx, + u32 *flushbits, + enum dpu_cdm blk); + + /** + * Set all blend stages to disabled + * @ctx : ctl path ctx pointer + */ + void (*clear_all_blendstages)(struct dpu_hw_ctl *ctx); + + /** + * Configure layer mixer to pipe configuration + * @ctx : ctl path ctx pointer + * @lm : layer mixer enumeration + * @cfg : blend stage configuration + */ + void (*setup_blendstage)(struct dpu_hw_ctl *ctx, + enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg); +}; + +/** + * struct dpu_hw_ctl : CTL PATH driver object + * @base: hardware block base structure + * @hw: block register map object + * @idx: control path index + * @caps: control path capabilities + * @mixer_count: number of mixers + * @mixer_hw_caps: mixer hardware capabilities + * @pending_flush_mask: storage for pending ctl_flush managed via ops + * @ops: operation list + */ +struct dpu_hw_ctl { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* ctl path */ + int idx; + const struct dpu_ctl_cfg *caps; + int mixer_count; + const struct dpu_lm_cfg *mixer_hw_caps; + u32 pending_flush_mask; + + /* ops */ + struct dpu_hw_ctl_ops ops; +}; + +/** + * dpu_hw_ctl - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_ctl, base); +} + +/** + * dpu_hw_ctl_init(): Initializes the ctl_path hw driver object. + * should be called before accessing every ctl path registers. + * @idx: ctl_path index for which driver object is required + * @addr: mapped register io address of MDP + * @m : pointer to mdss catalog data + */ +struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx, + void __iomem *addr, + struct dpu_mdss_cfg *m); + +/** + * dpu_hw_ctl_destroy(): Destroys ctl driver context + * should be called to free the context + */ +void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx); + +#endif /*_DPU_HW_CTL_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c new file mode 100644 index 000000000000..c0b7f0049365 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -0,0 +1,1183 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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/bitops.h> +#include <linux/slab.h> + +#include "dpu_kms.h" +#include "dpu_hw_interrupts.h" +#include "dpu_hw_util.h" +#include "dpu_hw_mdss.h" + +/** + * Register offsets in MDSS register file for the interrupt registers + * w.r.t. to the MDP base + */ +#define MDP_SSPP_TOP0_OFF 0x0 +#define MDP_INTF_0_OFF 0x6A000 +#define MDP_INTF_1_OFF 0x6A800 +#define MDP_INTF_2_OFF 0x6B000 +#define MDP_INTF_3_OFF 0x6B800 +#define MDP_INTF_4_OFF 0x6C000 +#define MDP_AD4_0_OFF 0x7C000 +#define MDP_AD4_1_OFF 0x7D000 +#define MDP_AD4_INTR_EN_OFF 0x41c +#define MDP_AD4_INTR_CLEAR_OFF 0x424 +#define MDP_AD4_INTR_STATUS_OFF 0x420 + +/** + * WB interrupt status bit definitions + */ +#define DPU_INTR_WB_0_DONE BIT(0) +#define DPU_INTR_WB_1_DONE BIT(1) +#define DPU_INTR_WB_2_DONE BIT(4) + +/** + * WDOG timer interrupt status bit definitions + */ +#define DPU_INTR_WD_TIMER_0_DONE BIT(2) +#define DPU_INTR_WD_TIMER_1_DONE BIT(3) +#define DPU_INTR_WD_TIMER_2_DONE BIT(5) +#define DPU_INTR_WD_TIMER_3_DONE BIT(6) +#define DPU_INTR_WD_TIMER_4_DONE BIT(7) + +/** + * Pingpong interrupt status bit definitions + */ +#define DPU_INTR_PING_PONG_0_DONE BIT(8) +#define DPU_INTR_PING_PONG_1_DONE BIT(9) +#define DPU_INTR_PING_PONG_2_DONE BIT(10) +#define DPU_INTR_PING_PONG_3_DONE BIT(11) +#define DPU_INTR_PING_PONG_0_RD_PTR BIT(12) +#define DPU_INTR_PING_PONG_1_RD_PTR BIT(13) +#define DPU_INTR_PING_PONG_2_RD_PTR BIT(14) +#define DPU_INTR_PING_PONG_3_RD_PTR BIT(15) +#define DPU_INTR_PING_PONG_0_WR_PTR BIT(16) +#define DPU_INTR_PING_PONG_1_WR_PTR BIT(17) +#define DPU_INTR_PING_PONG_2_WR_PTR BIT(18) +#define DPU_INTR_PING_PONG_3_WR_PTR BIT(19) +#define DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE BIT(20) +#define DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE BIT(21) +#define DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE BIT(22) +#define DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE BIT(23) + +/** + * Interface interrupt status bit definitions + */ +#define DPU_INTR_INTF_0_UNDERRUN BIT(24) +#define DPU_INTR_INTF_1_UNDERRUN BIT(26) +#define DPU_INTR_INTF_2_UNDERRUN BIT(28) +#define DPU_INTR_INTF_3_UNDERRUN BIT(30) +#define DPU_INTR_INTF_0_VSYNC BIT(25) +#define DPU_INTR_INTF_1_VSYNC BIT(27) +#define DPU_INTR_INTF_2_VSYNC BIT(29) +#define DPU_INTR_INTF_3_VSYNC BIT(31) + +/** + * Pingpong Secondary interrupt status bit definitions + */ +#define DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE BIT(0) +#define DPU_INTR_PING_PONG_S0_WR_PTR BIT(4) +#define DPU_INTR_PING_PONG_S0_RD_PTR BIT(8) +#define DPU_INTR_PING_PONG_S0_TEAR_DETECTED BIT(22) +#define DPU_INTR_PING_PONG_S0_TE_DETECTED BIT(28) + +/** + * Pingpong TEAR detection interrupt status bit definitions + */ +#define DPU_INTR_PING_PONG_0_TEAR_DETECTED BIT(16) +#define DPU_INTR_PING_PONG_1_TEAR_DETECTED BIT(17) +#define DPU_INTR_PING_PONG_2_TEAR_DETECTED BIT(18) +#define DPU_INTR_PING_PONG_3_TEAR_DETECTED BIT(19) + +/** + * Pingpong TE detection interrupt status bit definitions + */ +#define DPU_INTR_PING_PONG_0_TE_DETECTED BIT(24) +#define DPU_INTR_PING_PONG_1_TE_DETECTED BIT(25) +#define DPU_INTR_PING_PONG_2_TE_DETECTED BIT(26) +#define DPU_INTR_PING_PONG_3_TE_DETECTED BIT(27) + +/** + * Ctl start interrupt status bit definitions + */ +#define DPU_INTR_CTL_0_START BIT(9) +#define DPU_INTR_CTL_1_START BIT(10) +#define DPU_INTR_CTL_2_START BIT(11) +#define DPU_INTR_CTL_3_START BIT(12) +#define DPU_INTR_CTL_4_START BIT(13) + +/** + * Concurrent WB overflow interrupt status bit definitions + */ +#define DPU_INTR_CWB_2_OVERFLOW BIT(14) +#define DPU_INTR_CWB_3_OVERFLOW BIT(15) + +/** + * Histogram VIG done interrupt status bit definitions + */ +#define DPU_INTR_HIST_VIG_0_DONE BIT(0) +#define DPU_INTR_HIST_VIG_1_DONE BIT(4) +#define DPU_INTR_HIST_VIG_2_DONE BIT(8) +#define DPU_INTR_HIST_VIG_3_DONE BIT(10) + +/** + * Histogram VIG reset Sequence done interrupt status bit definitions + */ +#define DPU_INTR_HIST_VIG_0_RSTSEQ_DONE BIT(1) +#define DPU_INTR_HIST_VIG_1_RSTSEQ_DONE BIT(5) +#define DPU_INTR_HIST_VIG_2_RSTSEQ_DONE BIT(9) +#define DPU_INTR_HIST_VIG_3_RSTSEQ_DONE BIT(11) + +/** + * Histogram DSPP done interrupt status bit definitions + */ +#define DPU_INTR_HIST_DSPP_0_DONE BIT(12) +#define DPU_INTR_HIST_DSPP_1_DONE BIT(16) +#define DPU_INTR_HIST_DSPP_2_DONE BIT(20) +#define DPU_INTR_HIST_DSPP_3_DONE BIT(22) + +/** + * Histogram DSPP reset Sequence done interrupt status bit definitions + */ +#define DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE BIT(13) +#define DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE BIT(17) +#define DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE BIT(21) +#define DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE BIT(23) + +/** + * INTF interrupt status bit definitions + */ +#define DPU_INTR_VIDEO_INTO_STATIC BIT(0) +#define DPU_INTR_VIDEO_OUTOF_STATIC BIT(1) +#define DPU_INTR_DSICMD_0_INTO_STATIC BIT(2) +#define DPU_INTR_DSICMD_0_OUTOF_STATIC BIT(3) +#define DPU_INTR_DSICMD_1_INTO_STATIC BIT(4) +#define DPU_INTR_DSICMD_1_OUTOF_STATIC BIT(5) +#define DPU_INTR_DSICMD_2_INTO_STATIC BIT(6) +#define DPU_INTR_DSICMD_2_OUTOF_STATIC BIT(7) +#define DPU_INTR_PROG_LINE BIT(8) + +/** + * AD4 interrupt status bit definitions + */ +#define DPU_INTR_BRIGHTPR_UPDATED BIT(4) +#define DPU_INTR_DARKENH_UPDATED BIT(3) +#define DPU_INTR_STREN_OUTROI_UPDATED BIT(2) +#define DPU_INTR_STREN_INROI_UPDATED BIT(1) +#define DPU_INTR_BACKLIGHT_UPDATED BIT(0) +/** + * struct dpu_intr_reg - array of DPU register sets + * @clr_off: offset to CLEAR reg + * @en_off: offset to ENABLE reg + * @status_off: offset to STATUS reg + */ +struct dpu_intr_reg { + u32 clr_off; + u32 en_off; + u32 status_off; +}; + +/** + * struct dpu_irq_type - maps each irq with i/f + * @intr_type: type of interrupt listed in dpu_intr_type + * @instance_idx: instance index of the associated HW block in DPU + * @irq_mask: corresponding bit in the interrupt status reg + * @reg_idx: which reg set to use + */ +struct dpu_irq_type { + u32 intr_type; + u32 instance_idx; + u32 irq_mask; + u32 reg_idx; +}; + +/** + * List of DPU interrupt registers + */ +static const struct dpu_intr_reg dpu_intr_set[] = { + { + MDP_SSPP_TOP0_OFF+INTR_CLEAR, + MDP_SSPP_TOP0_OFF+INTR_EN, + MDP_SSPP_TOP0_OFF+INTR_STATUS + }, + { + MDP_SSPP_TOP0_OFF+INTR2_CLEAR, + MDP_SSPP_TOP0_OFF+INTR2_EN, + MDP_SSPP_TOP0_OFF+INTR2_STATUS + }, + { + MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR, + MDP_SSPP_TOP0_OFF+HIST_INTR_EN, + MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS + }, + { + MDP_INTF_0_OFF+INTF_INTR_CLEAR, + MDP_INTF_0_OFF+INTF_INTR_EN, + MDP_INTF_0_OFF+INTF_INTR_STATUS + }, + { + MDP_INTF_1_OFF+INTF_INTR_CLEAR, + MDP_INTF_1_OFF+INTF_INTR_EN, + MDP_INTF_1_OFF+INTF_INTR_STATUS + }, + { + MDP_INTF_2_OFF+INTF_INTR_CLEAR, + MDP_INTF_2_OFF+INTF_INTR_EN, + MDP_INTF_2_OFF+INTF_INTR_STATUS + }, + { + MDP_INTF_3_OFF+INTF_INTR_CLEAR, + MDP_INTF_3_OFF+INTF_INTR_EN, + MDP_INTF_3_OFF+INTF_INTR_STATUS + }, + { + MDP_INTF_4_OFF+INTF_INTR_CLEAR, + MDP_INTF_4_OFF+INTF_INTR_EN, + MDP_INTF_4_OFF+INTF_INTR_STATUS + }, + { + MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF, + MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF, + MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF, + }, + { + MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF, + MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF, + MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF, + } +}; + +/** + * IRQ mapping table - use for lookup an irq_idx in this table that have + * a matching interface type and instance index. + */ +static const struct dpu_irq_type dpu_irq_map[] = { + /* BEGIN MAP_RANGE: 0-31, INTR */ + /* irq_idx: 0-3 */ + { DPU_IRQ_TYPE_WB_ROT_COMP, WB_0, DPU_INTR_WB_0_DONE, 0}, + { DPU_IRQ_TYPE_WB_ROT_COMP, WB_1, DPU_INTR_WB_1_DONE, 0}, + { DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_0, DPU_INTR_WD_TIMER_0_DONE, 0}, + { DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_1, DPU_INTR_WD_TIMER_1_DONE, 0}, + /* irq_idx: 4-7 */ + { DPU_IRQ_TYPE_WB_WFD_COMP, WB_2, DPU_INTR_WB_2_DONE, 0}, + { DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_2, DPU_INTR_WD_TIMER_2_DONE, 0}, + { DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_3, DPU_INTR_WD_TIMER_3_DONE, 0}, + { DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_4, DPU_INTR_WD_TIMER_4_DONE, 0}, + /* irq_idx: 8-11 */ + { DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_0, + DPU_INTR_PING_PONG_0_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_1, + DPU_INTR_PING_PONG_1_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_2, + DPU_INTR_PING_PONG_2_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_3, + DPU_INTR_PING_PONG_3_DONE, 0}, + /* irq_idx: 12-15 */ + { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_0, + DPU_INTR_PING_PONG_0_RD_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_1, + DPU_INTR_PING_PONG_1_RD_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_2, + DPU_INTR_PING_PONG_2_RD_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_3, + DPU_INTR_PING_PONG_3_RD_PTR, 0}, + /* irq_idx: 16-19 */ + { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_0, + DPU_INTR_PING_PONG_0_WR_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_1, + DPU_INTR_PING_PONG_1_WR_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_2, + DPU_INTR_PING_PONG_2_WR_PTR, 0}, + { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_3, + DPU_INTR_PING_PONG_3_WR_PTR, 0}, + /* irq_idx: 20-23 */ + { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_0, + DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_1, + DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_2, + DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE, 0}, + { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_3, + DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE, 0}, + /* irq_idx: 24-27 */ + { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_0, DPU_INTR_INTF_0_UNDERRUN, 0}, + { DPU_IRQ_TYPE_INTF_VSYNC, INTF_0, DPU_INTR_INTF_0_VSYNC, 0}, + { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_1, DPU_INTR_INTF_1_UNDERRUN, 0}, + { DPU_IRQ_TYPE_INTF_VSYNC, INTF_1, DPU_INTR_INTF_1_VSYNC, 0}, + /* irq_idx: 28-31 */ + { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_2, DPU_INTR_INTF_2_UNDERRUN, 0}, + { DPU_IRQ_TYPE_INTF_VSYNC, INTF_2, DPU_INTR_INTF_2_VSYNC, 0}, + { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_3, DPU_INTR_INTF_3_UNDERRUN, 0}, + { DPU_IRQ_TYPE_INTF_VSYNC, INTF_3, DPU_INTR_INTF_3_VSYNC, 0}, + + /* BEGIN MAP_RANGE: 32-64, INTR2 */ + /* irq_idx: 32-35 */ + { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_S0, + DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + /* irq_idx: 36-39 */ + { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_S0, + DPU_INTR_PING_PONG_S0_WR_PTR, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + /* irq_idx: 40 */ + { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_S0, + DPU_INTR_PING_PONG_S0_RD_PTR, 1}, + /* irq_idx: 41-45 */ + { DPU_IRQ_TYPE_CTL_START, CTL_0, + DPU_INTR_CTL_0_START, 1}, + { DPU_IRQ_TYPE_CTL_START, CTL_1, + DPU_INTR_CTL_1_START, 1}, + { DPU_IRQ_TYPE_CTL_START, CTL_2, + DPU_INTR_CTL_2_START, 1}, + { DPU_IRQ_TYPE_CTL_START, CTL_3, + DPU_INTR_CTL_3_START, 1}, + { DPU_IRQ_TYPE_CTL_START, CTL_4, + DPU_INTR_CTL_4_START, 1}, + /* irq_idx: 46-47 */ + { DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_2, DPU_INTR_CWB_2_OVERFLOW, 1}, + { DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_3, DPU_INTR_CWB_3_OVERFLOW, 1}, + /* irq_idx: 48-51 */ + { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_0, + DPU_INTR_PING_PONG_0_TEAR_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_1, + DPU_INTR_PING_PONG_1_TEAR_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_2, + DPU_INTR_PING_PONG_2_TEAR_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_3, + DPU_INTR_PING_PONG_3_TEAR_DETECTED, 1}, + /* irq_idx: 52-55 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_S0, + DPU_INTR_PING_PONG_S0_TEAR_DETECTED, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + /* irq_idx: 56-59 */ + { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_0, + DPU_INTR_PING_PONG_0_TE_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_1, + DPU_INTR_PING_PONG_1_TE_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_2, + DPU_INTR_PING_PONG_2_TE_DETECTED, 1}, + { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_3, + DPU_INTR_PING_PONG_3_TE_DETECTED, 1}, + /* irq_idx: 60-63 */ + { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_S0, + DPU_INTR_PING_PONG_S0_TE_DETECTED, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + + /* BEGIN MAP_RANGE: 64-95 HIST */ + /* irq_idx: 64-67 */ + { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG0, DPU_INTR_HIST_VIG_0_DONE, 2}, + { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG0, + DPU_INTR_HIST_VIG_0_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* irq_idx: 68-71 */ + { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG1, DPU_INTR_HIST_VIG_1_DONE, 2}, + { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG1, + DPU_INTR_HIST_VIG_1_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* irq_idx: 72-75 */ + { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG2, DPU_INTR_HIST_VIG_2_DONE, 2}, + { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG2, + DPU_INTR_HIST_VIG_2_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG3, DPU_INTR_HIST_VIG_3_DONE, 2}, + { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG3, + DPU_INTR_HIST_VIG_3_RSTSEQ_DONE, 2}, + /* irq_idx: 76-79 */ + { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_0, DPU_INTR_HIST_DSPP_0_DONE, 2}, + { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_0, + DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* irq_idx: 80-83 */ + { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_1, DPU_INTR_HIST_DSPP_1_DONE, 2}, + { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_1, + DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* irq_idx: 84-87 */ + { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_2, DPU_INTR_HIST_DSPP_2_DONE, 2}, + { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_2, + DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE, 2}, + { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_3, DPU_INTR_HIST_DSPP_3_DONE, 2}, + { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_3, + DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE, 2}, + /* irq_idx: 88-91 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* irq_idx: 92-95 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + + /* BEGIN MAP_RANGE: 96-127 INTF_0_INTR */ + /* irq_idx: 96-99 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0, + DPU_INTR_VIDEO_INTO_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0, + DPU_INTR_VIDEO_OUTOF_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_0, + DPU_INTR_DSICMD_0_INTO_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 3}, + /* irq_idx: 100-103 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0, + DPU_INTR_DSICMD_1_INTO_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_0, + DPU_INTR_DSICMD_2_INTO_STATIC, 3}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 3}, + /* irq_idx: 104-107 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 108-111 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 112-115 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 116-119 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 120-123 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 124-127 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + + /* BEGIN MAP_RANGE: 128-159 INTF_1_INTR */ + /* irq_idx: 128-131 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1, + DPU_INTR_VIDEO_INTO_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1, + DPU_INTR_VIDEO_OUTOF_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_1, + DPU_INTR_DSICMD_0_INTO_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 4}, + /* irq_idx: 132-135 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1, + DPU_INTR_DSICMD_1_INTO_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_1, + DPU_INTR_DSICMD_2_INTO_STATIC, 4}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 4}, + /* irq_idx: 136-139 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* irq_idx: 140-143 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* irq_idx: 144-147 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* irq_idx: 148-151 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* irq_idx: 152-155 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* irq_idx: 156-159 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + + /* BEGIN MAP_RANGE: 160-191 INTF_2_INTR */ + /* irq_idx: 160-163 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_2, + DPU_INTR_VIDEO_INTO_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_2, + DPU_INTR_VIDEO_OUTOF_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_2, + DPU_INTR_DSICMD_0_INTO_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_2, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 5}, + /* irq_idx: 164-167 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_2, + DPU_INTR_DSICMD_1_INTO_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_2, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_2, + DPU_INTR_DSICMD_2_INTO_STATIC, 5}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_2, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 5}, + /* irq_idx: 168-171 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_2, DPU_INTR_PROG_LINE, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* irq_idx: 172-175 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* irq_idx: 176-179 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* irq_idx: 180-183 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* irq_idx: 184-187 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* irq_idx: 188-191 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + + /* BEGIN MAP_RANGE: 192-223 INTF_3_INTR */ + /* irq_idx: 192-195 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_3, + DPU_INTR_VIDEO_INTO_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_3, + DPU_INTR_VIDEO_OUTOF_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_3, + DPU_INTR_DSICMD_0_INTO_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_3, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 6}, + /* irq_idx: 196-199 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_3, + DPU_INTR_DSICMD_1_INTO_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_3, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_3, + DPU_INTR_DSICMD_2_INTO_STATIC, 6}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_3, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 6}, + /* irq_idx: 200-203 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_3, DPU_INTR_PROG_LINE, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* irq_idx: 204-207 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* irq_idx: 208-211 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* irq_idx: 212-215 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* irq_idx: 216-219 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* irq_idx: 220-223 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + + /* BEGIN MAP_RANGE: 224-255 INTF_4_INTR */ + /* irq_idx: 224-227 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_4, + DPU_INTR_VIDEO_INTO_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_4, + DPU_INTR_VIDEO_OUTOF_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_4, + DPU_INTR_DSICMD_0_INTO_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_4, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 7}, + /* irq_idx: 228-231 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_4, + DPU_INTR_DSICMD_1_INTO_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_4, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_4, + DPU_INTR_DSICMD_2_INTO_STATIC, 7}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_4, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 7}, + /* irq_idx: 232-235 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_4, DPU_INTR_PROG_LINE, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* irq_idx: 236-239 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* irq_idx: 240-243 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* irq_idx: 244-247 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* irq_idx: 248-251 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* irq_idx: 252-255 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + + /* BEGIN MAP_RANGE: 256-287 AD4_0_INTR */ + /* irq_idx: 256-259 */ + { DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_0, DPU_INTR_BACKLIGHT_UPDATED, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 260-263 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 264-267 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 268-271 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 272-275 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 276-279 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 280-283 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* irq_idx: 284-287 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + + /* BEGIN MAP_RANGE: 288-319 AD4_1_INTR */ + /* irq_idx: 288-291 */ + { DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_1, DPU_INTR_BACKLIGHT_UPDATED, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 292-295 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 296-299 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 300-303 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 304-307 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 308-311 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 312-315 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 315-319 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, +}; + +static int dpu_hw_intr_irqidx_lookup(enum dpu_intr_type intr_type, + u32 instance_idx) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(dpu_irq_map); i++) { + if (intr_type == dpu_irq_map[i].intr_type && + instance_idx == dpu_irq_map[i].instance_idx) + return i; + } + + pr_debug("IRQ lookup fail!! intr_type=%d, instance_idx=%d\n", + intr_type, instance_idx); + return -EINVAL; +} + +static void dpu_hw_intr_set_mask(struct dpu_hw_intr *intr, uint32_t reg_off, + uint32_t mask) +{ + if (!intr) + return; + + DPU_REG_WRITE(&intr->hw, reg_off, mask); + + /* ensure register writes go through */ + wmb(); +} + +static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, + void (*cbfunc)(void *, int), + void *arg) +{ + int reg_idx; + int irq_idx; + int start_idx; + int end_idx; + u32 irq_status; + unsigned long irq_flags; + + if (!intr) + return; + + /* + * The dispatcher will save the IRQ status before calling here. + * Now need to go through each IRQ status and find matching + * irq lookup index. + */ + spin_lock_irqsave(&intr->irq_lock, irq_flags); + for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) { + irq_status = intr->save_irq_status[reg_idx]; + + /* + * Each Interrupt register has a range of 32 indexes, and + * that is static for dpu_irq_map. + */ + start_idx = reg_idx * 32; + end_idx = start_idx + 32; + + if (start_idx >= ARRAY_SIZE(dpu_irq_map) || + end_idx > ARRAY_SIZE(dpu_irq_map)) + continue; + + /* + * Search through matching intr status from irq map. + * start_idx and end_idx defined the search range in + * the dpu_irq_map. + */ + for (irq_idx = start_idx; + (irq_idx < end_idx) && irq_status; + irq_idx++) + if ((irq_status & dpu_irq_map[irq_idx].irq_mask) && + (dpu_irq_map[irq_idx].reg_idx == reg_idx)) { + /* + * Once a match on irq mask, perform a callback + * to the given cbfunc. cbfunc will take care + * the interrupt status clearing. If cbfunc is + * not provided, then the interrupt clearing + * is here. + */ + if (cbfunc) + cbfunc(arg, irq_idx); + else + intr->ops.clear_intr_status_nolock( + intr, irq_idx); + + /* + * When callback finish, clear the irq_status + * with the matching mask. Once irq_status + * is all cleared, the search can be stopped. + */ + irq_status &= ~dpu_irq_map[irq_idx].irq_mask; + } + } + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); +} + +static int dpu_hw_intr_enable_irq(struct dpu_hw_intr *intr, int irq_idx) +{ + int reg_idx; + unsigned long irq_flags; + const struct dpu_intr_reg *reg; + const struct dpu_irq_type *irq; + const char *dbgstr = NULL; + uint32_t cache_irq_mask; + + if (!intr) + return -EINVAL; + + if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) { + pr_err("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + irq = &dpu_irq_map[irq_idx]; + reg_idx = irq->reg_idx; + reg = &dpu_intr_set[reg_idx]; + + spin_lock_irqsave(&intr->irq_lock, irq_flags); + cache_irq_mask = intr->cache_irq_mask[reg_idx]; + if (cache_irq_mask & irq->irq_mask) { + dbgstr = "DPU IRQ already set:"; + } else { + dbgstr = "DPU IRQ enabled:"; + + cache_irq_mask |= irq->irq_mask; + /* Cleaning any pending interrupt */ + DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask); + /* Enabling interrupts with the new mask */ + DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask); + + /* ensure register write goes through */ + wmb(); + + intr->cache_irq_mask[reg_idx] = cache_irq_mask; + } + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); + + pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr, + irq->irq_mask, cache_irq_mask); + + return 0; +} + +static int dpu_hw_intr_disable_irq_nolock(struct dpu_hw_intr *intr, int irq_idx) +{ + int reg_idx; + const struct dpu_intr_reg *reg; + const struct dpu_irq_type *irq; + const char *dbgstr = NULL; + uint32_t cache_irq_mask; + + if (!intr) + return -EINVAL; + + if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) { + pr_err("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + irq = &dpu_irq_map[irq_idx]; + reg_idx = irq->reg_idx; + reg = &dpu_intr_set[reg_idx]; + + cache_irq_mask = intr->cache_irq_mask[reg_idx]; + if ((cache_irq_mask & irq->irq_mask) == 0) { + dbgstr = "DPU IRQ is already cleared:"; + } else { + dbgstr = "DPU IRQ mask disable:"; + + cache_irq_mask &= ~irq->irq_mask; + /* Disable interrupts based on the new mask */ + DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask); + /* Cleaning any pending interrupt */ + DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask); + + /* ensure register write goes through */ + wmb(); + + intr->cache_irq_mask[reg_idx] = cache_irq_mask; + } + + pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr, + irq->irq_mask, cache_irq_mask); + + return 0; +} + +static int dpu_hw_intr_disable_irq(struct dpu_hw_intr *intr, int irq_idx) +{ + unsigned long irq_flags; + + if (!intr) + return -EINVAL; + + if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) { + pr_err("invalid IRQ index: [%d]\n", irq_idx); + return -EINVAL; + } + + spin_lock_irqsave(&intr->irq_lock, irq_flags); + dpu_hw_intr_disable_irq_nolock(intr, irq_idx); + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); + + return 0; +} + +static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr) +{ + int i; + + if (!intr) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) + DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, 0xffffffff); + + /* ensure register writes go through */ + wmb(); + + return 0; +} + +static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr) +{ + int i; + + if (!intr) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) + DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].en_off, 0x00000000); + + /* ensure register writes go through */ + wmb(); + + return 0; +} + +static int dpu_hw_intr_get_valid_interrupts(struct dpu_hw_intr *intr, + uint32_t *mask) +{ + if (!intr || !mask) + return -EINVAL; + + *mask = IRQ_SOURCE_MDP | IRQ_SOURCE_DSI0 | IRQ_SOURCE_DSI1 + | IRQ_SOURCE_HDMI | IRQ_SOURCE_EDP; + + return 0; +} + +static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr) +{ + int i; + u32 enable_mask; + unsigned long irq_flags; + + if (!intr) + return; + + spin_lock_irqsave(&intr->irq_lock, irq_flags); + for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) { + /* Read interrupt status */ + intr->save_irq_status[i] = DPU_REG_READ(&intr->hw, + dpu_intr_set[i].status_off); + + /* Read enable mask */ + enable_mask = DPU_REG_READ(&intr->hw, dpu_intr_set[i].en_off); + + /* and clear the interrupt */ + if (intr->save_irq_status[i]) + DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, + intr->save_irq_status[i]); + + /* Finally update IRQ status based on enable mask */ + intr->save_irq_status[i] &= enable_mask; + } + + /* ensure register writes go through */ + wmb(); + + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); +} + +static void dpu_hw_intr_clear_intr_status_nolock(struct dpu_hw_intr *intr, + int irq_idx) +{ + int reg_idx; + + if (!intr) + return; + + reg_idx = dpu_irq_map[irq_idx].reg_idx; + DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off, + dpu_irq_map[irq_idx].irq_mask); + + /* ensure register writes go through */ + wmb(); +} + +static void dpu_hw_intr_clear_interrupt_status(struct dpu_hw_intr *intr, + int irq_idx) +{ + unsigned long irq_flags; + + if (!intr) + return; + + spin_lock_irqsave(&intr->irq_lock, irq_flags); + dpu_hw_intr_clear_intr_status_nolock(intr, irq_idx); + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); +} + +static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr, + int irq_idx, bool clear) +{ + int reg_idx; + unsigned long irq_flags; + u32 intr_status; + + if (!intr) + return 0; + + if (irq_idx >= ARRAY_SIZE(dpu_irq_map) || irq_idx < 0) { + pr_err("invalid IRQ index: [%d]\n", irq_idx); + return 0; + } + + spin_lock_irqsave(&intr->irq_lock, irq_flags); + + reg_idx = dpu_irq_map[irq_idx].reg_idx; + intr_status = DPU_REG_READ(&intr->hw, + dpu_intr_set[reg_idx].status_off) & + dpu_irq_map[irq_idx].irq_mask; + if (intr_status && clear) + DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off, + intr_status); + + /* ensure register writes go through */ + wmb(); + + spin_unlock_irqrestore(&intr->irq_lock, irq_flags); + + return intr_status; +} + +static void __setup_intr_ops(struct dpu_hw_intr_ops *ops) +{ + ops->set_mask = dpu_hw_intr_set_mask; + ops->irq_idx_lookup = dpu_hw_intr_irqidx_lookup; + ops->enable_irq = dpu_hw_intr_enable_irq; + ops->disable_irq = dpu_hw_intr_disable_irq; + ops->dispatch_irqs = dpu_hw_intr_dispatch_irq; + ops->clear_all_irqs = dpu_hw_intr_clear_irqs; + ops->disable_all_irqs = dpu_hw_intr_disable_irqs; + ops->get_valid_interrupts = dpu_hw_intr_get_valid_interrupts; + ops->get_interrupt_statuses = dpu_hw_intr_get_interrupt_statuses; + ops->clear_interrupt_status = dpu_hw_intr_clear_interrupt_status; + ops->clear_intr_status_nolock = dpu_hw_intr_clear_intr_status_nolock; + ops->get_interrupt_status = dpu_hw_intr_get_interrupt_status; +} + +static void __intr_offset(struct dpu_mdss_cfg *m, + void __iomem *addr, struct dpu_hw_blk_reg_map *hw) +{ + hw->base_off = addr; + hw->blk_off = m->mdp[0].base; + hw->hwversion = m->hwversion; +} + +struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, + struct dpu_mdss_cfg *m) +{ + struct dpu_hw_intr *intr; + + if (!addr || !m) + return ERR_PTR(-EINVAL); + + intr = kzalloc(sizeof(*intr), GFP_KERNEL); + if (!intr) + return ERR_PTR(-ENOMEM); + + __intr_offset(m, addr, &intr->hw); + __setup_intr_ops(&intr->ops); + + intr->irq_idx_tbl_size = ARRAY_SIZE(dpu_irq_map); + + intr->cache_irq_mask = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32), + GFP_KERNEL); + if (intr->cache_irq_mask == NULL) { + kfree(intr); + return ERR_PTR(-ENOMEM); + } + + intr->save_irq_status = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32), + GFP_KERNEL); + if (intr->save_irq_status == NULL) { + kfree(intr->cache_irq_mask); + kfree(intr); + return ERR_PTR(-ENOMEM); + } + + spin_lock_init(&intr->irq_lock); + + return intr; +} + +void dpu_hw_intr_destroy(struct dpu_hw_intr *intr) +{ + if (intr) { + kfree(intr->cache_irq_mask); + kfree(intr->save_irq_status); + kfree(intr); + } +} + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h new file mode 100644 index 000000000000..61e4cba36562 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h @@ -0,0 +1,257 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_INTERRUPTS_H +#define _DPU_HW_INTERRUPTS_H + +#include <linux/types.h> + +#include "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_util.h" +#include "dpu_hw_mdss.h" + +#define IRQ_SOURCE_MDP BIT(0) +#define IRQ_SOURCE_DSI0 BIT(4) +#define IRQ_SOURCE_DSI1 BIT(5) +#define IRQ_SOURCE_HDMI BIT(8) +#define IRQ_SOURCE_EDP BIT(12) +#define IRQ_SOURCE_MHL BIT(16) + +/** + * dpu_intr_type - HW Interrupt Type + * @DPU_IRQ_TYPE_WB_ROT_COMP: WB rotator done + * @DPU_IRQ_TYPE_WB_WFD_COMP: WB WFD done + * @DPU_IRQ_TYPE_PING_PONG_COMP: PingPong done + * @DPU_IRQ_TYPE_PING_PONG_RD_PTR: PingPong read pointer + * @DPU_IRQ_TYPE_PING_PONG_WR_PTR: PingPong write pointer + * @DPU_IRQ_TYPE_PING_PONG_AUTO_REF: PingPong auto refresh + * @DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK: PingPong Tear check + * @DPU_IRQ_TYPE_PING_PONG_TE_CHECK: PingPong TE detection + * @DPU_IRQ_TYPE_INTF_UNDER_RUN: INTF underrun + * @DPU_IRQ_TYPE_INTF_VSYNC: INTF VSYNC + * @DPU_IRQ_TYPE_CWB_OVERFLOW: Concurrent WB overflow + * @DPU_IRQ_TYPE_HIST_VIG_DONE: VIG Histogram done + * @DPU_IRQ_TYPE_HIST_VIG_RSTSEQ: VIG Histogram reset + * @DPU_IRQ_TYPE_HIST_DSPP_DONE: DSPP Histogram done + * @DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ: DSPP Histogram reset + * @DPU_IRQ_TYPE_WD_TIMER: Watchdog timer + * @DPU_IRQ_TYPE_SFI_VIDEO_IN: Video static frame INTR into static + * @DPU_IRQ_TYPE_SFI_VIDEO_OUT: Video static frame INTR out-of static + * @DPU_IRQ_TYPE_SFI_CMD_0_IN: DSI CMD0 static frame INTR into static + * @DPU_IRQ_TYPE_SFI_CMD_0_OUT: DSI CMD0 static frame INTR out-of static + * @DPU_IRQ_TYPE_SFI_CMD_1_IN: DSI CMD1 static frame INTR into static + * @DPU_IRQ_TYPE_SFI_CMD_1_OUT: DSI CMD1 static frame INTR out-of static + * @DPU_IRQ_TYPE_SFI_CMD_2_IN: DSI CMD2 static frame INTR into static + * @DPU_IRQ_TYPE_SFI_CMD_2_OUT: DSI CMD2 static frame INTR out-of static + * @DPU_IRQ_TYPE_PROG_LINE: Programmable Line interrupt + * @DPU_IRQ_TYPE_AD4_BL_DONE: AD4 backlight + * @DPU_IRQ_TYPE_CTL_START: Control start + * @DPU_IRQ_TYPE_RESERVED: Reserved for expansion + */ +enum dpu_intr_type { + DPU_IRQ_TYPE_WB_ROT_COMP, + DPU_IRQ_TYPE_WB_WFD_COMP, + DPU_IRQ_TYPE_PING_PONG_COMP, + DPU_IRQ_TYPE_PING_PONG_RD_PTR, + DPU_IRQ_TYPE_PING_PONG_WR_PTR, + DPU_IRQ_TYPE_PING_PONG_AUTO_REF, + DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, + DPU_IRQ_TYPE_PING_PONG_TE_CHECK, + DPU_IRQ_TYPE_INTF_UNDER_RUN, + DPU_IRQ_TYPE_INTF_VSYNC, + DPU_IRQ_TYPE_CWB_OVERFLOW, + DPU_IRQ_TYPE_HIST_VIG_DONE, + DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, + DPU_IRQ_TYPE_HIST_DSPP_DONE, + DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, + DPU_IRQ_TYPE_WD_TIMER, + DPU_IRQ_TYPE_SFI_VIDEO_IN, + DPU_IRQ_TYPE_SFI_VIDEO_OUT, + DPU_IRQ_TYPE_SFI_CMD_0_IN, + DPU_IRQ_TYPE_SFI_CMD_0_OUT, + DPU_IRQ_TYPE_SFI_CMD_1_IN, + DPU_IRQ_TYPE_SFI_CMD_1_OUT, + DPU_IRQ_TYPE_SFI_CMD_2_IN, + DPU_IRQ_TYPE_SFI_CMD_2_OUT, + DPU_IRQ_TYPE_PROG_LINE, + DPU_IRQ_TYPE_AD4_BL_DONE, + DPU_IRQ_TYPE_CTL_START, + DPU_IRQ_TYPE_RESERVED, +}; + +struct dpu_hw_intr; + +/** + * Interrupt operations. + */ +struct dpu_hw_intr_ops { + /** + * set_mask - Programs the given interrupt register with the + * given interrupt mask. Register value will get overwritten. + * @intr: HW interrupt handle + * @reg_off: MDSS HW register offset + * @irqmask: IRQ mask value + */ + void (*set_mask)( + struct dpu_hw_intr *intr, + uint32_t reg, + uint32_t irqmask); + + /** + * irq_idx_lookup - Lookup IRQ index on the HW interrupt type + * Used for all irq related ops + * @intr_type: Interrupt type defined in dpu_intr_type + * @instance_idx: HW interrupt block instance + * @return: irq_idx or -EINVAL for lookup fail + */ + int (*irq_idx_lookup)( + enum dpu_intr_type intr_type, + u32 instance_idx); + + /** + * enable_irq - Enable IRQ based on lookup IRQ index + * @intr: HW interrupt handle + * @irq_idx: Lookup irq index return from irq_idx_lookup + * @return: 0 for success, otherwise failure + */ + int (*enable_irq)( + struct dpu_hw_intr *intr, + int irq_idx); + + /** + * disable_irq - Disable IRQ based on lookup IRQ index + * @intr: HW interrupt handle + * @irq_idx: Lookup irq index return from irq_idx_lookup + * @return: 0 for success, otherwise failure + */ + int (*disable_irq)( + struct dpu_hw_intr *intr, + int irq_idx); + + /** + * clear_all_irqs - Clears all the interrupts (i.e. acknowledges + * any asserted IRQs). Useful during reset. + * @intr: HW interrupt handle + * @return: 0 for success, otherwise failure + */ + int (*clear_all_irqs)( + struct dpu_hw_intr *intr); + + /** + * disable_all_irqs - Disables all the interrupts. Useful during reset. + * @intr: HW interrupt handle + * @return: 0 for success, otherwise failure + */ + int (*disable_all_irqs)( + struct dpu_hw_intr *intr); + + /** + * dispatch_irqs - IRQ dispatcher will call the given callback + * function when a matching interrupt status bit is + * found in the irq mapping table. + * @intr: HW interrupt handle + * @cbfunc: Callback function pointer + * @arg: Argument to pass back during callback + */ + void (*dispatch_irqs)( + struct dpu_hw_intr *intr, + void (*cbfunc)(void *arg, int irq_idx), + void *arg); + + /** + * get_interrupt_statuses - Gets and store value from all interrupt + * status registers that are currently fired. + * @intr: HW interrupt handle + */ + void (*get_interrupt_statuses)( + struct dpu_hw_intr *intr); + + /** + * clear_interrupt_status - Clears HW interrupt status based on given + * lookup IRQ index. + * @intr: HW interrupt handle + * @irq_idx: Lookup irq index return from irq_idx_lookup + */ + void (*clear_interrupt_status)( + struct dpu_hw_intr *intr, + int irq_idx); + + /** + * clear_intr_status_nolock() - clears the HW interrupts without lock + * @intr: HW interrupt handle + * @irq_idx: Lookup irq index return from irq_idx_lookup + */ + void (*clear_intr_status_nolock)( + struct dpu_hw_intr *intr, + int irq_idx); + + /** + * get_interrupt_status - Gets HW interrupt status, and clear if set, + * based on given lookup IRQ index. + * @intr: HW interrupt handle + * @irq_idx: Lookup irq index return from irq_idx_lookup + * @clear: True to clear irq after read + */ + u32 (*get_interrupt_status)( + struct dpu_hw_intr *intr, + int irq_idx, + bool clear); + + /** + * get_valid_interrupts - Gets a mask of all valid interrupt sources + * within DPU. These are actually status bits + * within interrupt registers that specify the + * source of the interrupt in IRQs. For example, + * valid interrupt sources can be MDP, DSI, + * HDMI etc. + * @intr: HW interrupt handle + * @mask: Returning the interrupt source MASK + * @return: 0 for success, otherwise failure + */ + int (*get_valid_interrupts)( + struct dpu_hw_intr *intr, + uint32_t *mask); +}; + +/** + * struct dpu_hw_intr: hw interrupts handling data structure + * @hw: virtual address mapping + * @ops: function pointer mapping for IRQ handling + * @cache_irq_mask: array of IRQ enable masks reg storage created during init + * @save_irq_status: array of IRQ status reg storage created during init + * @irq_idx_tbl_size: total number of irq_idx mapped in the hw_interrupts + * @irq_lock: spinlock for accessing IRQ resources + */ +struct dpu_hw_intr { + struct dpu_hw_blk_reg_map hw; + struct dpu_hw_intr_ops ops; + u32 *cache_irq_mask; + u32 *save_irq_status; + u32 irq_idx_tbl_size; + spinlock_t irq_lock; +}; + +/** + * dpu_hw_intr_init(): Initializes the interrupts hw object + * @addr: mapped register io address of MDP + * @m : pointer to mdss catalog data + */ +struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, + struct dpu_mdss_cfg *m); + +/** + * dpu_hw_intr_destroy(): Cleanup interrutps hw object + * @intr: pointer to interrupts hw object + */ +void dpu_hw_intr_destroy(struct dpu_hw_intr *intr); +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c new file mode 100644 index 000000000000..d280df5613c9 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -0,0 +1,349 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_intf.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define INTF_TIMING_ENGINE_EN 0x000 +#define INTF_CONFIG 0x004 +#define INTF_HSYNC_CTL 0x008 +#define INTF_VSYNC_PERIOD_F0 0x00C +#define INTF_VSYNC_PERIOD_F1 0x010 +#define INTF_VSYNC_PULSE_WIDTH_F0 0x014 +#define INTF_VSYNC_PULSE_WIDTH_F1 0x018 +#define INTF_DISPLAY_V_START_F0 0x01C +#define INTF_DISPLAY_V_START_F1 0x020 +#define INTF_DISPLAY_V_END_F0 0x024 +#define INTF_DISPLAY_V_END_F1 0x028 +#define INTF_ACTIVE_V_START_F0 0x02C +#define INTF_ACTIVE_V_START_F1 0x030 +#define INTF_ACTIVE_V_END_F0 0x034 +#define INTF_ACTIVE_V_END_F1 0x038 +#define INTF_DISPLAY_HCTL 0x03C +#define INTF_ACTIVE_HCTL 0x040 +#define INTF_BORDER_COLOR 0x044 +#define INTF_UNDERFLOW_COLOR 0x048 +#define INTF_HSYNC_SKEW 0x04C +#define INTF_POLARITY_CTL 0x050 +#define INTF_TEST_CTL 0x054 +#define INTF_TP_COLOR0 0x058 +#define INTF_TP_COLOR1 0x05C +#define INTF_FRAME_LINE_COUNT_EN 0x0A8 +#define INTF_FRAME_COUNT 0x0AC +#define INTF_LINE_COUNT 0x0B0 + +#define INTF_DEFLICKER_CONFIG 0x0F0 +#define INTF_DEFLICKER_STRNG_COEFF 0x0F4 +#define INTF_DEFLICKER_WEAK_COEFF 0x0F8 + +#define INTF_DSI_CMD_MODE_TRIGGER_EN 0x084 +#define INTF_PANEL_FORMAT 0x090 +#define INTF_TPG_ENABLE 0x100 +#define INTF_TPG_MAIN_CONTROL 0x104 +#define INTF_TPG_VIDEO_CONFIG 0x108 +#define INTF_TPG_COMPONENT_LIMITS 0x10C +#define INTF_TPG_RECTANGLE 0x110 +#define INTF_TPG_INITIAL_VALUE 0x114 +#define INTF_TPG_BLK_WHITE_PATTERN_FRAMES 0x118 +#define INTF_TPG_RGB_MAPPING 0x11C +#define INTF_PROG_FETCH_START 0x170 +#define INTF_PROG_ROT_START 0x174 + +#define INTF_FRAME_LINE_COUNT_EN 0x0A8 +#define INTF_FRAME_COUNT 0x0AC +#define INTF_LINE_COUNT 0x0B0 + +#define INTF_MISR_CTRL 0x180 +#define INTF_MISR_SIGNATURE 0x184 + +static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf, + struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->intf_count; i++) { + if ((intf == m->intf[i].id) && + (m->intf[i].type != INTF_NONE)) { + b->base_off = addr; + b->blk_off = m->intf[i].base; + b->length = m->intf[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_INTF; + return &m->intf[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, + const struct intf_timing_params *p, + const struct dpu_format *fmt) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 hsync_period, vsync_period; + u32 display_v_start, display_v_end; + u32 hsync_start_x, hsync_end_x; + u32 active_h_start, active_h_end; + u32 active_v_start, active_v_end; + u32 active_hctl, display_hctl, hsync_ctl; + u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity; + u32 panel_format; + u32 intf_cfg; + + /* read interface_cfg */ + intf_cfg = DPU_REG_READ(c, INTF_CONFIG); + hsync_period = p->hsync_pulse_width + p->h_back_porch + p->width + + p->h_front_porch; + vsync_period = p->vsync_pulse_width + p->v_back_porch + p->height + + p->v_front_porch; + + display_v_start = ((p->vsync_pulse_width + p->v_back_porch) * + hsync_period) + p->hsync_skew; + display_v_end = ((vsync_period - p->v_front_porch) * hsync_period) + + p->hsync_skew - 1; + + if (ctx->cap->type == INTF_EDP || ctx->cap->type == INTF_DP) { + display_v_start += p->hsync_pulse_width + p->h_back_porch; + display_v_end -= p->h_front_porch; + } + + hsync_start_x = p->h_back_porch + p->hsync_pulse_width; + hsync_end_x = hsync_period - p->h_front_porch - 1; + + if (p->width != p->xres) { + active_h_start = hsync_start_x; + active_h_end = active_h_start + p->xres - 1; + } else { + active_h_start = 0; + active_h_end = 0; + } + + if (p->height != p->yres) { + active_v_start = display_v_start; + active_v_end = active_v_start + (p->yres * hsync_period) - 1; + } else { + active_v_start = 0; + active_v_end = 0; + } + + if (active_h_end) { + active_hctl = (active_h_end << 16) | active_h_start; + intf_cfg |= BIT(29); /* ACTIVE_H_ENABLE */ + } else { + active_hctl = 0; + } + + if (active_v_end) + intf_cfg |= BIT(30); /* ACTIVE_V_ENABLE */ + + hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width; + display_hctl = (hsync_end_x << 16) | hsync_start_x; + + den_polarity = 0; + if (ctx->cap->type == INTF_HDMI) { + hsync_polarity = p->yres >= 720 ? 0 : 1; + vsync_polarity = p->yres >= 720 ? 0 : 1; + } else { + hsync_polarity = 0; + vsync_polarity = 0; + } + polarity_ctl = (den_polarity << 2) | /* DEN Polarity */ + (vsync_polarity << 1) | /* VSYNC Polarity */ + (hsync_polarity << 0); /* HSYNC Polarity */ + + if (!DPU_FORMAT_IS_YUV(fmt)) + panel_format = (fmt->bits[C0_G_Y] | + (fmt->bits[C1_B_Cb] << 2) | + (fmt->bits[C2_R_Cr] << 4) | + (0x21 << 8)); + else + /* Interface treats all the pixel data in RGB888 format */ + panel_format = (COLOR_8BIT | + (COLOR_8BIT << 2) | + (COLOR_8BIT << 4) | + (0x21 << 8)); + + DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl); + DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period); + DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0, + p->vsync_pulse_width * hsync_period); + DPU_REG_WRITE(c, INTF_DISPLAY_HCTL, display_hctl); + DPU_REG_WRITE(c, INTF_DISPLAY_V_START_F0, display_v_start); + DPU_REG_WRITE(c, INTF_DISPLAY_V_END_F0, display_v_end); + DPU_REG_WRITE(c, INTF_ACTIVE_HCTL, active_hctl); + DPU_REG_WRITE(c, INTF_ACTIVE_V_START_F0, active_v_start); + DPU_REG_WRITE(c, INTF_ACTIVE_V_END_F0, active_v_end); + DPU_REG_WRITE(c, INTF_BORDER_COLOR, p->border_clr); + DPU_REG_WRITE(c, INTF_UNDERFLOW_COLOR, p->underflow_clr); + DPU_REG_WRITE(c, INTF_HSYNC_SKEW, p->hsync_skew); + DPU_REG_WRITE(c, INTF_POLARITY_CTL, polarity_ctl); + DPU_REG_WRITE(c, INTF_FRAME_LINE_COUNT_EN, 0x3); + DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg); + DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format); +} + +static void dpu_hw_intf_enable_timing_engine( + struct dpu_hw_intf *intf, + u8 enable) +{ + struct dpu_hw_blk_reg_map *c = &intf->hw; + /* Note: Display interface select is handled in top block hw layer */ + DPU_REG_WRITE(c, INTF_TIMING_ENGINE_EN, enable != 0); +} + +static void dpu_hw_intf_setup_prg_fetch( + struct dpu_hw_intf *intf, + const struct intf_prog_fetch *fetch) +{ + struct dpu_hw_blk_reg_map *c = &intf->hw; + int fetch_enable; + + /* + * Fetch should always be outside the active lines. If the fetching + * is programmed within active region, hardware behavior is unknown. + */ + + fetch_enable = DPU_REG_READ(c, INTF_CONFIG); + if (fetch->enable) { + fetch_enable |= BIT(31); + DPU_REG_WRITE(c, INTF_PROG_FETCH_START, + fetch->fetch_start); + } else { + fetch_enable &= ~BIT(31); + } + + DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable); +} + +static void dpu_hw_intf_get_status( + struct dpu_hw_intf *intf, + struct intf_status *s) +{ + struct dpu_hw_blk_reg_map *c = &intf->hw; + + s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN); + if (s->is_en) { + s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT); + s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT); + } else { + s->line_count = 0; + s->frame_count = 0; + } +} + +static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf, + bool enable, u32 frame_count) +{ + struct dpu_hw_blk_reg_map *c = &intf->hw; + u32 config = 0; + + DPU_REG_WRITE(c, INTF_MISR_CTRL, MISR_CTRL_STATUS_CLEAR); + /* clear misr data */ + wmb(); + + if (enable) + config = (frame_count & MISR_FRAME_COUNT_MASK) | + MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK; + + DPU_REG_WRITE(c, INTF_MISR_CTRL, config); +} + +static u32 dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf) +{ + struct dpu_hw_blk_reg_map *c = &intf->hw; + + return DPU_REG_READ(c, INTF_MISR_SIGNATURE); +} + +static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf) +{ + struct dpu_hw_blk_reg_map *c; + + if (!intf) + return 0; + + c = &intf->hw; + + return DPU_REG_READ(c, INTF_LINE_COUNT); +} + +static void _setup_intf_ops(struct dpu_hw_intf_ops *ops, + unsigned long cap) +{ + ops->setup_timing_gen = dpu_hw_intf_setup_timing_engine; + ops->setup_prg_fetch = dpu_hw_intf_setup_prg_fetch; + ops->get_status = dpu_hw_intf_get_status; + ops->enable_timing = dpu_hw_intf_enable_timing_engine; + ops->setup_misr = dpu_hw_intf_setup_misr; + ops->collect_misr = dpu_hw_intf_collect_misr; + ops->get_line_count = dpu_hw_intf_get_line_count; +} + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx, + void __iomem *addr, + struct dpu_mdss_cfg *m) +{ + struct dpu_hw_intf *c; + struct dpu_intf_cfg *cfg; + int rc; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _intf_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + pr_err("failed to create dpu_hw_intf %d\n", idx); + return ERR_PTR(-EINVAL); + } + + /* + * Assign ops + */ + c->idx = idx; + c->cap = cfg; + c->mdss = m; + _setup_intf_ops(&c->ops, c->cap->features); + + rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + return c; + +blk_init_error: + kzfree(c); + + return ERR_PTR(rc); +} + +void dpu_hw_intf_destroy(struct dpu_hw_intf *intf) +{ + if (intf) + dpu_hw_blk_destroy(&intf->base); + kfree(intf); +} + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h new file mode 100644 index 000000000000..a79d735da68d --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -0,0 +1,128 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_INTF_H +#define _DPU_HW_INTF_H + +#include "dpu_hw_catalog.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_blk.h" + +struct dpu_hw_intf; + +/* intf timing settings */ +struct intf_timing_params { + u32 width; /* active width */ + u32 height; /* active height */ + u32 xres; /* Display panel width */ + u32 yres; /* Display panel height */ + + u32 h_back_porch; + u32 h_front_porch; + u32 v_back_porch; + u32 v_front_porch; + u32 hsync_pulse_width; + u32 vsync_pulse_width; + u32 hsync_polarity; + u32 vsync_polarity; + u32 border_clr; + u32 underflow_clr; + u32 hsync_skew; +}; + +struct intf_prog_fetch { + u8 enable; + /* vsync counter for the front porch pixel line */ + u32 fetch_start; +}; + +struct intf_status { + u8 is_en; /* interface timing engine is enabled or not */ + u32 frame_count; /* frame count since timing engine enabled */ + u32 line_count; /* current line count including blanking */ +}; + +/** + * struct dpu_hw_intf_ops : Interface to the interface Hw driver functions + * Assumption is these functions will be called after clocks are enabled + * @ setup_timing_gen : programs the timing engine + * @ setup_prog_fetch : enables/disables the programmable fetch logic + * @ enable_timing: enable/disable timing engine + * @ get_status: returns if timing engine is enabled or not + * @ setup_misr: enables/disables MISR in HW register + * @ collect_misr: reads and stores MISR data from HW register + * @ get_line_count: reads current vertical line counter + */ +struct dpu_hw_intf_ops { + void (*setup_timing_gen)(struct dpu_hw_intf *intf, + const struct intf_timing_params *p, + const struct dpu_format *fmt); + + void (*setup_prg_fetch)(struct dpu_hw_intf *intf, + const struct intf_prog_fetch *fetch); + + void (*enable_timing)(struct dpu_hw_intf *intf, + u8 enable); + + void (*get_status)(struct dpu_hw_intf *intf, + struct intf_status *status); + + void (*setup_misr)(struct dpu_hw_intf *intf, + bool enable, u32 frame_count); + + u32 (*collect_misr)(struct dpu_hw_intf *intf); + + u32 (*get_line_count)(struct dpu_hw_intf *intf); +}; + +struct dpu_hw_intf { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* intf */ + enum dpu_intf idx; + const struct dpu_intf_cfg *cap; + const struct dpu_mdss_cfg *mdss; + + /* ops */ + struct dpu_hw_intf_ops ops; +}; + +/** + * to_dpu_hw_intf - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_intf, base); +} + +/** + * dpu_hw_intf_init(): Initializes the intf driver for the passed + * interface idx. + * @idx: interface index for which driver object is required + * @addr: mapped register io address of MDP + * @m : pointer to mdss catalog data + */ +struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx, + void __iomem *addr, + struct dpu_mdss_cfg *m); + +/** + * dpu_hw_intf_destroy(): Destroys INTF driver context + * @intf: Pointer to INTF driver context + */ +void dpu_hw_intf_destroy(struct dpu_hw_intf *intf); + +#endif /*_DPU_HW_INTF_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c new file mode 100644 index 000000000000..4ab72b0f07a5 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c @@ -0,0 +1,261 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_kms.h" +#include "dpu_hw_catalog.h" +#include "dpu_hwio.h" +#include "dpu_hw_lm.h" +#include "dpu_hw_mdss.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define LM_OP_MODE 0x00 +#define LM_OUT_SIZE 0x04 +#define LM_BORDER_COLOR_0 0x08 +#define LM_BORDER_COLOR_1 0x010 + +/* These register are offset to mixer base + stage base */ +#define LM_BLEND0_OP 0x00 +#define LM_BLEND0_CONST_ALPHA 0x04 +#define LM_FG_COLOR_FILL_COLOR_0 0x08 +#define LM_FG_COLOR_FILL_COLOR_1 0x0C +#define LM_FG_COLOR_FILL_SIZE 0x10 +#define LM_FG_COLOR_FILL_XY 0x14 + +#define LM_BLEND0_FG_ALPHA 0x04 +#define LM_BLEND0_BG_ALPHA 0x08 + +#define LM_MISR_CTRL 0x310 +#define LM_MISR_SIGNATURE 0x314 + +static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer, + struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->mixer_count; i++) { + if (mixer == m->mixer[i].id) { + b->base_off = addr; + b->blk_off = m->mixer[i].base; + b->length = m->mixer[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_LM; + return &m->mixer[i]; + } + } + + return ERR_PTR(-ENOMEM); +} + +/** + * _stage_offset(): returns the relative offset of the blend registers + * for the stage to be setup + * @c: mixer ctx contains the mixer to be programmed + * @stage: stage index to setup + */ +static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage) +{ + const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk; + int rc; + + if (stage == DPU_STAGE_BASE) + rc = -EINVAL; + else if (stage <= sblk->maxblendstages) + rc = sblk->blendstage_base[stage - DPU_STAGE_0]; + else + rc = -EINVAL; + + return rc; +} + +static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx, + struct dpu_hw_mixer_cfg *mixer) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 outsize; + u32 op_mode; + + op_mode = DPU_REG_READ(c, LM_OP_MODE); + + outsize = mixer->out_height << 16 | mixer->out_width; + DPU_REG_WRITE(c, LM_OUT_SIZE, outsize); + + /* SPLIT_LEFT_RIGHT */ + if (mixer->right_mixer) + op_mode |= BIT(31); + else + op_mode &= ~BIT(31); + DPU_REG_WRITE(c, LM_OP_MODE, op_mode); +} + +static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx, + struct dpu_mdss_color *color, + u8 border_en) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + + if (border_en) { + DPU_REG_WRITE(c, LM_BORDER_COLOR_0, + (color->color_0 & 0xFFF) | + ((color->color_1 & 0xFFF) << 0x10)); + DPU_REG_WRITE(c, LM_BORDER_COLOR_1, + (color->color_2 & 0xFFF) | + ((color->color_3 & 0xFFF) << 0x10)); + } +} + +static void dpu_hw_lm_setup_blend_config_sdm845(struct dpu_hw_mixer *ctx, + u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int stage_off; + u32 const_alpha; + + if (stage == DPU_STAGE_BASE) + return; + + stage_off = _stage_offset(ctx, stage); + if (WARN_ON(stage_off < 0)) + return; + + const_alpha = (bg_alpha & 0xFF) | ((fg_alpha & 0xFF) << 16); + DPU_REG_WRITE(c, LM_BLEND0_CONST_ALPHA + stage_off, const_alpha); + DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op); +} + +static void dpu_hw_lm_setup_blend_config(struct dpu_hw_mixer *ctx, + u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int stage_off; + + if (stage == DPU_STAGE_BASE) + return; + + stage_off = _stage_offset(ctx, stage); + if (WARN_ON(stage_off < 0)) + return; + + DPU_REG_WRITE(c, LM_BLEND0_FG_ALPHA + stage_off, fg_alpha); + DPU_REG_WRITE(c, LM_BLEND0_BG_ALPHA + stage_off, bg_alpha); + DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op); +} + +static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx, + uint32_t mixer_op_mode) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int op_mode; + + /* read the existing op_mode configuration */ + op_mode = DPU_REG_READ(c, LM_OP_MODE); + + op_mode = (op_mode & (BIT(31) | BIT(30))) | mixer_op_mode; + + DPU_REG_WRITE(c, LM_OP_MODE, op_mode); +} + +static void dpu_hw_lm_gc(struct dpu_hw_mixer *mixer, + void *cfg) +{ +} + +static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx, + bool enable, u32 frame_count) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + u32 config = 0; + + DPU_REG_WRITE(c, LM_MISR_CTRL, MISR_CTRL_STATUS_CLEAR); + /* clear misr data */ + wmb(); + + if (enable) + config = (frame_count & MISR_FRAME_COUNT_MASK) | + MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK; + + DPU_REG_WRITE(c, LM_MISR_CTRL, config); +} + +static u32 dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + + return DPU_REG_READ(c, LM_MISR_SIGNATURE); +} + +static void _setup_mixer_ops(struct dpu_mdss_cfg *m, + struct dpu_hw_lm_ops *ops, + unsigned long features) +{ + ops->setup_mixer_out = dpu_hw_lm_setup_out; + if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion)) + ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845; + else + ops->setup_blend_config = dpu_hw_lm_setup_blend_config; + ops->setup_alpha_out = dpu_hw_lm_setup_color3; + ops->setup_border_color = dpu_hw_lm_setup_border_color; + ops->setup_gc = dpu_hw_lm_gc; + ops->setup_misr = dpu_hw_lm_setup_misr; + ops->collect_misr = dpu_hw_lm_collect_misr; +}; + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx, + void __iomem *addr, + struct dpu_mdss_cfg *m) +{ + struct dpu_hw_mixer *c; + struct dpu_lm_cfg *cfg; + int rc; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _lm_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + return ERR_PTR(-EINVAL); + } + + /* Assign ops */ + c->idx = idx; + c->cap = cfg; + _setup_mixer_ops(m, &c->ops, c->cap->features); + + rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + return c; + +blk_init_error: + kzfree(c); + + return ERR_PTR(rc); +} + +void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm) +{ + if (lm) + dpu_hw_blk_destroy(&lm->base); + kfree(lm); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h new file mode 100644 index 000000000000..e29e5dab31bf --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h @@ -0,0 +1,122 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_LM_H +#define _DPU_HW_LM_H + +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_blk.h" + +struct dpu_hw_mixer; + +struct dpu_hw_mixer_cfg { + u32 out_width; + u32 out_height; + bool right_mixer; + int flags; +}; + +struct dpu_hw_color3_cfg { + u8 keep_fg[DPU_STAGE_MAX]; +}; + +/** + * + * struct dpu_hw_lm_ops : Interface to the mixer Hw driver functions + * Assumption is these functions will be called after clocks are enabled + */ +struct dpu_hw_lm_ops { + /* + * Sets up mixer output width and height + * and border color if enabled + */ + void (*setup_mixer_out)(struct dpu_hw_mixer *ctx, + struct dpu_hw_mixer_cfg *cfg); + + /* + * Alpha blending configuration + * for the specified stage + */ + void (*setup_blend_config)(struct dpu_hw_mixer *ctx, uint32_t stage, + uint32_t fg_alpha, uint32_t bg_alpha, uint32_t blend_op); + + /* + * Alpha color component selection from either fg or bg + */ + void (*setup_alpha_out)(struct dpu_hw_mixer *ctx, uint32_t mixer_op); + + /** + * setup_border_color : enable/disable border color + */ + void (*setup_border_color)(struct dpu_hw_mixer *ctx, + struct dpu_mdss_color *color, + u8 border_en); + /** + * setup_gc : enable/disable gamma correction feature + */ + void (*setup_gc)(struct dpu_hw_mixer *mixer, + void *cfg); + + /* setup_misr: enables/disables MISR in HW register */ + void (*setup_misr)(struct dpu_hw_mixer *ctx, + bool enable, u32 frame_count); + + /* collect_misr: reads and stores MISR data from HW register */ + u32 (*collect_misr)(struct dpu_hw_mixer *ctx); +}; + +struct dpu_hw_mixer { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* lm */ + enum dpu_lm idx; + const struct dpu_lm_cfg *cap; + const struct dpu_mdp_cfg *mdp; + const struct dpu_ctl_cfg *ctl; + + /* ops */ + struct dpu_hw_lm_ops ops; + + /* store mixer info specific to display */ + struct dpu_hw_mixer_cfg cfg; +}; + +/** + * to_dpu_hw_mixer - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_mixer, base); +} + +/** + * dpu_hw_lm_init(): Initializes the mixer hw driver object. + * should be called once before accessing every mixer. + * @idx: mixer index for which driver object is required + * @addr: mapped register io address of MDP + * @m : pointer to mdss catalog data + */ +struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx, + void __iomem *addr, + struct dpu_mdss_cfg *m); + +/** + * dpu_hw_lm_destroy(): Destroys layer mixer driver context + * @lm: Pointer to LM driver context + */ +void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm); + +#endif /*_DPU_HW_LM_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h new file mode 100644 index 000000000000..35e6bf930924 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -0,0 +1,465 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_MDSS_H +#define _DPU_HW_MDSS_H + +#include <linux/kernel.h> +#include <linux/err.h> + +#include "msm_drv.h" + +#define DPU_DBG_NAME "dpu" + +#define DPU_NONE 0 + +#ifndef DPU_CSC_MATRIX_COEFF_SIZE +#define DPU_CSC_MATRIX_COEFF_SIZE 9 +#endif + +#ifndef DPU_CSC_CLAMP_SIZE +#define DPU_CSC_CLAMP_SIZE 6 +#endif + +#ifndef DPU_CSC_BIAS_SIZE +#define DPU_CSC_BIAS_SIZE 3 +#endif + +#ifndef DPU_MAX_PLANES +#define DPU_MAX_PLANES 4 +#endif + +#define PIPES_PER_STAGE 2 +#ifndef DPU_MAX_DE_CURVES +#define DPU_MAX_DE_CURVES 3 +#endif + +enum dpu_format_flags { + DPU_FORMAT_FLAG_YUV_BIT, + DPU_FORMAT_FLAG_DX_BIT, + DPU_FORMAT_FLAG_COMPRESSED_BIT, + DPU_FORMAT_FLAG_BIT_MAX, +}; + +#define DPU_FORMAT_FLAG_YUV BIT(DPU_FORMAT_FLAG_YUV_BIT) +#define DPU_FORMAT_FLAG_DX BIT(DPU_FORMAT_FLAG_DX_BIT) +#define DPU_FORMAT_FLAG_COMPRESSED BIT(DPU_FORMAT_FLAG_COMPRESSED_BIT) +#define DPU_FORMAT_IS_YUV(X) \ + (test_bit(DPU_FORMAT_FLAG_YUV_BIT, (X)->flag)) +#define DPU_FORMAT_IS_DX(X) \ + (test_bit(DPU_FORMAT_FLAG_DX_BIT, (X)->flag)) +#define DPU_FORMAT_IS_LINEAR(X) ((X)->fetch_mode == DPU_FETCH_LINEAR) +#define DPU_FORMAT_IS_TILE(X) \ + (((X)->fetch_mode == DPU_FETCH_UBWC) && \ + !test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag)) +#define DPU_FORMAT_IS_UBWC(X) \ + (((X)->fetch_mode == DPU_FETCH_UBWC) && \ + test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag)) + +#define DPU_BLEND_FG_ALPHA_FG_CONST (0 << 0) +#define DPU_BLEND_FG_ALPHA_BG_CONST (1 << 0) +#define DPU_BLEND_FG_ALPHA_FG_PIXEL (2 << 0) +#define DPU_BLEND_FG_ALPHA_BG_PIXEL (3 << 0) +#define DPU_BLEND_FG_INV_ALPHA (1 << 2) +#define DPU_BLEND_FG_MOD_ALPHA (1 << 3) +#define DPU_BLEND_FG_INV_MOD_ALPHA (1 << 4) +#define DPU_BLEND_FG_TRANSP_EN (1 << 5) +#define DPU_BLEND_BG_ALPHA_FG_CONST (0 << 8) +#define DPU_BLEND_BG_ALPHA_BG_CONST (1 << 8) +#define DPU_BLEND_BG_ALPHA_FG_PIXEL (2 << 8) +#define DPU_BLEND_BG_ALPHA_BG_PIXEL (3 << 8) +#define DPU_BLEND_BG_INV_ALPHA (1 << 10) +#define DPU_BLEND_BG_MOD_ALPHA (1 << 11) +#define DPU_BLEND_BG_INV_MOD_ALPHA (1 << 12) +#define DPU_BLEND_BG_TRANSP_EN (1 << 13) + +#define DPU_VSYNC0_SOURCE_GPIO 0 +#define DPU_VSYNC1_SOURCE_GPIO 1 +#define DPU_VSYNC2_SOURCE_GPIO 2 +#define DPU_VSYNC_SOURCE_INTF_0 3 +#define DPU_VSYNC_SOURCE_INTF_1 4 +#define DPU_VSYNC_SOURCE_INTF_2 5 +#define DPU_VSYNC_SOURCE_INTF_3 6 +#define DPU_VSYNC_SOURCE_WD_TIMER_4 11 +#define DPU_VSYNC_SOURCE_WD_TIMER_3 12 +#define DPU_VSYNC_SOURCE_WD_TIMER_2 13 +#define DPU_VSYNC_SOURCE_WD_TIMER_1 14 +#define DPU_VSYNC_SOURCE_WD_TIMER_0 15 + +enum dpu_hw_blk_type { + DPU_HW_BLK_TOP = 0, + DPU_HW_BLK_SSPP, + DPU_HW_BLK_LM, + DPU_HW_BLK_CTL, + DPU_HW_BLK_CDM, + DPU_HW_BLK_PINGPONG, + DPU_HW_BLK_INTF, + DPU_HW_BLK_WB, + DPU_HW_BLK_MAX, +}; + +enum dpu_mdp { + MDP_TOP = 0x1, + MDP_MAX, +}; + +enum dpu_sspp { + SSPP_NONE, + SSPP_VIG0, + SSPP_VIG1, + SSPP_VIG2, + SSPP_VIG3, + SSPP_RGB0, + SSPP_RGB1, + SSPP_RGB2, + SSPP_RGB3, + SSPP_DMA0, + SSPP_DMA1, + SSPP_DMA2, + SSPP_DMA3, + SSPP_CURSOR0, + SSPP_CURSOR1, + SSPP_MAX +}; + +enum dpu_sspp_type { + SSPP_TYPE_VIG, + SSPP_TYPE_RGB, + SSPP_TYPE_DMA, + SSPP_TYPE_CURSOR, + SSPP_TYPE_MAX +}; + +enum dpu_lm { + LM_0 = 1, + LM_1, + LM_2, + LM_3, + LM_4, + LM_5, + LM_6, + LM_MAX +}; + +enum dpu_stage { + DPU_STAGE_BASE = 0, + DPU_STAGE_0, + DPU_STAGE_1, + DPU_STAGE_2, + DPU_STAGE_3, + DPU_STAGE_4, + DPU_STAGE_5, + DPU_STAGE_6, + DPU_STAGE_7, + DPU_STAGE_8, + DPU_STAGE_9, + DPU_STAGE_10, + DPU_STAGE_MAX +}; +enum dpu_dspp { + DSPP_0 = 1, + DSPP_1, + DSPP_2, + DSPP_3, + DSPP_MAX +}; + +enum dpu_ds { + DS_TOP, + DS_0, + DS_1, + DS_MAX +}; + +enum dpu_ctl { + CTL_0 = 1, + CTL_1, + CTL_2, + CTL_3, + CTL_4, + CTL_MAX +}; + +enum dpu_cdm { + CDM_0 = 1, + CDM_1, + CDM_MAX +}; + +enum dpu_pingpong { + PINGPONG_0 = 1, + PINGPONG_1, + PINGPONG_2, + PINGPONG_3, + PINGPONG_4, + PINGPONG_S0, + PINGPONG_MAX +}; + +enum dpu_intf { + INTF_0 = 1, + INTF_1, + INTF_2, + INTF_3, + INTF_4, + INTF_5, + INTF_6, + INTF_MAX +}; + +enum dpu_intf_type { + INTF_NONE = 0x0, + INTF_DSI = 0x1, + INTF_HDMI = 0x3, + INTF_LCDC = 0x5, + INTF_EDP = 0x9, + INTF_DP = 0xa, + INTF_TYPE_MAX, + + /* virtual interfaces */ + INTF_WB = 0x100, +}; + +enum dpu_intf_mode { + INTF_MODE_NONE = 0, + INTF_MODE_CMD, + INTF_MODE_VIDEO, + INTF_MODE_WB_BLOCK, + INTF_MODE_WB_LINE, + INTF_MODE_MAX +}; + +enum dpu_wb { + WB_0 = 1, + WB_1, + WB_2, + WB_3, + WB_MAX +}; + +enum dpu_ad { + AD_0 = 0x1, + AD_1, + AD_MAX +}; + +enum dpu_cwb { + CWB_0 = 0x1, + CWB_1, + CWB_2, + CWB_3, + CWB_MAX +}; + +enum dpu_wd_timer { + WD_TIMER_0 = 0x1, + WD_TIMER_1, + WD_TIMER_2, + WD_TIMER_3, + WD_TIMER_4, + WD_TIMER_5, + WD_TIMER_MAX +}; + +enum dpu_vbif { + VBIF_0, + VBIF_1, + VBIF_MAX, + VBIF_RT = VBIF_0, + VBIF_NRT = VBIF_1 +}; + +enum dpu_iommu_domain { + DPU_IOMMU_DOMAIN_UNSECURE, + DPU_IOMMU_DOMAIN_SECURE, + DPU_IOMMU_DOMAIN_MAX +}; + +/** + * DPU HW,Component order color map + */ +enum { + C0_G_Y = 0, + C1_B_Cb = 1, + C2_R_Cr = 2, + C3_ALPHA = 3 +}; + +/** + * enum dpu_plane_type - defines how the color component pixel packing + * @DPU_PLANE_INTERLEAVED : Color components in single plane + * @DPU_PLANE_PLANAR : Color component in separate planes + * @DPU_PLANE_PSEUDO_PLANAR : Chroma components interleaved in separate plane + */ +enum dpu_plane_type { + DPU_PLANE_INTERLEAVED, + DPU_PLANE_PLANAR, + DPU_PLANE_PSEUDO_PLANAR, +}; + +/** + * enum dpu_chroma_samp_type - chroma sub-samplng type + * @DPU_CHROMA_RGB : No chroma subsampling + * @DPU_CHROMA_H2V1 : Chroma pixels are horizontally subsampled + * @DPU_CHROMA_H1V2 : Chroma pixels are vertically subsampled + * @DPU_CHROMA_420 : 420 subsampling + */ +enum dpu_chroma_samp_type { + DPU_CHROMA_RGB, + DPU_CHROMA_H2V1, + DPU_CHROMA_H1V2, + DPU_CHROMA_420 +}; + +/** + * dpu_fetch_type - Defines How DPU HW fetches data + * @DPU_FETCH_LINEAR : fetch is line by line + * @DPU_FETCH_TILE : fetches data in Z order from a tile + * @DPU_FETCH_UBWC : fetch and decompress data + */ +enum dpu_fetch_type { + DPU_FETCH_LINEAR, + DPU_FETCH_TILE, + DPU_FETCH_UBWC +}; + +/** + * Value of enum chosen to fit the number of bits + * expected by the HW programming. + */ +enum { + COLOR_ALPHA_1BIT = 0, + COLOR_ALPHA_4BIT = 1, + COLOR_4BIT = 0, + COLOR_5BIT = 1, /* No 5-bit Alpha */ + COLOR_6BIT = 2, /* 6-Bit Alpha also = 2 */ + COLOR_8BIT = 3, /* 8-Bit Alpha also = 3 */ +}; + +/** + * enum dpu_3d_blend_mode + * Desribes how the 3d data is blended + * @BLEND_3D_NONE : 3d blending not enabled + * @BLEND_3D_FRAME_INT : Frame interleaving + * @BLEND_3D_H_ROW_INT : Horizontal row interleaving + * @BLEND_3D_V_ROW_INT : vertical row interleaving + * @BLEND_3D_COL_INT : column interleaving + * @BLEND_3D_MAX : + */ +enum dpu_3d_blend_mode { + BLEND_3D_NONE = 0, + BLEND_3D_FRAME_INT, + BLEND_3D_H_ROW_INT, + BLEND_3D_V_ROW_INT, + BLEND_3D_COL_INT, + BLEND_3D_MAX +}; + +/** struct dpu_format - defines the format configuration which + * allows DPU HW to correctly fetch and decode the format + * @base: base msm_format struture containing fourcc code + * @fetch_planes: how the color components are packed in pixel format + * @element: element color ordering + * @bits: element bit widths + * @chroma_sample: chroma sub-samplng type + * @unpack_align_msb: unpack aligned, 0 to LSB, 1 to MSB + * @unpack_tight: 0 for loose, 1 for tight + * @unpack_count: 0 = 1 component, 1 = 2 component + * @bpp: bytes per pixel + * @alpha_enable: whether the format has an alpha channel + * @num_planes: number of planes (including meta data planes) + * @fetch_mode: linear, tiled, or ubwc hw fetch behavior + * @is_yuv: is format a yuv variant + * @flag: usage bit flags + * @tile_width: format tile width + * @tile_height: format tile height + */ +struct dpu_format { + struct msm_format base; + enum dpu_plane_type fetch_planes; + u8 element[DPU_MAX_PLANES]; + u8 bits[DPU_MAX_PLANES]; + enum dpu_chroma_samp_type chroma_sample; + u8 unpack_align_msb; + u8 unpack_tight; + u8 unpack_count; + u8 bpp; + u8 alpha_enable; + u8 num_planes; + enum dpu_fetch_type fetch_mode; + DECLARE_BITMAP(flag, DPU_FORMAT_FLAG_BIT_MAX); + u16 tile_width; + u16 tile_height; +}; +#define to_dpu_format(x) container_of(x, struct dpu_format, base) + +/** + * struct dpu_hw_fmt_layout - format information of the source pixel data + * @format: pixel format parameters + * @num_planes: number of planes (including meta data planes) + * @width: image width + * @height: image height + * @total_size: total size in bytes + * @plane_addr: address of each plane + * @plane_size: length of each plane + * @plane_pitch: pitch of each plane + */ +struct dpu_hw_fmt_layout { + const struct dpu_format *format; + uint32_t num_planes; + uint32_t width; + uint32_t height; + uint32_t total_size; + uint32_t plane_addr[DPU_MAX_PLANES]; + uint32_t plane_size[DPU_MAX_PLANES]; + uint32_t plane_pitch[DPU_MAX_PLANES]; +}; + +struct dpu_csc_cfg { + /* matrix coefficients in S15.16 format */ + uint32_t csc_mv[DPU_CSC_MATRIX_COEFF_SIZE]; + uint32_t csc_pre_bv[DPU_CSC_BIAS_SIZE]; + uint32_t csc_post_bv[DPU_CSC_BIAS_SIZE]; + uint32_t csc_pre_lv[DPU_CSC_CLAMP_SIZE]; + uint32_t csc_post_lv[DPU_CSC_CLAMP_SIZE]; +}; + +/** + * struct dpu_mdss_color - mdss color description + * color 0 : green + * color 1 : blue + * color 2 : red + * color 3 : alpha + */ +struct dpu_mdss_color { + u32 color_0; + u32 color_1; + u32 color_2; + u32 color_3; +}; + +/* + * Define bit masks for h/w logging. + */ +#define DPU_DBG_MASK_NONE (1 << 0) +#define DPU_DBG_MASK_CDM (1 << 1) +#define DPU_DBG_MASK_INTF (1 << 2) +#define DPU_DBG_MASK_LM (1 << 3) +#define DPU_DBG_MASK_CTL (1 << 4) +#define DPU_DBG_MASK_PINGPONG (1 << 5) +#define DPU_DBG_MASK_SSPP (1 << 6) +#define DPU_DBG_MASK_WB (1 << 7) +#define DPU_DBG_MASK_TOP (1 << 8) +#define DPU_DBG_MASK_VBIF (1 << 9) +#define DPU_DBG_MASK_ROT (1 << 10) + +#endif /* _DPU_HW_MDSS_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c new file mode 100644 index 000000000000..cc3a623903f4 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c @@ -0,0 +1,250 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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/iopoll.h> + +#include "dpu_hw_mdss.h" +#include "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_pingpong.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" +#include "dpu_trace.h" + +#define PP_TEAR_CHECK_EN 0x000 +#define PP_SYNC_CONFIG_VSYNC 0x004 +#define PP_SYNC_CONFIG_HEIGHT 0x008 +#define PP_SYNC_WRCOUNT 0x00C +#define PP_VSYNC_INIT_VAL 0x010 +#define PP_INT_COUNT_VAL 0x014 +#define PP_SYNC_THRESH 0x018 +#define PP_START_POS 0x01C +#define PP_RD_PTR_IRQ 0x020 +#define PP_WR_PTR_IRQ 0x024 +#define PP_OUT_LINE_COUNT 0x028 +#define PP_LINE_COUNT 0x02C + +#define PP_FBC_MODE 0x034 +#define PP_FBC_BUDGET_CTL 0x038 +#define PP_FBC_LOSSY_MODE 0x03C + +static struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp, + struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->pingpong_count; i++) { + if (pp == m->pingpong[i].id) { + b->base_off = addr; + b->blk_off = m->pingpong[i].base; + b->length = m->pingpong[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_PINGPONG; + return &m->pingpong[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp, + struct dpu_hw_tear_check *te) +{ + struct dpu_hw_blk_reg_map *c; + int cfg; + + if (!pp || !te) + return -EINVAL; + c = &pp->hw; + + cfg = BIT(19); /*VSYNC_COUNTER_EN */ + if (te->hw_vsync_mode) + cfg |= BIT(20); + + cfg |= te->vsync_count; + + DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg); + DPU_REG_WRITE(c, PP_SYNC_CONFIG_HEIGHT, te->sync_cfg_height); + DPU_REG_WRITE(c, PP_VSYNC_INIT_VAL, te->vsync_init_val); + DPU_REG_WRITE(c, PP_RD_PTR_IRQ, te->rd_ptr_irq); + DPU_REG_WRITE(c, PP_START_POS, te->start_pos); + DPU_REG_WRITE(c, PP_SYNC_THRESH, + ((te->sync_threshold_continue << 16) | + te->sync_threshold_start)); + DPU_REG_WRITE(c, PP_SYNC_WRCOUNT, + (te->start_pos + te->sync_threshold_start + 1)); + + return 0; +} + +static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp, + u32 timeout_us) +{ + struct dpu_hw_blk_reg_map *c; + u32 val; + int rc; + + if (!pp) + return -EINVAL; + + c = &pp->hw; + rc = readl_poll_timeout(c->base_off + c->blk_off + PP_LINE_COUNT, + val, (val & 0xffff) >= 1, 10, timeout_us); + + return rc; +} + +static int dpu_hw_pp_enable_te(struct dpu_hw_pingpong *pp, bool enable) +{ + struct dpu_hw_blk_reg_map *c; + + if (!pp) + return -EINVAL; + c = &pp->hw; + + DPU_REG_WRITE(c, PP_TEAR_CHECK_EN, enable); + return 0; +} + +static int dpu_hw_pp_connect_external_te(struct dpu_hw_pingpong *pp, + bool enable_external_te) +{ + struct dpu_hw_blk_reg_map *c = &pp->hw; + u32 cfg; + int orig; + + if (!pp) + return -EINVAL; + + c = &pp->hw; + cfg = DPU_REG_READ(c, PP_SYNC_CONFIG_VSYNC); + orig = (bool)(cfg & BIT(20)); + if (enable_external_te) + cfg |= BIT(20); + else + cfg &= ~BIT(20); + DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg); + trace_dpu_pp_connect_ext_te(pp->idx - PINGPONG_0, cfg); + + return orig; +} + +static int dpu_hw_pp_get_vsync_info(struct dpu_hw_pingpong *pp, + struct dpu_hw_pp_vsync_info *info) +{ + struct dpu_hw_blk_reg_map *c; + u32 val; + + if (!pp || !info) + return -EINVAL; + c = &pp->hw; + + val = DPU_REG_READ(c, PP_VSYNC_INIT_VAL); + info->rd_ptr_init_val = val & 0xffff; + + val = DPU_REG_READ(c, PP_INT_COUNT_VAL); + info->rd_ptr_frame_count = (val & 0xffff0000) >> 16; + info->rd_ptr_line_count = val & 0xffff; + + val = DPU_REG_READ(c, PP_LINE_COUNT); + info->wr_ptr_line_count = val & 0xffff; + + return 0; +} + +static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp) +{ + struct dpu_hw_blk_reg_map *c = &pp->hw; + u32 height, init; + u32 line = 0xFFFF; + + if (!pp) + return 0; + c = &pp->hw; + + init = DPU_REG_READ(c, PP_VSYNC_INIT_VAL) & 0xFFFF; + height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF; + + if (height < init) + goto line_count_exit; + + line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF; + + if (line < init) + line += (0xFFFF - init); + else + line -= init; + +line_count_exit: + return line; +} + +static void _setup_pingpong_ops(struct dpu_hw_pingpong_ops *ops, + const struct dpu_pingpong_cfg *hw_cap) +{ + ops->setup_tearcheck = dpu_hw_pp_setup_te_config; + ops->enable_tearcheck = dpu_hw_pp_enable_te; + ops->connect_external_te = dpu_hw_pp_connect_external_te; + ops->get_vsync_info = dpu_hw_pp_get_vsync_info; + ops->poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr; + ops->get_line_count = dpu_hw_pp_get_line_count; +}; + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx, + void __iomem *addr, + struct dpu_mdss_cfg *m) +{ + struct dpu_hw_pingpong *c; + struct dpu_pingpong_cfg *cfg; + int rc; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _pingpong_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + return ERR_PTR(-EINVAL); + } + + c->idx = idx; + c->caps = cfg; + _setup_pingpong_ops(&c->ops, c->caps); + + rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + return c; + +blk_init_error: + kzfree(c); + + return ERR_PTR(rc); +} + +void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp) +{ + if (pp) + dpu_hw_blk_destroy(&pp->base); + kfree(pp); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h new file mode 100644 index 000000000000..3caccd7d6a3e --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h @@ -0,0 +1,136 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_PINGPONG_H +#define _DPU_HW_PINGPONG_H + +#include "dpu_hw_catalog.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_blk.h" + +struct dpu_hw_pingpong; + +struct dpu_hw_tear_check { + /* + * This is ratio of MDP VSYNC clk freq(Hz) to + * refresh rate divided by no of lines + */ + u32 vsync_count; + u32 sync_cfg_height; + u32 vsync_init_val; + u32 sync_threshold_start; + u32 sync_threshold_continue; + u32 start_pos; + u32 rd_ptr_irq; + u8 hw_vsync_mode; +}; + +struct dpu_hw_pp_vsync_info { + u32 rd_ptr_init_val; /* value of rd pointer at vsync edge */ + u32 rd_ptr_frame_count; /* num frames sent since enabling interface */ + u32 rd_ptr_line_count; /* current line on panel (rd ptr) */ + u32 wr_ptr_line_count; /* current line within pp fifo (wr ptr) */ +}; + +/** + * + * struct dpu_hw_pingpong_ops : Interface to the pingpong Hw driver functions + * Assumption is these functions will be called after clocks are enabled + * @setup_tearcheck : program tear check values + * @enable_tearcheck : enables tear check + * @get_vsync_info : retries timing info of the panel + * @setup_dither : function to program the dither hw block + * @get_line_count: obtain current vertical line counter + */ +struct dpu_hw_pingpong_ops { + /** + * enables vysnc generation and sets up init value of + * read pointer and programs the tear check cofiguration + */ + int (*setup_tearcheck)(struct dpu_hw_pingpong *pp, + struct dpu_hw_tear_check *cfg); + + /** + * enables tear check block + */ + int (*enable_tearcheck)(struct dpu_hw_pingpong *pp, + bool enable); + + /** + * read, modify, write to either set or clear listening to external TE + * @Return: 1 if TE was originally connected, 0 if not, or -ERROR + */ + int (*connect_external_te)(struct dpu_hw_pingpong *pp, + bool enable_external_te); + + /** + * provides the programmed and current + * line_count + */ + int (*get_vsync_info)(struct dpu_hw_pingpong *pp, + struct dpu_hw_pp_vsync_info *info); + + /** + * poll until write pointer transmission starts + * @Return: 0 on success, -ETIMEDOUT on timeout + */ + int (*poll_timeout_wr_ptr)(struct dpu_hw_pingpong *pp, u32 timeout_us); + + /** + * Obtain current vertical line counter + */ + u32 (*get_line_count)(struct dpu_hw_pingpong *pp); +}; + +struct dpu_hw_pingpong { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* pingpong */ + enum dpu_pingpong idx; + const struct dpu_pingpong_cfg *caps; + + /* ops */ + struct dpu_hw_pingpong_ops ops; +}; + +/** + * dpu_hw_pingpong - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_pingpong, base); +} + +/** + * dpu_hw_pingpong_init - initializes the pingpong driver for the passed + * pingpong idx. + * @idx: Pingpong index for which driver object is required + * @addr: Mapped register io address of MDP + * @m: Pointer to mdss catalog data + * Returns: Error code or allocated dpu_hw_pingpong context + */ +struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx, + void __iomem *addr, + struct dpu_mdss_cfg *m); + +/** + * dpu_hw_pingpong_destroy - destroys pingpong driver context + * should be called to free the context + * @pp: Pointer to PP driver context returned by dpu_hw_pingpong_init + */ +void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp); + +#endif /*_DPU_HW_PINGPONG_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c new file mode 100644 index 000000000000..c25b52a6b219 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c @@ -0,0 +1,753 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_lm.h" +#include "dpu_hw_sspp.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define DPU_FETCH_CONFIG_RESET_VALUE 0x00000087 + +/* DPU_SSPP_SRC */ +#define SSPP_SRC_SIZE 0x00 +#define SSPP_SRC_XY 0x08 +#define SSPP_OUT_SIZE 0x0c +#define SSPP_OUT_XY 0x10 +#define SSPP_SRC0_ADDR 0x14 +#define SSPP_SRC1_ADDR 0x18 +#define SSPP_SRC2_ADDR 0x1C +#define SSPP_SRC3_ADDR 0x20 +#define SSPP_SRC_YSTRIDE0 0x24 +#define SSPP_SRC_YSTRIDE1 0x28 +#define SSPP_SRC_FORMAT 0x30 +#define SSPP_SRC_UNPACK_PATTERN 0x34 +#define SSPP_SRC_OP_MODE 0x38 + +/* SSPP_MULTIRECT*/ +#define SSPP_SRC_SIZE_REC1 0x16C +#define SSPP_SRC_XY_REC1 0x168 +#define SSPP_OUT_SIZE_REC1 0x160 +#define SSPP_OUT_XY_REC1 0x164 +#define SSPP_SRC_FORMAT_REC1 0x174 +#define SSPP_SRC_UNPACK_PATTERN_REC1 0x178 +#define SSPP_SRC_OP_MODE_REC1 0x17C +#define SSPP_MULTIRECT_OPMODE 0x170 +#define SSPP_SRC_CONSTANT_COLOR_REC1 0x180 +#define SSPP_EXCL_REC_SIZE_REC1 0x184 +#define SSPP_EXCL_REC_XY_REC1 0x188 + +#define MDSS_MDP_OP_DEINTERLACE BIT(22) +#define MDSS_MDP_OP_DEINTERLACE_ODD BIT(23) +#define MDSS_MDP_OP_IGC_ROM_1 BIT(18) +#define MDSS_MDP_OP_IGC_ROM_0 BIT(17) +#define MDSS_MDP_OP_IGC_EN BIT(16) +#define MDSS_MDP_OP_FLIP_UD BIT(14) +#define MDSS_MDP_OP_FLIP_LR BIT(13) +#define MDSS_MDP_OP_BWC_EN BIT(0) +#define MDSS_MDP_OP_PE_OVERRIDE BIT(31) +#define MDSS_MDP_OP_BWC_LOSSLESS (0 << 1) +#define MDSS_MDP_OP_BWC_Q_HIGH (1 << 1) +#define MDSS_MDP_OP_BWC_Q_MED (2 << 1) + +#define SSPP_SRC_CONSTANT_COLOR 0x3c +#define SSPP_EXCL_REC_CTL 0x40 +#define SSPP_UBWC_STATIC_CTRL 0x44 +#define SSPP_FETCH_CONFIG 0x048 +#define SSPP_DANGER_LUT 0x60 +#define SSPP_SAFE_LUT 0x64 +#define SSPP_CREQ_LUT 0x68 +#define SSPP_QOS_CTRL 0x6C +#define SSPP_DECIMATION_CONFIG 0xB4 +#define SSPP_SRC_ADDR_SW_STATUS 0x70 +#define SSPP_CREQ_LUT_0 0x74 +#define SSPP_CREQ_LUT_1 0x78 +#define SSPP_SW_PIX_EXT_C0_LR 0x100 +#define SSPP_SW_PIX_EXT_C0_TB 0x104 +#define SSPP_SW_PIX_EXT_C0_REQ_PIXELS 0x108 +#define SSPP_SW_PIX_EXT_C1C2_LR 0x110 +#define SSPP_SW_PIX_EXT_C1C2_TB 0x114 +#define SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS 0x118 +#define SSPP_SW_PIX_EXT_C3_LR 0x120 +#define SSPP_SW_PIX_EXT_C3_TB 0x124 +#define SSPP_SW_PIX_EXT_C3_REQ_PIXELS 0x128 +#define SSPP_TRAFFIC_SHAPER 0x130 +#define SSPP_CDP_CNTL 0x134 +#define SSPP_UBWC_ERROR_STATUS 0x138 +#define SSPP_TRAFFIC_SHAPER_PREFILL 0x150 +#define SSPP_TRAFFIC_SHAPER_REC1_PREFILL 0x154 +#define SSPP_TRAFFIC_SHAPER_REC1 0x158 +#define SSPP_EXCL_REC_SIZE 0x1B4 +#define SSPP_EXCL_REC_XY 0x1B8 +#define SSPP_VIG_OP_MODE 0x0 +#define SSPP_VIG_CSC_10_OP_MODE 0x0 +#define SSPP_TRAFFIC_SHAPER_BPC_MAX 0xFF + +/* SSPP_QOS_CTRL */ +#define SSPP_QOS_CTRL_VBLANK_EN BIT(16) +#define SSPP_QOS_CTRL_DANGER_SAFE_EN BIT(0) +#define SSPP_QOS_CTRL_DANGER_VBLANK_MASK 0x3 +#define SSPP_QOS_CTRL_DANGER_VBLANK_OFF 4 +#define SSPP_QOS_CTRL_CREQ_VBLANK_MASK 0x3 +#define SSPP_QOS_CTRL_CREQ_VBLANK_OFF 20 + +/* DPU_SSPP_SCALER_QSEED2 */ +#define SCALE_CONFIG 0x04 +#define COMP0_3_PHASE_STEP_X 0x10 +#define COMP0_3_PHASE_STEP_Y 0x14 +#define COMP1_2_PHASE_STEP_X 0x18 +#define COMP1_2_PHASE_STEP_Y 0x1c +#define COMP0_3_INIT_PHASE_X 0x20 +#define COMP0_3_INIT_PHASE_Y 0x24 +#define COMP1_2_INIT_PHASE_X 0x28 +#define COMP1_2_INIT_PHASE_Y 0x2C +#define VIG_0_QSEED2_SHARP 0x30 + +/* + * Definitions for ViG op modes + */ +#define VIG_OP_CSC_DST_DATAFMT BIT(19) +#define VIG_OP_CSC_SRC_DATAFMT BIT(18) +#define VIG_OP_CSC_EN BIT(17) +#define VIG_OP_MEM_PROT_CONT BIT(15) +#define VIG_OP_MEM_PROT_VAL BIT(14) +#define VIG_OP_MEM_PROT_SAT BIT(13) +#define VIG_OP_MEM_PROT_HUE BIT(12) +#define VIG_OP_HIST BIT(8) +#define VIG_OP_SKY_COL BIT(7) +#define VIG_OP_FOIL BIT(6) +#define VIG_OP_SKIN_COL BIT(5) +#define VIG_OP_PA_EN BIT(4) +#define VIG_OP_PA_SAT_ZERO_EXP BIT(2) +#define VIG_OP_MEM_PROT_BLEND BIT(1) + +/* + * Definitions for CSC 10 op modes + */ +#define VIG_CSC_10_SRC_DATAFMT BIT(1) +#define VIG_CSC_10_EN BIT(0) +#define CSC_10BIT_OFFSET 4 + +/* traffic shaper clock in Hz */ +#define TS_CLK 19200000 + +static inline int _sspp_subblk_offset(struct dpu_hw_pipe *ctx, + int s_id, + u32 *idx) +{ + int rc = 0; + const struct dpu_sspp_sub_blks *sblk = ctx->cap->sblk; + + if (!ctx) + return -EINVAL; + + switch (s_id) { + case DPU_SSPP_SRC: + *idx = sblk->src_blk.base; + break; + case DPU_SSPP_SCALER_QSEED2: + case DPU_SSPP_SCALER_QSEED3: + case DPU_SSPP_SCALER_RGB: + *idx = sblk->scaler_blk.base; + break; + case DPU_SSPP_CSC: + case DPU_SSPP_CSC_10BIT: + *idx = sblk->csc_blk.base; + break; + default: + rc = -EINVAL; + } + + return rc; +} + +static void dpu_hw_sspp_setup_multirect(struct dpu_hw_pipe *ctx, + enum dpu_sspp_multirect_index index, + enum dpu_sspp_multirect_mode mode) +{ + u32 mode_mask; + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (index == DPU_SSPP_RECT_SOLO) { + /** + * if rect index is RECT_SOLO, we cannot expect a + * virtual plane sharing the same SSPP id. So we go + * and disable multirect + */ + mode_mask = 0; + } else { + mode_mask = DPU_REG_READ(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx); + mode_mask |= index; + if (mode == DPU_SSPP_MULTIRECT_TIME_MX) + mode_mask |= BIT(2); + else + mode_mask &= ~BIT(2); + } + + DPU_REG_WRITE(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx, mode_mask); +} + +static void _sspp_setup_opmode(struct dpu_hw_pipe *ctx, + u32 mask, u8 en) +{ + u32 idx; + u32 opmode; + + if (!test_bit(DPU_SSPP_SCALER_QSEED2, &ctx->cap->features) || + _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED2, &idx) || + !test_bit(DPU_SSPP_CSC, &ctx->cap->features)) + return; + + opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_OP_MODE + idx); + + if (en) + opmode |= mask; + else + opmode &= ~mask; + + DPU_REG_WRITE(&ctx->hw, SSPP_VIG_OP_MODE + idx, opmode); +} + +static void _sspp_setup_csc10_opmode(struct dpu_hw_pipe *ctx, + u32 mask, u8 en) +{ + u32 idx; + u32 opmode; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC_10BIT, &idx)) + return; + + opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx); + if (en) + opmode |= mask; + else + opmode &= ~mask; + + DPU_REG_WRITE(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx, opmode); +} + +/** + * Setup source pixel format, flip, + */ +static void dpu_hw_sspp_setup_format(struct dpu_hw_pipe *ctx, + const struct dpu_format *fmt, u32 flags, + enum dpu_sspp_multirect_index rect_mode) +{ + struct dpu_hw_blk_reg_map *c; + u32 chroma_samp, unpack, src_format; + u32 opmode = 0; + u32 fast_clear = 0; + u32 op_mode_off, unpack_pat_off, format_off; + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !fmt) + return; + + if (rect_mode == DPU_SSPP_RECT_SOLO || rect_mode == DPU_SSPP_RECT_0) { + op_mode_off = SSPP_SRC_OP_MODE; + unpack_pat_off = SSPP_SRC_UNPACK_PATTERN; + format_off = SSPP_SRC_FORMAT; + } else { + op_mode_off = SSPP_SRC_OP_MODE_REC1; + unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1; + format_off = SSPP_SRC_FORMAT_REC1; + } + + c = &ctx->hw; + opmode = DPU_REG_READ(c, op_mode_off + idx); + opmode &= ~(MDSS_MDP_OP_FLIP_LR | MDSS_MDP_OP_FLIP_UD | + MDSS_MDP_OP_BWC_EN | MDSS_MDP_OP_PE_OVERRIDE); + + if (flags & DPU_SSPP_FLIP_LR) + opmode |= MDSS_MDP_OP_FLIP_LR; + if (flags & DPU_SSPP_FLIP_UD) + opmode |= MDSS_MDP_OP_FLIP_UD; + + chroma_samp = fmt->chroma_sample; + if (flags & DPU_SSPP_SOURCE_ROTATED_90) { + if (chroma_samp == DPU_CHROMA_H2V1) + chroma_samp = DPU_CHROMA_H1V2; + else if (chroma_samp == DPU_CHROMA_H1V2) + chroma_samp = DPU_CHROMA_H2V1; + } + + src_format = (chroma_samp << 23) | (fmt->fetch_planes << 19) | + (fmt->bits[C3_ALPHA] << 6) | (fmt->bits[C2_R_Cr] << 4) | + (fmt->bits[C1_B_Cb] << 2) | (fmt->bits[C0_G_Y] << 0); + + if (flags & DPU_SSPP_ROT_90) + src_format |= BIT(11); /* ROT90 */ + + if (fmt->alpha_enable && fmt->fetch_planes == DPU_PLANE_INTERLEAVED) + src_format |= BIT(8); /* SRCC3_EN */ + + if (flags & DPU_SSPP_SOLID_FILL) + src_format |= BIT(22); + + unpack = (fmt->element[3] << 24) | (fmt->element[2] << 16) | + (fmt->element[1] << 8) | (fmt->element[0] << 0); + src_format |= ((fmt->unpack_count - 1) << 12) | + (fmt->unpack_tight << 17) | + (fmt->unpack_align_msb << 18) | + ((fmt->bpp - 1) << 9); + + if (fmt->fetch_mode != DPU_FETCH_LINEAR) { + if (DPU_FORMAT_IS_UBWC(fmt)) + opmode |= MDSS_MDP_OP_BWC_EN; + src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */ + DPU_REG_WRITE(c, SSPP_FETCH_CONFIG, + DPU_FETCH_CONFIG_RESET_VALUE | + ctx->mdp->highest_bank_bit << 18); + if (IS_UBWC_20_SUPPORTED(ctx->catalog->caps->ubwc_version)) { + fast_clear = fmt->alpha_enable ? BIT(31) : 0; + DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL, + fast_clear | (ctx->mdp->ubwc_swizzle) | + (ctx->mdp->highest_bank_bit << 4)); + } + } + + opmode |= MDSS_MDP_OP_PE_OVERRIDE; + + /* if this is YUV pixel format, enable CSC */ + if (DPU_FORMAT_IS_YUV(fmt)) + src_format |= BIT(15); + + if (DPU_FORMAT_IS_DX(fmt)) + src_format |= BIT(14); + + /* update scaler opmode, if appropriate */ + if (test_bit(DPU_SSPP_CSC, &ctx->cap->features)) + _sspp_setup_opmode(ctx, VIG_OP_CSC_EN | VIG_OP_CSC_SRC_DATAFMT, + DPU_FORMAT_IS_YUV(fmt)); + else if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) + _sspp_setup_csc10_opmode(ctx, + VIG_CSC_10_EN | VIG_CSC_10_SRC_DATAFMT, + DPU_FORMAT_IS_YUV(fmt)); + + DPU_REG_WRITE(c, format_off + idx, src_format); + DPU_REG_WRITE(c, unpack_pat_off + idx, unpack); + DPU_REG_WRITE(c, op_mode_off + idx, opmode); + + /* clear previous UBWC error */ + DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS + idx, BIT(31)); +} + +static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_pipe *ctx, + struct dpu_hw_pixel_ext *pe_ext) +{ + struct dpu_hw_blk_reg_map *c; + u8 color; + u32 lr_pe[4], tb_pe[4], tot_req_pixels[4]; + const u32 bytemask = 0xff; + const u32 shortmask = 0xffff; + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !pe_ext) + return; + + c = &ctx->hw; + + /* program SW pixel extension override for all pipes*/ + for (color = 0; color < DPU_MAX_PLANES; color++) { + /* color 2 has the same set of registers as color 1 */ + if (color == 2) + continue; + + lr_pe[color] = ((pe_ext->right_ftch[color] & bytemask) << 24)| + ((pe_ext->right_rpt[color] & bytemask) << 16)| + ((pe_ext->left_ftch[color] & bytemask) << 8)| + (pe_ext->left_rpt[color] & bytemask); + + tb_pe[color] = ((pe_ext->btm_ftch[color] & bytemask) << 24)| + ((pe_ext->btm_rpt[color] & bytemask) << 16)| + ((pe_ext->top_ftch[color] & bytemask) << 8)| + (pe_ext->top_rpt[color] & bytemask); + + tot_req_pixels[color] = (((pe_ext->roi_h[color] + + pe_ext->num_ext_pxls_top[color] + + pe_ext->num_ext_pxls_btm[color]) & shortmask) << 16) | + ((pe_ext->roi_w[color] + + pe_ext->num_ext_pxls_left[color] + + pe_ext->num_ext_pxls_right[color]) & shortmask); + } + + /* color 0 */ + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_LR + idx, lr_pe[0]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_TB + idx, tb_pe[0]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_REQ_PIXELS + idx, + tot_req_pixels[0]); + + /* color 1 and color 2 */ + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_LR + idx, lr_pe[1]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_TB + idx, tb_pe[1]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS + idx, + tot_req_pixels[1]); + + /* color 3 */ + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_LR + idx, lr_pe[3]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_TB + idx, lr_pe[3]); + DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_REQ_PIXELS + idx, + tot_req_pixels[3]); +} + +static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *sspp, + struct dpu_hw_pixel_ext *pe, + void *scaler_cfg) +{ + u32 idx; + struct dpu_hw_scaler3_cfg *scaler3_cfg = scaler_cfg; + + (void)pe; + if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp + || !scaler3_cfg || !ctx || !ctx->cap || !ctx->cap->sblk) + return; + + dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx, + ctx->cap->sblk->scaler_blk.version, + sspp->layout.format); +} + +static u32 _dpu_hw_sspp_get_scaler3_ver(struct dpu_hw_pipe *ctx) +{ + u32 idx; + + if (!ctx || _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx)) + return 0; + + return dpu_hw_get_scaler3_ver(&ctx->hw, idx); +} + +/** + * dpu_hw_sspp_setup_rects() + */ +static void dpu_hw_sspp_setup_rects(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *cfg, + enum dpu_sspp_multirect_index rect_index) +{ + struct dpu_hw_blk_reg_map *c; + u32 src_size, src_xy, dst_size, dst_xy, ystride0, ystride1; + u32 src_size_off, src_xy_off, out_size_off, out_xy_off; + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !cfg) + return; + + c = &ctx->hw; + + if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) { + src_size_off = SSPP_SRC_SIZE; + src_xy_off = SSPP_SRC_XY; + out_size_off = SSPP_OUT_SIZE; + out_xy_off = SSPP_OUT_XY; + } else { + src_size_off = SSPP_SRC_SIZE_REC1; + src_xy_off = SSPP_SRC_XY_REC1; + out_size_off = SSPP_OUT_SIZE_REC1; + out_xy_off = SSPP_OUT_XY_REC1; + } + + + /* src and dest rect programming */ + src_xy = (cfg->src_rect.y1 << 16) | cfg->src_rect.x1; + src_size = (drm_rect_height(&cfg->src_rect) << 16) | + drm_rect_width(&cfg->src_rect); + dst_xy = (cfg->dst_rect.y1 << 16) | cfg->dst_rect.x1; + dst_size = (drm_rect_height(&cfg->dst_rect) << 16) | + drm_rect_width(&cfg->dst_rect); + + if (rect_index == DPU_SSPP_RECT_SOLO) { + ystride0 = (cfg->layout.plane_pitch[0]) | + (cfg->layout.plane_pitch[1] << 16); + ystride1 = (cfg->layout.plane_pitch[2]) | + (cfg->layout.plane_pitch[3] << 16); + } else { + ystride0 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE0 + idx); + ystride1 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE1 + idx); + + if (rect_index == DPU_SSPP_RECT_0) { + ystride0 = (ystride0 & 0xFFFF0000) | + (cfg->layout.plane_pitch[0] & 0x0000FFFF); + ystride1 = (ystride1 & 0xFFFF0000)| + (cfg->layout.plane_pitch[2] & 0x0000FFFF); + } else { + ystride0 = (ystride0 & 0x0000FFFF) | + ((cfg->layout.plane_pitch[0] << 16) & + 0xFFFF0000); + ystride1 = (ystride1 & 0x0000FFFF) | + ((cfg->layout.plane_pitch[2] << 16) & + 0xFFFF0000); + } + } + + /* rectangle register programming */ + DPU_REG_WRITE(c, src_size_off + idx, src_size); + DPU_REG_WRITE(c, src_xy_off + idx, src_xy); + DPU_REG_WRITE(c, out_size_off + idx, dst_size); + DPU_REG_WRITE(c, out_xy_off + idx, dst_xy); + + DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE0 + idx, ystride0); + DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE1 + idx, ystride1); +} + +static void dpu_hw_sspp_setup_sourceaddress(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *cfg, + enum dpu_sspp_multirect_index rect_mode) +{ + int i; + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (rect_mode == DPU_SSPP_RECT_SOLO) { + for (i = 0; i < ARRAY_SIZE(cfg->layout.plane_addr); i++) + DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx + i * 0x4, + cfg->layout.plane_addr[i]); + } else if (rect_mode == DPU_SSPP_RECT_0) { + DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx, + cfg->layout.plane_addr[0]); + DPU_REG_WRITE(&ctx->hw, SSPP_SRC2_ADDR + idx, + cfg->layout.plane_addr[2]); + } else { + DPU_REG_WRITE(&ctx->hw, SSPP_SRC1_ADDR + idx, + cfg->layout.plane_addr[0]); + DPU_REG_WRITE(&ctx->hw, SSPP_SRC3_ADDR + idx, + cfg->layout.plane_addr[2]); + } +} + +static void dpu_hw_sspp_setup_csc(struct dpu_hw_pipe *ctx, + struct dpu_csc_cfg *data) +{ + u32 idx; + bool csc10 = false; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC, &idx) || !data) + return; + + if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) { + idx += CSC_10BIT_OFFSET; + csc10 = true; + } + + dpu_hw_csc_setup(&ctx->hw, idx, data, csc10); +} + +static void dpu_hw_sspp_setup_solidfill(struct dpu_hw_pipe *ctx, u32 color, enum + dpu_sspp_multirect_index rect_index) +{ + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) + DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR + idx, color); + else + DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR_REC1 + idx, + color); +} + +static void dpu_hw_sspp_setup_danger_safe_lut(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg) +{ + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + DPU_REG_WRITE(&ctx->hw, SSPP_DANGER_LUT + idx, cfg->danger_lut); + DPU_REG_WRITE(&ctx->hw, SSPP_SAFE_LUT + idx, cfg->safe_lut); +} + +static void dpu_hw_sspp_setup_creq_lut(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg) +{ + u32 idx; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (ctx->cap && test_bit(DPU_SSPP_QOS_8LVL, &ctx->cap->features)) { + DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_0 + idx, cfg->creq_lut); + DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_1 + idx, + cfg->creq_lut >> 32); + } else { + DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT + idx, cfg->creq_lut); + } +} + +static void dpu_hw_sspp_setup_qos_ctrl(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg) +{ + u32 idx; + u32 qos_ctrl = 0; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (cfg->vblank_en) { + qos_ctrl |= ((cfg->creq_vblank & + SSPP_QOS_CTRL_CREQ_VBLANK_MASK) << + SSPP_QOS_CTRL_CREQ_VBLANK_OFF); + qos_ctrl |= ((cfg->danger_vblank & + SSPP_QOS_CTRL_DANGER_VBLANK_MASK) << + SSPP_QOS_CTRL_DANGER_VBLANK_OFF); + qos_ctrl |= SSPP_QOS_CTRL_VBLANK_EN; + } + + if (cfg->danger_safe_en) + qos_ctrl |= SSPP_QOS_CTRL_DANGER_SAFE_EN; + + DPU_REG_WRITE(&ctx->hw, SSPP_QOS_CTRL + idx, qos_ctrl); +} + +static void dpu_hw_sspp_setup_cdp(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cdp_cfg *cfg) +{ + u32 idx; + u32 cdp_cntl = 0; + + if (!ctx || !cfg) + return; + + if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx)) + return; + + if (cfg->enable) + cdp_cntl |= BIT(0); + if (cfg->ubwc_meta_enable) + cdp_cntl |= BIT(1); + if (cfg->tile_amortize_enable) + cdp_cntl |= BIT(2); + if (cfg->preload_ahead == DPU_SSPP_CDP_PRELOAD_AHEAD_64) + cdp_cntl |= BIT(3); + + DPU_REG_WRITE(&ctx->hw, SSPP_CDP_CNTL, cdp_cntl); +} + +static void _setup_layer_ops(struct dpu_hw_pipe *c, + unsigned long features) +{ + if (test_bit(DPU_SSPP_SRC, &features)) { + c->ops.setup_format = dpu_hw_sspp_setup_format; + c->ops.setup_rects = dpu_hw_sspp_setup_rects; + c->ops.setup_sourceaddress = dpu_hw_sspp_setup_sourceaddress; + c->ops.setup_solidfill = dpu_hw_sspp_setup_solidfill; + c->ops.setup_pe = dpu_hw_sspp_setup_pe_config; + } + + if (test_bit(DPU_SSPP_QOS, &features)) { + c->ops.setup_danger_safe_lut = + dpu_hw_sspp_setup_danger_safe_lut; + c->ops.setup_creq_lut = dpu_hw_sspp_setup_creq_lut; + c->ops.setup_qos_ctrl = dpu_hw_sspp_setup_qos_ctrl; + } + + if (test_bit(DPU_SSPP_CSC, &features) || + test_bit(DPU_SSPP_CSC_10BIT, &features)) + c->ops.setup_csc = dpu_hw_sspp_setup_csc; + + if (dpu_hw_sspp_multirect_enabled(c->cap)) + c->ops.setup_multirect = dpu_hw_sspp_setup_multirect; + + if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) { + c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3; + c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver; + } + + if (test_bit(DPU_SSPP_CDP, &features)) + c->ops.setup_cdp = dpu_hw_sspp_setup_cdp; +} + +static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp, + void __iomem *addr, + struct dpu_mdss_cfg *catalog, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + if ((sspp < SSPP_MAX) && catalog && addr && b) { + for (i = 0; i < catalog->sspp_count; i++) { + if (sspp == catalog->sspp[i].id) { + b->base_off = addr; + b->blk_off = catalog->sspp[i].base; + b->length = catalog->sspp[i].len; + b->hwversion = catalog->hwversion; + b->log_mask = DPU_DBG_MASK_SSPP; + return &catalog->sspp[i]; + } + } + } + + return ERR_PTR(-ENOMEM); +} + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx, + void __iomem *addr, struct dpu_mdss_cfg *catalog, + bool is_virtual_pipe) +{ + struct dpu_hw_pipe *hw_pipe; + struct dpu_sspp_cfg *cfg; + int rc; + + if (!addr || !catalog) + return ERR_PTR(-EINVAL); + + hw_pipe = kzalloc(sizeof(*hw_pipe), GFP_KERNEL); + if (!hw_pipe) + return ERR_PTR(-ENOMEM); + + cfg = _sspp_offset(idx, addr, catalog, &hw_pipe->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(hw_pipe); + return ERR_PTR(-EINVAL); + } + + /* Assign ops */ + hw_pipe->catalog = catalog; + hw_pipe->mdp = &catalog->mdp[0]; + hw_pipe->idx = idx; + hw_pipe->cap = cfg; + _setup_layer_ops(hw_pipe, hw_pipe->cap->features); + + rc = dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + return hw_pipe; + +blk_init_error: + kzfree(hw_pipe); + + return ERR_PTR(rc); +} + +void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx) +{ + if (ctx) + dpu_hw_blk_destroy(&ctx->base); + kfree(ctx); +} + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h new file mode 100644 index 000000000000..4d81e5f5ce1b --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h @@ -0,0 +1,424 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_SSPP_H +#define _DPU_HW_SSPP_H + +#include "dpu_hw_catalog.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_blk.h" +#include "dpu_formats.h" + +struct dpu_hw_pipe; + +/** + * Flags + */ +#define DPU_SSPP_FLIP_LR BIT(0) +#define DPU_SSPP_FLIP_UD BIT(1) +#define DPU_SSPP_SOURCE_ROTATED_90 BIT(2) +#define DPU_SSPP_ROT_90 BIT(3) +#define DPU_SSPP_SOLID_FILL BIT(4) + +/** + * Define all scaler feature bits in catalog + */ +#define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \ + (1UL << DPU_SSPP_SCALER_QSEED2) | \ + (1UL << DPU_SSPP_SCALER_QSEED3)) + +/** + * Component indices + */ +enum { + DPU_SSPP_COMP_0, + DPU_SSPP_COMP_1_2, + DPU_SSPP_COMP_2, + DPU_SSPP_COMP_3, + + DPU_SSPP_COMP_MAX +}; + +/** + * DPU_SSPP_RECT_SOLO - multirect disabled + * DPU_SSPP_RECT_0 - rect0 of a multirect pipe + * DPU_SSPP_RECT_1 - rect1 of a multirect pipe + * + * Note: HW supports multirect with either RECT0 or + * RECT1. Considering no benefit of such configs over + * SOLO mode and to keep the plane management simple, + * we dont support single rect multirect configs. + */ +enum dpu_sspp_multirect_index { + DPU_SSPP_RECT_SOLO = 0, + DPU_SSPP_RECT_0, + DPU_SSPP_RECT_1, +}; + +enum dpu_sspp_multirect_mode { + DPU_SSPP_MULTIRECT_NONE = 0, + DPU_SSPP_MULTIRECT_PARALLEL, + DPU_SSPP_MULTIRECT_TIME_MX, +}; + +enum { + DPU_FRAME_LINEAR, + DPU_FRAME_TILE_A4X, + DPU_FRAME_TILE_A5X, +}; + +enum dpu_hw_filter { + DPU_SCALE_FILTER_NEAREST = 0, + DPU_SCALE_FILTER_BIL, + DPU_SCALE_FILTER_PCMN, + DPU_SCALE_FILTER_CA, + DPU_SCALE_FILTER_MAX +}; + +enum dpu_hw_filter_alpa { + DPU_SCALE_ALPHA_PIXEL_REP, + DPU_SCALE_ALPHA_BIL +}; + +enum dpu_hw_filter_yuv { + DPU_SCALE_2D_4X4, + DPU_SCALE_2D_CIR, + DPU_SCALE_1D_SEP, + DPU_SCALE_BIL +}; + +struct dpu_hw_sharp_cfg { + u32 strength; + u32 edge_thr; + u32 smooth_thr; + u32 noise_thr; +}; + +struct dpu_hw_pixel_ext { + /* scaling factors are enabled for this input layer */ + uint8_t enable_pxl_ext; + + int init_phase_x[DPU_MAX_PLANES]; + int phase_step_x[DPU_MAX_PLANES]; + int init_phase_y[DPU_MAX_PLANES]; + int phase_step_y[DPU_MAX_PLANES]; + + /* + * Number of pixels extension in left, right, top and bottom direction + * for all color components. This pixel value for each color component + * should be sum of fetch + repeat pixels. + */ + int num_ext_pxls_left[DPU_MAX_PLANES]; + int num_ext_pxls_right[DPU_MAX_PLANES]; + int num_ext_pxls_top[DPU_MAX_PLANES]; + int num_ext_pxls_btm[DPU_MAX_PLANES]; + + /* + * Number of pixels needs to be overfetched in left, right, top and + * bottom directions from source image for scaling. + */ + int left_ftch[DPU_MAX_PLANES]; + int right_ftch[DPU_MAX_PLANES]; + int top_ftch[DPU_MAX_PLANES]; + int btm_ftch[DPU_MAX_PLANES]; + + /* + * Number of pixels needs to be repeated in left, right, top and + * bottom directions for scaling. + */ + int left_rpt[DPU_MAX_PLANES]; + int right_rpt[DPU_MAX_PLANES]; + int top_rpt[DPU_MAX_PLANES]; + int btm_rpt[DPU_MAX_PLANES]; + + uint32_t roi_w[DPU_MAX_PLANES]; + uint32_t roi_h[DPU_MAX_PLANES]; + + /* + * Filter type to be used for scaling in horizontal and vertical + * directions + */ + enum dpu_hw_filter horz_filter[DPU_MAX_PLANES]; + enum dpu_hw_filter vert_filter[DPU_MAX_PLANES]; + +}; + +/** + * struct dpu_hw_pipe_cfg : Pipe description + * @layout: format layout information for programming buffer to hardware + * @src_rect: src ROI, caller takes into account the different operations + * such as decimation, flip etc to program this field + * @dest_rect: destination ROI. + * @index: index of the rectangle of SSPP + * @mode: parallel or time multiplex multirect mode + */ +struct dpu_hw_pipe_cfg { + struct dpu_hw_fmt_layout layout; + struct drm_rect src_rect; + struct drm_rect dst_rect; + enum dpu_sspp_multirect_index index; + enum dpu_sspp_multirect_mode mode; +}; + +/** + * struct dpu_hw_pipe_qos_cfg : Source pipe QoS configuration + * @danger_lut: LUT for generate danger level based on fill level + * @safe_lut: LUT for generate safe level based on fill level + * @creq_lut: LUT for generate creq level based on fill level + * @creq_vblank: creq value generated to vbif during vertical blanking + * @danger_vblank: danger value generated during vertical blanking + * @vblank_en: enable creq_vblank and danger_vblank during vblank + * @danger_safe_en: enable danger safe generation + */ +struct dpu_hw_pipe_qos_cfg { + u32 danger_lut; + u32 safe_lut; + u64 creq_lut; + u32 creq_vblank; + u32 danger_vblank; + bool vblank_en; + bool danger_safe_en; +}; + +/** + * enum CDP preload ahead address size + */ +enum { + DPU_SSPP_CDP_PRELOAD_AHEAD_32, + DPU_SSPP_CDP_PRELOAD_AHEAD_64 +}; + +/** + * struct dpu_hw_pipe_cdp_cfg : CDP configuration + * @enable: true to enable CDP + * @ubwc_meta_enable: true to enable ubwc metadata preload + * @tile_amortize_enable: true to enable amortization control for tile format + * @preload_ahead: number of request to preload ahead + * DPU_SSPP_CDP_PRELOAD_AHEAD_32, + * DPU_SSPP_CDP_PRELOAD_AHEAD_64 + */ +struct dpu_hw_pipe_cdp_cfg { + bool enable; + bool ubwc_meta_enable; + bool tile_amortize_enable; + u32 preload_ahead; +}; + +/** + * struct dpu_hw_pipe_ts_cfg - traffic shaper configuration + * @size: size to prefill in bytes, or zero to disable + * @time: time to prefill in usec, or zero to disable + */ +struct dpu_hw_pipe_ts_cfg { + u64 size; + u64 time; +}; + +/** + * struct dpu_hw_sspp_ops - interface to the SSPP Hw driver functions + * Caller must call the init function to get the pipe context for each pipe + * Assumption is these functions will be called after clocks are enabled + */ +struct dpu_hw_sspp_ops { + /** + * setup_format - setup pixel format cropping rectangle, flip + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe config structure + * @flags: Extra flags for format config + * @index: rectangle index in multirect + */ + void (*setup_format)(struct dpu_hw_pipe *ctx, + const struct dpu_format *fmt, u32 flags, + enum dpu_sspp_multirect_index index); + + /** + * setup_rects - setup pipe ROI rectangles + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe config structure + * @index: rectangle index in multirect + */ + void (*setup_rects)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *cfg, + enum dpu_sspp_multirect_index index); + + /** + * setup_pe - setup pipe pixel extension + * @ctx: Pointer to pipe context + * @pe_ext: Pointer to pixel ext settings + */ + void (*setup_pe)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pixel_ext *pe_ext); + + /** + * setup_sourceaddress - setup pipe source addresses + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe config structure + * @index: rectangle index in multirect + */ + void (*setup_sourceaddress)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *cfg, + enum dpu_sspp_multirect_index index); + + /** + * setup_csc - setup color space coversion + * @ctx: Pointer to pipe context + * @data: Pointer to config structure + */ + void (*setup_csc)(struct dpu_hw_pipe *ctx, struct dpu_csc_cfg *data); + + /** + * setup_solidfill - enable/disable colorfill + * @ctx: Pointer to pipe context + * @const_color: Fill color value + * @flags: Pipe flags + * @index: rectangle index in multirect + */ + void (*setup_solidfill)(struct dpu_hw_pipe *ctx, u32 color, + enum dpu_sspp_multirect_index index); + + /** + * setup_multirect - setup multirect configuration + * @ctx: Pointer to pipe context + * @index: rectangle index in multirect + * @mode: parallel fetch / time multiplex multirect mode + */ + + void (*setup_multirect)(struct dpu_hw_pipe *ctx, + enum dpu_sspp_multirect_index index, + enum dpu_sspp_multirect_mode mode); + + /** + * setup_sharpening - setup sharpening + * @ctx: Pointer to pipe context + * @cfg: Pointer to config structure + */ + void (*setup_sharpening)(struct dpu_hw_pipe *ctx, + struct dpu_hw_sharp_cfg *cfg); + + /** + * setup_danger_safe_lut - setup danger safe LUTs + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe QoS configuration + * + */ + void (*setup_danger_safe_lut)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg); + + /** + * setup_creq_lut - setup CREQ LUT + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe QoS configuration + * + */ + void (*setup_creq_lut)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg); + + /** + * setup_qos_ctrl - setup QoS control + * @ctx: Pointer to pipe context + * @cfg: Pointer to pipe QoS configuration + * + */ + void (*setup_qos_ctrl)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_qos_cfg *cfg); + + /** + * setup_histogram - setup histograms + * @ctx: Pointer to pipe context + * @cfg: Pointer to histogram configuration + */ + void (*setup_histogram)(struct dpu_hw_pipe *ctx, + void *cfg); + + /** + * setup_scaler - setup scaler + * @ctx: Pointer to pipe context + * @pipe_cfg: Pointer to pipe configuration + * @pe_cfg: Pointer to pixel extension configuration + * @scaler_cfg: Pointer to scaler configuration + */ + void (*setup_scaler)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cfg *pipe_cfg, + struct dpu_hw_pixel_ext *pe_cfg, + void *scaler_cfg); + + /** + * get_scaler_ver - get scaler h/w version + * @ctx: Pointer to pipe context + */ + u32 (*get_scaler_ver)(struct dpu_hw_pipe *ctx); + + /** + * setup_cdp - setup client driven prefetch + * @ctx: Pointer to pipe context + * @cfg: Pointer to cdp configuration + */ + void (*setup_cdp)(struct dpu_hw_pipe *ctx, + struct dpu_hw_pipe_cdp_cfg *cfg); +}; + +/** + * struct dpu_hw_pipe - pipe description + * @base: hardware block base structure + * @hw: block hardware details + * @catalog: back pointer to catalog + * @mdp: pointer to associated mdp portion of the catalog + * @idx: pipe index + * @cap: pointer to layer_cfg + * @ops: pointer to operations possible for this pipe + */ +struct dpu_hw_pipe { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + struct dpu_mdss_cfg *catalog; + struct dpu_mdp_cfg *mdp; + + /* Pipe */ + enum dpu_sspp idx; + const struct dpu_sspp_cfg *cap; + + /* Ops */ + struct dpu_hw_sspp_ops ops; +}; + +/** + * dpu_hw_pipe - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_pipe *to_dpu_hw_pipe(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_pipe, base); +} + +/** + * dpu_hw_sspp_init - initializes the sspp hw driver object. + * Should be called once before accessing every pipe. + * @idx: Pipe index for which driver object is required + * @addr: Mapped register io address of MDP + * @catalog : Pointer to mdss catalog data + * @is_virtual_pipe: is this pipe virtual pipe + */ +struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx, + void __iomem *addr, struct dpu_mdss_cfg *catalog, + bool is_virtual_pipe); + +/** + * dpu_hw_sspp_destroy(): Destroys SSPP driver context + * should be called during Hw pipe cleanup. + * @ctx: Pointer to SSPP driver context returned by dpu_hw_sspp_init + */ +void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx); + +#endif /*_DPU_HW_SSPP_H */ + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c new file mode 100644 index 000000000000..db2798e862fc --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c @@ -0,0 +1,398 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_top.h" +#include "dpu_dbg.h" +#include "dpu_kms.h" + +#define SSPP_SPARE 0x28 +#define UBWC_STATIC 0x144 + +#define FLD_SPLIT_DISPLAY_CMD BIT(1) +#define FLD_SMART_PANEL_FREE_RUN BIT(2) +#define FLD_INTF_1_SW_TRG_MUX BIT(4) +#define FLD_INTF_2_SW_TRG_MUX BIT(8) +#define FLD_TE_LINE_INTER_WATERLEVEL_MASK 0xFFFF + +#define DANGER_STATUS 0x360 +#define SAFE_STATUS 0x364 + +#define TE_LINE_INTERVAL 0x3F4 + +#define TRAFFIC_SHAPER_EN BIT(31) +#define TRAFFIC_SHAPER_RD_CLIENT(num) (0x030 + (num * 4)) +#define TRAFFIC_SHAPER_WR_CLIENT(num) (0x060 + (num * 4)) +#define TRAFFIC_SHAPER_FIXPOINT_FACTOR 4 + +#define MDP_WD_TIMER_0_CTL 0x380 +#define MDP_WD_TIMER_0_CTL2 0x384 +#define MDP_WD_TIMER_0_LOAD_VALUE 0x388 +#define MDP_WD_TIMER_1_CTL 0x390 +#define MDP_WD_TIMER_1_CTL2 0x394 +#define MDP_WD_TIMER_1_LOAD_VALUE 0x398 +#define MDP_WD_TIMER_2_CTL 0x420 +#define MDP_WD_TIMER_2_CTL2 0x424 +#define MDP_WD_TIMER_2_LOAD_VALUE 0x428 +#define MDP_WD_TIMER_3_CTL 0x430 +#define MDP_WD_TIMER_3_CTL2 0x434 +#define MDP_WD_TIMER_3_LOAD_VALUE 0x438 +#define MDP_WD_TIMER_4_CTL 0x440 +#define MDP_WD_TIMER_4_CTL2 0x444 +#define MDP_WD_TIMER_4_LOAD_VALUE 0x448 + +#define MDP_TICK_COUNT 16 +#define XO_CLK_RATE 19200 +#define MS_TICKS_IN_SEC 1000 + +#define CALCULATE_WD_LOAD_VALUE(fps) \ + ((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps))) + +#define DCE_SEL 0x450 + +static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp, + struct split_pipe_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c; + u32 upper_pipe = 0; + u32 lower_pipe = 0; + + if (!mdp || !cfg) + return; + + c = &mdp->hw; + + if (cfg->en) { + if (cfg->mode == INTF_MODE_CMD) { + lower_pipe = FLD_SPLIT_DISPLAY_CMD; + /* interface controlling sw trigger */ + if (cfg->intf == INTF_2) + lower_pipe |= FLD_INTF_1_SW_TRG_MUX; + else + lower_pipe |= FLD_INTF_2_SW_TRG_MUX; + upper_pipe = lower_pipe; + } else { + if (cfg->intf == INTF_2) { + lower_pipe = FLD_INTF_1_SW_TRG_MUX; + upper_pipe = FLD_INTF_2_SW_TRG_MUX; + } else { + lower_pipe = FLD_INTF_2_SW_TRG_MUX; + upper_pipe = FLD_INTF_1_SW_TRG_MUX; + } + } + } + + DPU_REG_WRITE(c, SSPP_SPARE, cfg->split_flush_en ? 0x1 : 0x0); + DPU_REG_WRITE(c, SPLIT_DISPLAY_LOWER_PIPE_CTRL, lower_pipe); + DPU_REG_WRITE(c, SPLIT_DISPLAY_UPPER_PIPE_CTRL, upper_pipe); + DPU_REG_WRITE(c, SPLIT_DISPLAY_EN, cfg->en & 0x1); +} + +static void dpu_hw_setup_cdm_output(struct dpu_hw_mdp *mdp, + struct cdm_output_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c; + u32 out_ctl = 0; + + if (!mdp || !cfg) + return; + + c = &mdp->hw; + + if (cfg->intf_en) + out_ctl |= BIT(19); + + DPU_REG_WRITE(c, MDP_OUT_CTL_0, out_ctl); +} + +static bool dpu_hw_setup_clk_force_ctrl(struct dpu_hw_mdp *mdp, + enum dpu_clk_ctrl_type clk_ctrl, bool enable) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_off, bit_off; + u32 reg_val, new_val; + bool clk_forced_on; + + if (!mdp) + return false; + + c = &mdp->hw; + + if (clk_ctrl <= DPU_CLK_CTRL_NONE || clk_ctrl >= DPU_CLK_CTRL_MAX) + return false; + + reg_off = mdp->caps->clk_ctrls[clk_ctrl].reg_off; + bit_off = mdp->caps->clk_ctrls[clk_ctrl].bit_off; + + reg_val = DPU_REG_READ(c, reg_off); + + if (enable) + new_val = reg_val | BIT(bit_off); + else + new_val = reg_val & ~BIT(bit_off); + + DPU_REG_WRITE(c, reg_off, new_val); + + clk_forced_on = !(reg_val & BIT(bit_off)); + + return clk_forced_on; +} + + +static void dpu_hw_get_danger_status(struct dpu_hw_mdp *mdp, + struct dpu_danger_safe_status *status) +{ + struct dpu_hw_blk_reg_map *c; + u32 value; + + if (!mdp || !status) + return; + + c = &mdp->hw; + + value = DPU_REG_READ(c, DANGER_STATUS); + status->mdp = (value >> 0) & 0x3; + status->sspp[SSPP_VIG0] = (value >> 4) & 0x3; + status->sspp[SSPP_VIG1] = (value >> 6) & 0x3; + status->sspp[SSPP_VIG2] = (value >> 8) & 0x3; + status->sspp[SSPP_VIG3] = (value >> 10) & 0x3; + status->sspp[SSPP_RGB0] = (value >> 12) & 0x3; + status->sspp[SSPP_RGB1] = (value >> 14) & 0x3; + status->sspp[SSPP_RGB2] = (value >> 16) & 0x3; + status->sspp[SSPP_RGB3] = (value >> 18) & 0x3; + status->sspp[SSPP_DMA0] = (value >> 20) & 0x3; + status->sspp[SSPP_DMA1] = (value >> 22) & 0x3; + status->sspp[SSPP_DMA2] = (value >> 28) & 0x3; + status->sspp[SSPP_DMA3] = (value >> 30) & 0x3; + status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x3; + status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x3; +} + +static void dpu_hw_setup_vsync_source(struct dpu_hw_mdp *mdp, + struct dpu_vsync_source_cfg *cfg) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg, wd_load_value, wd_ctl, wd_ctl2, i; + static const u32 pp_offset[PINGPONG_MAX] = {0xC, 0x8, 0x4, 0x13, 0x18}; + + if (!mdp || !cfg || (cfg->pp_count > ARRAY_SIZE(cfg->ppnumber))) + return; + + c = &mdp->hw; + reg = DPU_REG_READ(c, MDP_VSYNC_SEL); + for (i = 0; i < cfg->pp_count; i++) { + int pp_idx = cfg->ppnumber[i] - PINGPONG_0; + + if (pp_idx >= ARRAY_SIZE(pp_offset)) + continue; + + reg &= ~(0xf << pp_offset[pp_idx]); + reg |= (cfg->vsync_source & 0xf) << pp_offset[pp_idx]; + } + DPU_REG_WRITE(c, MDP_VSYNC_SEL, reg); + + if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 && + cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_0) { + switch (cfg->vsync_source) { + case DPU_VSYNC_SOURCE_WD_TIMER_4: + wd_load_value = MDP_WD_TIMER_4_LOAD_VALUE; + wd_ctl = MDP_WD_TIMER_4_CTL; + wd_ctl2 = MDP_WD_TIMER_4_CTL2; + break; + case DPU_VSYNC_SOURCE_WD_TIMER_3: + wd_load_value = MDP_WD_TIMER_3_LOAD_VALUE; + wd_ctl = MDP_WD_TIMER_3_CTL; + wd_ctl2 = MDP_WD_TIMER_3_CTL2; + break; + case DPU_VSYNC_SOURCE_WD_TIMER_2: + wd_load_value = MDP_WD_TIMER_2_LOAD_VALUE; + wd_ctl = MDP_WD_TIMER_2_CTL; + wd_ctl2 = MDP_WD_TIMER_2_CTL2; + break; + case DPU_VSYNC_SOURCE_WD_TIMER_1: + wd_load_value = MDP_WD_TIMER_1_LOAD_VALUE; + wd_ctl = MDP_WD_TIMER_1_CTL; + wd_ctl2 = MDP_WD_TIMER_1_CTL2; + break; + case DPU_VSYNC_SOURCE_WD_TIMER_0: + default: + wd_load_value = MDP_WD_TIMER_0_LOAD_VALUE; + wd_ctl = MDP_WD_TIMER_0_CTL; + wd_ctl2 = MDP_WD_TIMER_0_CTL2; + break; + } + + DPU_REG_WRITE(c, wd_load_value, + CALCULATE_WD_LOAD_VALUE(cfg->frame_rate)); + + DPU_REG_WRITE(c, wd_ctl, BIT(0)); /* clear timer */ + reg = DPU_REG_READ(c, wd_ctl2); + reg |= BIT(8); /* enable heartbeat timer */ + reg |= BIT(0); /* enable WD timer */ + DPU_REG_WRITE(c, wd_ctl2, reg); + + /* make sure that timers are enabled/disabled for vsync state */ + wmb(); + } +} + +static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp, + struct dpu_danger_safe_status *status) +{ + struct dpu_hw_blk_reg_map *c; + u32 value; + + if (!mdp || !status) + return; + + c = &mdp->hw; + + value = DPU_REG_READ(c, SAFE_STATUS); + status->mdp = (value >> 0) & 0x1; + status->sspp[SSPP_VIG0] = (value >> 4) & 0x1; + status->sspp[SSPP_VIG1] = (value >> 6) & 0x1; + status->sspp[SSPP_VIG2] = (value >> 8) & 0x1; + status->sspp[SSPP_VIG3] = (value >> 10) & 0x1; + status->sspp[SSPP_RGB0] = (value >> 12) & 0x1; + status->sspp[SSPP_RGB1] = (value >> 14) & 0x1; + status->sspp[SSPP_RGB2] = (value >> 16) & 0x1; + status->sspp[SSPP_RGB3] = (value >> 18) & 0x1; + status->sspp[SSPP_DMA0] = (value >> 20) & 0x1; + status->sspp[SSPP_DMA1] = (value >> 22) & 0x1; + status->sspp[SSPP_DMA2] = (value >> 28) & 0x1; + status->sspp[SSPP_DMA3] = (value >> 30) & 0x1; + status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x1; + status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1; +} + +static void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m) +{ + struct dpu_hw_blk_reg_map c; + + if (!mdp || !m) + return; + + if (!IS_UBWC_20_SUPPORTED(m->caps->ubwc_version)) + return; + + /* force blk offset to zero to access beginning of register region */ + c = mdp->hw; + c.blk_off = 0x0; + DPU_REG_WRITE(&c, UBWC_STATIC, m->mdp[0].ubwc_static); +} + +static void dpu_hw_intf_audio_select(struct dpu_hw_mdp *mdp) +{ + struct dpu_hw_blk_reg_map *c; + + if (!mdp) + return; + + c = &mdp->hw; + + DPU_REG_WRITE(c, HDMI_DP_CORE_SELECT, 0x1); +} + +static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops, + unsigned long cap) +{ + ops->setup_split_pipe = dpu_hw_setup_split_pipe; + ops->setup_cdm_output = dpu_hw_setup_cdm_output; + ops->setup_clk_force_ctrl = dpu_hw_setup_clk_force_ctrl; + ops->get_danger_status = dpu_hw_get_danger_status; + ops->setup_vsync_source = dpu_hw_setup_vsync_source; + ops->get_safe_status = dpu_hw_get_safe_status; + ops->reset_ubwc = dpu_hw_reset_ubwc; + ops->intf_audio_select = dpu_hw_intf_audio_select; +} + +static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp, + const struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + if (!m || !addr || !b) + return ERR_PTR(-EINVAL); + + for (i = 0; i < m->mdp_count; i++) { + if (mdp == m->mdp[i].id) { + b->base_off = addr; + b->blk_off = m->mdp[i].base; + b->length = m->mdp[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_TOP; + return &m->mdp[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +static struct dpu_hw_blk_ops dpu_hw_ops = { + .start = NULL, + .stop = NULL, +}; + +struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx, + void __iomem *addr, + const struct dpu_mdss_cfg *m) +{ + struct dpu_hw_mdp *mdp; + const struct dpu_mdp_cfg *cfg; + int rc; + + if (!addr || !m) + return ERR_PTR(-EINVAL); + + mdp = kzalloc(sizeof(*mdp), GFP_KERNEL); + if (!mdp) + return ERR_PTR(-ENOMEM); + + cfg = _top_offset(idx, m, addr, &mdp->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(mdp); + return ERR_PTR(-EINVAL); + } + + /* + * Assign ops + */ + mdp->idx = idx; + mdp->caps = cfg; + _setup_mdp_ops(&mdp->ops, mdp->caps->features); + + rc = dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops); + if (rc) { + DPU_ERROR("failed to init hw blk %d\n", rc); + goto blk_init_error; + } + + dpu_dbg_set_dpu_top_offset(mdp->hw.blk_off); + + return mdp; + +blk_init_error: + kzfree(mdp); + + return ERR_PTR(rc); +} + +void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp) +{ + if (mdp) + dpu_hw_blk_destroy(&mdp->base); + kfree(mdp); +} + diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h new file mode 100644 index 000000000000..899925aaa6d7 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h @@ -0,0 +1,202 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_TOP_H +#define _DPU_HW_TOP_H + +#include "dpu_hw_catalog.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" +#include "dpu_hw_blk.h" + +struct dpu_hw_mdp; + +/** + * struct traffic_shaper_cfg: traffic shaper configuration + * @en : enable/disable traffic shaper + * @rd_client : true if read client; false if write client + * @client_id : client identifier + * @bpc_denom : denominator of byte per clk + * @bpc_numer : numerator of byte per clk + */ +struct traffic_shaper_cfg { + bool en; + bool rd_client; + u32 client_id; + u32 bpc_denom; + u64 bpc_numer; +}; + +/** + * struct split_pipe_cfg - pipe configuration for dual display panels + * @en : Enable/disable dual pipe confguration + * @mode : Panel interface mode + * @intf : Interface id for main control path + * @split_flush_en: Allows both the paths to be flushed when master path is + * flushed + */ +struct split_pipe_cfg { + bool en; + enum dpu_intf_mode mode; + enum dpu_intf intf; + bool split_flush_en; +}; + +/** + * struct cdm_output_cfg: output configuration for cdm + * @intf_en : enable/disable interface output + */ +struct cdm_output_cfg { + bool intf_en; +}; + +/** + * struct dpu_danger_safe_status: danger and safe status signals + * @mdp: top level status + * @sspp: source pipe status + */ +struct dpu_danger_safe_status { + u8 mdp; + u8 sspp[SSPP_MAX]; +}; + +/** + * struct dpu_vsync_source_cfg - configure vsync source and configure the + * watchdog timers if required. + * @pp_count: number of ping pongs active + * @frame_rate: Display frame rate + * @ppnumber: ping pong index array + * @vsync_source: vsync source selection + */ +struct dpu_vsync_source_cfg { + u32 pp_count; + u32 frame_rate; + u32 ppnumber[PINGPONG_MAX]; + u32 vsync_source; +}; + +/** + * struct dpu_hw_mdp_ops - interface to the MDP TOP Hw driver functions + * Assumption is these functions will be called after clocks are enabled. + * @setup_split_pipe : Programs the pipe control registers + * @setup_pp_split : Programs the pp split control registers + * @setup_cdm_output : programs cdm control + * @setup_traffic_shaper : programs traffic shaper control + */ +struct dpu_hw_mdp_ops { + /** setup_split_pipe() : Regsiters are not double buffered, thisk + * function should be called before timing control enable + * @mdp : mdp top context driver + * @cfg : upper and lower part of pipe configuration + */ + void (*setup_split_pipe)(struct dpu_hw_mdp *mdp, + struct split_pipe_cfg *p); + + /** + * setup_cdm_output() : Setup selection control of the cdm data path + * @mdp : mdp top context driver + * @cfg : cdm output configuration + */ + void (*setup_cdm_output)(struct dpu_hw_mdp *mdp, + struct cdm_output_cfg *cfg); + + /** + * setup_traffic_shaper() : Setup traffic shaper control + * @mdp : mdp top context driver + * @cfg : traffic shaper configuration + */ + void (*setup_traffic_shaper)(struct dpu_hw_mdp *mdp, + struct traffic_shaper_cfg *cfg); + + /** + * setup_clk_force_ctrl - set clock force control + * @mdp: mdp top context driver + * @clk_ctrl: clock to be controlled + * @enable: force on enable + * @return: if the clock is forced-on by this function + */ + bool (*setup_clk_force_ctrl)(struct dpu_hw_mdp *mdp, + enum dpu_clk_ctrl_type clk_ctrl, bool enable); + + /** + * get_danger_status - get danger status + * @mdp: mdp top context driver + * @status: Pointer to danger safe status + */ + void (*get_danger_status)(struct dpu_hw_mdp *mdp, + struct dpu_danger_safe_status *status); + + /** + * setup_vsync_source - setup vsync source configuration details + * @mdp: mdp top context driver + * @cfg: vsync source selection configuration + */ + void (*setup_vsync_source)(struct dpu_hw_mdp *mdp, + struct dpu_vsync_source_cfg *cfg); + + /** + * get_safe_status - get safe status + * @mdp: mdp top context driver + * @status: Pointer to danger safe status + */ + void (*get_safe_status)(struct dpu_hw_mdp *mdp, + struct dpu_danger_safe_status *status); + + /** + * reset_ubwc - reset top level UBWC configuration + * @mdp: mdp top context driver + * @m: pointer to mdss catalog data + */ + void (*reset_ubwc)(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m); + + /** + * intf_audio_select - select the external interface for audio + * @mdp: mdp top context driver + */ + void (*intf_audio_select)(struct dpu_hw_mdp *mdp); +}; + +struct dpu_hw_mdp { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + /* top */ + enum dpu_mdp idx; + const struct dpu_mdp_cfg *caps; + + /* ops */ + struct dpu_hw_mdp_ops ops; +}; + +/** + * to_dpu_hw_mdp - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_mdp *to_dpu_hw_mdp(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_mdp, base); +} + +/** + * dpu_hw_mdptop_init - initializes the top driver for the passed idx + * @idx: Interface index for which driver object is required + * @addr: Mapped register io address of MDP + * @m: Pointer to mdss catalog data + */ +struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx, + void __iomem *addr, + const struct dpu_mdss_cfg *m); + +void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp); + +#endif /*_DPU_HW_TOP_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c new file mode 100644 index 000000000000..4cabae480a7b --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c @@ -0,0 +1,368 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include "msm_drv.h" +#include "dpu_kms.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" + +/* using a file static variables for debugfs access */ +static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE; + +/* DPU_SCALER_QSEED3 */ +#define QSEED3_HW_VERSION 0x00 +#define QSEED3_OP_MODE 0x04 +#define QSEED3_RGB2Y_COEFF 0x08 +#define QSEED3_PHASE_INIT 0x0C +#define QSEED3_PHASE_STEP_Y_H 0x10 +#define QSEED3_PHASE_STEP_Y_V 0x14 +#define QSEED3_PHASE_STEP_UV_H 0x18 +#define QSEED3_PHASE_STEP_UV_V 0x1C +#define QSEED3_PRELOAD 0x20 +#define QSEED3_DE_SHARPEN 0x24 +#define QSEED3_DE_SHARPEN_CTL 0x28 +#define QSEED3_DE_SHAPE_CTL 0x2C +#define QSEED3_DE_THRESHOLD 0x30 +#define QSEED3_DE_ADJUST_DATA_0 0x34 +#define QSEED3_DE_ADJUST_DATA_1 0x38 +#define QSEED3_DE_ADJUST_DATA_2 0x3C +#define QSEED3_SRC_SIZE_Y_RGB_A 0x40 +#define QSEED3_SRC_SIZE_UV 0x44 +#define QSEED3_DST_SIZE 0x48 +#define QSEED3_COEF_LUT_CTRL 0x4C +#define QSEED3_COEF_LUT_SWAP_BIT 0 +#define QSEED3_COEF_LUT_DIR_BIT 1 +#define QSEED3_COEF_LUT_Y_CIR_BIT 2 +#define QSEED3_COEF_LUT_UV_CIR_BIT 3 +#define QSEED3_COEF_LUT_Y_SEP_BIT 4 +#define QSEED3_COEF_LUT_UV_SEP_BIT 5 +#define QSEED3_BUFFER_CTRL 0x50 +#define QSEED3_CLK_CTRL0 0x54 +#define QSEED3_CLK_CTRL1 0x58 +#define QSEED3_CLK_STATUS 0x5C +#define QSEED3_MISR_CTRL 0x70 +#define QSEED3_MISR_SIGNATURE_0 0x74 +#define QSEED3_MISR_SIGNATURE_1 0x78 +#define QSEED3_PHASE_INIT_Y_H 0x90 +#define QSEED3_PHASE_INIT_Y_V 0x94 +#define QSEED3_PHASE_INIT_UV_H 0x98 +#define QSEED3_PHASE_INIT_UV_V 0x9C +#define QSEED3_COEF_LUT 0x100 +#define QSEED3_FILTERS 5 +#define QSEED3_LUT_REGIONS 4 +#define QSEED3_CIRCULAR_LUTS 9 +#define QSEED3_SEPARABLE_LUTS 10 +#define QSEED3_LUT_SIZE 60 +#define QSEED3_ENABLE 2 +#define QSEED3_DIR_LUT_SIZE (200 * sizeof(u32)) +#define QSEED3_CIR_LUT_SIZE \ + (QSEED3_LUT_SIZE * QSEED3_CIRCULAR_LUTS * sizeof(u32)) +#define QSEED3_SEP_LUT_SIZE \ + (QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32)) + +void dpu_reg_write(struct dpu_hw_blk_reg_map *c, + u32 reg_off, + u32 val, + const char *name) +{ + /* don't need to mutex protect this */ + if (c->log_mask & dpu_hw_util_log_mask) + DPU_DEBUG_DRIVER("[%s:0x%X] <= 0x%X\n", + name, c->blk_off + reg_off, val); + writel_relaxed(val, c->base_off + c->blk_off + reg_off); +} + +int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off) +{ + return readl_relaxed(c->base_off + c->blk_off + reg_off); +} + +u32 *dpu_hw_util_get_log_mask_ptr(void) +{ + return &dpu_hw_util_log_mask; +} + +static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c, + struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset) +{ + int i, j, filter; + int config_lut = 0x0; + unsigned long lut_flags; + u32 lut_addr, lut_offset, lut_len; + u32 *lut[QSEED3_FILTERS] = {NULL, NULL, NULL, NULL, NULL}; + static const uint32_t off_tbl[QSEED3_FILTERS][QSEED3_LUT_REGIONS][2] = { + {{18, 0x000}, {12, 0x120}, {12, 0x1E0}, {8, 0x2A0} }, + {{6, 0x320}, {3, 0x3E0}, {3, 0x440}, {3, 0x4A0} }, + {{6, 0x500}, {3, 0x5c0}, {3, 0x620}, {3, 0x680} }, + {{6, 0x380}, {3, 0x410}, {3, 0x470}, {3, 0x4d0} }, + {{6, 0x560}, {3, 0x5f0}, {3, 0x650}, {3, 0x6b0} }, + }; + + lut_flags = (unsigned long) scaler3_cfg->lut_flag; + if (test_bit(QSEED3_COEF_LUT_DIR_BIT, &lut_flags) && + (scaler3_cfg->dir_len == QSEED3_DIR_LUT_SIZE)) { + lut[0] = scaler3_cfg->dir_lut; + config_lut = 1; + } + if (test_bit(QSEED3_COEF_LUT_Y_CIR_BIT, &lut_flags) && + (scaler3_cfg->y_rgb_cir_lut_idx < QSEED3_CIRCULAR_LUTS) && + (scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) { + lut[1] = scaler3_cfg->cir_lut + + scaler3_cfg->y_rgb_cir_lut_idx * QSEED3_LUT_SIZE; + config_lut = 1; + } + if (test_bit(QSEED3_COEF_LUT_UV_CIR_BIT, &lut_flags) && + (scaler3_cfg->uv_cir_lut_idx < QSEED3_CIRCULAR_LUTS) && + (scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) { + lut[2] = scaler3_cfg->cir_lut + + scaler3_cfg->uv_cir_lut_idx * QSEED3_LUT_SIZE; + config_lut = 1; + } + if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) && + (scaler3_cfg->y_rgb_sep_lut_idx < QSEED3_SEPARABLE_LUTS) && + (scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) { + lut[3] = scaler3_cfg->sep_lut + + scaler3_cfg->y_rgb_sep_lut_idx * QSEED3_LUT_SIZE; + config_lut = 1; + } + if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) && + (scaler3_cfg->uv_sep_lut_idx < QSEED3_SEPARABLE_LUTS) && + (scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) { + lut[4] = scaler3_cfg->sep_lut + + scaler3_cfg->uv_sep_lut_idx * QSEED3_LUT_SIZE; + config_lut = 1; + } + + if (config_lut) { + for (filter = 0; filter < QSEED3_FILTERS; filter++) { + if (!lut[filter]) + continue; + lut_offset = 0; + for (i = 0; i < QSEED3_LUT_REGIONS; i++) { + lut_addr = QSEED3_COEF_LUT + offset + + off_tbl[filter][i][1]; + lut_len = off_tbl[filter][i][0] << 2; + for (j = 0; j < lut_len; j++) { + DPU_REG_WRITE(c, + lut_addr, + (lut[filter])[lut_offset++]); + lut_addr += 4; + } + } + } + } + + if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags)) + DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0)); + +} + +static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c, + struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset) +{ + u32 sharp_lvl, sharp_ctl, shape_ctl, de_thr; + u32 adjust_a, adjust_b, adjust_c; + + if (!de_cfg->enable) + return; + + sharp_lvl = (de_cfg->sharpen_level1 & 0x1FF) | + ((de_cfg->sharpen_level2 & 0x1FF) << 16); + + sharp_ctl = ((de_cfg->limit & 0xF) << 9) | + ((de_cfg->prec_shift & 0x7) << 13) | + ((de_cfg->clip & 0x7) << 16); + + shape_ctl = (de_cfg->thr_quiet & 0xFF) | + ((de_cfg->thr_dieout & 0x3FF) << 16); + + de_thr = (de_cfg->thr_low & 0x3FF) | + ((de_cfg->thr_high & 0x3FF) << 16); + + adjust_a = (de_cfg->adjust_a[0] & 0x3FF) | + ((de_cfg->adjust_a[1] & 0x3FF) << 10) | + ((de_cfg->adjust_a[2] & 0x3FF) << 20); + + adjust_b = (de_cfg->adjust_b[0] & 0x3FF) | + ((de_cfg->adjust_b[1] & 0x3FF) << 10) | + ((de_cfg->adjust_b[2] & 0x3FF) << 20); + + adjust_c = (de_cfg->adjust_c[0] & 0x3FF) | + ((de_cfg->adjust_c[1] & 0x3FF) << 10) | + ((de_cfg->adjust_c[2] & 0x3FF) << 20); + + DPU_REG_WRITE(c, QSEED3_DE_SHARPEN + offset, sharp_lvl); + DPU_REG_WRITE(c, QSEED3_DE_SHARPEN_CTL + offset, sharp_ctl); + DPU_REG_WRITE(c, QSEED3_DE_SHAPE_CTL + offset, shape_ctl); + DPU_REG_WRITE(c, QSEED3_DE_THRESHOLD + offset, de_thr); + DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_0 + offset, adjust_a); + DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_1 + offset, adjust_b); + DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_2 + offset, adjust_c); + +} + +void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c, + struct dpu_hw_scaler3_cfg *scaler3_cfg, + u32 scaler_offset, u32 scaler_version, + const struct dpu_format *format) +{ + u32 op_mode = 0; + u32 phase_init, preload, src_y_rgb, src_uv, dst; + + if (!scaler3_cfg->enable) + goto end; + + op_mode |= BIT(0); + op_mode |= (scaler3_cfg->y_rgb_filter_cfg & 0x3) << 16; + + if (format && DPU_FORMAT_IS_YUV(format)) { + op_mode |= BIT(12); + op_mode |= (scaler3_cfg->uv_filter_cfg & 0x3) << 24; + } + + op_mode |= (scaler3_cfg->blend_cfg & 1) << 31; + op_mode |= (scaler3_cfg->dir_en) ? BIT(4) : 0; + + preload = + ((scaler3_cfg->preload_x[0] & 0x7F) << 0) | + ((scaler3_cfg->preload_y[0] & 0x7F) << 8) | + ((scaler3_cfg->preload_x[1] & 0x7F) << 16) | + ((scaler3_cfg->preload_y[1] & 0x7F) << 24); + + src_y_rgb = (scaler3_cfg->src_width[0] & 0x1FFFF) | + ((scaler3_cfg->src_height[0] & 0x1FFFF) << 16); + + src_uv = (scaler3_cfg->src_width[1] & 0x1FFFF) | + ((scaler3_cfg->src_height[1] & 0x1FFFF) << 16); + + dst = (scaler3_cfg->dst_width & 0x1FFFF) | + ((scaler3_cfg->dst_height & 0x1FFFF) << 16); + + if (scaler3_cfg->de.enable) { + _dpu_hw_setup_scaler3_de(c, &scaler3_cfg->de, scaler_offset); + op_mode |= BIT(8); + } + + if (scaler3_cfg->lut_flag) + _dpu_hw_setup_scaler3_lut(c, scaler3_cfg, + scaler_offset); + + if (scaler_version == 0x1002) { + phase_init = + ((scaler3_cfg->init_phase_x[0] & 0x3F) << 0) | + ((scaler3_cfg->init_phase_y[0] & 0x3F) << 8) | + ((scaler3_cfg->init_phase_x[1] & 0x3F) << 16) | + ((scaler3_cfg->init_phase_y[1] & 0x3F) << 24); + DPU_REG_WRITE(c, QSEED3_PHASE_INIT + scaler_offset, phase_init); + } else { + DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_H + scaler_offset, + scaler3_cfg->init_phase_x[0] & 0x1FFFFF); + DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_V + scaler_offset, + scaler3_cfg->init_phase_y[0] & 0x1FFFFF); + DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_H + scaler_offset, + scaler3_cfg->init_phase_x[1] & 0x1FFFFF); + DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_V + scaler_offset, + scaler3_cfg->init_phase_y[1] & 0x1FFFFF); + } + + DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_H + scaler_offset, + scaler3_cfg->phase_step_x[0] & 0xFFFFFF); + + DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_V + scaler_offset, + scaler3_cfg->phase_step_y[0] & 0xFFFFFF); + + DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_H + scaler_offset, + scaler3_cfg->phase_step_x[1] & 0xFFFFFF); + + DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_V + scaler_offset, + scaler3_cfg->phase_step_y[1] & 0xFFFFFF); + + DPU_REG_WRITE(c, QSEED3_PRELOAD + scaler_offset, preload); + + DPU_REG_WRITE(c, QSEED3_SRC_SIZE_Y_RGB_A + scaler_offset, src_y_rgb); + + DPU_REG_WRITE(c, QSEED3_SRC_SIZE_UV + scaler_offset, src_uv); + + DPU_REG_WRITE(c, QSEED3_DST_SIZE + scaler_offset, dst); + +end: + if (format && !DPU_FORMAT_IS_DX(format)) + op_mode |= BIT(14); + + if (format && format->alpha_enable) { + op_mode |= BIT(10); + if (scaler_version == 0x1002) + op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x1) << 30; + else + op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x3) << 29; + } + + DPU_REG_WRITE(c, QSEED3_OP_MODE + scaler_offset, op_mode); +} + +u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c, + u32 scaler_offset) +{ + return DPU_REG_READ(c, QSEED3_HW_VERSION + scaler_offset); +} + +void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c, + u32 csc_reg_off, + struct dpu_csc_cfg *data, bool csc10) +{ + static const u32 matrix_shift = 7; + u32 clamp_shift = csc10 ? 16 : 8; + u32 val; + + /* matrix coeff - convert S15.16 to S4.9 */ + val = ((data->csc_mv[0] >> matrix_shift) & 0x1FFF) | + (((data->csc_mv[1] >> matrix_shift) & 0x1FFF) << 16); + DPU_REG_WRITE(c, csc_reg_off, val); + val = ((data->csc_mv[2] >> matrix_shift) & 0x1FFF) | + (((data->csc_mv[3] >> matrix_shift) & 0x1FFF) << 16); + DPU_REG_WRITE(c, csc_reg_off + 0x4, val); + val = ((data->csc_mv[4] >> matrix_shift) & 0x1FFF) | + (((data->csc_mv[5] >> matrix_shift) & 0x1FFF) << 16); + DPU_REG_WRITE(c, csc_reg_off + 0x8, val); + val = ((data->csc_mv[6] >> matrix_shift) & 0x1FFF) | + (((data->csc_mv[7] >> matrix_shift) & 0x1FFF) << 16); + DPU_REG_WRITE(c, csc_reg_off + 0xc, val); + val = (data->csc_mv[8] >> matrix_shift) & 0x1FFF; + DPU_REG_WRITE(c, csc_reg_off + 0x10, val); + + /* Pre clamp */ + val = (data->csc_pre_lv[0] << clamp_shift) | data->csc_pre_lv[1]; + DPU_REG_WRITE(c, csc_reg_off + 0x14, val); + val = (data->csc_pre_lv[2] << clamp_shift) | data->csc_pre_lv[3]; + DPU_REG_WRITE(c, csc_reg_off + 0x18, val); + val = (data->csc_pre_lv[4] << clamp_shift) | data->csc_pre_lv[5]; + DPU_REG_WRITE(c, csc_reg_off + 0x1c, val); + + /* Post clamp */ + val = (data->csc_post_lv[0] << clamp_shift) | data->csc_post_lv[1]; + DPU_REG_WRITE(c, csc_reg_off + 0x20, val); + val = (data->csc_post_lv[2] << clamp_shift) | data->csc_post_lv[3]; + DPU_REG_WRITE(c, csc_reg_off + 0x24, val); + val = (data->csc_post_lv[4] << clamp_shift) | data->csc_post_lv[5]; + DPU_REG_WRITE(c, csc_reg_off + 0x28, val); + + /* Pre-Bias */ + DPU_REG_WRITE(c, csc_reg_off + 0x2c, data->csc_pre_bv[0]); + DPU_REG_WRITE(c, csc_reg_off + 0x30, data->csc_pre_bv[1]); + DPU_REG_WRITE(c, csc_reg_off + 0x34, data->csc_pre_bv[2]); + + /* Post-Bias */ + DPU_REG_WRITE(c, csc_reg_off + 0x38, data->csc_post_bv[0]); + DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]); + DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h new file mode 100644 index 000000000000..1240f505ca53 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h @@ -0,0 +1,348 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_UTIL_H +#define _DPU_HW_UTIL_H + +#include <linux/io.h> +#include <linux/slab.h> +#include "dpu_hw_mdss.h" + +#define REG_MASK(n) ((BIT(n)) - 1) +struct dpu_format_extended; + +/* + * This is the common struct maintained by each sub block + * for mapping the register offsets in this block to the + * absoulute IO address + * @base_off: mdp register mapped offset + * @blk_off: pipe offset relative to mdss offset + * @length length of register block offset + * @xin_id xin id + * @hwversion mdss hw version number + */ +struct dpu_hw_blk_reg_map { + void __iomem *base_off; + u32 blk_off; + u32 length; + u32 xin_id; + u32 hwversion; + u32 log_mask; +}; + +/** + * struct dpu_hw_scaler3_de_cfg : QSEEDv3 detail enhancer configuration + * @enable: detail enhancer enable/disable + * @sharpen_level1: sharpening strength for noise + * @sharpen_level2: sharpening strength for signal + * @ clip: clip shift + * @ limit: limit value + * @ thr_quiet: quiet threshold + * @ thr_dieout: dieout threshold + * @ thr_high: low threshold + * @ thr_high: high threshold + * @ prec_shift: precision shift + * @ adjust_a: A-coefficients for mapping curve + * @ adjust_b: B-coefficients for mapping curve + * @ adjust_c: C-coefficients for mapping curve + */ +struct dpu_hw_scaler3_de_cfg { + u32 enable; + int16_t sharpen_level1; + int16_t sharpen_level2; + uint16_t clip; + uint16_t limit; + uint16_t thr_quiet; + uint16_t thr_dieout; + uint16_t thr_low; + uint16_t thr_high; + uint16_t prec_shift; + int16_t adjust_a[DPU_MAX_DE_CURVES]; + int16_t adjust_b[DPU_MAX_DE_CURVES]; + int16_t adjust_c[DPU_MAX_DE_CURVES]; +}; + + +/** + * struct dpu_hw_scaler3_cfg : QSEEDv3 configuration + * @enable: scaler enable + * @dir_en: direction detection block enable + * @ init_phase_x: horizontal initial phase + * @ phase_step_x: horizontal phase step + * @ init_phase_y: vertical initial phase + * @ phase_step_y: vertical phase step + * @ preload_x: horizontal preload value + * @ preload_y: vertical preload value + * @ src_width: source width + * @ src_height: source height + * @ dst_width: destination width + * @ dst_height: destination height + * @ y_rgb_filter_cfg: y/rgb plane filter configuration + * @ uv_filter_cfg: uv plane filter configuration + * @ alpha_filter_cfg: alpha filter configuration + * @ blend_cfg: blend coefficients configuration + * @ lut_flag: scaler LUT update flags + * 0x1 swap LUT bank + * 0x2 update 2D filter LUT + * 0x4 update y circular filter LUT + * 0x8 update uv circular filter LUT + * 0x10 update y separable filter LUT + * 0x20 update uv separable filter LUT + * @ dir_lut_idx: 2D filter LUT index + * @ y_rgb_cir_lut_idx: y circular filter LUT index + * @ uv_cir_lut_idx: uv circular filter LUT index + * @ y_rgb_sep_lut_idx: y circular filter LUT index + * @ uv_sep_lut_idx: uv separable filter LUT index + * @ dir_lut: pointer to 2D LUT + * @ cir_lut: pointer to circular filter LUT + * @ sep_lut: pointer to separable filter LUT + * @ de: detail enhancer configuration + */ +struct dpu_hw_scaler3_cfg { + u32 enable; + u32 dir_en; + int32_t init_phase_x[DPU_MAX_PLANES]; + int32_t phase_step_x[DPU_MAX_PLANES]; + int32_t init_phase_y[DPU_MAX_PLANES]; + int32_t phase_step_y[DPU_MAX_PLANES]; + + u32 preload_x[DPU_MAX_PLANES]; + u32 preload_y[DPU_MAX_PLANES]; + u32 src_width[DPU_MAX_PLANES]; + u32 src_height[DPU_MAX_PLANES]; + + u32 dst_width; + u32 dst_height; + + u32 y_rgb_filter_cfg; + u32 uv_filter_cfg; + u32 alpha_filter_cfg; + u32 blend_cfg; + + u32 lut_flag; + u32 dir_lut_idx; + + u32 y_rgb_cir_lut_idx; + u32 uv_cir_lut_idx; + u32 y_rgb_sep_lut_idx; + u32 uv_sep_lut_idx; + u32 *dir_lut; + size_t dir_len; + u32 *cir_lut; + size_t cir_len; + u32 *sep_lut; + size_t sep_len; + + /* + * Detail enhancer settings + */ + struct dpu_hw_scaler3_de_cfg de; +}; + +struct dpu_hw_scaler3_lut_cfg { + bool is_configured; + u32 *dir_lut; + size_t dir_len; + u32 *cir_lut; + size_t cir_len; + u32 *sep_lut; + size_t sep_len; +}; + +/** + * struct dpu_drm_pix_ext_v1 - version 1 of pixel ext structure + * @num_ext_pxls_lr: Number of total horizontal pixels + * @num_ext_pxls_tb: Number of total vertical lines + * @left_ftch: Number of extra pixels to overfetch from left + * @right_ftch: Number of extra pixels to overfetch from right + * @top_ftch: Number of extra lines to overfetch from top + * @btm_ftch: Number of extra lines to overfetch from bottom + * @left_rpt: Number of extra pixels to repeat from left + * @right_rpt: Number of extra pixels to repeat from right + * @top_rpt: Number of extra lines to repeat from top + * @btm_rpt: Number of extra lines to repeat from bottom + */ +struct dpu_drm_pix_ext_v1 { + /* + * Number of pixels ext in left, right, top and bottom direction + * for all color components. + */ + int32_t num_ext_pxls_lr[DPU_MAX_PLANES]; + int32_t num_ext_pxls_tb[DPU_MAX_PLANES]; + + /* + * Number of pixels needs to be overfetched in left, right, top + * and bottom directions from source image for scaling. + */ + int32_t left_ftch[DPU_MAX_PLANES]; + int32_t right_ftch[DPU_MAX_PLANES]; + int32_t top_ftch[DPU_MAX_PLANES]; + int32_t btm_ftch[DPU_MAX_PLANES]; + /* + * Number of pixels needs to be repeated in left, right, top and + * bottom directions for scaling. + */ + int32_t left_rpt[DPU_MAX_PLANES]; + int32_t right_rpt[DPU_MAX_PLANES]; + int32_t top_rpt[DPU_MAX_PLANES]; + int32_t btm_rpt[DPU_MAX_PLANES]; + +}; + +/** + * struct dpu_drm_de_v1 - version 1 of detail enhancer structure + * @enable: Enables/disables detail enhancer + * @sharpen_level1: Sharpening strength for noise + * @sharpen_level2: Sharpening strength for context + * @clip: Clip coefficient + * @limit: Detail enhancer limit factor + * @thr_quiet: Quite zone threshold + * @thr_dieout: Die-out zone threshold + * @thr_low: Linear zone left threshold + * @thr_high: Linear zone right threshold + * @prec_shift: Detail enhancer precision + * @adjust_a: Mapping curves A coefficients + * @adjust_b: Mapping curves B coefficients + * @adjust_c: Mapping curves C coefficients + */ +struct dpu_drm_de_v1 { + uint32_t enable; + int16_t sharpen_level1; + int16_t sharpen_level2; + uint16_t clip; + uint16_t limit; + uint16_t thr_quiet; + uint16_t thr_dieout; + uint16_t thr_low; + uint16_t thr_high; + uint16_t prec_shift; + int16_t adjust_a[DPU_MAX_DE_CURVES]; + int16_t adjust_b[DPU_MAX_DE_CURVES]; + int16_t adjust_c[DPU_MAX_DE_CURVES]; +}; + +/** + * struct dpu_drm_scaler_v2 - version 2 of struct dpu_drm_scaler + * @enable: Scaler enable + * @dir_en: Detail enhancer enable + * @pe: Pixel extension settings + * @horz_decimate: Horizontal decimation factor + * @vert_decimate: Vertical decimation factor + * @init_phase_x: Initial scaler phase values for x + * @phase_step_x: Phase step values for x + * @init_phase_y: Initial scaler phase values for y + * @phase_step_y: Phase step values for y + * @preload_x: Horizontal preload value + * @preload_y: Vertical preload value + * @src_width: Source width + * @src_height: Source height + * @dst_width: Destination width + * @dst_height: Destination height + * @y_rgb_filter_cfg: Y/RGB plane filter configuration + * @uv_filter_cfg: UV plane filter configuration + * @alpha_filter_cfg: Alpha filter configuration + * @blend_cfg: Selection of blend coefficients + * @lut_flag: LUT configuration flags + * @dir_lut_idx: 2d 4x4 LUT index + * @y_rgb_cir_lut_idx: Y/RGB circular LUT index + * @uv_cir_lut_idx: UV circular LUT index + * @y_rgb_sep_lut_idx: Y/RGB separable LUT index + * @uv_sep_lut_idx: UV separable LUT index + * @de: Detail enhancer settings + */ +struct dpu_drm_scaler_v2 { + /* + * General definitions + */ + uint32_t enable; + uint32_t dir_en; + + /* + * Pix ext settings + */ + struct dpu_drm_pix_ext_v1 pe; + + /* + * Decimation settings + */ + uint32_t horz_decimate; + uint32_t vert_decimate; + + /* + * Phase settings + */ + int32_t init_phase_x[DPU_MAX_PLANES]; + int32_t phase_step_x[DPU_MAX_PLANES]; + int32_t init_phase_y[DPU_MAX_PLANES]; + int32_t phase_step_y[DPU_MAX_PLANES]; + + uint32_t preload_x[DPU_MAX_PLANES]; + uint32_t preload_y[DPU_MAX_PLANES]; + uint32_t src_width[DPU_MAX_PLANES]; + uint32_t src_height[DPU_MAX_PLANES]; + + uint32_t dst_width; + uint32_t dst_height; + + uint32_t y_rgb_filter_cfg; + uint32_t uv_filter_cfg; + uint32_t alpha_filter_cfg; + uint32_t blend_cfg; + + uint32_t lut_flag; + uint32_t dir_lut_idx; + + /* for Y(RGB) and UV planes*/ + uint32_t y_rgb_cir_lut_idx; + uint32_t uv_cir_lut_idx; + uint32_t y_rgb_sep_lut_idx; + uint32_t uv_sep_lut_idx; + + /* + * Detail enhancer settings + */ + struct dpu_drm_de_v1 de; +}; + + +u32 *dpu_hw_util_get_log_mask_ptr(void); + +void dpu_reg_write(struct dpu_hw_blk_reg_map *c, + u32 reg_off, + u32 val, + const char *name); +int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off); + +#define DPU_REG_WRITE(c, off, val) dpu_reg_write(c, off, val, #off) +#define DPU_REG_READ(c, off) dpu_reg_read(c, off) + +#define MISR_FRAME_COUNT_MASK 0xFF +#define MISR_CTRL_ENABLE BIT(8) +#define MISR_CTRL_STATUS BIT(9) +#define MISR_CTRL_STATUS_CLEAR BIT(10) +#define INTF_MISR_CTRL_FREE_RUN_MASK BIT(31) + +void *dpu_hw_util_get_dir(void); + +void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c, + struct dpu_hw_scaler3_cfg *scaler3_cfg, + u32 scaler_offset, u32 scaler_version, + const struct dpu_format *format); + +u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c, + u32 scaler_offset); + +void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c, + u32 csc_reg_off, + struct dpu_csc_cfg *data, bool csc10); + +#endif /* _DPU_HW_UTIL_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c new file mode 100644 index 000000000000..d43905525f92 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c @@ -0,0 +1,275 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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 "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_vbif.h" +#include "dpu_dbg.h" + +#define VBIF_VERSION 0x0000 +#define VBIF_CLK_FORCE_CTRL0 0x0008 +#define VBIF_CLK_FORCE_CTRL1 0x000C +#define VBIF_QOS_REMAP_00 0x0020 +#define VBIF_QOS_REMAP_01 0x0024 +#define VBIF_QOS_REMAP_10 0x0028 +#define VBIF_QOS_REMAP_11 0x002C +#define VBIF_WRITE_GATHER_EN 0x00AC +#define VBIF_IN_RD_LIM_CONF0 0x00B0 +#define VBIF_IN_RD_LIM_CONF1 0x00B4 +#define VBIF_IN_RD_LIM_CONF2 0x00B8 +#define VBIF_IN_WR_LIM_CONF0 0x00C0 +#define VBIF_IN_WR_LIM_CONF1 0x00C4 +#define VBIF_IN_WR_LIM_CONF2 0x00C8 +#define VBIF_OUT_RD_LIM_CONF0 0x00D0 +#define VBIF_OUT_WR_LIM_CONF0 0x00D4 +#define VBIF_OUT_AXI_AMEMTYPE_CONF0 0x0160 +#define VBIF_OUT_AXI_AMEMTYPE_CONF1 0x0164 +#define VBIF_XIN_PND_ERR 0x0190 +#define VBIF_XIN_SRC_ERR 0x0194 +#define VBIF_XIN_CLR_ERR 0x019C +#define VBIF_XIN_HALT_CTRL0 0x0200 +#define VBIF_XIN_HALT_CTRL1 0x0204 +#define VBIF_XINL_QOS_RP_REMAP_000 0x0550 +#define VBIF_XINL_QOS_LVL_REMAP_000 0x0590 + +static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif, + u32 *pnd_errors, u32 *src_errors) +{ + struct dpu_hw_blk_reg_map *c; + u32 pnd, src; + + if (!vbif) + return; + c = &vbif->hw; + pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR); + src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR); + + if (pnd_errors) + *pnd_errors = pnd; + if (src_errors) + *src_errors = src; + + DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src); +} + +static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 value) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_off; + u32 bit_off; + u32 reg_val; + + /* + * Assume 4 bits per bit field, 8 fields per 32-bit register so + * 16 bit fields maximum across two registers + */ + if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16) + return; + + c = &vbif->hw; + + if (xin_id >= 8) { + xin_id -= 8; + reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1; + } else { + reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0; + } + bit_off = (xin_id & 0x7) * 4; + reg_val = DPU_REG_READ(c, reg_off); + reg_val &= ~(0x7 << bit_off); + reg_val |= (value & 0x7) << bit_off; + DPU_REG_WRITE(c, reg_off, reg_val); +} + +static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd, u32 limit) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + u32 reg_off; + u32 bit_off; + + if (rd) + reg_off = VBIF_IN_RD_LIM_CONF0; + else + reg_off = VBIF_IN_WR_LIM_CONF0; + + reg_off += (xin_id / 4) * 4; + bit_off = (xin_id % 4) * 8; + reg_val = DPU_REG_READ(c, reg_off); + reg_val &= ~(0xFF << bit_off); + reg_val |= (limit) << bit_off; + DPU_REG_WRITE(c, reg_off, reg_val); +} + +static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + u32 reg_off; + u32 bit_off; + u32 limit; + + if (rd) + reg_off = VBIF_IN_RD_LIM_CONF0; + else + reg_off = VBIF_IN_WR_LIM_CONF0; + + reg_off += (xin_id / 4) * 4; + bit_off = (xin_id % 4) * 8; + reg_val = DPU_REG_READ(c, reg_off); + limit = (reg_val >> bit_off) & 0xFF; + + return limit; +} + +static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif, + u32 xin_id, bool enable) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + + reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0); + + if (enable) + reg_val |= BIT(xin_id); + else + reg_val &= ~BIT(xin_id); + + DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val); +} + +static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif, + u32 xin_id) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + + reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1); + + return (reg_val & BIT(xin_id)) ? true : false; +} + +static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 level, u32 remap_level) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift; + + if (!vbif) + return; + + c = &vbif->hw; + + reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8); + reg_shift = (xin_id & 0x7) * 4; + + reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high); + reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high); + + mask = 0x7 << reg_shift; + + reg_val &= ~mask; + reg_val |= (remap_level << reg_shift) & mask; + + reg_val_lvl &= ~mask; + reg_val_lvl |= (remap_level << reg_shift) & mask; + + DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val); + DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl); +} + +static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_val; + + if (!vbif || xin_id >= MAX_XIN_COUNT) + return; + + c = &vbif->hw; + + reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN); + reg_val |= BIT(xin_id); + DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val); +} + +static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops, + unsigned long cap) +{ + ops->set_limit_conf = dpu_hw_set_limit_conf; + ops->get_limit_conf = dpu_hw_get_limit_conf; + ops->set_halt_ctrl = dpu_hw_set_halt_ctrl; + ops->get_halt_ctrl = dpu_hw_get_halt_ctrl; + if (test_bit(DPU_VBIF_QOS_REMAP, &cap)) + ops->set_qos_remap = dpu_hw_set_qos_remap; + ops->set_mem_type = dpu_hw_set_mem_type; + ops->clear_errors = dpu_hw_clear_errors; + ops->set_write_gather_en = dpu_hw_set_write_gather_en; +} + +static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif, + const struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->vbif_count; i++) { + if (vbif == m->vbif[i].id) { + b->base_off = addr; + b->blk_off = m->vbif[i].base; + b->length = m->vbif[i].len; + b->hwversion = m->hwversion; + b->log_mask = DPU_DBG_MASK_VBIF; + return &m->vbif[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx, + void __iomem *addr, + const struct dpu_mdss_cfg *m) +{ + struct dpu_hw_vbif *c; + const struct dpu_vbif_cfg *cfg; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _top_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + return ERR_PTR(-EINVAL); + } + + /* + * Assign ops + */ + c->idx = idx; + c->cap = cfg; + _setup_vbif_ops(&c->ops, c->cap->features); + + /* no need to register sub-range in dpu dbg, dump entire vbif io base */ + + return c; +} + +void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif) +{ + kfree(vbif); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h new file mode 100644 index 000000000000..471ff673c045 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h @@ -0,0 +1,128 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HW_VBIF_H +#define _DPU_HW_VBIF_H + +#include "dpu_hw_catalog.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_util.h" + +struct dpu_hw_vbif; + +/** + * struct dpu_hw_vbif_ops : Interface to the VBIF hardware driver functions + * Assumption is these functions will be called after clocks are enabled + */ +struct dpu_hw_vbif_ops { + /** + * set_limit_conf - set transaction limit config + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @rd: true for read limit; false for write limit + * @limit: outstanding transaction limit + */ + void (*set_limit_conf)(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd, u32 limit); + + /** + * get_limit_conf - get transaction limit config + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @rd: true for read limit; false for write limit + * @return: outstanding transaction limit + */ + u32 (*get_limit_conf)(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd); + + /** + * set_halt_ctrl - set halt control + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @enable: halt control enable + */ + void (*set_halt_ctrl)(struct dpu_hw_vbif *vbif, + u32 xin_id, bool enable); + + /** + * get_halt_ctrl - get halt control + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @return: halt control enable + */ + bool (*get_halt_ctrl)(struct dpu_hw_vbif *vbif, + u32 xin_id); + + /** + * set_qos_remap - set QoS priority remap + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @level: priority level + * @remap_level: remapped level + */ + void (*set_qos_remap)(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 level, u32 remap_level); + + /** + * set_mem_type - set memory type + * @vbif: vbif context driver + * @xin_id: client interface identifier + * @value: memory type value + */ + void (*set_mem_type)(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 value); + + /** + * clear_errors - clear any vbif errors + * This function clears any detected pending/source errors + * on the VBIF interface, and optionally returns the detected + * error mask(s). + * @vbif: vbif context driver + * @pnd_errors: pointer to pending error reporting variable + * @src_errors: pointer to source error reporting variable + */ + void (*clear_errors)(struct dpu_hw_vbif *vbif, + u32 *pnd_errors, u32 *src_errors); + + /** + * set_write_gather_en - set write_gather enable + * @vbif: vbif context driver + * @xin_id: client interface identifier + */ + void (*set_write_gather_en)(struct dpu_hw_vbif *vbif, u32 xin_id); +}; + +struct dpu_hw_vbif { + /* base */ + struct dpu_hw_blk_reg_map hw; + + /* vbif */ + enum dpu_vbif idx; + const struct dpu_vbif_cfg *cap; + + /* ops */ + struct dpu_hw_vbif_ops ops; +}; + +/** + * dpu_hw_vbif_init - initializes the vbif driver for the passed interface idx + * @idx: Interface index for which driver object is required + * @addr: Mapped register io address of MDSS + * @m: Pointer to mdss catalog data + */ +struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx, + void __iomem *addr, + const struct dpu_mdss_cfg *m); + +void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif); + +#endif /*_DPU_HW_VBIF_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h new file mode 100644 index 000000000000..5b2bc9b65b15 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h @@ -0,0 +1,56 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef _DPU_HWIO_H +#define _DPU_HWIO_H + +#include "dpu_hw_util.h" + +/** + * MDP TOP block Register and bit fields and defines + */ +#define DISP_INTF_SEL 0x004 +#define INTR_EN 0x010 +#define INTR_STATUS 0x014 +#define INTR_CLEAR 0x018 +#define INTR2_EN 0x008 +#define INTR2_STATUS 0x00c +#define INTR2_CLEAR 0x02c +#define HIST_INTR_EN 0x01c +#define HIST_INTR_STATUS 0x020 +#define HIST_INTR_CLEAR 0x024 +#define INTF_INTR_EN 0x1C0 +#define INTF_INTR_STATUS 0x1C4 +#define INTF_INTR_CLEAR 0x1C8 +#define SPLIT_DISPLAY_EN 0x2F4 +#define SPLIT_DISPLAY_UPPER_PIPE_CTRL 0x2F8 +#define DSPP_IGC_COLOR0_RAM_LUTN 0x300 +#define DSPP_IGC_COLOR1_RAM_LUTN 0x304 +#define DSPP_IGC_COLOR2_RAM_LUTN 0x308 +#define HW_EVENTS_CTL 0x37C +#define CLK_CTRL3 0x3A8 +#define CLK_STATUS3 0x3AC +#define CLK_CTRL4 0x3B0 +#define CLK_STATUS4 0x3B4 +#define CLK_CTRL5 0x3B8 +#define CLK_STATUS5 0x3BC +#define CLK_CTRL7 0x3D0 +#define CLK_STATUS7 0x3D4 +#define SPLIT_DISPLAY_LOWER_PIPE_CTRL 0x3F0 +#define SPLIT_DISPLAY_TE_LINE_INTERVAL 0x3F4 +#define INTF_SW_RESET_MASK 0x3FC +#define HDMI_DP_CORE_SELECT 0x408 +#define MDP_OUT_CTL_0 0x410 +#define MDP_VSYNC_SEL 0x414 +#define DCE_SEL 0x450 + +#endif /*_DPU_HWIO_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c new file mode 100644 index 000000000000..790d39f816dc --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c @@ -0,0 +1,203 @@ +/* Copyright (c) 2012-2015, 2017-2018, The Linux Foundation. + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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> +#include <linux/clk/clk-conf.h> +#include <linux/err.h> +#include <linux/delay.h> + +#include "dpu_io_util.h" + +void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk) +{ + int i; + + for (i = num_clk - 1; i >= 0; i--) { + if (clk_arry[i].clk) + clk_put(clk_arry[i].clk); + clk_arry[i].clk = NULL; + } +} + +int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk) +{ + int i, rc = 0; + + for (i = 0; i < num_clk; i++) { + clk_arry[i].clk = clk_get(dev, clk_arry[i].clk_name); + rc = PTR_ERR_OR_ZERO(clk_arry[i].clk); + if (rc) { + DEV_ERR("%pS->%s: '%s' get failed. rc=%d\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name, rc); + goto error; + } + } + + return rc; + +error: + for (i--; i >= 0; i--) { + if (clk_arry[i].clk) + clk_put(clk_arry[i].clk); + clk_arry[i].clk = NULL; + } + + return rc; +} + +int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk) +{ + int i, rc = 0; + + for (i = 0; i < num_clk; i++) { + if (clk_arry[i].clk) { + if (clk_arry[i].type != DSS_CLK_AHB) { + DEV_DBG("%pS->%s: '%s' rate %ld\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name, + clk_arry[i].rate); + rc = clk_set_rate(clk_arry[i].clk, + clk_arry[i].rate); + if (rc) { + DEV_ERR("%pS->%s: %s failed. rc=%d\n", + __builtin_return_address(0), + __func__, + clk_arry[i].clk_name, rc); + break; + } + } + } else { + DEV_ERR("%pS->%s: '%s' is not available\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name); + rc = -EPERM; + break; + } + } + + return rc; +} + +int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable) +{ + int i, rc = 0; + + if (enable) { + for (i = 0; i < num_clk; i++) { + DEV_DBG("%pS->%s: enable '%s'\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name); + if (clk_arry[i].clk) { + rc = clk_prepare_enable(clk_arry[i].clk); + if (rc) + DEV_ERR("%pS->%s: %s en fail. rc=%d\n", + __builtin_return_address(0), + __func__, + clk_arry[i].clk_name, rc); + } else { + DEV_ERR("%pS->%s: '%s' is not available\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name); + rc = -EPERM; + } + + if (rc) { + msm_dss_enable_clk(&clk_arry[i], + i, false); + break; + } + } + } else { + for (i = num_clk - 1; i >= 0; i--) { + DEV_DBG("%pS->%s: disable '%s'\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name); + + if (clk_arry[i].clk) + clk_disable_unprepare(clk_arry[i].clk); + else + DEV_ERR("%pS->%s: '%s' is not available\n", + __builtin_return_address(0), __func__, + clk_arry[i].clk_name); + } + } + + return rc; +} + +int msm_dss_parse_clock(struct platform_device *pdev, + struct dss_module_power *mp) +{ + u32 i, rc = 0; + const char *clock_name; + int num_clk = 0; + + if (!pdev || !mp) + return -EINVAL; + + mp->num_clk = 0; + num_clk = of_property_count_strings(pdev->dev.of_node, "clock-names"); + if (num_clk <= 0) { + pr_debug("clocks are not defined\n"); + return 0; + } + + mp->clk_config = devm_kzalloc(&pdev->dev, + sizeof(struct dss_clk) * num_clk, + GFP_KERNEL); + if (!mp->clk_config) + return -ENOMEM; + + for (i = 0; i < num_clk; i++) { + rc = of_property_read_string_index(pdev->dev.of_node, + "clock-names", i, + &clock_name); + if (rc) { + dev_err(&pdev->dev, "Failed to get clock name for %d\n", + i); + break; + } + strlcpy(mp->clk_config[i].clk_name, clock_name, + sizeof(mp->clk_config[i].clk_name)); + + mp->clk_config[i].type = DSS_CLK_AHB; + } + + rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk); + if (rc) { + dev_err(&pdev->dev, "Failed to get clock refs %d\n", rc); + goto err; + } + + rc = of_clk_set_defaults(pdev->dev.of_node, false); + if (rc) { + dev_err(&pdev->dev, "Failed to set clock defaults %d\n", rc); + goto err; + } + + for (i = 0; i < num_clk; i++) { + u32 rate = clk_get_rate(mp->clk_config[i].clk); + if (!rate) + continue; + mp->clk_config[i].rate = rate; + mp->clk_config[i].type = DSS_CLK_PCLK; + } + + mp->num_clk = num_clk; + return 0; + +err: + msm_dss_put_clk(mp->clk_config, num_clk); + return rc; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h new file mode 100644 index 000000000000..bc07381d7429 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h @@ -0,0 +1,57 @@ +/* Copyright (c) 2012, 2017-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef __DPU_IO_UTIL_H__ +#define __DPU_IO_UTIL_H__ + +#include <linux/gpio.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define DEV_DBG(fmt, args...) pr_debug(fmt, ##args) +#define DEV_INFO(fmt, args...) pr_info(fmt, ##args) +#define DEV_WARN(fmt, args...) pr_warn(fmt, ##args) +#define DEV_ERR(fmt, args...) pr_err(fmt, ##args) + +struct dss_gpio { + unsigned int gpio; + unsigned int value; + char gpio_name[32]; +}; + +enum dss_clk_type { + DSS_CLK_AHB, /* no set rate. rate controlled through rpm */ + DSS_CLK_PCLK, +}; + +struct dss_clk { + struct clk *clk; /* clk handle */ + char clk_name[32]; + enum dss_clk_type type; + unsigned long rate; + unsigned long max_rate; +}; + +struct dss_module_power { + unsigned int num_gpio; + struct dss_gpio *gpio_config; + unsigned int num_clk; + struct dss_clk *clk_config; +}; + +int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk); +void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk); +int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk); +int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable); +int msm_dss_parse_clock(struct platform_device *pdev, + struct dss_module_power *mp); +#endif /* __DPU_IO_UTIL_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c new file mode 100644 index 000000000000..d5e6ce0140cf --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c @@ -0,0 +1,66 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/irqdomain.h> +#include <linux/irq.h> +#include <linux/kthread.h> + +#include "dpu_irq.h" +#include "dpu_core_irq.h" + +irqreturn_t dpu_irq(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + + return dpu_core_irq(dpu_kms); +} + +void dpu_irq_preinstall(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + + if (!dpu_kms->dev || !dpu_kms->dev->dev) { + pr_err("invalid device handles\n"); + return; + } + + dpu_core_irq_preinstall(dpu_kms); +} + +int dpu_irq_postinstall(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + int rc; + + if (!kms) { + DPU_ERROR("invalid parameters\n"); + return -EINVAL; + } + + rc = dpu_core_irq_postinstall(dpu_kms); + + return rc; +} + +void dpu_irq_uninstall(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + + if (!kms) { + DPU_ERROR("invalid parameters\n"); + return; + } + + dpu_core_irq_uninstall(dpu_kms); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h new file mode 100644 index 000000000000..3e147f7176e2 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h @@ -0,0 +1,59 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef __DPU_IRQ_H__ +#define __DPU_IRQ_H__ + +#include <linux/kernel.h> +#include <linux/irqdomain.h> + +#include "msm_kms.h" + +/** + * dpu_irq_controller - define MDSS level interrupt controller context + * @enabled_mask: enable status of MDSS level interrupt + * @domain: interrupt domain of this controller + */ +struct dpu_irq_controller { + unsigned long enabled_mask; + struct irq_domain *domain; +}; + +/** + * dpu_irq_preinstall - perform pre-installation of MDSS IRQ handler + * @kms: pointer to kms context + * @return: none + */ +void dpu_irq_preinstall(struct msm_kms *kms); + +/** + * dpu_irq_postinstall - perform post-installation of MDSS IRQ handler + * @kms: pointer to kms context + * @return: 0 if success; error code otherwise + */ +int dpu_irq_postinstall(struct msm_kms *kms); + +/** + * dpu_irq_uninstall - uninstall MDSS IRQ handler + * @drm_dev: pointer to kms context + * @return: none + */ +void dpu_irq_uninstall(struct msm_kms *kms); + +/** + * dpu_irq - MDSS level IRQ handler + * @kms: pointer to kms context + * @return: interrupt handling status + */ +irqreturn_t dpu_irq(struct msm_kms *kms); + +#endif /* __DPU_IRQ_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c new file mode 100644 index 000000000000..7dd6bd2d6d37 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -0,0 +1,1345 @@ +/* + * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <drm/drm_crtc.h> +#include <linux/debugfs.h> +#include <linux/of_irq.h> +#include <linux/dma-buf.h> + +#include "msm_drv.h" +#include "msm_mmu.h" +#include "msm_gem.h" + +#include "dpu_kms.h" +#include "dpu_core_irq.h" +#include "dpu_formats.h" +#include "dpu_hw_vbif.h" +#include "dpu_vbif.h" +#include "dpu_encoder.h" +#include "dpu_plane.h" +#include "dpu_crtc.h" + +#define CREATE_TRACE_POINTS +#include "dpu_trace.h" + +static const char * const iommu_ports[] = { + "mdp_0", +}; + +/* + * To enable overall DRM driver logging + * # echo 0x2 > /sys/module/drm/parameters/debug + * + * To enable DRM driver h/w logging + * # echo <mask> > /sys/kernel/debug/dri/0/debug/hw_log_mask + * + * See dpu_hw_mdss.h for h/w logging mask definitions (search for DPU_DBG_MASK_) + */ +#define DPU_DEBUGFS_DIR "msm_dpu" +#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" + +static int dpu_kms_hw_init(struct msm_kms *kms); +static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); + +static unsigned long dpu_iomap_size(struct platform_device *pdev, + const char *name) +{ + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); + if (!res) { + DRM_ERROR("failed to get memory resource: %s\n", name); + return 0; + } + + return resource_size(res); +} + +#ifdef CONFIG_DEBUG_FS +static int _dpu_danger_signal_status(struct seq_file *s, + bool danger_status) +{ + struct dpu_kms *kms = (struct dpu_kms *)s->private; + struct msm_drm_private *priv; + struct dpu_danger_safe_status status; + int i; + + if (!kms || !kms->dev || !kms->dev->dev_private || !kms->hw_mdp) { + DPU_ERROR("invalid arg(s)\n"); + return 0; + } + + priv = kms->dev->dev_private; + memset(&status, 0, sizeof(struct dpu_danger_safe_status)); + + pm_runtime_get_sync(&kms->pdev->dev); + if (danger_status) { + seq_puts(s, "\nDanger signal status:\n"); + if (kms->hw_mdp->ops.get_danger_status) + kms->hw_mdp->ops.get_danger_status(kms->hw_mdp, + &status); + } else { + seq_puts(s, "\nSafe signal status:\n"); + if (kms->hw_mdp->ops.get_danger_status) + kms->hw_mdp->ops.get_danger_status(kms->hw_mdp, + &status); + } + pm_runtime_put_sync(&kms->pdev->dev); + + seq_printf(s, "MDP : 0x%x\n", status.mdp); + + for (i = SSPP_VIG0; i < SSPP_MAX; i++) + seq_printf(s, "SSPP%d : 0x%x \t", i - SSPP_VIG0, + status.sspp[i]); + seq_puts(s, "\n"); + + return 0; +} + +#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix) \ +static int __prefix ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __prefix ## _show, inode->i_private); \ +} \ +static const struct file_operations __prefix ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __prefix ## _open, \ + .release = single_release, \ + .read = seq_read, \ + .llseek = seq_lseek, \ +} + +static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v) +{ + return _dpu_danger_signal_status(s, true); +} +DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_danger_stats); + +static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v) +{ + return _dpu_danger_signal_status(s, false); +} +DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats); + +static void dpu_debugfs_danger_destroy(struct dpu_kms *dpu_kms) +{ + debugfs_remove_recursive(dpu_kms->debugfs_danger); + dpu_kms->debugfs_danger = NULL; +} + +static int dpu_debugfs_danger_init(struct dpu_kms *dpu_kms, + struct dentry *parent) +{ + dpu_kms->debugfs_danger = debugfs_create_dir("danger", + parent); + if (!dpu_kms->debugfs_danger) { + DPU_ERROR("failed to create danger debugfs\n"); + return -EINVAL; + } + + debugfs_create_file("danger_status", 0600, dpu_kms->debugfs_danger, + dpu_kms, &dpu_debugfs_danger_stats_fops); + debugfs_create_file("safe_status", 0600, dpu_kms->debugfs_danger, + dpu_kms, &dpu_debugfs_safe_stats_fops); + + return 0; +} + +static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data) +{ + struct dpu_debugfs_regset32 *regset; + struct dpu_kms *dpu_kms; + struct drm_device *dev; + struct msm_drm_private *priv; + void __iomem *base; + uint32_t i, addr; + + if (!s || !s->private) + return 0; + + regset = s->private; + + dpu_kms = regset->dpu_kms; + if (!dpu_kms || !dpu_kms->mmio) + return 0; + + dev = dpu_kms->dev; + if (!dev) + return 0; + + priv = dev->dev_private; + if (!priv) + return 0; + + base = dpu_kms->mmio + regset->offset; + + /* insert padding spaces, if needed */ + if (regset->offset & 0xF) { + seq_printf(s, "[%x]", regset->offset & ~0xF); + for (i = 0; i < (regset->offset & 0xF); i += 4) + seq_puts(s, " "); + } + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + + /* main register output */ + for (i = 0; i < regset->blk_len; i += 4) { + addr = regset->offset + i; + if ((addr & 0xF) == 0x0) + seq_printf(s, i ? "\n[%x]" : "[%x]", addr); + seq_printf(s, " %08x", readl_relaxed(base + i)); + } + seq_puts(s, "\n"); + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + return 0; +} + +static int dpu_debugfs_open_regset32(struct inode *inode, + struct file *file) +{ + return single_open(file, _dpu_debugfs_show_regset32, inode->i_private); +} + +static const struct file_operations dpu_fops_regset32 = { + .open = dpu_debugfs_open_regset32, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset, + uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms) +{ + if (regset) { + regset->offset = offset; + regset->blk_len = length; + regset->dpu_kms = dpu_kms; + } +} + +void *dpu_debugfs_create_regset32(const char *name, umode_t mode, + void *parent, struct dpu_debugfs_regset32 *regset) +{ + if (!name || !regset || !regset->dpu_kms || !regset->blk_len) + return NULL; + + /* make sure offset is a multiple of 4 */ + regset->offset = round_down(regset->offset, 4); + + return debugfs_create_file(name, mode, parent, + regset, &dpu_fops_regset32); +} + +static int _dpu_debugfs_init(struct dpu_kms *dpu_kms) +{ + void *p; + int rc; + + p = dpu_hw_util_get_log_mask_ptr(); + + if (!dpu_kms || !p) + return -EINVAL; + + dpu_kms->debugfs_root = debugfs_create_dir("debug", + dpu_kms->dev->primary->debugfs_root); + if (IS_ERR_OR_NULL(dpu_kms->debugfs_root)) { + DRM_ERROR("debugfs create_dir failed %ld\n", + PTR_ERR(dpu_kms->debugfs_root)); + return PTR_ERR(dpu_kms->debugfs_root); + } + + rc = dpu_dbg_debugfs_register(dpu_kms->debugfs_root); + if (rc) { + DRM_ERROR("failed to reg dpu dbg debugfs: %d\n", rc); + return rc; + } + + /* allow root to be NULL */ + debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, dpu_kms->debugfs_root, p); + + (void) dpu_debugfs_danger_init(dpu_kms, dpu_kms->debugfs_root); + (void) dpu_debugfs_vbif_init(dpu_kms, dpu_kms->debugfs_root); + (void) dpu_debugfs_core_irq_init(dpu_kms, dpu_kms->debugfs_root); + + rc = dpu_core_perf_debugfs_init(&dpu_kms->perf, dpu_kms->debugfs_root); + if (rc) { + DPU_ERROR("failed to init perf %d\n", rc); + return rc; + } + + return 0; +} + +static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms) +{ + /* don't need to NULL check debugfs_root */ + if (dpu_kms) { + dpu_debugfs_vbif_destroy(dpu_kms); + dpu_debugfs_danger_destroy(dpu_kms); + dpu_debugfs_core_irq_destroy(dpu_kms); + debugfs_remove_recursive(dpu_kms->debugfs_root); + } +} +#else +static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms) +{ +} +#endif + +static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc) +{ + return dpu_crtc_vblank(crtc, true); +} + +static void dpu_kms_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc) +{ + dpu_crtc_vblank(crtc, false); +} + +static void dpu_kms_prepare_commit(struct msm_kms *kms, + struct drm_atomic_state *state) +{ + struct dpu_kms *dpu_kms; + struct msm_drm_private *priv; + struct drm_device *dev; + struct drm_encoder *encoder; + + if (!kms) + return; + dpu_kms = to_dpu_kms(kms); + dev = dpu_kms->dev; + + if (!dev || !dev->dev_private) + return; + priv = dev->dev_private; + pm_runtime_get_sync(&dpu_kms->pdev->dev); + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) + if (encoder->crtc != NULL) + dpu_encoder_prepare_commit(encoder); +} + +/* + * Override the encoder enable since we need to setup the inline rotator and do + * some crtc magic before enabling any bridge that might be present. + */ +void dpu_kms_encoder_enable(struct drm_encoder *encoder) +{ + const struct drm_encoder_helper_funcs *funcs = encoder->helper_private; + struct drm_crtc *crtc = encoder->crtc; + + /* Forward this enable call to the commit hook */ + if (funcs && funcs->commit) + funcs->commit(encoder); + + if (crtc && crtc->state->active) { + trace_dpu_kms_enc_enable(DRMID(crtc)); + dpu_crtc_commit_kickoff(crtc); + } +} + +static void dpu_kms_commit(struct msm_kms *kms, struct drm_atomic_state *state) +{ + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + int i; + + for_each_new_crtc_in_state(state, crtc, crtc_state, i) { + /* If modeset is required, kickoff is run in encoder_enable */ + if (drm_atomic_crtc_needs_modeset(crtc_state)) + continue; + + if (crtc->state->active) { + trace_dpu_kms_commit(DRMID(crtc)); + dpu_crtc_commit_kickoff(crtc); + } + } +} + +static void dpu_kms_complete_commit(struct msm_kms *kms, + struct drm_atomic_state *old_state) +{ + struct dpu_kms *dpu_kms; + struct msm_drm_private *priv; + struct drm_crtc *crtc; + struct drm_crtc_state *old_crtc_state; + int i; + + if (!kms || !old_state) + return; + dpu_kms = to_dpu_kms(kms); + + if (!dpu_kms->dev || !dpu_kms->dev->dev_private) + return; + priv = dpu_kms->dev->dev_private; + + DPU_ATRACE_BEGIN("kms_complete_commit"); + + for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i) + dpu_crtc_complete_commit(crtc, old_crtc_state); + + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + DPU_ATRACE_END("kms_complete_commit"); +} + +static void dpu_kms_wait_for_commit_done(struct msm_kms *kms, + struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + struct drm_device *dev; + int ret; + + if (!kms || !crtc || !crtc->state) { + DPU_ERROR("invalid params\n"); + return; + } + + dev = crtc->dev; + + if (!crtc->state->enable) { + DPU_DEBUG("[crtc:%d] not enable\n", crtc->base.id); + return; + } + + if (!crtc->state->active) { + DPU_DEBUG("[crtc:%d] not active\n", crtc->base.id); + return; + } + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + if (encoder->crtc != crtc) + continue; + /* + * Wait for post-flush if necessary to delay before + * plane_cleanup. For example, wait for vsync in case of video + * mode panels. This may be a no-op for command mode panels. + */ + trace_dpu_kms_wait_for_commit_done(DRMID(crtc)); + ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE); + if (ret && ret != -EWOULDBLOCK) { + DPU_ERROR("wait for commit done returned %d\n", ret); + break; + } + } +} + +static void _dpu_kms_initialize_dsi(struct drm_device *dev, + struct msm_drm_private *priv, + struct dpu_kms *dpu_kms) +{ + struct drm_encoder *encoder = NULL; + int i, rc; + + /*TODO: Support two independent DSI connectors */ + encoder = dpu_encoder_init(dev, DRM_MODE_CONNECTOR_DSI); + if (IS_ERR_OR_NULL(encoder)) { + DPU_ERROR("encoder init failed for dsi display\n"); + return; + } + + priv->encoders[priv->num_encoders++] = encoder; + + for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) { + if (!priv->dsi[i]) { + DPU_DEBUG("invalid msm_dsi for ctrl %d\n", i); + return; + } + + rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder); + if (rc) { + DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n", + i, rc); + continue; + } + } +} + +/** + * _dpu_kms_setup_displays - create encoders, bridges and connectors + * for underlying displays + * @dev: Pointer to drm device structure + * @priv: Pointer to private drm device data + * @dpu_kms: Pointer to dpu kms structure + * Returns: Zero on success + */ +static void _dpu_kms_setup_displays(struct drm_device *dev, + struct msm_drm_private *priv, + struct dpu_kms *dpu_kms) +{ + _dpu_kms_initialize_dsi(dev, priv, dpu_kms); + + /** + * Extend this function to initialize other + * types of displays + */ +} + +static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms) +{ + struct msm_drm_private *priv; + int i; + + if (!dpu_kms) { + DPU_ERROR("invalid dpu_kms\n"); + return; + } else if (!dpu_kms->dev) { + DPU_ERROR("invalid dev\n"); + return; + } else if (!dpu_kms->dev->dev_private) { + DPU_ERROR("invalid dev_private\n"); + return; + } + priv = dpu_kms->dev->dev_private; + + for (i = 0; i < priv->num_crtcs; i++) + priv->crtcs[i]->funcs->destroy(priv->crtcs[i]); + priv->num_crtcs = 0; + + for (i = 0; i < priv->num_planes; i++) + priv->planes[i]->funcs->destroy(priv->planes[i]); + priv->num_planes = 0; + + for (i = 0; i < priv->num_connectors; i++) + priv->connectors[i]->funcs->destroy(priv->connectors[i]); + priv->num_connectors = 0; + + for (i = 0; i < priv->num_encoders; i++) + priv->encoders[i]->funcs->destroy(priv->encoders[i]); + priv->num_encoders = 0; +} + +static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) +{ + struct drm_device *dev; + struct drm_plane *primary_planes[MAX_PLANES], *plane; + struct drm_crtc *crtc; + + struct msm_drm_private *priv; + struct dpu_mdss_cfg *catalog; + + int primary_planes_idx = 0, i, ret; + int max_crtc_count; + + if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) { + DPU_ERROR("invalid dpu_kms\n"); + return -EINVAL; + } + + dev = dpu_kms->dev; + priv = dev->dev_private; + catalog = dpu_kms->catalog; + + /* + * Create encoder and query display drivers to create + * bridges and connectors + */ + _dpu_kms_setup_displays(dev, priv, dpu_kms); + + max_crtc_count = min(catalog->mixer_count, priv->num_encoders); + + /* Create the planes */ + for (i = 0; i < catalog->sspp_count; i++) { + bool primary = true; + + if (catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR) + || primary_planes_idx >= max_crtc_count) + primary = false; + + plane = dpu_plane_init(dev, catalog->sspp[i].id, primary, + (1UL << max_crtc_count) - 1, 0); + if (IS_ERR(plane)) { + DPU_ERROR("dpu_plane_init failed\n"); + ret = PTR_ERR(plane); + goto fail; + } + priv->planes[priv->num_planes++] = plane; + + if (primary) + primary_planes[primary_planes_idx++] = plane; + } + + max_crtc_count = min(max_crtc_count, primary_planes_idx); + + /* Create one CRTC per encoder */ + for (i = 0; i < max_crtc_count; i++) { + crtc = dpu_crtc_init(dev, primary_planes[i]); + if (IS_ERR(crtc)) { + ret = PTR_ERR(crtc); + goto fail; + } + priv->crtcs[priv->num_crtcs++] = crtc; + } + + /* All CRTCs are compatible with all encoders */ + for (i = 0; i < priv->num_encoders; i++) + priv->encoders[i]->possible_crtcs = (1 << priv->num_crtcs) - 1; + + return 0; +fail: + _dpu_kms_drm_obj_destroy(dpu_kms); + return ret; +} + +#ifdef CONFIG_DEBUG_FS +static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor) +{ + struct dpu_kms *dpu_kms = to_dpu_kms(kms); + struct drm_device *dev; + int rc; + + if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) { + DPU_ERROR("invalid dpu_kms\n"); + return -EINVAL; + } + + dev = dpu_kms->dev; + + rc = _dpu_debugfs_init(dpu_kms); + if (rc) + DPU_ERROR("dpu_debugfs init failed: %d\n", rc); + + return rc; +} +#endif + +static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate, + struct drm_encoder *encoder) +{ + return rate; +} + +static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) +{ + struct drm_device *dev; + int i; + + dev = dpu_kms->dev; + if (!dev) + return; + + if (dpu_kms->hw_intr) + dpu_hw_intr_destroy(dpu_kms->hw_intr); + dpu_kms->hw_intr = NULL; + + if (dpu_kms->power_event) + dpu_power_handle_unregister_event( + &dpu_kms->phandle, dpu_kms->power_event); + + /* safe to call these more than once during shutdown */ + _dpu_debugfs_destroy(dpu_kms); + _dpu_kms_mmu_destroy(dpu_kms); + + if (dpu_kms->catalog) { + for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { + u32 vbif_idx = dpu_kms->catalog->vbif[i].id; + + if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx]) + dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]); + } + } + + if (dpu_kms->rm_init) + dpu_rm_destroy(&dpu_kms->rm); + dpu_kms->rm_init = false; + + if (dpu_kms->catalog) + dpu_hw_catalog_deinit(dpu_kms->catalog); + dpu_kms->catalog = NULL; + + if (dpu_kms->core_client) + dpu_power_client_destroy(&dpu_kms->phandle, + dpu_kms->core_client); + dpu_kms->core_client = NULL; + + if (dpu_kms->vbif[VBIF_NRT]) + devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]); + dpu_kms->vbif[VBIF_NRT] = NULL; + + if (dpu_kms->vbif[VBIF_RT]) + devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_RT]); + dpu_kms->vbif[VBIF_RT] = NULL; + + if (dpu_kms->mmio) + devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->mmio); + dpu_kms->mmio = NULL; +} + +static void dpu_kms_destroy(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms; + + if (!kms) { + DPU_ERROR("invalid kms\n"); + return; + } + + dpu_kms = to_dpu_kms(kms); + + dpu_dbg_destroy(); + _dpu_kms_hw_destroy(dpu_kms); +} + +static int dpu_kms_pm_suspend(struct device *dev) +{ + struct drm_device *ddev; + struct drm_modeset_acquire_ctx ctx; + struct drm_atomic_state *state; + struct dpu_kms *dpu_kms; + int ret = 0, num_crtcs = 0; + + if (!dev) + return -EINVAL; + + ddev = dev_get_drvdata(dev); + if (!ddev || !ddev_to_msm_kms(ddev)) + return -EINVAL; + + dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev)); + + /* disable hot-plug polling */ + drm_kms_helper_poll_disable(ddev); + + /* acquire modeset lock(s) */ + drm_modeset_acquire_init(&ctx, 0); + +retry: + DPU_ATRACE_BEGIN("kms_pm_suspend"); + + ret = drm_modeset_lock_all_ctx(ddev, &ctx); + if (ret) + goto unlock; + + /* save current state for resume */ + if (dpu_kms->suspend_state) + drm_atomic_state_put(dpu_kms->suspend_state); + dpu_kms->suspend_state = drm_atomic_helper_duplicate_state(ddev, &ctx); + if (IS_ERR_OR_NULL(dpu_kms->suspend_state)) { + DRM_ERROR("failed to back up suspend state\n"); + dpu_kms->suspend_state = NULL; + goto unlock; + } + + /* create atomic state to disable all CRTCs */ + state = drm_atomic_state_alloc(ddev); + if (IS_ERR_OR_NULL(state)) { + DRM_ERROR("failed to allocate crtc disable state\n"); + goto unlock; + } + + state->acquire_ctx = &ctx; + + /* check for nothing to do */ + if (num_crtcs == 0) { + DRM_DEBUG("all crtcs are already in the off state\n"); + drm_atomic_state_put(state); + goto suspended; + } + + /* commit the "disable all" state */ + ret = drm_atomic_commit(state); + if (ret < 0) { + DRM_ERROR("failed to disable crtcs, %d\n", ret); + drm_atomic_state_put(state); + goto unlock; + } + +suspended: + dpu_kms->suspend_block = true; + +unlock: + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + goto retry; + } + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + + DPU_ATRACE_END("kms_pm_suspend"); + return 0; +} + +static int dpu_kms_pm_resume(struct device *dev) +{ + struct drm_device *ddev; + struct dpu_kms *dpu_kms; + int ret; + + if (!dev) + return -EINVAL; + + ddev = dev_get_drvdata(dev); + if (!ddev || !ddev_to_msm_kms(ddev)) + return -EINVAL; + + dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev)); + + DPU_ATRACE_BEGIN("kms_pm_resume"); + + drm_mode_config_reset(ddev); + + drm_modeset_lock_all(ddev); + + dpu_kms->suspend_block = false; + + if (dpu_kms->suspend_state) { + dpu_kms->suspend_state->acquire_ctx = + ddev->mode_config.acquire_ctx; + ret = drm_atomic_commit(dpu_kms->suspend_state); + if (ret < 0) { + DRM_ERROR("failed to restore state, %d\n", ret); + drm_atomic_state_put(dpu_kms->suspend_state); + } + dpu_kms->suspend_state = NULL; + } + drm_modeset_unlock_all(ddev); + + /* enable hot-plug polling */ + drm_kms_helper_poll_enable(ddev); + + DPU_ATRACE_END("kms_pm_resume"); + return 0; +} + +static void _dpu_kms_set_encoder_mode(struct msm_kms *kms, + struct drm_encoder *encoder, + bool cmd_mode) +{ + struct msm_display_info info; + struct msm_drm_private *priv = encoder->dev->dev_private; + int i, rc = 0; + + memset(&info, 0, sizeof(info)); + + info.intf_type = encoder->encoder_type; + info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE : + MSM_DISPLAY_CAP_VID_MODE; + + /* TODO: No support for DSI swap */ + for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) { + if (priv->dsi[i]) { + info.h_tile_instance[info.num_of_h_tiles] = i; + info.num_of_h_tiles++; + } + } + + rc = dpu_encoder_setup(encoder->dev, encoder, &info); + if (rc) + DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n", + encoder->base.id, rc); +} + +static const struct msm_kms_funcs kms_funcs = { + .hw_init = dpu_kms_hw_init, + .irq_preinstall = dpu_irq_preinstall, + .irq_postinstall = dpu_irq_postinstall, + .irq_uninstall = dpu_irq_uninstall, + .irq = dpu_irq, + .prepare_commit = dpu_kms_prepare_commit, + .commit = dpu_kms_commit, + .complete_commit = dpu_kms_complete_commit, + .wait_for_crtc_commit_done = dpu_kms_wait_for_commit_done, + .enable_vblank = dpu_kms_enable_vblank, + .disable_vblank = dpu_kms_disable_vblank, + .check_modified_format = dpu_format_check_modified_format, + .get_format = dpu_get_msm_format, + .round_pixclk = dpu_kms_round_pixclk, + .pm_suspend = dpu_kms_pm_suspend, + .pm_resume = dpu_kms_pm_resume, + .destroy = dpu_kms_destroy, + .set_encoder_mode = _dpu_kms_set_encoder_mode, +#ifdef CONFIG_DEBUG_FS + .debugfs_init = dpu_kms_debugfs_init, +#endif +}; + +/* the caller api needs to turn on clock before calling it */ +static inline void _dpu_kms_core_hw_rev_init(struct dpu_kms *dpu_kms) +{ + dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0); +} + +static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms) +{ + struct msm_mmu *mmu; + + mmu = dpu_kms->base.aspace->mmu; + + mmu->funcs->detach(mmu, (const char **)iommu_ports, + ARRAY_SIZE(iommu_ports)); + msm_gem_address_space_put(dpu_kms->base.aspace); + + return 0; +} + +static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms) +{ + struct iommu_domain *domain; + struct msm_gem_address_space *aspace; + int ret; + + domain = iommu_domain_alloc(&platform_bus_type); + if (!domain) + return 0; + + aspace = msm_gem_address_space_create(dpu_kms->dev->dev, + domain, "dpu1"); + if (IS_ERR(aspace)) { + ret = PTR_ERR(aspace); + goto fail; + } + + dpu_kms->base.aspace = aspace; + + ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports, + ARRAY_SIZE(iommu_ports)); + if (ret) { + DPU_ERROR("failed to attach iommu %d\n", ret); + msm_gem_address_space_put(aspace); + goto fail; + } + + return 0; +fail: + _dpu_kms_mmu_destroy(dpu_kms); + + return ret; +} + +static struct dss_clk *_dpu_kms_get_clk(struct dpu_kms *dpu_kms, + char *clock_name) +{ + struct dss_module_power *mp = &dpu_kms->mp; + int i; + + for (i = 0; i < mp->num_clk; i++) { + if (!strcmp(mp->clk_config[i].clk_name, clock_name)) + return &mp->clk_config[i]; + } + + return NULL; +} + +u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name) +{ + struct dss_clk *clk; + + clk = _dpu_kms_get_clk(dpu_kms, clock_name); + if (!clk) + return -EINVAL; + + return clk_get_rate(clk->clk); +} + +static void dpu_kms_handle_power_event(u32 event_type, void *usr) +{ + struct dpu_kms *dpu_kms = usr; + + if (!dpu_kms) + return; + + if (event_type == DPU_POWER_EVENT_POST_ENABLE) + dpu_vbif_init_memtypes(dpu_kms); +} + +static int dpu_kms_hw_init(struct msm_kms *kms) +{ + struct dpu_kms *dpu_kms; + struct drm_device *dev; + struct msm_drm_private *priv; + int i, rc = -EINVAL; + + if (!kms) { + DPU_ERROR("invalid kms\n"); + goto end; + } + + dpu_kms = to_dpu_kms(kms); + dev = dpu_kms->dev; + if (!dev) { + DPU_ERROR("invalid device\n"); + goto end; + } + + rc = dpu_dbg_init(&dpu_kms->pdev->dev); + if (rc) { + DRM_ERROR("failed to init dpu dbg: %d\n", rc); + goto end; + } + + priv = dev->dev_private; + if (!priv) { + DPU_ERROR("invalid private data\n"); + goto dbg_destroy; + } + + dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp"); + if (IS_ERR(dpu_kms->mmio)) { + rc = PTR_ERR(dpu_kms->mmio); + DPU_ERROR("mdp register memory map failed: %d\n", rc); + dpu_kms->mmio = NULL; + goto error; + } + DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + dpu_kms->mmio_len = dpu_iomap_size(dpu_kms->pdev, "mdp"); + + dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif", "vbif"); + if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { + rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]); + DPU_ERROR("vbif register memory map failed: %d\n", rc); + dpu_kms->vbif[VBIF_RT] = NULL; + goto error; + } + dpu_kms->vbif_len[VBIF_RT] = dpu_iomap_size(dpu_kms->pdev, "vbif"); + dpu_kms->vbif[VBIF_NRT] = msm_ioremap(dpu_kms->pdev, "vbif_nrt", "vbif_nrt"); + if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) { + dpu_kms->vbif[VBIF_NRT] = NULL; + DPU_DEBUG("VBIF NRT is not defined"); + } else { + dpu_kms->vbif_len[VBIF_NRT] = dpu_iomap_size(dpu_kms->pdev, + "vbif_nrt"); + } + + dpu_kms->reg_dma = msm_ioremap(dpu_kms->pdev, "regdma", "regdma"); + if (IS_ERR(dpu_kms->reg_dma)) { + dpu_kms->reg_dma = NULL; + DPU_DEBUG("REG_DMA is not defined"); + } else { + dpu_kms->reg_dma_len = dpu_iomap_size(dpu_kms->pdev, "regdma"); + } + + dpu_kms->core_client = dpu_power_client_create(&dpu_kms->phandle, + "core"); + if (IS_ERR_OR_NULL(dpu_kms->core_client)) { + rc = PTR_ERR(dpu_kms->core_client); + if (!dpu_kms->core_client) + rc = -EINVAL; + DPU_ERROR("dpu power client create failed: %d\n", rc); + dpu_kms->core_client = NULL; + goto error; + } + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + + _dpu_kms_core_hw_rev_init(dpu_kms); + + pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev); + + dpu_kms->catalog = dpu_hw_catalog_init(dpu_kms->core_rev); + if (IS_ERR_OR_NULL(dpu_kms->catalog)) { + rc = PTR_ERR(dpu_kms->catalog); + if (!dpu_kms->catalog) + rc = -EINVAL; + DPU_ERROR("catalog init failed: %d\n", rc); + dpu_kms->catalog = NULL; + goto power_error; + } + + dpu_dbg_init_dbg_buses(dpu_kms->core_rev); + + /* + * Now we need to read the HW catalog and initialize resources such as + * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc + */ + rc = _dpu_kms_mmu_init(dpu_kms); + if (rc) { + DPU_ERROR("dpu_kms_mmu_init failed: %d\n", rc); + goto power_error; + } + + rc = dpu_rm_init(&dpu_kms->rm, dpu_kms->catalog, dpu_kms->mmio, + dpu_kms->dev); + if (rc) { + DPU_ERROR("rm init failed: %d\n", rc); + goto power_error; + } + + dpu_kms->rm_init = true; + + dpu_kms->hw_mdp = dpu_rm_get_mdp(&dpu_kms->rm); + if (IS_ERR_OR_NULL(dpu_kms->hw_mdp)) { + rc = PTR_ERR(dpu_kms->hw_mdp); + if (!dpu_kms->hw_mdp) + rc = -EINVAL; + DPU_ERROR("failed to get hw_mdp: %d\n", rc); + dpu_kms->hw_mdp = NULL; + goto power_error; + } + + for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { + u32 vbif_idx = dpu_kms->catalog->vbif[i].id; + + dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx, + dpu_kms->vbif[vbif_idx], dpu_kms->catalog); + if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) { + rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]); + if (!dpu_kms->hw_vbif[vbif_idx]) + rc = -EINVAL; + DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc); + dpu_kms->hw_vbif[vbif_idx] = NULL; + goto power_error; + } + } + + rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog, + &dpu_kms->phandle, + _dpu_kms_get_clk(dpu_kms, "core")); + if (rc) { + DPU_ERROR("failed to init perf %d\n", rc); + goto perf_err; + } + + dpu_kms->hw_intr = dpu_hw_intr_init(dpu_kms->mmio, dpu_kms->catalog); + if (IS_ERR_OR_NULL(dpu_kms->hw_intr)) { + rc = PTR_ERR(dpu_kms->hw_intr); + DPU_ERROR("hw_intr init failed: %d\n", rc); + dpu_kms->hw_intr = NULL; + goto hw_intr_init_err; + } + + /* + * _dpu_kms_drm_obj_init should create the DRM related objects + * i.e. CRTCs, planes, encoders, connectors and so forth + */ + rc = _dpu_kms_drm_obj_init(dpu_kms); + if (rc) { + DPU_ERROR("modeset init failed: %d\n", rc); + goto drm_obj_init_err; + } + + dev->mode_config.min_width = 0; + dev->mode_config.min_height = 0; + + /* + * max crtc width is equal to the max mixer width * 2 and max height is + * is 4K + */ + dev->mode_config.max_width = + dpu_kms->catalog->caps->max_mixer_width * 2; + dev->mode_config.max_height = 4096; + + /* + * Support format modifiers for compression etc. + */ + dev->mode_config.allow_fb_modifiers = true; + + /* + * Handle (re)initializations during power enable + */ + dpu_kms_handle_power_event(DPU_POWER_EVENT_POST_ENABLE, dpu_kms); + dpu_kms->power_event = dpu_power_handle_register_event( + &dpu_kms->phandle, + DPU_POWER_EVENT_POST_ENABLE, + dpu_kms_handle_power_event, dpu_kms, "kms"); + + pm_runtime_put_sync(&dpu_kms->pdev->dev); + + return 0; + +drm_obj_init_err: + dpu_core_perf_destroy(&dpu_kms->perf); +hw_intr_init_err: +perf_err: +power_error: + pm_runtime_put_sync(&dpu_kms->pdev->dev); +error: + _dpu_kms_hw_destroy(dpu_kms); +dbg_destroy: + dpu_dbg_destroy(); +end: + return rc; +} + +struct msm_kms *dpu_kms_init(struct drm_device *dev) +{ + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + int irq; + + if (!dev || !dev->dev_private) { + DPU_ERROR("drm device node invalid\n"); + return ERR_PTR(-EINVAL); + } + + priv = dev->dev_private; + dpu_kms = to_dpu_kms(priv->kms); + + irq = irq_of_parse_and_map(dpu_kms->pdev->dev.of_node, 0); + if (irq < 0) { + DPU_ERROR("failed to get irq: %d\n", irq); + return ERR_PTR(irq); + } + dpu_kms->base.irq = irq; + + return &dpu_kms->base; +} + +static int dpu_bind(struct device *dev, struct device *master, void *data) +{ + struct drm_device *ddev = dev_get_drvdata(master); + struct platform_device *pdev = to_platform_device(dev); + struct msm_drm_private *priv = ddev->dev_private; + struct dpu_kms *dpu_kms; + struct dss_module_power *mp; + int ret = 0; + + dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL); + if (!dpu_kms) + return -ENOMEM; + + mp = &dpu_kms->mp; + ret = msm_dss_parse_clock(pdev, mp); + if (ret) { + DPU_ERROR("failed to parse clocks, ret=%d\n", ret); + return ret; + } + + dpu_power_resource_init(pdev, &dpu_kms->phandle); + + platform_set_drvdata(pdev, dpu_kms); + + msm_kms_init(&dpu_kms->base, &kms_funcs); + dpu_kms->dev = ddev; + dpu_kms->pdev = pdev; + + pm_runtime_enable(&pdev->dev); + dpu_kms->rpm_enabled = true; + + priv->kms = &dpu_kms->base; + return ret; +} + +static void dpu_unbind(struct device *dev, struct device *master, void *data) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); + struct dss_module_power *mp = &dpu_kms->mp; + + dpu_power_resource_deinit(pdev, &dpu_kms->phandle); + msm_dss_put_clk(mp->clk_config, mp->num_clk); + devm_kfree(&pdev->dev, mp->clk_config); + mp->num_clk = 0; + + if (dpu_kms->rpm_enabled) + pm_runtime_disable(&pdev->dev); +} + +static const struct component_ops dpu_ops = { + .bind = dpu_bind, + .unbind = dpu_unbind, +}; + +static int dpu_dev_probe(struct platform_device *pdev) +{ + return component_add(&pdev->dev, &dpu_ops); +} + +static int dpu_dev_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &dpu_ops); + return 0; +} + +static int __maybe_unused dpu_runtime_suspend(struct device *dev) +{ + int rc = -1; + struct platform_device *pdev = to_platform_device(dev); + struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); + struct drm_device *ddev; + struct dss_module_power *mp = &dpu_kms->mp; + + ddev = dpu_kms->dev; + if (!ddev) { + DPU_ERROR("invalid drm_device\n"); + goto exit; + } + + rc = dpu_power_resource_enable(&dpu_kms->phandle, + dpu_kms->core_client, false); + if (rc) + DPU_ERROR("resource disable failed: %d\n", rc); + + rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); + if (rc) + DPU_ERROR("clock disable failed rc:%d\n", rc); + +exit: + return rc; +} + +static int __maybe_unused dpu_runtime_resume(struct device *dev) +{ + int rc = -1; + struct platform_device *pdev = to_platform_device(dev); + struct dpu_kms *dpu_kms = platform_get_drvdata(pdev); + struct drm_device *ddev; + struct dss_module_power *mp = &dpu_kms->mp; + + ddev = dpu_kms->dev; + if (!ddev) { + DPU_ERROR("invalid drm_device\n"); + goto exit; + } + + rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); + if (rc) { + DPU_ERROR("clock enable failed rc:%d\n", rc); + goto exit; + } + + rc = dpu_power_resource_enable(&dpu_kms->phandle, + dpu_kms->core_client, true); + if (rc) + DPU_ERROR("resource enable failed: %d\n", rc); + +exit: + return rc; +} + +static const struct dev_pm_ops dpu_pm_ops = { + SET_RUNTIME_PM_OPS(dpu_runtime_suspend, dpu_runtime_resume, NULL) +}; + +static const struct of_device_id dpu_dt_match[] = { + { .compatible = "qcom,sdm845-dpu", }, + {} +}; +MODULE_DEVICE_TABLE(of, dpu_dt_match); + +static struct platform_driver dpu_driver = { + .probe = dpu_dev_probe, + .remove = dpu_dev_remove, + .driver = { + .name = "msm_dpu", + .of_match_table = dpu_dt_match, + .pm = &dpu_pm_ops, + }, +}; + +void __init msm_dpu_register(void) +{ + platform_driver_register(&dpu_driver); +} + +void __exit msm_dpu_unregister(void) +{ + platform_driver_unregister(&dpu_driver); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h new file mode 100644 index 000000000000..66d466628e2b --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -0,0 +1,290 @@ +/* + * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __DPU_KMS_H__ +#define __DPU_KMS_H__ + +#include "msm_drv.h" +#include "msm_kms.h" +#include "msm_mmu.h" +#include "msm_gem.h" +#include "dpu_dbg.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_ctl.h" +#include "dpu_hw_lm.h" +#include "dpu_hw_interrupts.h" +#include "dpu_hw_top.h" +#include "dpu_rm.h" +#include "dpu_power_handle.h" +#include "dpu_irq.h" +#include "dpu_core_perf.h" + +#define DRMID(x) ((x) ? (x)->base.id : -1) + +/** + * DPU_DEBUG - macro for kms/plane/crtc/encoder/connector logs + * @fmt: Pointer to format string + */ +#define DPU_DEBUG(fmt, ...) \ + do { \ + if (unlikely(drm_debug & DRM_UT_KMS)) \ + DRM_DEBUG(fmt, ##__VA_ARGS__); \ + else \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) + +/** + * DPU_DEBUG_DRIVER - macro for hardware driver logging + * @fmt: Pointer to format string + */ +#define DPU_DEBUG_DRIVER(fmt, ...) \ + do { \ + if (unlikely(drm_debug & DRM_UT_DRIVER)) \ + DRM_ERROR(fmt, ##__VA_ARGS__); \ + else \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) + +#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) + +/** + * ktime_compare_safe - compare two ktime structures + * This macro is similar to the standard ktime_compare() function, but + * attempts to also handle ktime overflows. + * @A: First ktime value + * @B: Second ktime value + * Returns: -1 if A < B, 0 if A == B, 1 if A > B + */ +#define ktime_compare_safe(A, B) \ + ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0)) + +#define DPU_NAME_SIZE 12 + +/* timeout in frames waiting for frame done */ +#define DPU_FRAME_DONE_TIMEOUT 60 + +/* + * struct dpu_irq_callback - IRQ callback handlers + * @list: list to callback + * @func: intr handler + * @arg: argument for the handler + */ +struct dpu_irq_callback { + struct list_head list; + void (*func)(void *arg, int irq_idx); + void *arg; +}; + +/** + * struct dpu_irq: IRQ structure contains callback registration info + * @total_irq: total number of irq_idx obtained from HW interrupts mapping + * @irq_cb_tbl: array of IRQ callbacks setting + * @enable_counts array of IRQ enable counts + * @cb_lock: callback lock + * @debugfs_file: debugfs file for irq statistics + */ +struct dpu_irq { + u32 total_irqs; + struct list_head *irq_cb_tbl; + atomic_t *enable_counts; + atomic_t *irq_counts; + spinlock_t cb_lock; + struct dentry *debugfs_file; +}; + +struct dpu_kms { + struct msm_kms base; + struct drm_device *dev; + int core_rev; + struct dpu_mdss_cfg *catalog; + + struct dpu_power_handle phandle; + struct dpu_power_client *core_client; + struct dpu_power_event *power_event; + + /* directory entry for debugfs */ + struct dentry *debugfs_root; + struct dentry *debugfs_danger; + struct dentry *debugfs_vbif; + + /* io/register spaces: */ + void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma; + unsigned long mmio_len, vbif_len[VBIF_MAX], reg_dma_len; + + struct regulator *vdd; + struct regulator *mmagic; + struct regulator *venus; + + struct dpu_hw_intr *hw_intr; + struct dpu_irq irq_obj; + + struct dpu_core_perf perf; + + /* saved atomic state during system suspend */ + struct drm_atomic_state *suspend_state; + bool suspend_block; + + struct dpu_rm rm; + bool rm_init; + + struct dpu_hw_vbif *hw_vbif[VBIF_MAX]; + struct dpu_hw_mdp *hw_mdp; + + bool has_danger_ctrl; + + struct platform_device *pdev; + bool rpm_enabled; + struct dss_module_power mp; +}; + +struct vsync_info { + u32 frame_count; + u32 line_count; +}; + +#define to_dpu_kms(x) container_of(x, struct dpu_kms, base) + +/* get struct msm_kms * from drm_device * */ +#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \ + ((struct msm_drm_private *)((D)->dev_private))->kms : NULL) + +/** + * dpu_kms_is_suspend_state - whether or not the system is pm suspended + * @dev: Pointer to drm device + * Return: Suspend status + */ +static inline bool dpu_kms_is_suspend_state(struct drm_device *dev) +{ + if (!ddev_to_msm_kms(dev)) + return false; + + return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_state != NULL; +} + +/** + * dpu_kms_is_suspend_blocked - whether or not commits are blocked due to pm + * suspend status + * @dev: Pointer to drm device + * Return: True if commits should be rejected due to pm suspend + */ +static inline bool dpu_kms_is_suspend_blocked(struct drm_device *dev) +{ + if (!dpu_kms_is_suspend_state(dev)) + return false; + + return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_block; +} + +/** + * Debugfs functions - extra helper functions for debugfs support + * + * Main debugfs documentation is located at, + * + * Documentation/filesystems/debugfs.txt + * + * @dpu_debugfs_setup_regset32: Initialize data for dpu_debugfs_create_regset32 + * @dpu_debugfs_create_regset32: Create 32-bit register dump file + * @dpu_debugfs_get_root: Get root dentry for DPU_KMS's debugfs node + */ + +/** + * Companion structure for dpu_debugfs_create_regset32. Do not initialize the + * members of this structure explicitly; use dpu_debugfs_setup_regset32 instead. + */ +struct dpu_debugfs_regset32 { + uint32_t offset; + uint32_t blk_len; + struct dpu_kms *dpu_kms; +}; + +/** + * dpu_debugfs_setup_regset32 - Initialize register block definition for debugfs + * This function is meant to initialize dpu_debugfs_regset32 structures for use + * with dpu_debugfs_create_regset32. + * @regset: opaque register definition structure + * @offset: sub-block offset + * @length: sub-block length, in bytes + * @dpu_kms: pointer to dpu kms structure + */ +void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset, + uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms); + +/** + * dpu_debugfs_create_regset32 - Create register read back file for debugfs + * + * This function is almost identical to the standard debugfs_create_regset32() + * function, with the main difference being that a list of register + * names/offsets do not need to be provided. The 'read' function simply outputs + * sequential register values over a specified range. + * + * Similar to the related debugfs_create_regset32 API, the structure pointed to + * by regset needs to persist for the lifetime of the created file. The calling + * code is responsible for initialization/management of this structure. + * + * The structure pointed to by regset is meant to be opaque. Please use + * dpu_debugfs_setup_regset32 to initialize it. + * + * @name: File name within debugfs + * @mode: File mode within debugfs + * @parent: Parent directory entry within debugfs, can be NULL + * @regset: Pointer to persistent register block definition + * + * Return: dentry pointer for newly created file, use either debugfs_remove() + * or debugfs_remove_recursive() (on a parent directory) to remove the + * file + */ +void *dpu_debugfs_create_regset32(const char *name, umode_t mode, + void *parent, struct dpu_debugfs_regset32 *regset); + +/** + * dpu_debugfs_get_root - Return root directory entry for KMS's debugfs + * + * The return value should be passed as the 'parent' argument to subsequent + * debugfs create calls. + * + * @dpu_kms: Pointer to DPU's KMS structure + * + * Return: dentry pointer for DPU's debugfs location + */ +void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms); + +/** + * DPU info management functions + * These functions/definitions allow for building up a 'dpu_info' structure + * containing one or more "key=value\n" entries. + */ +#define DPU_KMS_INFO_MAX_SIZE 4096 + +/** + * Vblank enable/disable functions + */ +int dpu_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc); +void dpu_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc); + +void dpu_kms_encoder_enable(struct drm_encoder *encoder); + +/** + * dpu_kms_get_clk_rate() - get the clock rate + * @dpu_kms: poiner to dpu_kms structure + * @clock_name: clock name to get the rate + * + * Return: current clock rate + */ +u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name); + +#endif /* __dpu_kms_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c new file mode 100644 index 000000000000..9e533b86682c --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -0,0 +1,245 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018, The Linux Foundation + */ + +#include "dpu_kms.h" + +#define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base) + +#define HW_INTR_STATUS 0x0010 + +struct dpu_mdss { + struct msm_mdss base; + void __iomem *mmio; + unsigned long mmio_len; + u32 hwversion; + struct dss_module_power mp; + struct dpu_irq_controller irq_controller; +}; + +static irqreturn_t dpu_mdss_irq(int irq, void *arg) +{ + struct dpu_mdss *dpu_mdss = arg; + u32 interrupts; + + interrupts = readl_relaxed(dpu_mdss->mmio + HW_INTR_STATUS); + + while (interrupts) { + irq_hw_number_t hwirq = fls(interrupts) - 1; + unsigned int mapping; + int rc; + + mapping = irq_find_mapping(dpu_mdss->irq_controller.domain, + hwirq); + if (mapping == 0) { + DRM_ERROR("couldn't find irq mapping for %lu\n", hwirq); + return IRQ_NONE; + } + + rc = generic_handle_irq(mapping); + if (rc < 0) { + DRM_ERROR("handle irq fail: irq=%lu mapping=%u rc=%d\n", + hwirq, mapping, rc); + return IRQ_NONE; + } + + interrupts &= ~(1 << hwirq); + } + + return IRQ_HANDLED; +} + +static void dpu_mdss_irq_mask(struct irq_data *irqd) +{ + struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd); + + /* memory barrier */ + smp_mb__before_atomic(); + clear_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask); + /* memory barrier */ + smp_mb__after_atomic(); +} + +static void dpu_mdss_irq_unmask(struct irq_data *irqd) +{ + struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd); + + /* memory barrier */ + smp_mb__before_atomic(); + set_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask); + /* memory barrier */ + smp_mb__after_atomic(); +} + +static struct irq_chip dpu_mdss_irq_chip = { + .name = "dpu_mdss", + .irq_mask = dpu_mdss_irq_mask, + .irq_unmask = dpu_mdss_irq_unmask, +}; + +static int dpu_mdss_irqdomain_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + struct dpu_mdss *dpu_mdss = domain->host_data; + int ret; + + irq_set_chip_and_handler(irq, &dpu_mdss_irq_chip, handle_level_irq); + ret = irq_set_chip_data(irq, dpu_mdss); + + return ret; +} + +static const struct irq_domain_ops dpu_mdss_irqdomain_ops = { + .map = dpu_mdss_irqdomain_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss) +{ + struct device *dev; + struct irq_domain *domain; + + dev = dpu_mdss->base.dev->dev; + + domain = irq_domain_add_linear(dev->of_node, 32, + &dpu_mdss_irqdomain_ops, dpu_mdss); + if (!domain) { + DPU_ERROR("failed to add irq_domain\n"); + return -EINVAL; + } + + dpu_mdss->irq_controller.enabled_mask = 0; + dpu_mdss->irq_controller.domain = domain; + + return 0; +} + +static int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss) +{ + if (dpu_mdss->irq_controller.domain) { + irq_domain_remove(dpu_mdss->irq_controller.domain); + dpu_mdss->irq_controller.domain = NULL; + } + return 0; +} +static int dpu_mdss_enable(struct msm_mdss *mdss) +{ + struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); + struct dss_module_power *mp = &dpu_mdss->mp; + int ret; + + ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); + if (ret) + DPU_ERROR("clock enable failed, ret:%d\n", ret); + + return ret; +} + +static int dpu_mdss_disable(struct msm_mdss *mdss) +{ + struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); + struct dss_module_power *mp = &dpu_mdss->mp; + int ret; + + ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); + if (ret) + DPU_ERROR("clock disable failed, ret:%d\n", ret); + + return ret; +} + +static void dpu_mdss_destroy(struct drm_device *dev) +{ + struct platform_device *pdev = to_platform_device(dev->dev); + struct msm_drm_private *priv = dev->dev_private; + struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss); + struct dss_module_power *mp = &dpu_mdss->mp; + + _dpu_mdss_irq_domain_fini(dpu_mdss); + + msm_dss_put_clk(mp->clk_config, mp->num_clk); + devm_kfree(&pdev->dev, mp->clk_config); + + if (dpu_mdss->mmio) + devm_iounmap(&pdev->dev, dpu_mdss->mmio); + dpu_mdss->mmio = NULL; + + pm_runtime_disable(dev->dev); + priv->mdss = NULL; +} + +static const struct msm_mdss_funcs mdss_funcs = { + .enable = dpu_mdss_enable, + .disable = dpu_mdss_disable, + .destroy = dpu_mdss_destroy, +}; + +int dpu_mdss_init(struct drm_device *dev) +{ + struct platform_device *pdev = to_platform_device(dev->dev); + struct msm_drm_private *priv = dev->dev_private; + struct resource *res; + struct dpu_mdss *dpu_mdss; + struct dss_module_power *mp; + int ret = 0; + + dpu_mdss = devm_kzalloc(dev->dev, sizeof(*dpu_mdss), GFP_KERNEL); + if (!dpu_mdss) + return -ENOMEM; + + dpu_mdss->mmio = msm_ioremap(pdev, "mdss", "mdss"); + if (IS_ERR(dpu_mdss->mmio)) + return PTR_ERR(dpu_mdss->mmio); + + DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mdss"); + if (!res) { + DRM_ERROR("failed to get memory resource for mdss\n"); + return -ENOMEM; + } + dpu_mdss->mmio_len = resource_size(res); + + mp = &dpu_mdss->mp; + ret = msm_dss_parse_clock(pdev, mp); + if (ret) { + DPU_ERROR("failed to parse clocks, ret=%d\n", ret); + goto clk_parse_err; + } + + dpu_mdss->base.dev = dev; + dpu_mdss->base.funcs = &mdss_funcs; + + ret = _dpu_mdss_irq_domain_add(dpu_mdss); + if (ret) + goto irq_domain_error; + + ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0), + dpu_mdss_irq, 0, "dpu_mdss_isr", dpu_mdss); + if (ret) { + DPU_ERROR("failed to init irq: %d\n", ret); + goto irq_error; + } + + pm_runtime_enable(dev->dev); + + pm_runtime_get_sync(dev->dev); + dpu_mdss->hwversion = readl_relaxed(dpu_mdss->mmio); + pm_runtime_put_sync(dev->dev); + + priv->mdss = &dpu_mdss->base; + + return ret; + +irq_error: + _dpu_mdss_irq_domain_fini(dpu_mdss); +irq_domain_error: + msm_dss_put_clk(mp->clk_config, mp->num_clk); +clk_parse_err: + devm_kfree(&pdev->dev, mp->clk_config); + if (dpu_mdss->mmio) + devm_iounmap(&pdev->dev, dpu_mdss->mmio); + dpu_mdss->mmio = NULL; + return ret; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c new file mode 100644 index 000000000000..b640e39ebaca --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -0,0 +1,1963 @@ +/* + * Copyright (C) 2014-2018 The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/debugfs.h> +#include <linux/dma-buf.h> + +#include "msm_drv.h" +#include "dpu_kms.h" +#include "dpu_formats.h" +#include "dpu_hw_sspp.h" +#include "dpu_hw_catalog_format.h" +#include "dpu_trace.h" +#include "dpu_crtc.h" +#include "dpu_vbif.h" +#include "dpu_plane.h" + +#define DPU_DEBUG_PLANE(pl, fmt, ...) DPU_DEBUG("plane%d " fmt,\ + (pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__) + +#define DPU_ERROR_PLANE(pl, fmt, ...) DPU_ERROR("plane%d " fmt,\ + (pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__) + +#define DECIMATED_DIMENSION(dim, deci) (((dim) + ((1 << (deci)) - 1)) >> (deci)) +#define PHASE_STEP_SHIFT 21 +#define PHASE_STEP_UNIT_SCALE ((int) (1 << PHASE_STEP_SHIFT)) +#define PHASE_RESIDUAL 15 + +#define SHARP_STRENGTH_DEFAULT 32 +#define SHARP_EDGE_THR_DEFAULT 112 +#define SHARP_SMOOTH_THR_DEFAULT 8 +#define SHARP_NOISE_THR_DEFAULT 2 + +#define DPU_NAME_SIZE 12 + +#define DPU_PLANE_COLOR_FILL_FLAG BIT(31) +#define DPU_ZPOS_MAX 255 + +/* multirect rect index */ +enum { + R0, + R1, + R_MAX +}; + +#define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4 +#define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3 + +#define DEFAULT_REFRESH_RATE 60 + +/** + * enum dpu_plane_qos - Different qos configurations for each pipe + * + * @DPU_PLANE_QOS_VBLANK_CTRL: Setup VBLANK qos for the pipe. + * @DPU_PLANE_QOS_VBLANK_AMORTIZE: Enables Amortization within pipe. + * this configuration is mutually exclusive from VBLANK_CTRL. + * @DPU_PLANE_QOS_PANIC_CTRL: Setup panic for the pipe. + */ +enum dpu_plane_qos { + DPU_PLANE_QOS_VBLANK_CTRL = BIT(0), + DPU_PLANE_QOS_VBLANK_AMORTIZE = BIT(1), + DPU_PLANE_QOS_PANIC_CTRL = BIT(2), +}; + +/* + * struct dpu_plane - local dpu plane structure + * @aspace: address space pointer + * @csc_ptr: Points to dpu_csc_cfg structure to use for current + * @mplane_list: List of multirect planes of the same pipe + * @catalog: Points to dpu catalog structure + * @revalidate: force revalidation of all the plane properties + */ +struct dpu_plane { + struct drm_plane base; + + struct mutex lock; + + enum dpu_sspp pipe; + uint32_t features; /* capabilities from catalog */ + uint32_t nformats; + uint32_t formats[64]; + + struct dpu_hw_pipe *pipe_hw; + struct dpu_hw_pipe_cfg pipe_cfg; + struct dpu_hw_pipe_qos_cfg pipe_qos_cfg; + uint32_t color_fill; + bool is_error; + bool is_rt_pipe; + bool is_virtual; + struct list_head mplane_list; + struct dpu_mdss_cfg *catalog; + + struct dpu_csc_cfg *csc_ptr; + + const struct dpu_sspp_sub_blks *pipe_sblk; + char pipe_name[DPU_NAME_SIZE]; + + /* debugfs related stuff */ + struct dentry *debugfs_root; + struct dpu_debugfs_regset32 debugfs_src; + struct dpu_debugfs_regset32 debugfs_scaler; + struct dpu_debugfs_regset32 debugfs_csc; + bool debugfs_default_scale; +}; + +#define to_dpu_plane(x) container_of(x, struct dpu_plane, base) + +static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane) +{ + struct msm_drm_private *priv; + + if (!plane || !plane->dev) + return NULL; + priv = plane->dev->dev_private; + if (!priv) + return NULL; + return to_dpu_kms(priv->kms); +} + +static bool dpu_plane_enabled(struct drm_plane_state *state) +{ + return state && state->fb && state->crtc; +} + +static bool dpu_plane_sspp_enabled(struct drm_plane_state *state) +{ + return state && state->crtc; +} + +/** + * _dpu_plane_calc_fill_level - calculate fill level of the given source format + * @plane: Pointer to drm plane + * @fmt: Pointer to source buffer format + * @src_wdith: width of source buffer + * Return: fill level corresponding to the source buffer/format or 0 if error + */ +static inline int _dpu_plane_calc_fill_level(struct drm_plane *plane, + const struct dpu_format *fmt, u32 src_width) +{ + struct dpu_plane *pdpu, *tmp; + struct dpu_plane_state *pstate; + u32 fixed_buff_size; + u32 total_fl; + + if (!plane || !fmt || !plane->state || !src_width || !fmt->bpp) { + DPU_ERROR("invalid arguments\n"); + return 0; + } + + pdpu = to_dpu_plane(plane); + pstate = to_dpu_plane_state(plane->state); + fixed_buff_size = pdpu->pipe_sblk->common->pixel_ram_size; + + list_for_each_entry(tmp, &pdpu->mplane_list, mplane_list) { + if (!dpu_plane_enabled(tmp->base.state)) + continue; + DPU_DEBUG("plane%d/%d src_width:%d/%d\n", + pdpu->base.base.id, tmp->base.base.id, + src_width, + drm_rect_width(&tmp->pipe_cfg.src_rect)); + src_width = max_t(u32, src_width, + drm_rect_width(&tmp->pipe_cfg.src_rect)); + } + + if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) { + if (fmt->chroma_sample == DPU_CHROMA_420) { + /* NV12 */ + total_fl = (fixed_buff_size / 2) / + ((src_width + 32) * fmt->bpp); + } else { + /* non NV12 */ + total_fl = (fixed_buff_size / 2) * 2 / + ((src_width + 32) * fmt->bpp); + } + } else { + if (pstate->multirect_mode == DPU_SSPP_MULTIRECT_PARALLEL) { + total_fl = (fixed_buff_size / 2) * 2 / + ((src_width + 32) * fmt->bpp); + } else { + total_fl = (fixed_buff_size) * 2 / + ((src_width + 32) * fmt->bpp); + } + } + + DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s w:%u fl:%u\n", + plane->base.id, pdpu->pipe - SSPP_VIG0, + (char *)&fmt->base.pixel_format, + src_width, total_fl); + + return total_fl; +} + +/** + * _dpu_plane_get_qos_lut - get LUT mapping based on fill level + * @tbl: Pointer to LUT table + * @total_fl: fill level + * Return: LUT setting corresponding to the fill level + */ +static u64 _dpu_plane_get_qos_lut(const struct dpu_qos_lut_tbl *tbl, + u32 total_fl) +{ + int i; + + if (!tbl || !tbl->nentry || !tbl->entries) + return 0; + + for (i = 0; i < tbl->nentry; i++) + if (total_fl <= tbl->entries[i].fl) + return tbl->entries[i].lut; + + /* if last fl is zero, use as default */ + if (!tbl->entries[i-1].fl) + return tbl->entries[i-1].lut; + + return 0; +} + +/** + * _dpu_plane_set_qos_lut - set QoS LUT of the given plane + * @plane: Pointer to drm plane + * @fb: Pointer to framebuffer associated with the given plane + */ +static void _dpu_plane_set_qos_lut(struct drm_plane *plane, + struct drm_framebuffer *fb) +{ + struct dpu_plane *pdpu; + const struct dpu_format *fmt = NULL; + u64 qos_lut; + u32 total_fl = 0, lut_usage; + + if (!plane || !fb) { + DPU_ERROR("invalid arguments plane %d fb %d\n", + plane != 0, fb != 0); + return; + } + + pdpu = to_dpu_plane(plane); + + if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) { + DPU_ERROR("invalid arguments\n"); + return; + } else if (!pdpu->pipe_hw->ops.setup_creq_lut) { + return; + } + + if (!pdpu->is_rt_pipe) { + lut_usage = DPU_QOS_LUT_USAGE_NRT; + } else { + fmt = dpu_get_dpu_format_ext( + fb->format->format, + fb->modifier); + total_fl = _dpu_plane_calc_fill_level(plane, fmt, + drm_rect_width(&pdpu->pipe_cfg.src_rect)); + + if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) + lut_usage = DPU_QOS_LUT_USAGE_LINEAR; + else + lut_usage = DPU_QOS_LUT_USAGE_MACROTILE; + } + + qos_lut = _dpu_plane_get_qos_lut( + &pdpu->catalog->perf.qos_lut_tbl[lut_usage], total_fl); + + pdpu->pipe_qos_cfg.creq_lut = qos_lut; + + trace_dpu_perf_set_qos_luts(pdpu->pipe - SSPP_VIG0, + (fmt) ? fmt->base.pixel_format : 0, + pdpu->is_rt_pipe, total_fl, qos_lut, lut_usage); + + DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s rt:%d fl:%u lut:0x%llx\n", + plane->base.id, + pdpu->pipe - SSPP_VIG0, + fmt ? (char *)&fmt->base.pixel_format : NULL, + pdpu->is_rt_pipe, total_fl, qos_lut); + + pdpu->pipe_hw->ops.setup_creq_lut(pdpu->pipe_hw, &pdpu->pipe_qos_cfg); +} + +/** + * _dpu_plane_set_panic_lut - set danger/safe LUT of the given plane + * @plane: Pointer to drm plane + * @fb: Pointer to framebuffer associated with the given plane + */ +static void _dpu_plane_set_danger_lut(struct drm_plane *plane, + struct drm_framebuffer *fb) +{ + struct dpu_plane *pdpu; + const struct dpu_format *fmt = NULL; + u32 danger_lut, safe_lut; + + if (!plane || !fb) { + DPU_ERROR("invalid arguments\n"); + return; + } + + pdpu = to_dpu_plane(plane); + + if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) { + DPU_ERROR("invalid arguments\n"); + return; + } else if (!pdpu->pipe_hw->ops.setup_danger_safe_lut) { + return; + } + + if (!pdpu->is_rt_pipe) { + danger_lut = pdpu->catalog->perf.danger_lut_tbl + [DPU_QOS_LUT_USAGE_NRT]; + safe_lut = pdpu->catalog->perf.safe_lut_tbl + [DPU_QOS_LUT_USAGE_NRT]; + } else { + fmt = dpu_get_dpu_format_ext( + fb->format->format, + fb->modifier); + + if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) { + danger_lut = pdpu->catalog->perf.danger_lut_tbl + [DPU_QOS_LUT_USAGE_LINEAR]; + safe_lut = pdpu->catalog->perf.safe_lut_tbl + [DPU_QOS_LUT_USAGE_LINEAR]; + } else { + danger_lut = pdpu->catalog->perf.danger_lut_tbl + [DPU_QOS_LUT_USAGE_MACROTILE]; + safe_lut = pdpu->catalog->perf.safe_lut_tbl + [DPU_QOS_LUT_USAGE_MACROTILE]; + } + } + + pdpu->pipe_qos_cfg.danger_lut = danger_lut; + pdpu->pipe_qos_cfg.safe_lut = safe_lut; + + trace_dpu_perf_set_danger_luts(pdpu->pipe - SSPP_VIG0, + (fmt) ? fmt->base.pixel_format : 0, + (fmt) ? fmt->fetch_mode : 0, + pdpu->pipe_qos_cfg.danger_lut, + pdpu->pipe_qos_cfg.safe_lut); + + DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s mode:%d luts[0x%x, 0x%x]\n", + plane->base.id, + pdpu->pipe - SSPP_VIG0, + fmt ? (char *)&fmt->base.pixel_format : NULL, + fmt ? fmt->fetch_mode : -1, + pdpu->pipe_qos_cfg.danger_lut, + pdpu->pipe_qos_cfg.safe_lut); + + pdpu->pipe_hw->ops.setup_danger_safe_lut(pdpu->pipe_hw, + &pdpu->pipe_qos_cfg); +} + +/** + * _dpu_plane_set_qos_ctrl - set QoS control of the given plane + * @plane: Pointer to drm plane + * @enable: true to enable QoS control + * @flags: QoS control mode (enum dpu_plane_qos) + */ +static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane, + bool enable, u32 flags) +{ + struct dpu_plane *pdpu; + + if (!plane) { + DPU_ERROR("invalid arguments\n"); + return; + } + + pdpu = to_dpu_plane(plane); + + if (!pdpu->pipe_hw || !pdpu->pipe_sblk) { + DPU_ERROR("invalid arguments\n"); + return; + } else if (!pdpu->pipe_hw->ops.setup_qos_ctrl) { + return; + } + + if (flags & DPU_PLANE_QOS_VBLANK_CTRL) { + pdpu->pipe_qos_cfg.creq_vblank = pdpu->pipe_sblk->creq_vblank; + pdpu->pipe_qos_cfg.danger_vblank = + pdpu->pipe_sblk->danger_vblank; + pdpu->pipe_qos_cfg.vblank_en = enable; + } + + if (flags & DPU_PLANE_QOS_VBLANK_AMORTIZE) { + /* this feature overrules previous VBLANK_CTRL */ + pdpu->pipe_qos_cfg.vblank_en = false; + pdpu->pipe_qos_cfg.creq_vblank = 0; /* clear vblank bits */ + } + + if (flags & DPU_PLANE_QOS_PANIC_CTRL) + pdpu->pipe_qos_cfg.danger_safe_en = enable; + + if (!pdpu->is_rt_pipe) { + pdpu->pipe_qos_cfg.vblank_en = false; + pdpu->pipe_qos_cfg.danger_safe_en = false; + } + + DPU_DEBUG("plane%u: pnum:%d ds:%d vb:%d pri[0x%x, 0x%x] is_rt:%d\n", + plane->base.id, + pdpu->pipe - SSPP_VIG0, + pdpu->pipe_qos_cfg.danger_safe_en, + pdpu->pipe_qos_cfg.vblank_en, + pdpu->pipe_qos_cfg.creq_vblank, + pdpu->pipe_qos_cfg.danger_vblank, + pdpu->is_rt_pipe); + + pdpu->pipe_hw->ops.setup_qos_ctrl(pdpu->pipe_hw, + &pdpu->pipe_qos_cfg); +} + +int dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) +{ + struct dpu_plane *pdpu; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!plane || !plane->dev) { + DPU_ERROR("invalid arguments\n"); + return -EINVAL; + } + + priv = plane->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid KMS reference\n"); + return -EINVAL; + } + + dpu_kms = to_dpu_kms(priv->kms); + pdpu = to_dpu_plane(plane); + + if (!pdpu->is_rt_pipe) + goto end; + + pm_runtime_get_sync(&dpu_kms->pdev->dev); + _dpu_plane_set_qos_ctrl(plane, enable, DPU_PLANE_QOS_PANIC_CTRL); + pm_runtime_put_sync(&dpu_kms->pdev->dev); + +end: + return 0; +} + +/** + * _dpu_plane_set_ot_limit - set OT limit for the given plane + * @plane: Pointer to drm plane + * @crtc: Pointer to drm crtc + */ +static void _dpu_plane_set_ot_limit(struct drm_plane *plane, + struct drm_crtc *crtc) +{ + struct dpu_plane *pdpu; + struct dpu_vbif_set_ot_params ot_params; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!plane || !plane->dev || !crtc) { + DPU_ERROR("invalid arguments plane %d crtc %d\n", + plane != 0, crtc != 0); + return; + } + + priv = plane->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid KMS reference\n"); + return; + } + + dpu_kms = to_dpu_kms(priv->kms); + pdpu = to_dpu_plane(plane); + if (!pdpu->pipe_hw) { + DPU_ERROR("invalid pipe reference\n"); + return; + } + + memset(&ot_params, 0, sizeof(ot_params)); + ot_params.xin_id = pdpu->pipe_hw->cap->xin_id; + ot_params.num = pdpu->pipe_hw->idx - SSPP_NONE; + ot_params.width = drm_rect_width(&pdpu->pipe_cfg.src_rect); + ot_params.height = drm_rect_height(&pdpu->pipe_cfg.src_rect); + ot_params.is_wfd = !pdpu->is_rt_pipe; + ot_params.frame_rate = crtc->mode.vrefresh; + ot_params.vbif_idx = VBIF_RT; + ot_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl; + ot_params.rd = true; + + dpu_vbif_set_ot_limit(dpu_kms, &ot_params); +} + +/** + * _dpu_plane_set_vbif_qos - set vbif QoS for the given plane + * @plane: Pointer to drm plane + */ +static void _dpu_plane_set_qos_remap(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + struct dpu_vbif_set_qos_params qos_params; + struct msm_drm_private *priv; + struct dpu_kms *dpu_kms; + + if (!plane || !plane->dev) { + DPU_ERROR("invalid arguments\n"); + return; + } + + priv = plane->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid KMS reference\n"); + return; + } + + dpu_kms = to_dpu_kms(priv->kms); + pdpu = to_dpu_plane(plane); + if (!pdpu->pipe_hw) { + DPU_ERROR("invalid pipe reference\n"); + return; + } + + memset(&qos_params, 0, sizeof(qos_params)); + qos_params.vbif_idx = VBIF_RT; + qos_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl; + qos_params.xin_id = pdpu->pipe_hw->cap->xin_id; + qos_params.num = pdpu->pipe_hw->idx - SSPP_VIG0; + qos_params.is_rt = pdpu->is_rt_pipe; + + DPU_DEBUG("plane%d pipe:%d vbif:%d xin:%d rt:%d, clk_ctrl:%d\n", + plane->base.id, qos_params.num, + qos_params.vbif_idx, + qos_params.xin_id, qos_params.is_rt, + qos_params.clk_ctrl); + + dpu_vbif_set_qos_remap(dpu_kms, &qos_params); +} + +/** + * _dpu_plane_get_aspace: gets the address space + */ +static int _dpu_plane_get_aspace( + struct dpu_plane *pdpu, + struct dpu_plane_state *pstate, + struct msm_gem_address_space **aspace) +{ + struct dpu_kms *kms; + + if (!pdpu || !pstate || !aspace) { + DPU_ERROR("invalid parameters\n"); + return -EINVAL; + } + + kms = _dpu_plane_get_kms(&pdpu->base); + if (!kms) { + DPU_ERROR("invalid kms\n"); + return -EINVAL; + } + + *aspace = kms->base.aspace; + + return 0; +} + +static inline void _dpu_plane_set_scanout(struct drm_plane *plane, + struct dpu_plane_state *pstate, + struct dpu_hw_pipe_cfg *pipe_cfg, + struct drm_framebuffer *fb) +{ + struct dpu_plane *pdpu; + struct msm_gem_address_space *aspace = NULL; + int ret; + + if (!plane || !pstate || !pipe_cfg || !fb) { + DPU_ERROR( + "invalid arg(s), plane %d state %d cfg %d fb %d\n", + plane != 0, pstate != 0, pipe_cfg != 0, fb != 0); + return; + } + + pdpu = to_dpu_plane(plane); + if (!pdpu->pipe_hw) { + DPU_ERROR_PLANE(pdpu, "invalid pipe_hw\n"); + return; + } + + ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace); + if (ret) { + DPU_ERROR_PLANE(pdpu, "Failed to get aspace %d\n", ret); + return; + } + + ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout); + if (ret == -EAGAIN) + DPU_DEBUG_PLANE(pdpu, "not updating same src addrs\n"); + else if (ret) + DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + else if (pdpu->pipe_hw->ops.setup_sourceaddress) { + trace_dpu_plane_set_scanout(pdpu->pipe_hw->idx, + &pipe_cfg->layout, + pstate->multirect_index); + pdpu->pipe_hw->ops.setup_sourceaddress(pdpu->pipe_hw, pipe_cfg, + pstate->multirect_index); + } +} + +static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu, + struct dpu_plane_state *pstate, + uint32_t src_w, uint32_t src_h, uint32_t dst_w, uint32_t dst_h, + struct dpu_hw_scaler3_cfg *scale_cfg, + const struct dpu_format *fmt, + uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v) +{ + uint32_t i; + + if (!pdpu || !pstate || !scale_cfg || !fmt || !chroma_subsmpl_h || + !chroma_subsmpl_v) { + DPU_ERROR( + "pdpu %d pstate %d scale_cfg %d fmt %d smp_h %d smp_v %d\n", + !!pdpu, !!pstate, !!scale_cfg, !!fmt, chroma_subsmpl_h, + chroma_subsmpl_v); + return; + } + + memset(scale_cfg, 0, sizeof(*scale_cfg)); + memset(&pstate->pixel_ext, 0, sizeof(struct dpu_hw_pixel_ext)); + + scale_cfg->phase_step_x[DPU_SSPP_COMP_0] = + mult_frac((1 << PHASE_STEP_SHIFT), src_w, dst_w); + scale_cfg->phase_step_y[DPU_SSPP_COMP_0] = + mult_frac((1 << PHASE_STEP_SHIFT), src_h, dst_h); + + + scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2] = + scale_cfg->phase_step_y[DPU_SSPP_COMP_0] / chroma_subsmpl_v; + scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2] = + scale_cfg->phase_step_x[DPU_SSPP_COMP_0] / chroma_subsmpl_h; + + scale_cfg->phase_step_x[DPU_SSPP_COMP_2] = + scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2]; + scale_cfg->phase_step_y[DPU_SSPP_COMP_2] = + scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2]; + + scale_cfg->phase_step_x[DPU_SSPP_COMP_3] = + scale_cfg->phase_step_x[DPU_SSPP_COMP_0]; + scale_cfg->phase_step_y[DPU_SSPP_COMP_3] = + scale_cfg->phase_step_y[DPU_SSPP_COMP_0]; + + for (i = 0; i < DPU_MAX_PLANES; i++) { + scale_cfg->src_width[i] = src_w; + scale_cfg->src_height[i] = src_h; + if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) { + scale_cfg->src_width[i] /= chroma_subsmpl_h; + scale_cfg->src_height[i] /= chroma_subsmpl_v; + } + scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H; + scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V; + pstate->pixel_ext.num_ext_pxls_top[i] = + scale_cfg->src_height[i]; + pstate->pixel_ext.num_ext_pxls_left[i] = + scale_cfg->src_width[i]; + } + if (!(DPU_FORMAT_IS_YUV(fmt)) && (src_h == dst_h) + && (src_w == dst_w)) + return; + + scale_cfg->dst_width = dst_w; + scale_cfg->dst_height = dst_h; + scale_cfg->y_rgb_filter_cfg = DPU_SCALE_BIL; + scale_cfg->uv_filter_cfg = DPU_SCALE_BIL; + scale_cfg->alpha_filter_cfg = DPU_SCALE_ALPHA_BIL; + scale_cfg->lut_flag = 0; + scale_cfg->blend_cfg = 1; + scale_cfg->enable = 1; +} + +static inline void _dpu_plane_setup_csc(struct dpu_plane *pdpu) +{ + static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = { + { + /* S15.16 format */ + 0x00012A00, 0x00000000, 0x00019880, + 0x00012A00, 0xFFFF9B80, 0xFFFF3000, + 0x00012A00, 0x00020480, 0x00000000, + }, + /* signed bias */ + { 0xfff0, 0xff80, 0xff80,}, + { 0x0, 0x0, 0x0,}, + /* unsigned clamp */ + { 0x10, 0xeb, 0x10, 0xf0, 0x10, 0xf0,}, + { 0x00, 0xff, 0x00, 0xff, 0x00, 0xff,}, + }; + static const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L = { + { + /* S15.16 format */ + 0x00012A00, 0x00000000, 0x00019880, + 0x00012A00, 0xFFFF9B80, 0xFFFF3000, + 0x00012A00, 0x00020480, 0x00000000, + }, + /* signed bias */ + { 0xffc0, 0xfe00, 0xfe00,}, + { 0x0, 0x0, 0x0,}, + /* unsigned clamp */ + { 0x40, 0x3ac, 0x40, 0x3c0, 0x40, 0x3c0,}, + { 0x00, 0x3ff, 0x00, 0x3ff, 0x00, 0x3ff,}, + }; + + if (!pdpu) { + DPU_ERROR("invalid plane\n"); + return; + } + + if (BIT(DPU_SSPP_CSC_10BIT) & pdpu->features) + pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc10_YUV2RGB_601L; + else + pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc_YUV2RGB_601L; + + DPU_DEBUG_PLANE(pdpu, "using 0x%X 0x%X 0x%X...\n", + pdpu->csc_ptr->csc_mv[0], + pdpu->csc_ptr->csc_mv[1], + pdpu->csc_ptr->csc_mv[2]); +} + +static void _dpu_plane_setup_scaler(struct dpu_plane *pdpu, + struct dpu_plane_state *pstate, + const struct dpu_format *fmt, bool color_fill) +{ + struct dpu_hw_pixel_ext *pe; + uint32_t chroma_subsmpl_h, chroma_subsmpl_v; + + if (!pdpu || !fmt || !pstate) { + DPU_ERROR("invalid arg(s), plane %d fmt %d state %d\n", + pdpu != 0, fmt != 0, pstate != 0); + return; + } + + pe = &pstate->pixel_ext; + + /* don't chroma subsample if decimating */ + chroma_subsmpl_h = + drm_format_horz_chroma_subsampling(fmt->base.pixel_format); + chroma_subsmpl_v = + drm_format_vert_chroma_subsampling(fmt->base.pixel_format); + + /* update scaler. calculate default config for QSEED3 */ + _dpu_plane_setup_scaler3(pdpu, pstate, + drm_rect_width(&pdpu->pipe_cfg.src_rect), + drm_rect_height(&pdpu->pipe_cfg.src_rect), + drm_rect_width(&pdpu->pipe_cfg.dst_rect), + drm_rect_height(&pdpu->pipe_cfg.dst_rect), + &pstate->scaler3_cfg, fmt, + chroma_subsmpl_h, chroma_subsmpl_v); +} + +/** + * _dpu_plane_color_fill - enables color fill on plane + * @pdpu: Pointer to DPU plane object + * @color: RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red + * @alpha: 8-bit fill alpha value, 255 selects 100% alpha + * Returns: 0 on success + */ +static int _dpu_plane_color_fill(struct dpu_plane *pdpu, + uint32_t color, uint32_t alpha) +{ + const struct dpu_format *fmt; + const struct drm_plane *plane; + struct dpu_plane_state *pstate; + + if (!pdpu || !pdpu->base.state) { + DPU_ERROR("invalid plane\n"); + return -EINVAL; + } + + if (!pdpu->pipe_hw) { + DPU_ERROR_PLANE(pdpu, "invalid plane h/w pointer\n"); + return -EINVAL; + } + + plane = &pdpu->base; + pstate = to_dpu_plane_state(plane->state); + + DPU_DEBUG_PLANE(pdpu, "\n"); + + /* + * select fill format to match user property expectation, + * h/w only supports RGB variants + */ + fmt = dpu_get_dpu_format(DRM_FORMAT_ABGR8888); + + /* update sspp */ + if (fmt && pdpu->pipe_hw->ops.setup_solidfill) { + pdpu->pipe_hw->ops.setup_solidfill(pdpu->pipe_hw, + (color & 0xFFFFFF) | ((alpha & 0xFF) << 24), + pstate->multirect_index); + + /* override scaler/decimation if solid fill */ + pdpu->pipe_cfg.src_rect.x1 = 0; + pdpu->pipe_cfg.src_rect.y1 = 0; + pdpu->pipe_cfg.src_rect.x2 = + drm_rect_width(&pdpu->pipe_cfg.dst_rect); + pdpu->pipe_cfg.src_rect.y2 = + drm_rect_height(&pdpu->pipe_cfg.dst_rect); + _dpu_plane_setup_scaler(pdpu, pstate, fmt, true); + + if (pdpu->pipe_hw->ops.setup_format) + pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, + fmt, DPU_SSPP_SOLID_FILL, + pstate->multirect_index); + + if (pdpu->pipe_hw->ops.setup_rects) + pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw, + &pdpu->pipe_cfg, + pstate->multirect_index); + + if (pdpu->pipe_hw->ops.setup_pe) + pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw, + &pstate->pixel_ext); + + if (pdpu->pipe_hw->ops.setup_scaler && + pstate->multirect_index != DPU_SSPP_RECT_1) + pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw, + &pdpu->pipe_cfg, &pstate->pixel_ext, + &pstate->scaler3_cfg); + } + + return 0; +} + +void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state) +{ + struct dpu_plane_state *pstate; + + if (!drm_state) + return; + + pstate = to_dpu_plane_state(drm_state); + + pstate->multirect_index = DPU_SSPP_RECT_SOLO; + pstate->multirect_mode = DPU_SSPP_MULTIRECT_NONE; +} + +int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane) +{ + struct dpu_plane_state *pstate[R_MAX]; + const struct drm_plane_state *drm_state[R_MAX]; + struct drm_rect src[R_MAX], dst[R_MAX]; + struct dpu_plane *dpu_plane[R_MAX]; + const struct dpu_format *fmt[R_MAX]; + int i, buffer_lines; + unsigned int max_tile_height = 1; + bool parallel_fetch_qualified = true; + bool has_tiled_rect = false; + + for (i = 0; i < R_MAX; i++) { + const struct msm_format *msm_fmt; + + drm_state[i] = i ? plane->r1 : plane->r0; + msm_fmt = msm_framebuffer_format(drm_state[i]->fb); + fmt[i] = to_dpu_format(msm_fmt); + + if (DPU_FORMAT_IS_UBWC(fmt[i])) { + has_tiled_rect = true; + if (fmt[i]->tile_height > max_tile_height) + max_tile_height = fmt[i]->tile_height; + } + } + + for (i = 0; i < R_MAX; i++) { + int width_threshold; + + pstate[i] = to_dpu_plane_state(drm_state[i]); + dpu_plane[i] = to_dpu_plane(drm_state[i]->plane); + + if (pstate[i] == NULL) { + DPU_ERROR("DPU plane state of plane id %d is NULL\n", + drm_state[i]->plane->base.id); + return -EINVAL; + } + + src[i].x1 = drm_state[i]->src_x >> 16; + src[i].y1 = drm_state[i]->src_y >> 16; + src[i].x2 = src[i].x1 + (drm_state[i]->src_w >> 16); + src[i].y2 = src[i].y1 + (drm_state[i]->src_h >> 16); + + dst[i] = drm_plane_state_dest(drm_state[i]); + + if (drm_rect_calc_hscale(&src[i], &dst[i], 1, 1) != 1 || + drm_rect_calc_vscale(&src[i], &dst[i], 1, 1) != 1) { + DPU_ERROR_PLANE(dpu_plane[i], + "scaling is not supported in multirect mode\n"); + return -EINVAL; + } + + if (DPU_FORMAT_IS_YUV(fmt[i])) { + DPU_ERROR_PLANE(dpu_plane[i], + "Unsupported format for multirect mode\n"); + return -EINVAL; + } + + /** + * SSPP PD_MEM is split half - one for each RECT. + * Tiled formats need 5 lines of buffering while fetching + * whereas linear formats need only 2 lines. + * So we cannot support more than half of the supported SSPP + * width for tiled formats. + */ + width_threshold = dpu_plane[i]->pipe_sblk->common->maxlinewidth; + if (has_tiled_rect) + width_threshold /= 2; + + if (parallel_fetch_qualified && + drm_rect_width(&src[i]) > width_threshold) + parallel_fetch_qualified = false; + + } + + /* Validate RECT's and set the mode */ + + /* Prefer PARALLEL FETCH Mode over TIME_MX Mode */ + if (parallel_fetch_qualified) { + pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + + goto done; + } + + /* TIME_MX Mode */ + buffer_lines = 2 * max_tile_height; + + if (dst[R1].y1 >= dst[R0].y2 + buffer_lines || + dst[R0].y1 >= dst[R1].y2 + buffer_lines) { + pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX; + pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX; + } else { + DPU_ERROR( + "No multirect mode possible for the planes (%d - %d)\n", + drm_state[R0]->plane->base.id, + drm_state[R1]->plane->base.id); + return -EINVAL; + } + +done: + if (dpu_plane[R0]->is_virtual) { + pstate[R0]->multirect_index = DPU_SSPP_RECT_1; + pstate[R1]->multirect_index = DPU_SSPP_RECT_0; + } else { + pstate[R0]->multirect_index = DPU_SSPP_RECT_0; + pstate[R1]->multirect_index = DPU_SSPP_RECT_1; + }; + + DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n", + pstate[R0]->multirect_mode, pstate[R0]->multirect_index); + DPU_DEBUG_PLANE(dpu_plane[R1], "R1: %d - %d\n", + pstate[R1]->multirect_mode, pstate[R1]->multirect_index); + return 0; +} + +/** + * dpu_plane_get_ctl_flush - get control flush for the given plane + * @plane: Pointer to drm plane structure + * @ctl: Pointer to hardware control driver + * @flush_sspp: Pointer to sspp flush control word + */ +void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl, + u32 *flush_sspp) +{ + struct dpu_plane_state *pstate; + + if (!plane || !flush_sspp) { + DPU_ERROR("invalid parameters\n"); + return; + } + + pstate = to_dpu_plane_state(plane->state); + + *flush_sspp = ctl->ops.get_bitmask_sspp(ctl, dpu_plane_pipe(plane)); +} + +static int dpu_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *new_state) +{ + struct drm_framebuffer *fb = new_state->fb; + struct dpu_plane *pdpu = to_dpu_plane(plane); + struct dpu_plane_state *pstate = to_dpu_plane_state(new_state); + struct dpu_hw_fmt_layout layout; + struct drm_gem_object *obj; + struct msm_gem_object *msm_obj; + struct dma_fence *fence; + struct msm_gem_address_space *aspace; + int ret; + + if (!new_state->fb) + return 0; + + DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id); + + ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace); + if (ret) { + DPU_ERROR_PLANE(pdpu, "Failed to get aspace\n"); + return ret; + } + + /* cache aspace */ + pstate->aspace = aspace; + + /* + * TODO: Need to sort out the msm_framebuffer_prepare() call below so + * we can use msm_atomic_prepare_fb() instead of doing the + * implicit fence and fb prepare by hand here. + */ + obj = msm_framebuffer_bo(new_state->fb, 0); + msm_obj = to_msm_bo(obj); + fence = reservation_object_get_excl_rcu(msm_obj->resv); + if (fence) + drm_atomic_set_fence_for_plane(new_state, fence); + + if (pstate->aspace) { + ret = msm_framebuffer_prepare(new_state->fb, + pstate->aspace); + if (ret) { + DPU_ERROR("failed to prepare framebuffer\n"); + return ret; + } + } + + /* validate framebuffer layout before commit */ + ret = dpu_format_populate_layout(pstate->aspace, + new_state->fb, &layout); + if (ret) { + DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + return ret; + } + + return 0; +} + +static void dpu_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct dpu_plane *pdpu = to_dpu_plane(plane); + struct dpu_plane_state *old_pstate; + + if (!old_state || !old_state->fb) + return; + + old_pstate = to_dpu_plane_state(old_state); + + DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id); + + msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace); +} + +static bool dpu_plane_validate_src(struct drm_rect *src, + struct drm_rect *fb_rect, + uint32_t min_src_size) +{ + /* Ensure fb size is supported */ + if (drm_rect_width(fb_rect) > MAX_IMG_WIDTH || + drm_rect_height(fb_rect) > MAX_IMG_HEIGHT) + return false; + + /* Ensure src rect is above the minimum size */ + if (drm_rect_width(src) < min_src_size || + drm_rect_height(src) < min_src_size) + return false; + + /* Ensure src is fully encapsulated in fb */ + return drm_rect_intersect(fb_rect, src) && + drm_rect_equals(fb_rect, src); +} + +static int dpu_plane_sspp_atomic_check(struct drm_plane *plane, + struct drm_plane_state *state) +{ + int ret = 0; + struct dpu_plane *pdpu; + struct dpu_plane_state *pstate; + const struct dpu_format *fmt; + struct drm_rect src, dst, fb_rect = { 0 }; + uint32_t max_upscale = 1, max_downscale = 1; + uint32_t min_src_size, max_linewidth; + int hscale = 1, vscale = 1; + + if (!plane || !state) { + DPU_ERROR("invalid arg(s), plane %d state %d\n", + plane != 0, state != 0); + ret = -EINVAL; + goto exit; + } + + pdpu = to_dpu_plane(plane); + pstate = to_dpu_plane_state(state); + + if (!pdpu->pipe_sblk) { + DPU_ERROR_PLANE(pdpu, "invalid catalog\n"); + ret = -EINVAL; + goto exit; + } + + src.x1 = state->src_x >> 16; + src.y1 = state->src_y >> 16; + src.x2 = src.x1 + (state->src_w >> 16); + src.y2 = src.y1 + (state->src_h >> 16); + + dst = drm_plane_state_dest(state); + + fb_rect.x2 = state->fb->width; + fb_rect.y2 = state->fb->height; + + max_linewidth = pdpu->pipe_sblk->common->maxlinewidth; + + if (pdpu->features & DPU_SSPP_SCALER) { + max_downscale = pdpu->pipe_sblk->maxdwnscale; + max_upscale = pdpu->pipe_sblk->maxupscale; + } + if (drm_rect_width(&src) < drm_rect_width(&dst)) + hscale = drm_rect_calc_hscale(&src, &dst, 1, max_upscale); + else + hscale = drm_rect_calc_hscale(&dst, &src, 1, max_downscale); + if (drm_rect_height(&src) < drm_rect_height(&dst)) + vscale = drm_rect_calc_vscale(&src, &dst, 1, max_upscale); + else + vscale = drm_rect_calc_vscale(&dst, &src, 1, max_downscale); + + DPU_DEBUG_PLANE(pdpu, "check %d -> %d\n", + dpu_plane_enabled(plane->state), dpu_plane_enabled(state)); + + if (!dpu_plane_enabled(state)) + goto exit; + + fmt = to_dpu_format(msm_framebuffer_format(state->fb)); + + min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1; + + if (DPU_FORMAT_IS_YUV(fmt) && + (!(pdpu->features & DPU_SSPP_SCALER) || + !(pdpu->features & (BIT(DPU_SSPP_CSC) + | BIT(DPU_SSPP_CSC_10BIT))))) { + DPU_ERROR_PLANE(pdpu, + "plane doesn't have scaler/csc for yuv\n"); + ret = -EINVAL; + + /* check src bounds */ + } else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) { + DPU_ERROR_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&src)); + ret = -E2BIG; + + /* valid yuv image */ + } else if (DPU_FORMAT_IS_YUV(fmt) && + (src.x1 & 0x1 || src.y1 & 0x1 || + drm_rect_width(&src) & 0x1 || + drm_rect_height(&src) & 0x1)) { + DPU_ERROR_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&src)); + ret = -EINVAL; + + /* min dst support */ + } else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) { + DPU_ERROR_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&dst)); + ret = -EINVAL; + + /* check decimated source width */ + } else if (drm_rect_width(&src) > max_linewidth) { + DPU_ERROR_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n", + DRM_RECT_ARG(&src), max_linewidth); + ret = -E2BIG; + + /* check scaler capability */ + } else if (hscale < 0 || vscale < 0) { + DPU_ERROR_PLANE(pdpu, "invalid scaling requested src=" + DRM_RECT_FMT " dst=" DRM_RECT_FMT "\n", + DRM_RECT_ARG(&src), DRM_RECT_ARG(&dst)); + ret = -E2BIG; + } + +exit: + return ret; +} + +static int dpu_plane_atomic_check(struct drm_plane *plane, + struct drm_plane_state *state) +{ + if (!state->fb) + return 0; + + DPU_DEBUG_PLANE(to_dpu_plane(plane), "\n"); + + return dpu_plane_sspp_atomic_check(plane, state); +} + +void dpu_plane_flush(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + struct dpu_plane_state *pstate; + + if (!plane || !plane->state) { + DPU_ERROR("invalid plane\n"); + return; + } + + pdpu = to_dpu_plane(plane); + pstate = to_dpu_plane_state(plane->state); + + /* + * These updates have to be done immediately before the plane flush + * timing, and may not be moved to the atomic_update/mode_set functions. + */ + if (pdpu->is_error) + /* force white frame with 100% alpha pipe output on error */ + _dpu_plane_color_fill(pdpu, 0xFFFFFF, 0xFF); + else if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) + /* force 100% alpha */ + _dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF); + else if (pdpu->pipe_hw && pdpu->csc_ptr && pdpu->pipe_hw->ops.setup_csc) + pdpu->pipe_hw->ops.setup_csc(pdpu->pipe_hw, pdpu->csc_ptr); + + /* flag h/w flush complete */ + if (plane->state) + pstate->pending = false; +} + +/** + * dpu_plane_set_error: enable/disable error condition + * @plane: pointer to drm_plane structure + */ +void dpu_plane_set_error(struct drm_plane *plane, bool error) +{ + struct dpu_plane *pdpu; + + if (!plane) + return; + + pdpu = to_dpu_plane(plane); + pdpu->is_error = error; +} + +static int dpu_plane_sspp_atomic_update(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + uint32_t nplanes, src_flags; + struct dpu_plane *pdpu; + struct drm_plane_state *state; + struct dpu_plane_state *pstate; + struct dpu_plane_state *old_pstate; + const struct dpu_format *fmt; + struct drm_crtc *crtc; + struct drm_framebuffer *fb; + struct drm_rect src, dst; + + if (!plane) { + DPU_ERROR("invalid plane\n"); + return -EINVAL; + } else if (!plane->state) { + DPU_ERROR("invalid plane state\n"); + return -EINVAL; + } else if (!old_state) { + DPU_ERROR("invalid old state\n"); + return -EINVAL; + } + + pdpu = to_dpu_plane(plane); + state = plane->state; + + pstate = to_dpu_plane_state(state); + + old_pstate = to_dpu_plane_state(old_state); + + crtc = state->crtc; + fb = state->fb; + if (!crtc || !fb) { + DPU_ERROR_PLANE(pdpu, "invalid crtc %d or fb %d\n", + crtc != 0, fb != 0); + return -EINVAL; + } + fmt = to_dpu_format(msm_framebuffer_format(fb)); + nplanes = fmt->num_planes; + + memset(&(pdpu->pipe_cfg), 0, sizeof(struct dpu_hw_pipe_cfg)); + + _dpu_plane_set_scanout(plane, pstate, &pdpu->pipe_cfg, fb); + + pstate->pending = true; + + pdpu->is_rt_pipe = (dpu_crtc_get_client_type(crtc) != NRT_CLIENT); + _dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL); + + src.x1 = state->src_x >> 16; + src.y1 = state->src_y >> 16; + src.x2 = src.x1 + (state->src_w >> 16); + src.y2 = src.y1 + (state->src_h >> 16); + + dst = drm_plane_state_dest(state); + + DPU_DEBUG_PLANE(pdpu, "FB[%u] " DRM_RECT_FMT "->crtc%u " DRM_RECT_FMT + ", %4.4s ubwc %d\n", fb->base.id, DRM_RECT_ARG(&src), + crtc->base.id, DRM_RECT_ARG(&dst), + (char *)&fmt->base.pixel_format, + DPU_FORMAT_IS_UBWC(fmt)); + + pdpu->pipe_cfg.src_rect = src; + pdpu->pipe_cfg.dst_rect = dst; + + _dpu_plane_setup_scaler(pdpu, pstate, fmt, false); + + /* override for color fill */ + if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) { + /* skip remaining processing on color fill */ + return 0; + } + + if (pdpu->pipe_hw->ops.setup_rects) { + pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw, + &pdpu->pipe_cfg, + pstate->multirect_index); + } + + if (pdpu->pipe_hw->ops.setup_pe && + (pstate->multirect_index != DPU_SSPP_RECT_1)) + pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw, + &pstate->pixel_ext); + + /** + * when programmed in multirect mode, scalar block will be + * bypassed. Still we need to update alpha and bitwidth + * ONLY for RECT0 + */ + if (pdpu->pipe_hw->ops.setup_scaler && + pstate->multirect_index != DPU_SSPP_RECT_1) + pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw, + &pdpu->pipe_cfg, &pstate->pixel_ext, + &pstate->scaler3_cfg); + + if (pdpu->pipe_hw->ops.setup_multirect) + pdpu->pipe_hw->ops.setup_multirect( + pdpu->pipe_hw, + pstate->multirect_index, + pstate->multirect_mode); + + if (pdpu->pipe_hw->ops.setup_format) { + src_flags = 0x0; + + /* update format */ + pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, fmt, src_flags, + pstate->multirect_index); + + if (pdpu->pipe_hw->ops.setup_cdp) { + struct dpu_hw_pipe_cdp_cfg *cdp_cfg = &pstate->cdp_cfg; + + memset(cdp_cfg, 0, sizeof(struct dpu_hw_pipe_cdp_cfg)); + + cdp_cfg->enable = pdpu->catalog->perf.cdp_cfg + [DPU_PERF_CDP_USAGE_RT].rd_enable; + cdp_cfg->ubwc_meta_enable = + DPU_FORMAT_IS_UBWC(fmt); + cdp_cfg->tile_amortize_enable = + DPU_FORMAT_IS_UBWC(fmt) || + DPU_FORMAT_IS_TILE(fmt); + cdp_cfg->preload_ahead = DPU_SSPP_CDP_PRELOAD_AHEAD_64; + + pdpu->pipe_hw->ops.setup_cdp(pdpu->pipe_hw, cdp_cfg); + } + + /* update csc */ + if (DPU_FORMAT_IS_YUV(fmt)) + _dpu_plane_setup_csc(pdpu); + else + pdpu->csc_ptr = 0; + } + + _dpu_plane_set_qos_lut(plane, fb); + _dpu_plane_set_danger_lut(plane, fb); + + if (plane->type != DRM_PLANE_TYPE_CURSOR) { + _dpu_plane_set_qos_ctrl(plane, true, DPU_PLANE_QOS_PANIC_CTRL); + _dpu_plane_set_ot_limit(plane, crtc); + } + + _dpu_plane_set_qos_remap(plane); + return 0; +} + +static void _dpu_plane_atomic_disable(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct dpu_plane *pdpu; + struct drm_plane_state *state; + struct dpu_plane_state *pstate; + + if (!plane) { + DPU_ERROR("invalid plane\n"); + return; + } else if (!plane->state) { + DPU_ERROR("invalid plane state\n"); + return; + } else if (!old_state) { + DPU_ERROR("invalid old state\n"); + return; + } + + pdpu = to_dpu_plane(plane); + state = plane->state; + pstate = to_dpu_plane_state(state); + + trace_dpu_plane_disable(DRMID(plane), is_dpu_plane_virtual(plane), + pstate->multirect_mode); + + pstate->pending = true; + + if (is_dpu_plane_virtual(plane) && + pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_multirect) + pdpu->pipe_hw->ops.setup_multirect(pdpu->pipe_hw, + DPU_SSPP_RECT_SOLO, DPU_SSPP_MULTIRECT_NONE); +} + +static void dpu_plane_atomic_update(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct dpu_plane *pdpu; + struct drm_plane_state *state; + + if (!plane) { + DPU_ERROR("invalid plane\n"); + return; + } else if (!plane->state) { + DPU_ERROR("invalid plane state\n"); + return; + } + + pdpu = to_dpu_plane(plane); + pdpu->is_error = false; + state = plane->state; + + DPU_DEBUG_PLANE(pdpu, "\n"); + + if (!dpu_plane_sspp_enabled(state)) { + _dpu_plane_atomic_disable(plane, old_state); + } else { + int ret; + + ret = dpu_plane_sspp_atomic_update(plane, old_state); + /* atomic_check should have ensured that this doesn't fail */ + WARN_ON(ret < 0); + } +} + +void dpu_plane_restore(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + + if (!plane || !plane->state) { + DPU_ERROR("invalid plane\n"); + return; + } + + pdpu = to_dpu_plane(plane); + + DPU_DEBUG_PLANE(pdpu, "\n"); + + /* last plane state is same as current state */ + dpu_plane_atomic_update(plane, plane->state); +} + +static void dpu_plane_destroy(struct drm_plane *plane) +{ + struct dpu_plane *pdpu = plane ? to_dpu_plane(plane) : NULL; + + DPU_DEBUG_PLANE(pdpu, "\n"); + + if (pdpu) { + _dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL); + + mutex_destroy(&pdpu->lock); + + drm_plane_helper_disable(plane, NULL); + + /* this will destroy the states as well */ + drm_plane_cleanup(plane); + + if (pdpu->pipe_hw) + dpu_hw_sspp_destroy(pdpu->pipe_hw); + + kfree(pdpu); + } +} + +static void dpu_plane_destroy_state(struct drm_plane *plane, + struct drm_plane_state *state) +{ + struct dpu_plane_state *pstate; + + if (!plane || !state) { + DPU_ERROR("invalid arg(s), plane %d state %d\n", + plane != 0, state != 0); + return; + } + + pstate = to_dpu_plane_state(state); + + /* remove ref count for frame buffers */ + if (state->fb) + drm_framebuffer_put(state->fb); + + kfree(pstate); +} + +static struct drm_plane_state * +dpu_plane_duplicate_state(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + struct dpu_plane_state *pstate; + struct dpu_plane_state *old_state; + + if (!plane) { + DPU_ERROR("invalid plane\n"); + return NULL; + } else if (!plane->state) { + DPU_ERROR("invalid plane state\n"); + return NULL; + } + + old_state = to_dpu_plane_state(plane->state); + pdpu = to_dpu_plane(plane); + pstate = kmemdup(old_state, sizeof(*old_state), GFP_KERNEL); + if (!pstate) { + DPU_ERROR_PLANE(pdpu, "failed to allocate state\n"); + return NULL; + } + + DPU_DEBUG_PLANE(pdpu, "\n"); + + pstate->pending = false; + + __drm_atomic_helper_plane_duplicate_state(plane, &pstate->base); + + return &pstate->base; +} + +static void dpu_plane_reset(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + struct dpu_plane_state *pstate; + + if (!plane) { + DPU_ERROR("invalid plane\n"); + return; + } + + pdpu = to_dpu_plane(plane); + DPU_DEBUG_PLANE(pdpu, "\n"); + + /* remove previous state, if present */ + if (plane->state) { + dpu_plane_destroy_state(plane, plane->state); + plane->state = 0; + } + + pstate = kzalloc(sizeof(*pstate), GFP_KERNEL); + if (!pstate) { + DPU_ERROR_PLANE(pdpu, "failed to allocate state\n"); + return; + } + + pstate->base.plane = plane; + + plane->state = &pstate->base; +} + +#ifdef CONFIG_DEBUG_FS +static ssize_t _dpu_plane_danger_read(struct file *file, + char __user *buff, size_t count, loff_t *ppos) +{ + struct dpu_kms *kms = file->private_data; + struct dpu_mdss_cfg *cfg = kms->catalog; + int len = 0; + char buf[40] = {'\0'}; + + if (!cfg) + return -ENODEV; + + if (*ppos) + return 0; /* the end */ + + len = snprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl); + if (len < 0 || len >= sizeof(buf)) + return 0; + + if ((count < sizeof(buf)) || copy_to_user(buff, buf, len)) + return -EFAULT; + + *ppos += len; /* increase offset */ + + return len; +} + +static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable) +{ + struct drm_plane *plane; + + drm_for_each_plane(plane, kms->dev) { + if (plane->fb && plane->state) { + dpu_plane_danger_signal_ctrl(plane, enable); + DPU_DEBUG("plane:%d img:%dx%d ", + plane->base.id, plane->fb->width, + plane->fb->height); + DPU_DEBUG("src[%d,%d,%d,%d] dst[%d,%d,%d,%d]\n", + plane->state->src_x >> 16, + plane->state->src_y >> 16, + plane->state->src_w >> 16, + plane->state->src_h >> 16, + plane->state->crtc_x, plane->state->crtc_y, + plane->state->crtc_w, plane->state->crtc_h); + } else { + DPU_DEBUG("Inactive plane:%d\n", plane->base.id); + } + } +} + +static ssize_t _dpu_plane_danger_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + struct dpu_kms *kms = file->private_data; + struct dpu_mdss_cfg *cfg = kms->catalog; + int disable_panic; + char buf[10]; + + if (!cfg) + return -EFAULT; + + if (count >= sizeof(buf)) + return -EFAULT; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + buf[count] = 0; /* end of string */ + + if (kstrtoint(buf, 0, &disable_panic)) + return -EFAULT; + + if (disable_panic) { + /* Disable panic signal for all active pipes */ + DPU_DEBUG("Disabling danger:\n"); + _dpu_plane_set_danger_state(kms, false); + kms->has_danger_ctrl = false; + } else { + /* Enable panic signal for all active pipes */ + DPU_DEBUG("Enabling danger:\n"); + kms->has_danger_ctrl = true; + _dpu_plane_set_danger_state(kms, true); + } + + return count; +} + +static const struct file_operations dpu_plane_danger_enable = { + .open = simple_open, + .read = _dpu_plane_danger_read, + .write = _dpu_plane_danger_write, +}; + +static int _dpu_plane_init_debugfs(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + struct dpu_kms *kms; + struct msm_drm_private *priv; + const struct dpu_sspp_sub_blks *sblk = 0; + const struct dpu_sspp_cfg *cfg = 0; + + if (!plane || !plane->dev) { + DPU_ERROR("invalid arguments\n"); + return -EINVAL; + } + + priv = plane->dev->dev_private; + if (!priv || !priv->kms) { + DPU_ERROR("invalid KMS reference\n"); + return -EINVAL; + } + + kms = to_dpu_kms(priv->kms); + pdpu = to_dpu_plane(plane); + + if (pdpu && pdpu->pipe_hw) + cfg = pdpu->pipe_hw->cap; + if (cfg) + sblk = cfg->sblk; + + if (!sblk) + return 0; + + /* create overall sub-directory for the pipe */ + pdpu->debugfs_root = + debugfs_create_dir(pdpu->pipe_name, + plane->dev->primary->debugfs_root); + + if (!pdpu->debugfs_root) + return -ENOMEM; + + /* don't error check these */ + debugfs_create_x32("features", 0600, + pdpu->debugfs_root, &pdpu->features); + + /* add register dump support */ + dpu_debugfs_setup_regset32(&pdpu->debugfs_src, + sblk->src_blk.base + cfg->base, + sblk->src_blk.len, + kms); + dpu_debugfs_create_regset32("src_blk", 0400, + pdpu->debugfs_root, &pdpu->debugfs_src); + + if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) || + cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) { + dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler, + sblk->scaler_blk.base + cfg->base, + sblk->scaler_blk.len, + kms); + dpu_debugfs_create_regset32("scaler_blk", 0400, + pdpu->debugfs_root, + &pdpu->debugfs_scaler); + debugfs_create_bool("default_scaling", + 0600, + pdpu->debugfs_root, + &pdpu->debugfs_default_scale); + } + + if (cfg->features & BIT(DPU_SSPP_CSC) || + cfg->features & BIT(DPU_SSPP_CSC_10BIT)) { + dpu_debugfs_setup_regset32(&pdpu->debugfs_csc, + sblk->csc_blk.base + cfg->base, + sblk->csc_blk.len, + kms); + dpu_debugfs_create_regset32("csc_blk", 0400, + pdpu->debugfs_root, &pdpu->debugfs_csc); + } + + debugfs_create_u32("xin_id", + 0400, + pdpu->debugfs_root, + (u32 *) &cfg->xin_id); + debugfs_create_u32("clk_ctrl", + 0400, + pdpu->debugfs_root, + (u32 *) &cfg->clk_ctrl); + debugfs_create_x32("creq_vblank", + 0600, + pdpu->debugfs_root, + (u32 *) &sblk->creq_vblank); + debugfs_create_x32("danger_vblank", + 0600, + pdpu->debugfs_root, + (u32 *) &sblk->danger_vblank); + + debugfs_create_file("disable_danger", + 0600, + pdpu->debugfs_root, + kms, &dpu_plane_danger_enable); + + return 0; +} + +static void _dpu_plane_destroy_debugfs(struct drm_plane *plane) +{ + struct dpu_plane *pdpu; + + if (!plane) + return; + pdpu = to_dpu_plane(plane); + + debugfs_remove_recursive(pdpu->debugfs_root); +} +#else +static int _dpu_plane_init_debugfs(struct drm_plane *plane) +{ + return 0; +} +static void _dpu_plane_destroy_debugfs(struct drm_plane *plane) +{ +} +#endif + +static int dpu_plane_late_register(struct drm_plane *plane) +{ + return _dpu_plane_init_debugfs(plane); +} + +static void dpu_plane_early_unregister(struct drm_plane *plane) +{ + _dpu_plane_destroy_debugfs(plane); +} + +static const struct drm_plane_funcs dpu_plane_funcs = { + .update_plane = drm_atomic_helper_update_plane, + .disable_plane = drm_atomic_helper_disable_plane, + .destroy = dpu_plane_destroy, + .reset = dpu_plane_reset, + .atomic_duplicate_state = dpu_plane_duplicate_state, + .atomic_destroy_state = dpu_plane_destroy_state, + .late_register = dpu_plane_late_register, + .early_unregister = dpu_plane_early_unregister, +}; + +static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = { + .prepare_fb = dpu_plane_prepare_fb, + .cleanup_fb = dpu_plane_cleanup_fb, + .atomic_check = dpu_plane_atomic_check, + .atomic_update = dpu_plane_atomic_update, +}; + +enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane) +{ + return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE; +} + +bool is_dpu_plane_virtual(struct drm_plane *plane) +{ + return plane ? to_dpu_plane(plane)->is_virtual : false; +} + +/* initialize plane */ +struct drm_plane *dpu_plane_init(struct drm_device *dev, + uint32_t pipe, bool primary_plane, + unsigned long possible_crtcs, u32 master_plane_id) +{ + struct drm_plane *plane = NULL, *master_plane = NULL; + const struct dpu_format_extended *format_list; + struct dpu_plane *pdpu; + struct msm_drm_private *priv; + struct dpu_kms *kms; + enum drm_plane_type type; + int zpos_max = DPU_ZPOS_MAX; + int ret = -EINVAL; + + if (!dev) { + DPU_ERROR("[%u]device is NULL\n", pipe); + goto exit; + } + + priv = dev->dev_private; + if (!priv) { + DPU_ERROR("[%u]private data is NULL\n", pipe); + goto exit; + } + + if (!priv->kms) { + DPU_ERROR("[%u]invalid KMS reference\n", pipe); + goto exit; + } + kms = to_dpu_kms(priv->kms); + + if (!kms->catalog) { + DPU_ERROR("[%u]invalid catalog reference\n", pipe); + goto exit; + } + + /* create and zero local structure */ + pdpu = kzalloc(sizeof(*pdpu), GFP_KERNEL); + if (!pdpu) { + DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe); + ret = -ENOMEM; + goto exit; + } + + /* cache local stuff for later */ + plane = &pdpu->base; + pdpu->pipe = pipe; + pdpu->is_virtual = (master_plane_id != 0); + INIT_LIST_HEAD(&pdpu->mplane_list); + master_plane = drm_plane_find(dev, NULL, master_plane_id); + if (master_plane) { + struct dpu_plane *mpdpu = to_dpu_plane(master_plane); + + list_add_tail(&pdpu->mplane_list, &mpdpu->mplane_list); + } + + /* initialize underlying h/w driver */ + pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog, + master_plane_id != 0); + if (IS_ERR(pdpu->pipe_hw)) { + DPU_ERROR("[%u]SSPP init failed\n", pipe); + ret = PTR_ERR(pdpu->pipe_hw); + goto clean_plane; + } else if (!pdpu->pipe_hw->cap || !pdpu->pipe_hw->cap->sblk) { + DPU_ERROR("[%u]SSPP init returned invalid cfg\n", pipe); + goto clean_sspp; + } + + /* cache features mask for later */ + pdpu->features = pdpu->pipe_hw->cap->features; + pdpu->pipe_sblk = pdpu->pipe_hw->cap->sblk; + if (!pdpu->pipe_sblk) { + DPU_ERROR("[%u]invalid sblk\n", pipe); + goto clean_sspp; + } + + if (!master_plane_id) + format_list = pdpu->pipe_sblk->format_list; + else + format_list = pdpu->pipe_sblk->virt_format_list; + + pdpu->nformats = dpu_populate_formats(format_list, + pdpu->formats, + 0, + ARRAY_SIZE(pdpu->formats)); + + if (!pdpu->nformats) { + DPU_ERROR("[%u]no valid formats for plane\n", pipe); + goto clean_sspp; + } + + if (pdpu->features & BIT(DPU_SSPP_CURSOR)) + type = DRM_PLANE_TYPE_CURSOR; + else if (primary_plane) + type = DRM_PLANE_TYPE_PRIMARY; + else + type = DRM_PLANE_TYPE_OVERLAY; + ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs, + pdpu->formats, pdpu->nformats, + NULL, type, NULL); + if (ret) + goto clean_sspp; + + pdpu->catalog = kms->catalog; + + if (kms->catalog->mixer_count && + kms->catalog->mixer[0].sblk->maxblendstages) { + zpos_max = kms->catalog->mixer[0].sblk->maxblendstages - 1; + if (zpos_max > DPU_STAGE_MAX - DPU_STAGE_0 - 1) + zpos_max = DPU_STAGE_MAX - DPU_STAGE_0 - 1; + } + + ret = drm_plane_create_zpos_property(plane, 0, 0, zpos_max); + if (ret) + DPU_ERROR("failed to install zpos property, rc = %d\n", ret); + + /* success! finalize initialization */ + drm_plane_helper_add(plane, &dpu_plane_helper_funcs); + + /* save user friendly pipe name for later */ + snprintf(pdpu->pipe_name, DPU_NAME_SIZE, "plane%u", plane->base.id); + + mutex_init(&pdpu->lock); + + DPU_DEBUG("%s created for pipe:%u id:%u virtual:%u\n", pdpu->pipe_name, + pipe, plane->base.id, master_plane_id); + return plane; + +clean_sspp: + if (pdpu && pdpu->pipe_hw) + dpu_hw_sspp_destroy(pdpu->pipe_hw); +clean_plane: + kfree(pdpu); +exit: + return ERR_PTR(ret); +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h new file mode 100644 index 000000000000..f6fe6ddc7a3a --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -0,0 +1,175 @@ +/* + * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2013 Red Hat + * Author: Rob Clark <robdclark@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _DPU_PLANE_H_ +#define _DPU_PLANE_H_ + +#include <drm/drm_crtc.h> + +#include "dpu_kms.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_sspp.h" + +/** + * struct dpu_plane_state: Define dpu extension of drm plane state object + * @base: base drm plane state object + * @property_state: Local storage for msm_prop properties + * @property_values: cached plane property values + * @aspace: pointer to address space for input/output buffers + * @input_fence: dereferenced input fence pointer + * @stage: assigned by crtc blender + * @multirect_index: index of the rectangle of SSPP + * @multirect_mode: parallel or time multiplex multirect mode + * @pending: whether the current update is still pending + * @scaler3_cfg: configuration data for scaler3 + * @pixel_ext: configuration data for pixel extensions + * @scaler_check_state: indicates status of user provided pixel extension data + * @cdp_cfg: CDP configuration + */ +struct dpu_plane_state { + struct drm_plane_state base; + struct msm_gem_address_space *aspace; + void *input_fence; + enum dpu_stage stage; + uint32_t multirect_index; + uint32_t multirect_mode; + bool pending; + + /* scaler configuration */ + struct dpu_hw_scaler3_cfg scaler3_cfg; + struct dpu_hw_pixel_ext pixel_ext; + + struct dpu_hw_pipe_cdp_cfg cdp_cfg; +}; + +/** + * struct dpu_multirect_plane_states: Defines multirect pair of drm plane states + * @r0: drm plane configured on rect 0 + * @r1: drm plane configured on rect 1 + */ +struct dpu_multirect_plane_states { + const struct drm_plane_state *r0; + const struct drm_plane_state *r1; +}; + +#define to_dpu_plane_state(x) \ + container_of(x, struct dpu_plane_state, base) + +/** + * dpu_plane_pipe - return sspp identifier for the given plane + * @plane: Pointer to DRM plane object + * Returns: sspp identifier of the given plane + */ +enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane); + +/** + * is_dpu_plane_virtual - check for virtual plane + * @plane: Pointer to DRM plane object + * returns: true - if the plane is virtual + * false - if the plane is primary + */ +bool is_dpu_plane_virtual(struct drm_plane *plane); + +/** + * dpu_plane_get_ctl_flush - get control flush mask + * @plane: Pointer to DRM plane object + * @ctl: Pointer to control hardware + * @flush_sspp: Pointer to sspp flush control word + */ +void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl, + u32 *flush_sspp); + +/** + * dpu_plane_restore - restore hw state if previously power collapsed + * @plane: Pointer to drm plane structure + */ +void dpu_plane_restore(struct drm_plane *plane); + +/** + * dpu_plane_flush - final plane operations before commit flush + * @plane: Pointer to drm plane structure + */ +void dpu_plane_flush(struct drm_plane *plane); + +/** + * dpu_plane_kickoff - final plane operations before commit kickoff + * @plane: Pointer to drm plane structure + */ +void dpu_plane_kickoff(struct drm_plane *plane); + +/** + * dpu_plane_set_error: enable/disable error condition + * @plane: pointer to drm_plane structure + */ +void dpu_plane_set_error(struct drm_plane *plane, bool error); + +/** + * dpu_plane_init - create new dpu plane for the given pipe + * @dev: Pointer to DRM device + * @pipe: dpu hardware pipe identifier + * @primary_plane: true if this pipe is primary plane for crtc + * @possible_crtcs: bitmask of crtc that can be attached to the given pipe + * @master_plane_id: primary plane id of a multirect pipe. 0 value passed for + * a regular plane initialization. A non-zero primary plane + * id will be passed for a virtual pipe initialization. + * + */ +struct drm_plane *dpu_plane_init(struct drm_device *dev, + uint32_t pipe, bool primary_plane, + unsigned long possible_crtcs, u32 master_plane_id); + +/** + * dpu_plane_validate_multirecti_v2 - validate the multirect planes + * against hw limitations + * @plane: drm plate states of the multirect pair + */ +int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane); + +/** + * dpu_plane_clear_multirect - clear multirect bits for the given pipe + * @drm_state: Pointer to DRM plane state + */ +void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state); + +/** + * dpu_plane_wait_input_fence - wait for input fence object + * @plane: Pointer to DRM plane object + * @wait_ms: Wait timeout value + * Returns: Zero on success + */ +int dpu_plane_wait_input_fence(struct drm_plane *plane, uint32_t wait_ms); + +/** + * dpu_plane_color_fill - enables color fill on plane + * @plane: Pointer to DRM plane object + * @color: RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red + * @alpha: 8-bit fill alpha value, 255 selects 100% alpha + * Returns: 0 on success + */ +int dpu_plane_color_fill(struct drm_plane *plane, + uint32_t color, uint32_t alpha); + +/** + * dpu_plane_set_revalidate - sets revalidate flag which forces a full + * validation of the plane properties in the next atomic check + * @plane: Pointer to DRM plane object + * @enable: Boolean to set/unset the flag + */ +void dpu_plane_set_revalidate(struct drm_plane *plane, bool enable); + +#endif /* _DPU_PLANE_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c new file mode 100644 index 000000000000..a68f1249388c --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c @@ -0,0 +1,249 @@ +/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#define pr_fmt(fmt) "[drm:%s:%d]: " fmt, __func__, __LINE__ + +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/string.h> +#include <linux/of_address.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/of_platform.h> + +#include "dpu_power_handle.h" +#include "dpu_trace.h" + +static const char *data_bus_name[DPU_POWER_HANDLE_DBUS_ID_MAX] = { + [DPU_POWER_HANDLE_DBUS_ID_MNOC] = "qcom,dpu-data-bus", + [DPU_POWER_HANDLE_DBUS_ID_LLCC] = "qcom,dpu-llcc-bus", + [DPU_POWER_HANDLE_DBUS_ID_EBI] = "qcom,dpu-ebi-bus", +}; + +const char *dpu_power_handle_get_dbus_name(u32 bus_id) +{ + if (bus_id < DPU_POWER_HANDLE_DBUS_ID_MAX) + return data_bus_name[bus_id]; + + return NULL; +} + +static void dpu_power_event_trigger_locked(struct dpu_power_handle *phandle, + u32 event_type) +{ + struct dpu_power_event *event; + + list_for_each_entry(event, &phandle->event_list, list) { + if (event->event_type & event_type) + event->cb_fnc(event_type, event->usr); + } +} + +struct dpu_power_client *dpu_power_client_create( + struct dpu_power_handle *phandle, char *client_name) +{ + struct dpu_power_client *client; + static u32 id; + + if (!client_name || !phandle) { + pr_err("client name is null or invalid power data\n"); + return ERR_PTR(-EINVAL); + } + + client = kzalloc(sizeof(struct dpu_power_client), GFP_KERNEL); + if (!client) + return ERR_PTR(-ENOMEM); + + mutex_lock(&phandle->phandle_lock); + strlcpy(client->name, client_name, MAX_CLIENT_NAME_LEN); + client->usecase_ndx = VOTE_INDEX_DISABLE; + client->id = id; + client->active = true; + pr_debug("client %s created:%pK id :%d\n", client_name, + client, id); + id++; + list_add(&client->list, &phandle->power_client_clist); + mutex_unlock(&phandle->phandle_lock); + + return client; +} + +void dpu_power_client_destroy(struct dpu_power_handle *phandle, + struct dpu_power_client *client) +{ + if (!client || !phandle) { + pr_err("reg bus vote: invalid client handle\n"); + } else if (!client->active) { + pr_err("dpu power deinit already done\n"); + kfree(client); + } else { + pr_debug("bus vote client %s destroyed:%pK id:%u\n", + client->name, client, client->id); + mutex_lock(&phandle->phandle_lock); + list_del_init(&client->list); + mutex_unlock(&phandle->phandle_lock); + kfree(client); + } +} + +void dpu_power_resource_init(struct platform_device *pdev, + struct dpu_power_handle *phandle) +{ + phandle->dev = &pdev->dev; + + INIT_LIST_HEAD(&phandle->power_client_clist); + INIT_LIST_HEAD(&phandle->event_list); + + mutex_init(&phandle->phandle_lock); +} + +void dpu_power_resource_deinit(struct platform_device *pdev, + struct dpu_power_handle *phandle) +{ + struct dpu_power_client *curr_client, *next_client; + struct dpu_power_event *curr_event, *next_event; + + if (!phandle || !pdev) { + pr_err("invalid input param\n"); + return; + } + + mutex_lock(&phandle->phandle_lock); + list_for_each_entry_safe(curr_client, next_client, + &phandle->power_client_clist, list) { + pr_err("cliend:%s-%d still registered with refcount:%d\n", + curr_client->name, curr_client->id, + curr_client->refcount); + curr_client->active = false; + list_del(&curr_client->list); + } + + list_for_each_entry_safe(curr_event, next_event, + &phandle->event_list, list) { + pr_err("event:%d, client:%s still registered\n", + curr_event->event_type, + curr_event->client_name); + curr_event->active = false; + list_del(&curr_event->list); + } + mutex_unlock(&phandle->phandle_lock); +} + +int dpu_power_resource_enable(struct dpu_power_handle *phandle, + struct dpu_power_client *pclient, bool enable) +{ + bool changed = false; + u32 max_usecase_ndx = VOTE_INDEX_DISABLE, prev_usecase_ndx; + struct dpu_power_client *client; + + if (!phandle || !pclient) { + pr_err("invalid input argument\n"); + return -EINVAL; + } + + mutex_lock(&phandle->phandle_lock); + if (enable) + pclient->refcount++; + else if (pclient->refcount) + pclient->refcount--; + + if (pclient->refcount) + pclient->usecase_ndx = VOTE_INDEX_LOW; + else + pclient->usecase_ndx = VOTE_INDEX_DISABLE; + + list_for_each_entry(client, &phandle->power_client_clist, list) { + if (client->usecase_ndx < VOTE_INDEX_MAX && + client->usecase_ndx > max_usecase_ndx) + max_usecase_ndx = client->usecase_ndx; + } + + if (phandle->current_usecase_ndx != max_usecase_ndx) { + changed = true; + prev_usecase_ndx = phandle->current_usecase_ndx; + phandle->current_usecase_ndx = max_usecase_ndx; + } + + pr_debug("%pS: changed=%d current idx=%d request client %s id:%u enable:%d refcount:%d\n", + __builtin_return_address(0), changed, max_usecase_ndx, + pclient->name, pclient->id, enable, pclient->refcount); + + if (!changed) + goto end; + + if (enable) { + dpu_power_event_trigger_locked(phandle, + DPU_POWER_EVENT_PRE_ENABLE); + dpu_power_event_trigger_locked(phandle, + DPU_POWER_EVENT_POST_ENABLE); + + } else { + dpu_power_event_trigger_locked(phandle, + DPU_POWER_EVENT_PRE_DISABLE); + dpu_power_event_trigger_locked(phandle, + DPU_POWER_EVENT_POST_DISABLE); + } + +end: + mutex_unlock(&phandle->phandle_lock); + return 0; +} + +struct dpu_power_event *dpu_power_handle_register_event( + struct dpu_power_handle *phandle, + u32 event_type, void (*cb_fnc)(u32 event_type, void *usr), + void *usr, char *client_name) +{ + struct dpu_power_event *event; + + if (!phandle) { + pr_err("invalid power handle\n"); + return ERR_PTR(-EINVAL); + } else if (!cb_fnc || !event_type) { + pr_err("no callback fnc or event type\n"); + return ERR_PTR(-EINVAL); + } + + event = kzalloc(sizeof(struct dpu_power_event), GFP_KERNEL); + if (!event) + return ERR_PTR(-ENOMEM); + + event->event_type = event_type; + event->cb_fnc = cb_fnc; + event->usr = usr; + strlcpy(event->client_name, client_name, MAX_CLIENT_NAME_LEN); + event->active = true; + + mutex_lock(&phandle->phandle_lock); + list_add(&event->list, &phandle->event_list); + mutex_unlock(&phandle->phandle_lock); + + return event; +} + +void dpu_power_handle_unregister_event( + struct dpu_power_handle *phandle, + struct dpu_power_event *event) +{ + if (!phandle || !event) { + pr_err("invalid phandle or event\n"); + } else if (!event->active) { + pr_err("power handle deinit already done\n"); + kfree(event); + } else { + mutex_lock(&phandle->phandle_lock); + list_del_init(&event->list); + mutex_unlock(&phandle->phandle_lock); + kfree(event); + } +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h new file mode 100644 index 000000000000..344f74464eca --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h @@ -0,0 +1,225 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#ifndef _DPU_POWER_HANDLE_H_ +#define _DPU_POWER_HANDLE_H_ + +#define MAX_CLIENT_NAME_LEN 128 + +#define DPU_POWER_HANDLE_ENABLE_BUS_AB_QUOTA 0 +#define DPU_POWER_HANDLE_DISABLE_BUS_AB_QUOTA 0 +#define DPU_POWER_HANDLE_ENABLE_BUS_IB_QUOTA 1600000000 +#define DPU_POWER_HANDLE_DISABLE_BUS_IB_QUOTA 0 + +#include "dpu_io_util.h" + +/* event will be triggered before power handler disable */ +#define DPU_POWER_EVENT_PRE_DISABLE 0x1 + +/* event will be triggered after power handler disable */ +#define DPU_POWER_EVENT_POST_DISABLE 0x2 + +/* event will be triggered before power handler enable */ +#define DPU_POWER_EVENT_PRE_ENABLE 0x4 + +/* event will be triggered after power handler enable */ +#define DPU_POWER_EVENT_POST_ENABLE 0x8 + +/** + * mdss_bus_vote_type: register bus vote type + * VOTE_INDEX_DISABLE: removes the client vote + * VOTE_INDEX_LOW: keeps the lowest vote for register bus + * VOTE_INDEX_MAX: invalid + */ +enum mdss_bus_vote_type { + VOTE_INDEX_DISABLE, + VOTE_INDEX_LOW, + VOTE_INDEX_MAX, +}; + +/** + * enum dpu_power_handle_data_bus_client - type of axi bus clients + * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT: core real-time bus client + * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT: core non-real-time bus client + * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX: maximum number of bus client type + */ +enum dpu_power_handle_data_bus_client { + DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT, + DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT, + DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX +}; + +/** + * enum DPU_POWER_HANDLE_DBUS_ID - data bus identifier + * @DPU_POWER_HANDLE_DBUS_ID_MNOC: DPU/MNOC data bus + * @DPU_POWER_HANDLE_DBUS_ID_LLCC: MNOC/LLCC data bus + * @DPU_POWER_HANDLE_DBUS_ID_EBI: LLCC/EBI data bus + */ +enum DPU_POWER_HANDLE_DBUS_ID { + DPU_POWER_HANDLE_DBUS_ID_MNOC, + DPU_POWER_HANDLE_DBUS_ID_LLCC, + DPU_POWER_HANDLE_DBUS_ID_EBI, + DPU_POWER_HANDLE_DBUS_ID_MAX, +}; + +/** + * struct dpu_power_client: stores the power client for dpu driver + * @name: name of the client + * @usecase_ndx: current regs bus vote type + * @refcount: current refcount if multiple modules are using same + * same client for enable/disable. Power module will + * aggregate the refcount and vote accordingly for this + * client. + * @id: assigned during create. helps for debugging. + * @list: list to attach power handle master list + * @ab: arbitrated bandwidth for each bus client + * @ib: instantaneous bandwidth for each bus client + * @active: inidcates the state of dpu power handle + */ +struct dpu_power_client { + char name[MAX_CLIENT_NAME_LEN]; + short usecase_ndx; + short refcount; + u32 id; + struct list_head list; + u64 ab[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX]; + u64 ib[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX]; + bool active; +}; + +/* + * struct dpu_power_event - local event registration structure + * @client_name: name of the client registering + * @cb_fnc: pointer to desired callback function + * @usr: user pointer to pass to callback event trigger + * @event: refer to DPU_POWER_HANDLE_EVENT_* + * @list: list to attach event master list + * @active: indicates the state of dpu power handle + */ +struct dpu_power_event { + char client_name[MAX_CLIENT_NAME_LEN]; + void (*cb_fnc)(u32 event_type, void *usr); + void *usr; + u32 event_type; + struct list_head list; + bool active; +}; + +/** + * struct dpu_power_handle: power handle main struct + * @client_clist: master list to store all clients + * @phandle_lock: lock to synchronize the enable/disable + * @dev: pointer to device structure + * @usecase_ndx: current usecase index + * @event_list: current power handle event list + */ +struct dpu_power_handle { + struct list_head power_client_clist; + struct mutex phandle_lock; + struct device *dev; + u32 current_usecase_ndx; + struct list_head event_list; +}; + +/** + * dpu_power_resource_init() - initializes the dpu power handle + * @pdev: platform device to search the power resources + * @pdata: power handle to store the power resources + */ +void dpu_power_resource_init(struct platform_device *pdev, + struct dpu_power_handle *pdata); + +/** + * dpu_power_resource_deinit() - release the dpu power handle + * @pdev: platform device for power resources + * @pdata: power handle containing the resources + * + * Return: error code. + */ +void dpu_power_resource_deinit(struct platform_device *pdev, + struct dpu_power_handle *pdata); + +/** + * dpu_power_client_create() - create the client on power handle + * @pdata: power handle containing the resources + * @client_name: new client name for registration + * + * Return: error code. + */ +struct dpu_power_client *dpu_power_client_create(struct dpu_power_handle *pdata, + char *client_name); + +/** + * dpu_power_client_destroy() - destroy the client on power handle + * @pdata: power handle containing the resources + * @client_name: new client name for registration + * + * Return: none + */ +void dpu_power_client_destroy(struct dpu_power_handle *phandle, + struct dpu_power_client *client); + +/** + * dpu_power_resource_enable() - enable/disable the power resources + * @pdata: power handle containing the resources + * @client: client information to enable/disable its vote + * @enable: boolean request for enable/disable + * + * Return: error code. + */ +int dpu_power_resource_enable(struct dpu_power_handle *pdata, + struct dpu_power_client *pclient, bool enable); + +/** + * dpu_power_data_bus_bandwidth_ctrl() - control data bus bandwidth enable + * @phandle: power handle containing the resources + * @client: client information to bandwidth control + * @enable: true to enable bandwidth for data base + * + * Return: none + */ +void dpu_power_data_bus_bandwidth_ctrl(struct dpu_power_handle *phandle, + struct dpu_power_client *pclient, int enable); + +/** + * dpu_power_handle_register_event - register a callback function for an event. + * Clients can register for multiple events with a single register. + * Any block with access to phandle can register for the event + * notification. + * @phandle: power handle containing the resources + * @event_type: event type to register; refer DPU_POWER_HANDLE_EVENT_* + * @cb_fnc: pointer to desired callback function + * @usr: user pointer to pass to callback on event trigger + * + * Return: event pointer if success, or error code otherwise + */ +struct dpu_power_event *dpu_power_handle_register_event( + struct dpu_power_handle *phandle, + u32 event_type, void (*cb_fnc)(u32 event_type, void *usr), + void *usr, char *client_name); +/** + * dpu_power_handle_unregister_event - unregister callback for event(s) + * @phandle: power handle containing the resources + * @event: event pointer returned after power handle register + */ +void dpu_power_handle_unregister_event(struct dpu_power_handle *phandle, + struct dpu_power_event *event); + +/** + * dpu_power_handle_get_dbus_name - get name of given data bus identifier + * @bus_id: data bus identifier + * Return: Pointer to name string if success; NULL otherwise + */ +const char *dpu_power_handle_get_dbus_name(u32 bus_id); + +#endif /* _DPU_POWER_HANDLE_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c new file mode 100644 index 000000000000..13c0a36d4ef9 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -0,0 +1,1079 @@ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#define pr_fmt(fmt) "[drm:%s] " fmt, __func__ +#include "dpu_kms.h" +#include "dpu_hw_lm.h" +#include "dpu_hw_ctl.h" +#include "dpu_hw_cdm.h" +#include "dpu_hw_pingpong.h" +#include "dpu_hw_intf.h" +#include "dpu_encoder.h" +#include "dpu_trace.h" + +#define RESERVED_BY_OTHER(h, r) \ + ((h)->rsvp && ((h)->rsvp->enc_id != (r)->enc_id)) + +#define RM_RQ_LOCK(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_LOCK)) +#define RM_RQ_CLEAR(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_CLEAR)) +#define RM_RQ_DS(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_DS)) +#define RM_IS_TOPOLOGY_MATCH(t, r) ((t).num_lm == (r).num_lm && \ + (t).num_comp_enc == (r).num_enc && \ + (t).num_intf == (r).num_intf) + +struct dpu_rm_topology_def { + enum dpu_rm_topology_name top_name; + int num_lm; + int num_comp_enc; + int num_intf; + int num_ctl; + int needs_split_display; +}; + +static const struct dpu_rm_topology_def g_top_table[] = { + { DPU_RM_TOPOLOGY_NONE, 0, 0, 0, 0, false }, + { DPU_RM_TOPOLOGY_SINGLEPIPE, 1, 0, 1, 1, false }, + { DPU_RM_TOPOLOGY_DUALPIPE, 2, 0, 2, 2, true }, + { DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE, 2, 0, 1, 1, false }, +}; + +/** + * struct dpu_rm_requirements - Reservation requirements parameter bundle + * @top_ctrl: topology control preference from kernel client + * @top: selected topology for the display + * @hw_res: Hardware resources required as reported by the encoders + */ +struct dpu_rm_requirements { + uint64_t top_ctrl; + const struct dpu_rm_topology_def *topology; + struct dpu_encoder_hw_resources hw_res; +}; + +/** + * struct dpu_rm_rsvp - Use Case Reservation tagging structure + * Used to tag HW blocks as reserved by a CRTC->Encoder->Connector chain + * By using as a tag, rather than lists of pointers to HW blocks used + * we can avoid some list management since we don't know how many blocks + * of each type a given use case may require. + * @list: List head for list of all reservations + * @seq: Global RSVP sequence number for debugging, especially for + * differentiating differenct allocations for same encoder. + * @enc_id: Reservations are tracked by Encoder DRM object ID. + * CRTCs may be connected to multiple Encoders. + * An encoder or connector id identifies the display path. + * @topology DRM<->HW topology use case + */ +struct dpu_rm_rsvp { + struct list_head list; + uint32_t seq; + uint32_t enc_id; + enum dpu_rm_topology_name topology; +}; + +/** + * struct dpu_rm_hw_blk - hardware block tracking list member + * @list: List head for list of all hardware blocks tracking items + * @rsvp: Pointer to use case reservation if reserved by a client + * @rsvp_nxt: Temporary pointer used during reservation to the incoming + * request. Will be swapped into rsvp if proposal is accepted + * @type: Type of hardware block this structure tracks + * @id: Hardware ID number, within it's own space, ie. LM_X + * @catalog: Pointer to the hardware catalog entry for this block + * @hw: Pointer to the hardware register access object for this block + */ +struct dpu_rm_hw_blk { + struct list_head list; + struct dpu_rm_rsvp *rsvp; + struct dpu_rm_rsvp *rsvp_nxt; + enum dpu_hw_blk_type type; + uint32_t id; + struct dpu_hw_blk *hw; +}; + +/** + * dpu_rm_dbg_rsvp_stage - enum of steps in making reservation for event logging + */ +enum dpu_rm_dbg_rsvp_stage { + DPU_RM_STAGE_BEGIN, + DPU_RM_STAGE_AFTER_CLEAR, + DPU_RM_STAGE_AFTER_RSVPNEXT, + DPU_RM_STAGE_FINAL +}; + +static void _dpu_rm_print_rsvps( + struct dpu_rm *rm, + enum dpu_rm_dbg_rsvp_stage stage) +{ + struct dpu_rm_rsvp *rsvp; + struct dpu_rm_hw_blk *blk; + enum dpu_hw_blk_type type; + + DPU_DEBUG("%d\n", stage); + + list_for_each_entry(rsvp, &rm->rsvps, list) { + DRM_DEBUG_KMS("%d rsvp[s%ue%u] topology %d\n", stage, rsvp->seq, + rsvp->enc_id, rsvp->topology); + } + + for (type = 0; type < DPU_HW_BLK_MAX; type++) { + list_for_each_entry(blk, &rm->hw_blks[type], list) { + if (!blk->rsvp && !blk->rsvp_nxt) + continue; + + DRM_DEBUG_KMS("%d rsvp[s%ue%u->s%ue%u] %d %d\n", stage, + (blk->rsvp) ? blk->rsvp->seq : 0, + (blk->rsvp) ? blk->rsvp->enc_id : 0, + (blk->rsvp_nxt) ? blk->rsvp_nxt->seq : 0, + (blk->rsvp_nxt) ? blk->rsvp_nxt->enc_id : 0, + blk->type, blk->id); + } + } +} + +struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm) +{ + return rm->hw_mdp; +} + +enum dpu_rm_topology_name +dpu_rm_get_topology_name(struct msm_display_topology topology) +{ + int i; + + for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++) + if (RM_IS_TOPOLOGY_MATCH(g_top_table[i], topology)) + return g_top_table[i].top_name; + + return DPU_RM_TOPOLOGY_NONE; +} + +void dpu_rm_init_hw_iter( + struct dpu_rm_hw_iter *iter, + uint32_t enc_id, + enum dpu_hw_blk_type type) +{ + memset(iter, 0, sizeof(*iter)); + iter->enc_id = enc_id; + iter->type = type; +} + +static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i) +{ + struct list_head *blk_list; + + if (!rm || !i || i->type >= DPU_HW_BLK_MAX) { + DPU_ERROR("invalid rm\n"); + return false; + } + + i->hw = NULL; + blk_list = &rm->hw_blks[i->type]; + + if (i->blk && (&i->blk->list == blk_list)) { + DPU_DEBUG("attempt resume iteration past last\n"); + return false; + } + + i->blk = list_prepare_entry(i->blk, blk_list, list); + + list_for_each_entry_continue(i->blk, blk_list, list) { + struct dpu_rm_rsvp *rsvp = i->blk->rsvp; + + if (i->blk->type != i->type) { + DPU_ERROR("found incorrect block type %d on %d list\n", + i->blk->type, i->type); + return false; + } + + if ((i->enc_id == 0) || (rsvp && rsvp->enc_id == i->enc_id)) { + i->hw = i->blk->hw; + DPU_DEBUG("found type %d id %d for enc %d\n", + i->type, i->blk->id, i->enc_id); + return true; + } + } + + DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id); + + return false; +} + +bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i) +{ + bool ret; + + mutex_lock(&rm->rm_lock); + ret = _dpu_rm_get_hw_locked(rm, i); + mutex_unlock(&rm->rm_lock); + + return ret; +} + +static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw) +{ + switch (type) { + case DPU_HW_BLK_LM: + dpu_hw_lm_destroy(hw); + break; + case DPU_HW_BLK_CTL: + dpu_hw_ctl_destroy(hw); + break; + case DPU_HW_BLK_CDM: + dpu_hw_cdm_destroy(hw); + break; + case DPU_HW_BLK_PINGPONG: + dpu_hw_pingpong_destroy(hw); + break; + case DPU_HW_BLK_INTF: + dpu_hw_intf_destroy(hw); + break; + case DPU_HW_BLK_SSPP: + /* SSPPs are not managed by the resource manager */ + case DPU_HW_BLK_TOP: + /* Top is a singleton, not managed in hw_blks list */ + case DPU_HW_BLK_MAX: + default: + DPU_ERROR("unsupported block type %d\n", type); + break; + } +} + +int dpu_rm_destroy(struct dpu_rm *rm) +{ + + struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt; + struct dpu_rm_hw_blk *hw_cur, *hw_nxt; + enum dpu_hw_blk_type type; + + if (!rm) { + DPU_ERROR("invalid rm\n"); + return -EINVAL; + } + + list_for_each_entry_safe(rsvp_cur, rsvp_nxt, &rm->rsvps, list) { + list_del(&rsvp_cur->list); + kfree(rsvp_cur); + } + + + for (type = 0; type < DPU_HW_BLK_MAX; type++) { + list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type], + list) { + list_del(&hw_cur->list); + _dpu_rm_hw_destroy(hw_cur->type, hw_cur->hw); + kfree(hw_cur); + } + } + + dpu_hw_mdp_destroy(rm->hw_mdp); + rm->hw_mdp = NULL; + + mutex_destroy(&rm->rm_lock); + + return 0; +} + +static int _dpu_rm_hw_blk_create( + struct dpu_rm *rm, + struct dpu_mdss_cfg *cat, + void __iomem *mmio, + enum dpu_hw_blk_type type, + uint32_t id, + void *hw_catalog_info) +{ + struct dpu_rm_hw_blk *blk; + struct dpu_hw_mdp *hw_mdp; + void *hw; + + hw_mdp = rm->hw_mdp; + + switch (type) { + case DPU_HW_BLK_LM: + hw = dpu_hw_lm_init(id, mmio, cat); + break; + case DPU_HW_BLK_CTL: + hw = dpu_hw_ctl_init(id, mmio, cat); + break; + case DPU_HW_BLK_CDM: + hw = dpu_hw_cdm_init(id, mmio, cat, hw_mdp); + break; + case DPU_HW_BLK_PINGPONG: + hw = dpu_hw_pingpong_init(id, mmio, cat); + break; + case DPU_HW_BLK_INTF: + hw = dpu_hw_intf_init(id, mmio, cat); + break; + case DPU_HW_BLK_SSPP: + /* SSPPs are not managed by the resource manager */ + case DPU_HW_BLK_TOP: + /* Top is a singleton, not managed in hw_blks list */ + case DPU_HW_BLK_MAX: + default: + DPU_ERROR("unsupported block type %d\n", type); + return -EINVAL; + } + + if (IS_ERR_OR_NULL(hw)) { + DPU_ERROR("failed hw object creation: type %d, err %ld\n", + type, PTR_ERR(hw)); + return -EFAULT; + } + + blk = kzalloc(sizeof(*blk), GFP_KERNEL); + if (!blk) { + _dpu_rm_hw_destroy(type, hw); + return -ENOMEM; + } + + blk->type = type; + blk->id = id; + blk->hw = hw; + list_add_tail(&blk->list, &rm->hw_blks[type]); + + return 0; +} + +int dpu_rm_init(struct dpu_rm *rm, + struct dpu_mdss_cfg *cat, + void __iomem *mmio, + struct drm_device *dev) +{ + int rc, i; + enum dpu_hw_blk_type type; + + if (!rm || !cat || !mmio || !dev) { + DPU_ERROR("invalid kms\n"); + return -EINVAL; + } + + /* Clear, setup lists */ + memset(rm, 0, sizeof(*rm)); + + mutex_init(&rm->rm_lock); + + INIT_LIST_HEAD(&rm->rsvps); + for (type = 0; type < DPU_HW_BLK_MAX; type++) + INIT_LIST_HEAD(&rm->hw_blks[type]); + + rm->dev = dev; + + /* Some of the sub-blocks require an mdptop to be created */ + rm->hw_mdp = dpu_hw_mdptop_init(MDP_TOP, mmio, cat); + if (IS_ERR_OR_NULL(rm->hw_mdp)) { + rc = PTR_ERR(rm->hw_mdp); + rm->hw_mdp = NULL; + DPU_ERROR("failed: mdp hw not available\n"); + goto fail; + } + + /* Interrogate HW catalog and create tracking items for hw blocks */ + for (i = 0; i < cat->mixer_count; i++) { + struct dpu_lm_cfg *lm = &cat->mixer[i]; + + if (lm->pingpong == PINGPONG_MAX) { + DPU_DEBUG("skip mixer %d without pingpong\n", lm->id); + continue; + } + + rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM, + cat->mixer[i].id, &cat->mixer[i]); + if (rc) { + DPU_ERROR("failed: lm hw not available\n"); + goto fail; + } + + if (!rm->lm_max_width) { + rm->lm_max_width = lm->sblk->maxwidth; + } else if (rm->lm_max_width != lm->sblk->maxwidth) { + /* + * Don't expect to have hw where lm max widths differ. + * If found, take the min. + */ + DPU_ERROR("unsupported: lm maxwidth differs\n"); + if (rm->lm_max_width > lm->sblk->maxwidth) + rm->lm_max_width = lm->sblk->maxwidth; + } + } + + for (i = 0; i < cat->pingpong_count; i++) { + rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG, + cat->pingpong[i].id, &cat->pingpong[i]); + if (rc) { + DPU_ERROR("failed: pp hw not available\n"); + goto fail; + } + } + + for (i = 0; i < cat->intf_count; i++) { + if (cat->intf[i].type == INTF_NONE) { + DPU_DEBUG("skip intf %d with type none\n", i); + continue; + } + + rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF, + cat->intf[i].id, &cat->intf[i]); + if (rc) { + DPU_ERROR("failed: intf hw not available\n"); + goto fail; + } + } + + for (i = 0; i < cat->ctl_count; i++) { + rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL, + cat->ctl[i].id, &cat->ctl[i]); + if (rc) { + DPU_ERROR("failed: ctl hw not available\n"); + goto fail; + } + } + + for (i = 0; i < cat->cdm_count; i++) { + rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CDM, + cat->cdm[i].id, &cat->cdm[i]); + if (rc) { + DPU_ERROR("failed: cdm hw not available\n"); + goto fail; + } + } + + return 0; + +fail: + dpu_rm_destroy(rm); + + return rc; +} + +/** + * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets + * proposed use case requirements, incl. hardwired dependent blocks like + * pingpong + * @rm: dpu resource manager handle + * @rsvp: reservation currently being created + * @reqs: proposed use case requirements + * @lm: proposed layer mixer, function checks if lm, and all other hardwired + * blocks connected to the lm (pp) is available and appropriate + * @pp: output parameter, pingpong block attached to the layer mixer. + * NULL if pp was not available, or not matching requirements. + * @primary_lm: if non-null, this function check if lm is compatible primary_lm + * as well as satisfying all other requirements + * @Return: true if lm matches all requirements, false otherwise + */ +static bool _dpu_rm_check_lm_and_get_connected_blks( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + struct dpu_rm_requirements *reqs, + struct dpu_rm_hw_blk *lm, + struct dpu_rm_hw_blk **pp, + struct dpu_rm_hw_blk *primary_lm) +{ + const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap; + struct dpu_rm_hw_iter iter; + + *pp = NULL; + + DPU_DEBUG("check lm %d pp %d\n", + lm_cfg->id, lm_cfg->pingpong); + + /* Check if this layer mixer is a peer of the proposed primary LM */ + if (primary_lm) { + const struct dpu_lm_cfg *prim_lm_cfg = + to_dpu_hw_mixer(primary_lm->hw)->cap; + + if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) { + DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id, + prim_lm_cfg->id); + return false; + } + } + + /* Already reserved? */ + if (RESERVED_BY_OTHER(lm, rsvp)) { + DPU_DEBUG("lm %d already reserved\n", lm_cfg->id); + return false; + } + + dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG); + while (_dpu_rm_get_hw_locked(rm, &iter)) { + if (iter.blk->id == lm_cfg->pingpong) { + *pp = iter.blk; + break; + } + } + + if (!*pp) { + DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong); + return false; + } + + if (RESERVED_BY_OTHER(*pp, rsvp)) { + DPU_DEBUG("lm %d pp %d already reserved\n", lm->id, + (*pp)->id); + return false; + } + + return true; +} + +static int _dpu_rm_reserve_lms( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + struct dpu_rm_requirements *reqs) + +{ + struct dpu_rm_hw_blk *lm[MAX_BLOCKS]; + struct dpu_rm_hw_blk *pp[MAX_BLOCKS]; + struct dpu_rm_hw_iter iter_i, iter_j; + int lm_count = 0; + int i, rc = 0; + + if (!reqs->topology->num_lm) { + DPU_ERROR("invalid number of lm: %d\n", reqs->topology->num_lm); + return -EINVAL; + } + + /* Find a primary mixer */ + dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM); + while (lm_count != reqs->topology->num_lm && + _dpu_rm_get_hw_locked(rm, &iter_i)) { + memset(&lm, 0, sizeof(lm)); + memset(&pp, 0, sizeof(pp)); + + lm_count = 0; + lm[lm_count] = iter_i.blk; + + if (!_dpu_rm_check_lm_and_get_connected_blks( + rm, rsvp, reqs, lm[lm_count], + &pp[lm_count], NULL)) + continue; + + ++lm_count; + + /* Valid primary mixer found, find matching peers */ + dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM); + + while (lm_count != reqs->topology->num_lm && + _dpu_rm_get_hw_locked(rm, &iter_j)) { + if (iter_i.blk == iter_j.blk) + continue; + + if (!_dpu_rm_check_lm_and_get_connected_blks( + rm, rsvp, reqs, iter_j.blk, + &pp[lm_count], iter_i.blk)) + continue; + + lm[lm_count] = iter_j.blk; + ++lm_count; + } + } + + if (lm_count != reqs->topology->num_lm) { + DPU_DEBUG("unable to find appropriate mixers\n"); + return -ENAVAIL; + } + + for (i = 0; i < ARRAY_SIZE(lm); i++) { + if (!lm[i]) + break; + + lm[i]->rsvp_nxt = rsvp; + pp[i]->rsvp_nxt = rsvp; + + trace_dpu_rm_reserve_lms(lm[i]->id, lm[i]->type, rsvp->enc_id, + pp[i]->id); + } + + return rc; +} + +static int _dpu_rm_reserve_ctls( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + const struct dpu_rm_topology_def *top) +{ + struct dpu_rm_hw_blk *ctls[MAX_BLOCKS]; + struct dpu_rm_hw_iter iter; + int i = 0; + + memset(&ctls, 0, sizeof(ctls)); + + dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL); + while (_dpu_rm_get_hw_locked(rm, &iter)) { + const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw); + unsigned long features = ctl->caps->features; + bool has_split_display; + + if (RESERVED_BY_OTHER(iter.blk, rsvp)) + continue; + + has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features; + + DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features); + + if (top->needs_split_display != has_split_display) + continue; + + ctls[i] = iter.blk; + DPU_DEBUG("ctl %d match\n", iter.blk->id); + + if (++i == top->num_ctl) + break; + } + + if (i != top->num_ctl) + return -ENAVAIL; + + for (i = 0; i < ARRAY_SIZE(ctls) && i < top->num_ctl; i++) { + ctls[i]->rsvp_nxt = rsvp; + trace_dpu_rm_reserve_ctls(ctls[i]->id, ctls[i]->type, + rsvp->enc_id); + } + + return 0; +} + +static int _dpu_rm_reserve_cdm( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + uint32_t id, + enum dpu_hw_blk_type type) +{ + struct dpu_rm_hw_iter iter; + + DRM_DEBUG_KMS("type %d id %d\n", type, id); + + dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CDM); + while (_dpu_rm_get_hw_locked(rm, &iter)) { + const struct dpu_hw_cdm *cdm = to_dpu_hw_cdm(iter.blk->hw); + const struct dpu_cdm_cfg *caps = cdm->caps; + bool match = false; + + if (RESERVED_BY_OTHER(iter.blk, rsvp)) + continue; + + if (type == DPU_HW_BLK_INTF && id != INTF_MAX) + match = test_bit(id, &caps->intf_connect); + + DRM_DEBUG_KMS("iter: type:%d id:%d enc:%d cdm:%lu match:%d\n", + iter.blk->type, iter.blk->id, rsvp->enc_id, + caps->intf_connect, match); + + if (!match) + continue; + + trace_dpu_rm_reserve_cdm(iter.blk->id, iter.blk->type, + rsvp->enc_id); + iter.blk->rsvp_nxt = rsvp; + break; + } + + if (!iter.hw) { + DPU_ERROR("couldn't reserve cdm for type %d id %d\n", type, id); + return -ENAVAIL; + } + + return 0; +} + +static int _dpu_rm_reserve_intf( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + uint32_t id, + enum dpu_hw_blk_type type, + bool needs_cdm) +{ + struct dpu_rm_hw_iter iter; + int ret = 0; + + /* Find the block entry in the rm, and note the reservation */ + dpu_rm_init_hw_iter(&iter, 0, type); + while (_dpu_rm_get_hw_locked(rm, &iter)) { + if (iter.blk->id != id) + continue; + + if (RESERVED_BY_OTHER(iter.blk, rsvp)) { + DPU_ERROR("type %d id %d already reserved\n", type, id); + return -ENAVAIL; + } + + iter.blk->rsvp_nxt = rsvp; + trace_dpu_rm_reserve_intf(iter.blk->id, iter.blk->type, + rsvp->enc_id); + break; + } + + /* Shouldn't happen since intfs are fixed at probe */ + if (!iter.hw) { + DPU_ERROR("couldn't find type %d id %d\n", type, id); + return -EINVAL; + } + + if (needs_cdm) + ret = _dpu_rm_reserve_cdm(rm, rsvp, id, type); + + return ret; +} + +static int _dpu_rm_reserve_intf_related_hw( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + struct dpu_encoder_hw_resources *hw_res) +{ + int i, ret = 0; + u32 id; + + for (i = 0; i < ARRAY_SIZE(hw_res->intfs); i++) { + if (hw_res->intfs[i] == INTF_MODE_NONE) + continue; + id = i + INTF_0; + ret = _dpu_rm_reserve_intf(rm, rsvp, id, + DPU_HW_BLK_INTF, hw_res->needs_cdm); + if (ret) + return ret; + } + + return ret; +} + +static int _dpu_rm_make_next_rsvp( + struct dpu_rm *rm, + struct drm_encoder *enc, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + struct dpu_rm_rsvp *rsvp, + struct dpu_rm_requirements *reqs) +{ + int ret; + struct dpu_rm_topology_def topology; + + /* Create reservation info, tag reserved blocks with it as we go */ + rsvp->seq = ++rm->rsvp_next_seq; + rsvp->enc_id = enc->base.id; + rsvp->topology = reqs->topology->top_name; + list_add_tail(&rsvp->list, &rm->rsvps); + + ret = _dpu_rm_reserve_lms(rm, rsvp, reqs); + if (ret) { + DPU_ERROR("unable to find appropriate mixers\n"); + return ret; + } + + /* + * Do assignment preferring to give away low-resource CTLs first: + * - Check mixers without Split Display + * - Only then allow to grab from CTLs with split display capability + */ + _dpu_rm_reserve_ctls(rm, rsvp, reqs->topology); + if (ret && !reqs->topology->needs_split_display) { + memcpy(&topology, reqs->topology, sizeof(topology)); + topology.needs_split_display = true; + _dpu_rm_reserve_ctls(rm, rsvp, &topology); + } + if (ret) { + DPU_ERROR("unable to find appropriate CTL\n"); + return ret; + } + + /* Assign INTFs and blks whose usage is tied to them: CTL & CDM */ + ret = _dpu_rm_reserve_intf_related_hw(rm, rsvp, &reqs->hw_res); + if (ret) + return ret; + + return ret; +} + +static int _dpu_rm_populate_requirements( + struct dpu_rm *rm, + struct drm_encoder *enc, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + struct dpu_rm_requirements *reqs, + struct msm_display_topology req_topology) +{ + int i; + + memset(reqs, 0, sizeof(*reqs)); + + dpu_encoder_get_hw_resources(enc, &reqs->hw_res, conn_state); + + for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++) { + if (RM_IS_TOPOLOGY_MATCH(g_top_table[i], + req_topology)) { + reqs->topology = &g_top_table[i]; + break; + } + } + + if (!reqs->topology) { + DPU_ERROR("invalid topology for the display\n"); + return -EINVAL; + } + + /** + * Set the requirement based on caps if not set from user space + * This will ensure to select LM tied with DS blocks + * Currently, DS blocks are tied with LM 0 and LM 1 (primary display) + */ + if (!RM_RQ_DS(reqs) && rm->hw_mdp->caps->has_dest_scaler && + conn_state->connector->connector_type == DRM_MODE_CONNECTOR_DSI) + reqs->top_ctrl |= BIT(DPU_RM_TOPCTL_DS); + + DRM_DEBUG_KMS("top_ctrl: 0x%llX num_h_tiles: %d\n", reqs->top_ctrl, + reqs->hw_res.display_num_of_h_tiles); + DRM_DEBUG_KMS("num_lm: %d num_ctl: %d topology: %d split_display: %d\n", + reqs->topology->num_lm, reqs->topology->num_ctl, + reqs->topology->top_name, + reqs->topology->needs_split_display); + + return 0; +} + +static struct dpu_rm_rsvp *_dpu_rm_get_rsvp( + struct dpu_rm *rm, + struct drm_encoder *enc) +{ + struct dpu_rm_rsvp *i; + + if (!rm || !enc) { + DPU_ERROR("invalid params\n"); + return NULL; + } + + if (list_empty(&rm->rsvps)) + return NULL; + + list_for_each_entry(i, &rm->rsvps, list) + if (i->enc_id == enc->base.id) + return i; + + return NULL; +} + +static struct drm_connector *_dpu_rm_get_connector( + struct drm_encoder *enc) +{ + struct drm_connector *conn = NULL; + struct list_head *connector_list = + &enc->dev->mode_config.connector_list; + + list_for_each_entry(conn, connector_list, head) + if (conn->encoder == enc) + return conn; + + return NULL; +} + +/** + * _dpu_rm_release_rsvp - release resources and release a reservation + * @rm: KMS handle + * @rsvp: RSVP pointer to release and release resources for + */ +static void _dpu_rm_release_rsvp( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + struct drm_connector *conn) +{ + struct dpu_rm_rsvp *rsvp_c, *rsvp_n; + struct dpu_rm_hw_blk *blk; + enum dpu_hw_blk_type type; + + if (!rsvp) + return; + + DPU_DEBUG("rel rsvp %d enc %d\n", rsvp->seq, rsvp->enc_id); + + list_for_each_entry_safe(rsvp_c, rsvp_n, &rm->rsvps, list) { + if (rsvp == rsvp_c) { + list_del(&rsvp_c->list); + break; + } + } + + for (type = 0; type < DPU_HW_BLK_MAX; type++) { + list_for_each_entry(blk, &rm->hw_blks[type], list) { + if (blk->rsvp == rsvp) { + blk->rsvp = NULL; + DPU_DEBUG("rel rsvp %d enc %d %d %d\n", + rsvp->seq, rsvp->enc_id, + blk->type, blk->id); + } + if (blk->rsvp_nxt == rsvp) { + blk->rsvp_nxt = NULL; + DPU_DEBUG("rel rsvp_nxt %d enc %d %d %d\n", + rsvp->seq, rsvp->enc_id, + blk->type, blk->id); + } + } + } + + kfree(rsvp); +} + +void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc) +{ + struct dpu_rm_rsvp *rsvp; + struct drm_connector *conn; + + if (!rm || !enc) { + DPU_ERROR("invalid params\n"); + return; + } + + mutex_lock(&rm->rm_lock); + + rsvp = _dpu_rm_get_rsvp(rm, enc); + if (!rsvp) { + DPU_ERROR("failed to find rsvp for enc %d\n", enc->base.id); + goto end; + } + + conn = _dpu_rm_get_connector(enc); + if (!conn) { + DPU_ERROR("failed to get connector for enc %d\n", enc->base.id); + goto end; + } + + _dpu_rm_release_rsvp(rm, rsvp, conn); +end: + mutex_unlock(&rm->rm_lock); +} + +static int _dpu_rm_commit_rsvp( + struct dpu_rm *rm, + struct dpu_rm_rsvp *rsvp, + struct drm_connector_state *conn_state) +{ + struct dpu_rm_hw_blk *blk; + enum dpu_hw_blk_type type; + int ret = 0; + + /* Swap next rsvp to be the active */ + for (type = 0; type < DPU_HW_BLK_MAX; type++) { + list_for_each_entry(blk, &rm->hw_blks[type], list) { + if (blk->rsvp_nxt) { + blk->rsvp = blk->rsvp_nxt; + blk->rsvp_nxt = NULL; + } + } + } + + if (!ret) + DRM_DEBUG_KMS("rsrv enc %d topology %d\n", rsvp->enc_id, + rsvp->topology); + + return ret; +} + +int dpu_rm_reserve( + struct dpu_rm *rm, + struct drm_encoder *enc, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + struct msm_display_topology topology, + bool test_only) +{ + struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt; + struct dpu_rm_requirements reqs; + int ret; + + if (!rm || !enc || !crtc_state || !conn_state) { + DPU_ERROR("invalid arguments\n"); + return -EINVAL; + } + + /* Check if this is just a page-flip */ + if (!drm_atomic_crtc_needs_modeset(crtc_state)) + return 0; + + DRM_DEBUG_KMS("reserving hw for conn %d enc %d crtc %d test_only %d\n", + conn_state->connector->base.id, enc->base.id, + crtc_state->crtc->base.id, test_only); + + mutex_lock(&rm->rm_lock); + + _dpu_rm_print_rsvps(rm, DPU_RM_STAGE_BEGIN); + + ret = _dpu_rm_populate_requirements(rm, enc, crtc_state, + conn_state, &reqs, topology); + if (ret) { + DPU_ERROR("failed to populate hw requirements\n"); + goto end; + } + + /* + * We only support one active reservation per-hw-block. But to implement + * transactional semantics for test-only, and for allowing failure while + * modifying your existing reservation, over the course of this + * function we can have two reservations: + * Current: Existing reservation + * Next: Proposed reservation. The proposed reservation may fail, or may + * be discarded if in test-only mode. + * If reservation is successful, and we're not in test-only, then we + * replace the current with the next. + */ + rsvp_nxt = kzalloc(sizeof(*rsvp_nxt), GFP_KERNEL); + if (!rsvp_nxt) { + ret = -ENOMEM; + goto end; + } + + rsvp_cur = _dpu_rm_get_rsvp(rm, enc); + + /* + * User can request that we clear out any reservation during the + * atomic_check phase by using this CLEAR bit + */ + if (rsvp_cur && test_only && RM_RQ_CLEAR(&reqs)) { + DPU_DEBUG("test_only & CLEAR: clear rsvp[s%de%d]\n", + rsvp_cur->seq, rsvp_cur->enc_id); + _dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector); + rsvp_cur = NULL; + _dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_CLEAR); + } + + /* Check the proposed reservation, store it in hw's "next" field */ + ret = _dpu_rm_make_next_rsvp(rm, enc, crtc_state, conn_state, + rsvp_nxt, &reqs); + + _dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_RSVPNEXT); + + if (ret) { + DPU_ERROR("failed to reserve hw resources: %d\n", ret); + _dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector); + } else if (test_only && !RM_RQ_LOCK(&reqs)) { + /* + * Normally, if test_only, test the reservation and then undo + * However, if the user requests LOCK, then keep the reservation + * made during the atomic_check phase. + */ + DPU_DEBUG("test_only: discard test rsvp[s%de%d]\n", + rsvp_nxt->seq, rsvp_nxt->enc_id); + _dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector); + } else { + if (test_only && RM_RQ_LOCK(&reqs)) + DPU_DEBUG("test_only & LOCK: lock rsvp[s%de%d]\n", + rsvp_nxt->seq, rsvp_nxt->enc_id); + + _dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector); + + ret = _dpu_rm_commit_rsvp(rm, rsvp_nxt, conn_state); + } + + _dpu_rm_print_rsvps(rm, DPU_RM_STAGE_FINAL); + +end: + mutex_unlock(&rm->rm_lock); + + return ret; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h new file mode 100644 index 000000000000..ffd1841a6067 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -0,0 +1,199 @@ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + * + */ + +#ifndef __DPU_RM_H__ +#define __DPU_RM_H__ + +#include <linux/list.h> + +#include "msm_kms.h" +#include "dpu_hw_top.h" + +/** + * enum dpu_rm_topology_name - HW resource use case in use by connector + * @DPU_RM_TOPOLOGY_NONE: No topology in use currently + * @DPU_RM_TOPOLOGY_SINGLEPIPE: 1 LM, 1 PP, 1 INTF/WB + * @DPU_RM_TOPOLOGY_DUALPIPE: 2 LM, 2 PP, 2 INTF/WB + * @DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE: 2 LM, 2 PP, 3DMux, 1 INTF/WB + */ +enum dpu_rm_topology_name { + DPU_RM_TOPOLOGY_NONE = 0, + DPU_RM_TOPOLOGY_SINGLEPIPE, + DPU_RM_TOPOLOGY_DUALPIPE, + DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE, + DPU_RM_TOPOLOGY_MAX, +}; + +/** + * enum dpu_rm_topology_control - HW resource use case in use by connector + * @DPU_RM_TOPCTL_RESERVE_LOCK: If set, in AtomicTest phase, after a successful + * test, reserve the resources for this display. + * Normal behavior would not impact the reservation + * list during the AtomicTest phase. + * @DPU_RM_TOPCTL_RESERVE_CLEAR: If set, in AtomicTest phase, before testing, + * release any reservation held by this display. + * Normal behavior would not impact the + * reservation list during the AtomicTest phase. + * @DPU_RM_TOPCTL_DS : Require layer mixers with DS capabilities + */ +enum dpu_rm_topology_control { + DPU_RM_TOPCTL_RESERVE_LOCK, + DPU_RM_TOPCTL_RESERVE_CLEAR, + DPU_RM_TOPCTL_DS, +}; + +/** + * struct dpu_rm - DPU dynamic hardware resource manager + * @dev: device handle for event logging purposes + * @rsvps: list of hardware reservations by each crtc->encoder->connector + * @hw_blks: array of lists of hardware resources present in the system, one + * list per type of hardware block + * @hw_mdp: hardware object for mdp_top + * @lm_max_width: cached layer mixer maximum width + * @rsvp_next_seq: sequence number for next reservation for debugging purposes + * @rm_lock: resource manager mutex + */ +struct dpu_rm { + struct drm_device *dev; + struct list_head rsvps; + struct list_head hw_blks[DPU_HW_BLK_MAX]; + struct dpu_hw_mdp *hw_mdp; + uint32_t lm_max_width; + uint32_t rsvp_next_seq; + struct mutex rm_lock; +}; + +/** + * struct dpu_rm_hw_blk - resource manager internal structure + * forward declaration for single iterator definition without void pointer + */ +struct dpu_rm_hw_blk; + +/** + * struct dpu_rm_hw_iter - iterator for use with dpu_rm + * @hw: dpu_hw object requested, or NULL on failure + * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator. + * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder + * @type: Hardware Block Type client wishes to search for. + */ +struct dpu_rm_hw_iter { + void *hw; + struct dpu_rm_hw_blk *blk; + uint32_t enc_id; + enum dpu_hw_blk_type type; +}; + +/** + * dpu_rm_init - Read hardware catalog and create reservation tracking objects + * for all HW blocks. + * @rm: DPU Resource Manager handle + * @cat: Pointer to hardware catalog + * @mmio: mapped register io address of MDP + * @dev: device handle for event logging purposes + * @Return: 0 on Success otherwise -ERROR + */ +int dpu_rm_init(struct dpu_rm *rm, + struct dpu_mdss_cfg *cat, + void __iomem *mmio, + struct drm_device *dev); + +/** + * dpu_rm_destroy - Free all memory allocated by dpu_rm_init + * @rm: DPU Resource Manager handle + * @Return: 0 on Success otherwise -ERROR + */ +int dpu_rm_destroy(struct dpu_rm *rm); + +/** + * dpu_rm_reserve - Given a CRTC->Encoder->Connector display chain, analyze + * the use connections and user requirements, specified through related + * topology control properties, and reserve hardware blocks to that + * display chain. + * HW blocks can then be accessed through dpu_rm_get_* functions. + * HW Reservations should be released via dpu_rm_release_hw. + * @rm: DPU Resource Manager handle + * @drm_enc: DRM Encoder handle + * @crtc_state: Proposed Atomic DRM CRTC State handle + * @conn_state: Proposed Atomic DRM Connector State handle + * @topology: Pointer to topology info for the display + * @test_only: Atomic-Test phase, discard results (unless property overrides) + * @Return: 0 on Success otherwise -ERROR + */ +int dpu_rm_reserve(struct dpu_rm *rm, + struct drm_encoder *drm_enc, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + struct msm_display_topology topology, + bool test_only); + +/** + * dpu_rm_reserve - Given the encoder for the display chain, release any + * HW blocks previously reserved for that use case. + * @rm: DPU Resource Manager handle + * @enc: DRM Encoder handle + * @Return: 0 on Success otherwise -ERROR + */ +void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc); + +/** + * dpu_rm_get_mdp - Retrieve HW block for MDP TOP. + * This is never reserved, and is usable by any display. + * @rm: DPU Resource Manager handle + * @Return: Pointer to hw block or NULL + */ +struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm); + +/** + * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list + * using dpu_rm_get_hw + * @iter: iter object to initialize + * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder + * @type: Hardware Block Type client wishes to search for. + */ +void dpu_rm_init_hw_iter( + struct dpu_rm_hw_iter *iter, + uint32_t enc_id, + enum dpu_hw_blk_type type); +/** + * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type + * Meant to do a single pass through the hardware list to iteratively + * retrieve hardware blocks of a given type for a given encoder. + * Initialize an iterator object. + * Set hw block type of interest. Set encoder id of interest, 0 for any. + * Function returns first hw of type for that encoder. + * Subsequent calls will return the next reserved hw of that type in-order. + * Iterator HW pointer will be null on failure to find hw. + * @rm: DPU Resource Manager handle + * @iter: iterator object + * @Return: true on match found, false on no match found + */ +bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter); + +/** + * dpu_rm_check_property_topctl - validate property bitmask before it is set + * @val: user's proposed topology control bitmask + * @Return: 0 on success or error + */ +int dpu_rm_check_property_topctl(uint64_t val); + +/** + * dpu_rm_get_topology_name - returns the name of the the given topology + * definition + * @topology: topology definition + * @Return: name of the topology + */ +enum dpu_rm_topology_name +dpu_rm_get_topology_name(struct msm_display_topology topology); + +#endif /* __DPU_RM_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h new file mode 100644 index 000000000000..ae0ca5076238 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h @@ -0,0 +1,1007 @@ +/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#if !defined(_DPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _DPU_TRACE_H_ + +#include <linux/stringify.h> +#include <linux/types.h> +#include <linux/tracepoint.h> + +#include <drm/drm_rect.h> +#include "dpu_crtc.h" +#include "dpu_encoder_phys.h" +#include "dpu_hw_mdss.h" +#include "dpu_hw_vbif.h" +#include "dpu_plane.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM dpu +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE dpu_trace + +TRACE_EVENT(dpu_perf_set_qos_luts, + TP_PROTO(u32 pnum, u32 fmt, bool rt, u32 fl, + u32 lut, u32 lut_usage), + TP_ARGS(pnum, fmt, rt, fl, lut, lut_usage), + TP_STRUCT__entry( + __field(u32, pnum) + __field(u32, fmt) + __field(bool, rt) + __field(u32, fl) + __field(u64, lut) + __field(u32, lut_usage) + ), + TP_fast_assign( + __entry->pnum = pnum; + __entry->fmt = fmt; + __entry->rt = rt; + __entry->fl = fl; + __entry->lut = lut; + __entry->lut_usage = lut_usage; + ), + TP_printk("pnum=%d fmt=%x rt=%d fl=%d lut=0x%llx lut_usage=%d", + __entry->pnum, __entry->fmt, + __entry->rt, __entry->fl, + __entry->lut, __entry->lut_usage) +); + +TRACE_EVENT(dpu_perf_set_danger_luts, + TP_PROTO(u32 pnum, u32 fmt, u32 mode, u32 danger_lut, + u32 safe_lut), + TP_ARGS(pnum, fmt, mode, danger_lut, safe_lut), + TP_STRUCT__entry( + __field(u32, pnum) + __field(u32, fmt) + __field(u32, mode) + __field(u32, danger_lut) + __field(u32, safe_lut) + ), + TP_fast_assign( + __entry->pnum = pnum; + __entry->fmt = fmt; + __entry->mode = mode; + __entry->danger_lut = danger_lut; + __entry->safe_lut = safe_lut; + ), + TP_printk("pnum=%d fmt=%x mode=%d luts[0x%x, 0x%x]", + __entry->pnum, __entry->fmt, + __entry->mode, __entry->danger_lut, + __entry->safe_lut) +); + +TRACE_EVENT(dpu_perf_set_ot, + TP_PROTO(u32 pnum, u32 xin_id, u32 rd_lim, u32 vbif_idx), + TP_ARGS(pnum, xin_id, rd_lim, vbif_idx), + TP_STRUCT__entry( + __field(u32, pnum) + __field(u32, xin_id) + __field(u32, rd_lim) + __field(u32, vbif_idx) + ), + TP_fast_assign( + __entry->pnum = pnum; + __entry->xin_id = xin_id; + __entry->rd_lim = rd_lim; + __entry->vbif_idx = vbif_idx; + ), + TP_printk("pnum:%d xin_id:%d ot:%d vbif:%d", + __entry->pnum, __entry->xin_id, __entry->rd_lim, + __entry->vbif_idx) +) + +TRACE_EVENT(dpu_perf_update_bus, + TP_PROTO(int client, unsigned long long ab_quota, + unsigned long long ib_quota), + TP_ARGS(client, ab_quota, ib_quota), + TP_STRUCT__entry( + __field(int, client) + __field(u64, ab_quota) + __field(u64, ib_quota) + ), + TP_fast_assign( + __entry->client = client; + __entry->ab_quota = ab_quota; + __entry->ib_quota = ib_quota; + ), + TP_printk("Request client:%d ab=%llu ib=%llu", + __entry->client, + __entry->ab_quota, + __entry->ib_quota) +) + + +TRACE_EVENT(dpu_cmd_release_bw, + TP_PROTO(u32 crtc_id), + TP_ARGS(crtc_id), + TP_STRUCT__entry( + __field(u32, crtc_id) + ), + TP_fast_assign( + __entry->crtc_id = crtc_id; + ), + TP_printk("crtc:%d", __entry->crtc_id) +); + +TRACE_EVENT(tracing_mark_write, + TP_PROTO(int pid, const char *name, bool trace_begin), + TP_ARGS(pid, name, trace_begin), + TP_STRUCT__entry( + __field(int, pid) + __string(trace_name, name) + __field(bool, trace_begin) + ), + TP_fast_assign( + __entry->pid = pid; + __assign_str(trace_name, name); + __entry->trace_begin = trace_begin; + ), + TP_printk("%s|%d|%s", __entry->trace_begin ? "B" : "E", + __entry->pid, __get_str(trace_name)) +) + +TRACE_EVENT(dpu_trace_counter, + TP_PROTO(int pid, char *name, int value), + TP_ARGS(pid, name, value), + TP_STRUCT__entry( + __field(int, pid) + __string(counter_name, name) + __field(int, value) + ), + TP_fast_assign( + __entry->pid = current->tgid; + __assign_str(counter_name, name); + __entry->value = value; + ), + TP_printk("%d|%s|%d", __entry->pid, + __get_str(counter_name), __entry->value) +) + +TRACE_EVENT(dpu_perf_crtc_update, + TP_PROTO(u32 crtc, u64 bw_ctl_mnoc, u64 bw_ctl_llcc, + u64 bw_ctl_ebi, u32 core_clk_rate, + bool stop_req, u32 update_bus, u32 update_clk), + TP_ARGS(crtc, bw_ctl_mnoc, bw_ctl_llcc, bw_ctl_ebi, core_clk_rate, + stop_req, update_bus, update_clk), + TP_STRUCT__entry( + __field(u32, crtc) + __field(u64, bw_ctl_mnoc) + __field(u64, bw_ctl_llcc) + __field(u64, bw_ctl_ebi) + __field(u32, core_clk_rate) + __field(bool, stop_req) + __field(u32, update_bus) + __field(u32, update_clk) + ), + TP_fast_assign( + __entry->crtc = crtc; + __entry->bw_ctl_mnoc = bw_ctl_mnoc; + __entry->bw_ctl_llcc = bw_ctl_llcc; + __entry->bw_ctl_ebi = bw_ctl_ebi; + __entry->core_clk_rate = core_clk_rate; + __entry->stop_req = stop_req; + __entry->update_bus = update_bus; + __entry->update_clk = update_clk; + ), + TP_printk( + "crtc=%d bw_mnoc=%llu bw_llcc=%llu bw_ebi=%llu clk_rate=%u stop_req=%d u_bus=%d u_clk=%d", + __entry->crtc, + __entry->bw_ctl_mnoc, + __entry->bw_ctl_llcc, + __entry->bw_ctl_ebi, + __entry->core_clk_rate, + __entry->stop_req, + __entry->update_bus, + __entry->update_clk) +); + +DECLARE_EVENT_CLASS(dpu_enc_irq_template, + TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx, + int irq_idx), + TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_intr_idx, intr_idx ) + __field( int, hw_idx ) + __field( int, irq_idx ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->intr_idx = intr_idx; + __entry->hw_idx = hw_idx; + __entry->irq_idx = irq_idx; + ), + TP_printk("id=%u, intr=%d, hw=%d, irq=%d", + __entry->drm_id, __entry->intr_idx, __entry->hw_idx, + __entry->irq_idx) +); +DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_register_success, + TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx, + int irq_idx), + TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx) +); +DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_unregister_success, + TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx, + int irq_idx), + TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx) +); + +TRACE_EVENT(dpu_enc_irq_wait_success, + TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx, + int irq_idx, enum dpu_pingpong pp_idx, int atomic_cnt), + TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx, pp_idx, atomic_cnt), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_intr_idx, intr_idx ) + __field( int, hw_idx ) + __field( int, irq_idx ) + __field( enum dpu_pingpong, pp_idx ) + __field( int, atomic_cnt ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->intr_idx = intr_idx; + __entry->hw_idx = hw_idx; + __entry->irq_idx = irq_idx; + __entry->pp_idx = pp_idx; + __entry->atomic_cnt = atomic_cnt; + ), + TP_printk("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, atomic_cnt=%d", + __entry->drm_id, __entry->intr_idx, __entry->hw_idx, + __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt) +); + +DECLARE_EVENT_CLASS(dpu_drm_obj_template, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + ), + TP_printk("id=%u", __entry->drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_atomic_check, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_mode_set, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_disable, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_kickoff, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff_reset, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_flip, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_vblank_cb, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_commit, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_enc_enable, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_commit, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); +DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done, + TP_PROTO(uint32_t drm_id), + TP_ARGS(drm_id) +); + +TRACE_EVENT(dpu_enc_enable, + TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay), + TP_ARGS(drm_id, hdisplay, vdisplay), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( int, hdisplay ) + __field( int, vdisplay ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->hdisplay = hdisplay; + __entry->vdisplay = vdisplay; + ), + TP_printk("id=%u, mode=%dx%d", + __entry->drm_id, __entry->hdisplay, __entry->vdisplay) +); + +DECLARE_EVENT_CLASS(dpu_enc_keyval_template, + TP_PROTO(uint32_t drm_id, int val), + TP_ARGS(drm_id, val), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( int, val ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->val = val; + ), + TP_printk("id=%u, val=%d", __entry->drm_id, __entry->val) +); +DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_underrun_cb, + TP_PROTO(uint32_t drm_id, int count), + TP_ARGS(drm_id, count) +); +DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_trigger_start, + TP_PROTO(uint32_t drm_id, int ctl_idx), + TP_ARGS(drm_id, ctl_idx) +); + +TRACE_EVENT(dpu_enc_atomic_check_flags, + TP_PROTO(uint32_t drm_id, unsigned int flags, int private_flags), + TP_ARGS(drm_id, flags, private_flags), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( unsigned int, flags ) + __field( int, private_flags ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->flags = flags; + __entry->private_flags = private_flags; + ), + TP_printk("id=%u, flags=%u, private_flags=%d", + __entry->drm_id, __entry->flags, __entry->private_flags) +); + +DECLARE_EVENT_CLASS(dpu_enc_id_enable_template, + TP_PROTO(uint32_t drm_id, bool enable), + TP_ARGS(drm_id, enable), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( bool, enable ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->enable = enable; + ), + TP_printk("id=%u, enable=%s", + __entry->drm_id, __entry->enable ? "true" : "false") +); +DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_rc_helper, + TP_PROTO(uint32_t drm_id, bool enable), + TP_ARGS(drm_id, enable) +); +DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_vblank_cb, + TP_PROTO(uint32_t drm_id, bool enable), + TP_ARGS(drm_id, enable) +); +DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_frame_event_cb, + TP_PROTO(uint32_t drm_id, bool enable), + TP_ARGS(drm_id, enable) +); +DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_phys_cmd_connect_te, + TP_PROTO(uint32_t drm_id, bool enable), + TP_ARGS(drm_id, enable) +); + +TRACE_EVENT(dpu_enc_rc, + TP_PROTO(uint32_t drm_id, u32 sw_event, bool idle_pc_supported, + int rc_state, const char *stage), + TP_ARGS(drm_id, sw_event, idle_pc_supported, rc_state, stage), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( u32, sw_event ) + __field( bool, idle_pc_supported ) + __field( int, rc_state ) + __string( stage_str, stage ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->sw_event = sw_event; + __entry->idle_pc_supported = idle_pc_supported; + __entry->rc_state = rc_state; + __assign_str(stage_str, stage); + ), + TP_printk("%s: id:%u, sw_event:%d, idle_pc_supported:%s, rc_state:%d\n", + __get_str(stage_str), __entry->drm_id, __entry->sw_event, + __entry->idle_pc_supported ? "true" : "false", + __entry->rc_state) +); + +TRACE_EVENT(dpu_enc_frame_done_cb_not_busy, + TP_PROTO(uint32_t drm_id, u32 event, enum dpu_intf intf_idx), + TP_ARGS(drm_id, event, intf_idx), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( u32, event ) + __field( enum dpu_intf, intf_idx ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->event = event; + __entry->intf_idx = intf_idx; + ), + TP_printk("id=%u, event=%u, intf=%d", __entry->drm_id, __entry->event, + __entry->intf_idx) +); + +TRACE_EVENT(dpu_enc_frame_done_cb, + TP_PROTO(uint32_t drm_id, unsigned int idx, + unsigned long frame_busy_mask), + TP_ARGS(drm_id, idx, frame_busy_mask), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( unsigned int, idx ) + __field( unsigned long, frame_busy_mask ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->idx = idx; + __entry->frame_busy_mask = frame_busy_mask; + ), + TP_printk("id=%u, idx=%u, frame_busy_mask=%lx", __entry->drm_id, + __entry->idx, __entry->frame_busy_mask) +); + +TRACE_EVENT(dpu_enc_trigger_flush, + TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, + int pending_kickoff_cnt, int ctl_idx, u32 pending_flush_ret), + TP_ARGS(drm_id, intf_idx, pending_kickoff_cnt, ctl_idx, + pending_flush_ret), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_intf, intf_idx ) + __field( int, pending_kickoff_cnt ) + __field( int, ctl_idx ) + __field( u32, pending_flush_ret ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->intf_idx = intf_idx; + __entry->pending_kickoff_cnt = pending_kickoff_cnt; + __entry->ctl_idx = ctl_idx; + __entry->pending_flush_ret = pending_flush_ret; + ), + TP_printk("id=%u, intf_idx=%d, pending_kickoff_cnt=%d ctl_idx=%d " + "pending_flush_ret=%u", __entry->drm_id, + __entry->intf_idx, __entry->pending_kickoff_cnt, + __entry->ctl_idx, __entry->pending_flush_ret) +); + +DECLARE_EVENT_CLASS(dpu_enc_ktime_template, + TP_PROTO(uint32_t drm_id, ktime_t time), + TP_ARGS(drm_id, time), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( ktime_t, time ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->time = time; + ), + TP_printk("id=%u, time=%lld", __entry->drm_id, + ktime_to_ms(__entry->time)) +); +DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_vsync_event_work, + TP_PROTO(uint32_t drm_id, ktime_t time), + TP_ARGS(drm_id, time) +); +DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_early_kickoff, + TP_PROTO(uint32_t drm_id, ktime_t time), + TP_ARGS(drm_id, time) +); + +DECLARE_EVENT_CLASS(dpu_id_event_template, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( u32, event ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->event = event; + ), + TP_printk("id=%u, event=%u", __entry->drm_id, __entry->event) +); +DEFINE_EVENT(dpu_id_event_template, dpu_enc_frame_done_timeout, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event) +); +DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event) +); +DEFINE_EVENT(dpu_id_event_template, dpu_crtc_handle_power_event, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event) +); +DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event) +); +DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending, + TP_PROTO(uint32_t drm_id, u32 event), + TP_ARGS(drm_id, event) +); + +TRACE_EVENT(dpu_enc_wait_event_timeout, + TP_PROTO(uint32_t drm_id, int32_t hw_id, int rc, s64 time, + s64 expected_time, int atomic_cnt), + TP_ARGS(drm_id, hw_id, rc, time, expected_time, atomic_cnt), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( int32_t, hw_id ) + __field( int, rc ) + __field( s64, time ) + __field( s64, expected_time ) + __field( int, atomic_cnt ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->hw_id = hw_id; + __entry->rc = rc; + __entry->time = time; + __entry->expected_time = expected_time; + __entry->atomic_cnt = atomic_cnt; + ), + TP_printk("id=%u, hw_id=%d, rc=%d, time=%lld, expected=%lld cnt=%d", + __entry->drm_id, __entry->hw_id, __entry->rc, __entry->time, + __entry->expected_time, __entry->atomic_cnt) +); + +TRACE_EVENT(dpu_enc_phys_cmd_irq_ctrl, + TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, bool enable, + int refcnt), + TP_ARGS(drm_id, pp, enable, refcnt), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_pingpong, pp ) + __field( bool, enable ) + __field( int, refcnt ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->pp = pp; + __entry->enable = enable; + __entry->refcnt = refcnt; + ), + TP_printk("id=%u, pp=%d, enable=%s, refcnt=%d", __entry->drm_id, + __entry->pp, __entry->enable ? "true" : "false", + __entry->refcnt) +); + +TRACE_EVENT(dpu_enc_phys_cmd_pp_tx_done, + TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int new_count, + u32 event), + TP_ARGS(drm_id, pp, new_count, event), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_pingpong, pp ) + __field( int, new_count ) + __field( u32, event ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->pp = pp; + __entry->new_count = new_count; + __entry->event = event; + ), + TP_printk("id=%u, pp=%d, new_count=%d, event=%u", __entry->drm_id, + __entry->pp, __entry->new_count, __entry->event) +); + +TRACE_EVENT(dpu_enc_phys_cmd_pdone_timeout, + TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int timeout_count, + int kickoff_count, u32 event), + TP_ARGS(drm_id, pp, timeout_count, kickoff_count, event), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_pingpong, pp ) + __field( int, timeout_count ) + __field( int, kickoff_count ) + __field( u32, event ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->pp = pp; + __entry->timeout_count = timeout_count; + __entry->kickoff_count = kickoff_count; + __entry->event = event; + ), + TP_printk("id=%u, pp=%d, timeout_count=%d, kickoff_count=%d, event=%u", + __entry->drm_id, __entry->pp, __entry->timeout_count, + __entry->kickoff_count, __entry->event) +); + +TRACE_EVENT(dpu_enc_phys_vid_post_kickoff, + TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx), + TP_ARGS(drm_id, intf_idx), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_intf, intf_idx ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->intf_idx = intf_idx; + ), + TP_printk("id=%u, intf_idx=%d", __entry->drm_id, __entry->intf_idx) +); + +TRACE_EVENT(dpu_enc_phys_vid_irq_ctrl, + TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, bool enable, + int refcnt), + TP_ARGS(drm_id, intf_idx, enable, refcnt), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( enum dpu_intf, intf_idx ) + __field( bool, enable ) + __field( int, refcnt ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->intf_idx = intf_idx; + __entry->enable = enable; + __entry->refcnt = refcnt; + ), + TP_printk("id=%u, intf_idx=%d enable=%s refcnt=%d", __entry->drm_id, + __entry->intf_idx, __entry->enable ? "true" : "false", + __entry->drm_id) +); + +TRACE_EVENT(dpu_crtc_setup_mixer, + TP_PROTO(uint32_t crtc_id, uint32_t plane_id, + struct drm_plane_state *state, struct dpu_plane_state *pstate, + uint32_t stage_idx, enum dpu_sspp sspp, uint32_t pixel_format, + uint64_t modifier), + TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, sspp, + pixel_format, modifier), + TP_STRUCT__entry( + __field( uint32_t, crtc_id ) + __field( uint32_t, plane_id ) + __field( struct drm_plane_state*,state ) + __field( struct dpu_plane_state*,pstate ) + __field( uint32_t, stage_idx ) + __field( enum dpu_sspp, sspp ) + __field( uint32_t, pixel_format ) + __field( uint64_t, modifier ) + ), + TP_fast_assign( + __entry->crtc_id = crtc_id; + __entry->plane_id = plane_id; + __entry->state = state; + __entry->pstate = pstate; + __entry->stage_idx = stage_idx; + __entry->sspp = sspp; + __entry->pixel_format = pixel_format; + __entry->modifier = modifier; + ), + TP_printk("crtc_id:%u plane_id:%u fb_id:%u src:{%ux%u+%ux%u} " + "dst:{%ux%u+%ux%u} stage_idx:%u stage:%d, sspp:%d " + "multirect_index:%d multirect_mode:%u pix_format:%u " + "modifier:%llu", + __entry->crtc_id, __entry->plane_id, + __entry->state->fb ? __entry->state->fb->base.id : -1, + __entry->state->src_w >> 16, __entry->state->src_h >> 16, + __entry->state->src_x >> 16, __entry->state->src_y >> 16, + __entry->state->crtc_w, __entry->state->crtc_h, + __entry->state->crtc_x, __entry->state->crtc_y, + __entry->stage_idx, __entry->pstate->stage, __entry->sspp, + __entry->pstate->multirect_index, + __entry->pstate->multirect_mode, __entry->pixel_format, + __entry->modifier) +); + +TRACE_EVENT(dpu_crtc_setup_lm_bounds, + TP_PROTO(uint32_t drm_id, int mixer, struct drm_rect *bounds), + TP_ARGS(drm_id, mixer, bounds), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( int, mixer ) + __field( struct drm_rect *, bounds ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->mixer = mixer; + __entry->bounds = bounds; + ), + TP_printk("id:%u mixer:%d bounds:" DRM_RECT_FMT, __entry->drm_id, + __entry->mixer, DRM_RECT_ARG(__entry->bounds)) +); + +TRACE_EVENT(dpu_crtc_vblank_enable, + TP_PROTO(uint32_t drm_id, uint32_t enc_id, bool enable, + struct dpu_crtc *crtc), + TP_ARGS(drm_id, enc_id, enable, crtc), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( uint32_t, enc_id ) + __field( bool, enable ) + __field( struct dpu_crtc *, crtc ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->enc_id = enc_id; + __entry->enable = enable; + __entry->crtc = crtc; + ), + TP_printk("id:%u encoder:%u enable:%s state{enabled:%s suspend:%s " + "vblank_req:%s}", + __entry->drm_id, __entry->enc_id, + __entry->enable ? "true" : "false", + __entry->crtc->enabled ? "true" : "false", + __entry->crtc->suspend ? "true" : "false", + __entry->crtc->vblank_requested ? "true" : "false") +); + +DECLARE_EVENT_CLASS(dpu_crtc_enable_template, + TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc), + TP_ARGS(drm_id, enable, crtc), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( bool, enable ) + __field( struct dpu_crtc *, crtc ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->enable = enable; + __entry->crtc = crtc; + ), + TP_printk("id:%u enable:%s state{enabled:%s suspend:%s vblank_req:%s}", + __entry->drm_id, __entry->enable ? "true" : "false", + __entry->crtc->enabled ? "true" : "false", + __entry->crtc->suspend ? "true" : "false", + __entry->crtc->vblank_requested ? "true" : "false") +); +DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_set_suspend, + TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc), + TP_ARGS(drm_id, enable, crtc) +); +DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable, + TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc), + TP_ARGS(drm_id, enable, crtc) +); +DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_disable, + TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc), + TP_ARGS(drm_id, enable, crtc) +); +DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_vblank, + TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc), + TP_ARGS(drm_id, enable, crtc) +); + +TRACE_EVENT(dpu_crtc_disable_frame_pending, + TP_PROTO(uint32_t drm_id, int frame_pending), + TP_ARGS(drm_id, frame_pending), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( int, frame_pending ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->frame_pending = frame_pending; + ), + TP_printk("id:%u frame_pending:%d", __entry->drm_id, + __entry->frame_pending) +); + +TRACE_EVENT(dpu_plane_set_scanout, + TP_PROTO(enum dpu_sspp index, struct dpu_hw_fmt_layout *layout, + enum dpu_sspp_multirect_index multirect_index), + TP_ARGS(index, layout, multirect_index), + TP_STRUCT__entry( + __field( enum dpu_sspp, index ) + __field( struct dpu_hw_fmt_layout*, layout ) + __field( enum dpu_sspp_multirect_index, multirect_index) + ), + TP_fast_assign( + __entry->index = index; + __entry->layout = layout; + __entry->multirect_index = multirect_index; + ), + TP_printk("index:%d layout:{%ux%u @ [%u/%u, %u/%u, %u/%u, %u/%u]} " + "multirect_index:%d", __entry->index, __entry->layout->width, + __entry->layout->height, __entry->layout->plane_addr[0], + __entry->layout->plane_size[0], + __entry->layout->plane_addr[1], + __entry->layout->plane_size[1], + __entry->layout->plane_addr[2], + __entry->layout->plane_size[2], + __entry->layout->plane_addr[3], + __entry->layout->plane_size[3], __entry->multirect_index) +); + +TRACE_EVENT(dpu_plane_disable, + TP_PROTO(uint32_t drm_id, bool is_virtual, uint32_t multirect_mode), + TP_ARGS(drm_id, is_virtual, multirect_mode), + TP_STRUCT__entry( + __field( uint32_t, drm_id ) + __field( bool, is_virtual ) + __field( uint32_t, multirect_mode ) + ), + TP_fast_assign( + __entry->drm_id = drm_id; + __entry->is_virtual = is_virtual; + __entry->multirect_mode = multirect_mode; + ), + TP_printk("id:%u is_virtual:%s multirect_mode:%u", __entry->drm_id, + __entry->is_virtual ? "true" : "false", + __entry->multirect_mode) +); + +DECLARE_EVENT_CLASS(dpu_rm_iter_template, + TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id), + TP_ARGS(id, type, enc_id), + TP_STRUCT__entry( + __field( uint32_t, id ) + __field( enum dpu_hw_blk_type, type ) + __field( uint32_t, enc_id ) + ), + TP_fast_assign( + __entry->id = id; + __entry->type = type; + __entry->enc_id = enc_id; + ), + TP_printk("id:%d type:%d enc_id:%u", __entry->id, __entry->type, + __entry->enc_id) +); +DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_cdm, + TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id), + TP_ARGS(id, type, enc_id) +); +DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_intf, + TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id), + TP_ARGS(id, type, enc_id) +); +DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_ctls, + TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id), + TP_ARGS(id, type, enc_id) +); + +TRACE_EVENT(dpu_rm_reserve_lms, + TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id, + uint32_t pp_id), + TP_ARGS(id, type, enc_id, pp_id), + TP_STRUCT__entry( + __field( uint32_t, id ) + __field( enum dpu_hw_blk_type, type ) + __field( uint32_t, enc_id ) + __field( uint32_t, pp_id ) + ), + TP_fast_assign( + __entry->id = id; + __entry->type = type; + __entry->enc_id = enc_id; + __entry->pp_id = pp_id; + ), + TP_printk("id:%d type:%d enc_id:%u pp_id:%u", __entry->id, + __entry->type, __entry->enc_id, __entry->pp_id) +); + +TRACE_EVENT(dpu_vbif_wait_xin_halt_fail, + TP_PROTO(enum dpu_vbif index, u32 xin_id), + TP_ARGS(index, xin_id), + TP_STRUCT__entry( + __field( enum dpu_vbif, index ) + __field( u32, xin_id ) + ), + TP_fast_assign( + __entry->index = index; + __entry->xin_id = xin_id; + ), + TP_printk("index:%d xin_id:%u", __entry->index, __entry->xin_id) +); + +TRACE_EVENT(dpu_pp_connect_ext_te, + TP_PROTO(enum dpu_pingpong pp, u32 cfg), + TP_ARGS(pp, cfg), + TP_STRUCT__entry( + __field( enum dpu_pingpong, pp ) + __field( u32, cfg ) + ), + TP_fast_assign( + __entry->pp = pp; + __entry->cfg = cfg; + ), + TP_printk("pp:%d cfg:%u", __entry->pp, __entry->cfg) +); + +DECLARE_EVENT_CLASS(dpu_core_irq_idx_cnt_template, + TP_PROTO(int irq_idx, int enable_count), + TP_ARGS(irq_idx, enable_count), + TP_STRUCT__entry( + __field( int, irq_idx ) + __field( int, enable_count ) + ), + TP_fast_assign( + __entry->irq_idx = irq_idx; + __entry->enable_count = enable_count; + ), + TP_printk("irq_idx:%d enable_count:%u", __entry->irq_idx, + __entry->enable_count) +); +DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_enable_idx, + TP_PROTO(int irq_idx, int enable_count), + TP_ARGS(irq_idx, enable_count) +); +DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_disable_idx, + TP_PROTO(int irq_idx, int enable_count), + TP_ARGS(irq_idx, enable_count) +); + +DECLARE_EVENT_CLASS(dpu_core_irq_callback_template, + TP_PROTO(int irq_idx, struct dpu_irq_callback *callback), + TP_ARGS(irq_idx, callback), + TP_STRUCT__entry( + __field( int, irq_idx ) + __field( struct dpu_irq_callback *, callback) + ), + TP_fast_assign( + __entry->irq_idx = irq_idx; + __entry->callback = callback; + ), + TP_printk("irq_idx:%d callback:%pK", __entry->irq_idx, + __entry->callback) +); +DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_register_callback, + TP_PROTO(int irq_idx, struct dpu_irq_callback *callback), + TP_ARGS(irq_idx, callback) +); +DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_unregister_callback, + TP_PROTO(int irq_idx, struct dpu_irq_callback *callback), + TP_ARGS(irq_idx, callback) +); + +TRACE_EVENT(dpu_core_perf_update_clk, + TP_PROTO(struct drm_device *dev, bool stop_req, u64 clk_rate), + TP_ARGS(dev, stop_req, clk_rate), + TP_STRUCT__entry( + __field( struct drm_device *, dev ) + __field( bool, stop_req ) + __field( u64, clk_rate ) + ), + TP_fast_assign( + __entry->dev = dev; + __entry->stop_req = stop_req; + __entry->clk_rate = clk_rate; + ), + TP_printk("dev:%s stop_req:%s clk_rate:%llu", __entry->dev->unique, + __entry->stop_req ? "true" : "false", __entry->clk_rate) +); + +#define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0) +#define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1) +#define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__) + +#define DPU_ATRACE_INT(name, value) \ + trace_dpu_trace_counter(current->tgid, name, value) + +#endif /* _DPU_TRACE_H_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#include <trace/define_trace.h> diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c new file mode 100644 index 000000000000..295528292296 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c @@ -0,0 +1,384 @@ +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ + +#include <linux/debugfs.h> + +#include "dpu_vbif.h" +#include "dpu_hw_vbif.h" +#include "dpu_trace.h" + +/** + * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt + * @vbif: Pointer to hardware vbif driver + * @xin_id: Client interface identifier + * @return: 0 if success; error code otherwise + */ +static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id) +{ + ktime_t timeout; + bool status; + int rc; + + if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) { + DPU_ERROR("invalid arguments vbif %d\n", vbif != 0); + return -EINVAL; + } + + timeout = ktime_add_us(ktime_get(), vbif->cap->xin_halt_timeout); + for (;;) { + status = vbif->ops.get_halt_ctrl(vbif, xin_id); + if (status) + break; + if (ktime_compare_safe(ktime_get(), timeout) > 0) { + status = vbif->ops.get_halt_ctrl(vbif, xin_id); + break; + } + usleep_range(501, 1000); + } + + if (!status) { + rc = -ETIMEDOUT; + DPU_ERROR("VBIF %d client %d not halting. TIMEDOUT.\n", + vbif->idx - VBIF_0, xin_id); + } else { + rc = 0; + DPU_DEBUG("VBIF %d client %d is halted\n", + vbif->idx - VBIF_0, xin_id); + } + + return rc; +} + +/** + * _dpu_vbif_apply_dynamic_ot_limit - determine OT based on usecase parameters + * @vbif: Pointer to hardware vbif driver + * @ot_lim: Pointer to OT limit to be modified + * @params: Pointer to usecase parameters + */ +static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif, + u32 *ot_lim, struct dpu_vbif_set_ot_params *params) +{ + u64 pps; + const struct dpu_vbif_dynamic_ot_tbl *tbl; + u32 i; + + if (!vbif || !(vbif->cap->features & BIT(DPU_VBIF_QOS_OTLIM))) + return; + + /* Dynamic OT setting done only for WFD */ + if (!params->is_wfd) + return; + + pps = params->frame_rate; + pps *= params->width; + pps *= params->height; + + tbl = params->rd ? &vbif->cap->dynamic_ot_rd_tbl : + &vbif->cap->dynamic_ot_wr_tbl; + + for (i = 0; i < tbl->count; i++) { + if (pps <= tbl->cfg[i].pps) { + *ot_lim = tbl->cfg[i].ot_limit; + break; + } + } + + DPU_DEBUG("vbif:%d xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n", + vbif->idx - VBIF_0, params->xin_id, + params->width, params->height, params->frame_rate, + pps, *ot_lim); +} + +/** + * _dpu_vbif_get_ot_limit - get OT based on usecase & configuration parameters + * @vbif: Pointer to hardware vbif driver + * @params: Pointer to usecase parameters + * @return: OT limit + */ +static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif, + struct dpu_vbif_set_ot_params *params) +{ + u32 ot_lim = 0; + u32 val; + + if (!vbif || !vbif->cap) { + DPU_ERROR("invalid arguments vbif %d\n", vbif != 0); + return -EINVAL; + } + + if (vbif->cap->default_ot_wr_limit && !params->rd) + ot_lim = vbif->cap->default_ot_wr_limit; + else if (vbif->cap->default_ot_rd_limit && params->rd) + ot_lim = vbif->cap->default_ot_rd_limit; + + /* + * If default ot is not set from dt/catalog, + * then do not configure it. + */ + if (ot_lim == 0) + goto exit; + + /* Modify the limits if the target and the use case requires it */ + _dpu_vbif_apply_dynamic_ot_limit(vbif, &ot_lim, params); + + if (vbif && vbif->ops.get_limit_conf) { + val = vbif->ops.get_limit_conf(vbif, + params->xin_id, params->rd); + if (val == ot_lim) + ot_lim = 0; + } + +exit: + DPU_DEBUG("vbif:%d xin:%d ot_lim:%d\n", + vbif->idx - VBIF_0, params->xin_id, ot_lim); + return ot_lim; +} + +/** + * dpu_vbif_set_ot_limit - set OT based on usecase & configuration parameters + * @vbif: Pointer to hardware vbif driver + * @params: Pointer to usecase parameters + * + * Note this function would block waiting for bus halt. + */ +void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, + struct dpu_vbif_set_ot_params *params) +{ + struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_mdp *mdp; + bool forced_on = false; + u32 ot_lim; + int ret, i; + + if (!dpu_kms) { + DPU_ERROR("invalid arguments\n"); + return; + } + mdp = dpu_kms->hw_mdp; + + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + if (dpu_kms->hw_vbif[i] && + dpu_kms->hw_vbif[i]->idx == params->vbif_idx) + vbif = dpu_kms->hw_vbif[i]; + } + + if (!vbif || !mdp) { + DPU_DEBUG("invalid arguments vbif %d mdp %d\n", + vbif != 0, mdp != 0); + return; + } + + if (!mdp->ops.setup_clk_force_ctrl || + !vbif->ops.set_limit_conf || + !vbif->ops.set_halt_ctrl) + return; + + /* set write_gather_en for all write clients */ + if (vbif->ops.set_write_gather_en && !params->rd) + vbif->ops.set_write_gather_en(vbif, params->xin_id); + + ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF; + + if (ot_lim == 0) + goto exit; + + trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim, + params->vbif_idx); + + forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true); + + vbif->ops.set_limit_conf(vbif, params->xin_id, params->rd, ot_lim); + + vbif->ops.set_halt_ctrl(vbif, params->xin_id, true); + + ret = _dpu_vbif_wait_for_xin_halt(vbif, params->xin_id); + if (ret) + trace_dpu_vbif_wait_xin_halt_fail(vbif->idx, params->xin_id); + + vbif->ops.set_halt_ctrl(vbif, params->xin_id, false); + + if (forced_on) + mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false); +exit: + return; +} + +void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, + struct dpu_vbif_set_qos_params *params) +{ + struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_mdp *mdp; + bool forced_on = false; + const struct dpu_vbif_qos_tbl *qos_tbl; + int i; + + if (!dpu_kms || !params || !dpu_kms->hw_mdp) { + DPU_ERROR("invalid arguments\n"); + return; + } + mdp = dpu_kms->hw_mdp; + + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + if (dpu_kms->hw_vbif[i] && + dpu_kms->hw_vbif[i]->idx == params->vbif_idx) { + vbif = dpu_kms->hw_vbif[i]; + break; + } + } + + if (!vbif || !vbif->cap) { + DPU_ERROR("invalid vbif %d\n", params->vbif_idx); + return; + } + + if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) { + DPU_DEBUG("qos remap not supported\n"); + return; + } + + qos_tbl = params->is_rt ? &vbif->cap->qos_rt_tbl : + &vbif->cap->qos_nrt_tbl; + + if (!qos_tbl->npriority_lvl || !qos_tbl->priority_lvl) { + DPU_DEBUG("qos tbl not defined\n"); + return; + } + + forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true); + + for (i = 0; i < qos_tbl->npriority_lvl; i++) { + DPU_DEBUG("vbif:%d xin:%d lvl:%d/%d\n", + params->vbif_idx, params->xin_id, i, + qos_tbl->priority_lvl[i]); + vbif->ops.set_qos_remap(vbif, params->xin_id, i, + qos_tbl->priority_lvl[i]); + } + + if (forced_on) + mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false); +} + +void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms) +{ + struct dpu_hw_vbif *vbif; + u32 i, pnd, src; + + if (!dpu_kms) { + DPU_ERROR("invalid argument\n"); + return; + } + + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + vbif = dpu_kms->hw_vbif[i]; + if (vbif && vbif->ops.clear_errors) { + vbif->ops.clear_errors(vbif, &pnd, &src); + if (pnd || src) { + DRM_DEBUG_KMS("VBIF %d: pnd 0x%X, src 0x%X\n", + vbif->idx - VBIF_0, pnd, src); + } + } + } +} + +void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms) +{ + struct dpu_hw_vbif *vbif; + int i, j; + + if (!dpu_kms) { + DPU_ERROR("invalid argument\n"); + return; + } + + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + vbif = dpu_kms->hw_vbif[i]; + if (vbif && vbif->cap && vbif->ops.set_mem_type) { + for (j = 0; j < vbif->cap->memtype_count; j++) + vbif->ops.set_mem_type( + vbif, j, vbif->cap->memtype[j]); + } + } +} + +#ifdef CONFIG_DEBUG_FS +void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms) +{ + debugfs_remove_recursive(dpu_kms->debugfs_vbif); + dpu_kms->debugfs_vbif = NULL; +} + +int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root) +{ + char vbif_name[32]; + struct dentry *debugfs_vbif; + int i, j; + + dpu_kms->debugfs_vbif = debugfs_create_dir("vbif", debugfs_root); + if (!dpu_kms->debugfs_vbif) { + DPU_ERROR("failed to create vbif debugfs\n"); + return -EINVAL; + } + + for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { + struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i]; + + snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id); + + debugfs_vbif = debugfs_create_dir(vbif_name, + dpu_kms->debugfs_vbif); + + debugfs_create_u32("features", 0600, debugfs_vbif, + (u32 *)&vbif->features); + + debugfs_create_u32("xin_halt_timeout", 0400, debugfs_vbif, + (u32 *)&vbif->xin_halt_timeout); + + debugfs_create_u32("default_rd_ot_limit", 0400, debugfs_vbif, + (u32 *)&vbif->default_ot_rd_limit); + + debugfs_create_u32("default_wr_ot_limit", 0400, debugfs_vbif, + (u32 *)&vbif->default_ot_wr_limit); + + for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) { + struct dpu_vbif_dynamic_ot_cfg *cfg = + &vbif->dynamic_ot_rd_tbl.cfg[j]; + + snprintf(vbif_name, sizeof(vbif_name), + "dynamic_ot_rd_%d_pps", j); + debugfs_create_u64(vbif_name, 0400, debugfs_vbif, + (u64 *)&cfg->pps); + snprintf(vbif_name, sizeof(vbif_name), + "dynamic_ot_rd_%d_ot_limit", j); + debugfs_create_u32(vbif_name, 0400, debugfs_vbif, + (u32 *)&cfg->ot_limit); + } + + for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) { + struct dpu_vbif_dynamic_ot_cfg *cfg = + &vbif->dynamic_ot_wr_tbl.cfg[j]; + + snprintf(vbif_name, sizeof(vbif_name), + "dynamic_ot_wr_%d_pps", j); + debugfs_create_u64(vbif_name, 0400, debugfs_vbif, + (u64 *)&cfg->pps); + snprintf(vbif_name, sizeof(vbif_name), + "dynamic_ot_wr_%d_ot_limit", j); + debugfs_create_u32(vbif_name, 0400, debugfs_vbif, + (u32 *)&cfg->ot_limit); + } + } + + return 0; +} +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h new file mode 100644 index 000000000000..f17af52dbbd5 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h @@ -0,0 +1,94 @@ +/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * 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. + */ + +#ifndef __DPU_VBIF_H__ +#define __DPU_VBIF_H__ + +#include "dpu_kms.h" + +struct dpu_vbif_set_ot_params { + u32 xin_id; + u32 num; + u32 width; + u32 height; + u32 frame_rate; + bool rd; + bool is_wfd; + u32 vbif_idx; + u32 clk_ctrl; +}; + +struct dpu_vbif_set_memtype_params { + u32 xin_id; + u32 vbif_idx; + u32 clk_ctrl; + bool is_cacheable; +}; + +/** + * struct dpu_vbif_set_qos_params - QoS remapper parameter + * @vbif_idx: vbif identifier + * @xin_id: client interface identifier + * @clk_ctrl: clock control identifier of the xin + * @num: pipe identifier (debug only) + * @is_rt: true if pipe is used in real-time use case + */ +struct dpu_vbif_set_qos_params { + u32 vbif_idx; + u32 xin_id; + u32 clk_ctrl; + u32 num; + bool is_rt; +}; + +/** + * dpu_vbif_set_ot_limit - set OT limit for vbif client + * @dpu_kms: DPU handler + * @params: Pointer to OT configuration parameters + */ +void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, + struct dpu_vbif_set_ot_params *params); + +/** + * dpu_vbif_set_qos_remap - set QoS priority level remap + * @dpu_kms: DPU handler + * @params: Pointer to QoS configuration parameters + */ +void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, + struct dpu_vbif_set_qos_params *params); + +/** + * dpu_vbif_clear_errors - clear any vbif errors + * @dpu_kms: DPU handler + */ +void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms); + +/** + * dpu_vbif_init_memtypes - initialize xin memory types for vbif + * @dpu_kms: DPU handler + */ +void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms); + +#ifdef CONFIG_DEBUG_FS +int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root); +void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms); +#else +static inline int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, + struct dentry *debugfs_root) +{ + return 0; +} +static inline void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms) +{ +} +#endif +#endif /* __DPU_VBIF_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h new file mode 100644 index 000000000000..4f12e5c534c8 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h @@ -0,0 +1,1376 @@ +#ifndef __MEDIA_INFO_H__ +#define __MEDIA_INFO_H__ + +#ifndef MSM_MEDIA_ALIGN +#define MSM_MEDIA_ALIGN(__sz, __align) (((__align) & ((__align) - 1)) ?\ + ((((__sz) + (__align) - 1) / (__align)) * (__align)) :\ + (((__sz) + (__align) - 1) & (~((__align) - 1)))) +#endif + +#ifndef MSM_MEDIA_ROUNDUP +#define MSM_MEDIA_ROUNDUP(__sz, __r) (((__sz) + ((__r) - 1)) / (__r)) +#endif + +#ifndef MSM_MEDIA_MAX +#define MSM_MEDIA_MAX(__a, __b) ((__a) > (__b)?(__a):(__b)) +#endif + +enum color_fmts { + /* Venus NV12: + * YUV 4:2:0 image with a plane of 8 bit Y samples followed + * by an interleaved U/V plane containing 8 bit 2x2 subsampled + * colour difference samples. + * + * <-------- Y/UV_Stride --------> + * <------- Width -------> + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^ + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | Y_Scanlines + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * U V U V U V U V U V U V . . . . ^ + * U V U V U V U V U V U V . . . . | + * U V U V U V U V U V U V . . . . | + * U V U V U V U V U V U V . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . --> Buffer size alignment + * + * Y_Stride : Width aligned to 128 + * UV_Stride : Width aligned to 128 + * Y_Scanlines: Height aligned to 32 + * UV_Scanlines: Height/2 aligned to 16 + * Extradata: Arbitrary (software-imposed) padding + * Total size = align((Y_Stride * Y_Scanlines + * + UV_Stride * UV_Scanlines + * + max(Extradata, Y_Stride * 8), 4096) + */ + COLOR_FMT_NV12, + + /* Venus NV21: + * YUV 4:2:0 image with a plane of 8 bit Y samples followed + * by an interleaved V/U plane containing 8 bit 2x2 subsampled + * colour difference samples. + * + * <-------- Y/UV_Stride --------> + * <------- Width -------> + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^ + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | Y_Scanlines + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * V U V U V U V U V U V U . . . . ^ + * V U V U V U V U V U V U . . . . | + * V U V U V U V U V U V U . . . . | + * V U V U V U V U V U V U . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . --> Padding & Buffer size alignment + * + * Y_Stride : Width aligned to 128 + * UV_Stride : Width aligned to 128 + * Y_Scanlines: Height aligned to 32 + * UV_Scanlines: Height/2 aligned to 16 + * Extradata: Arbitrary (software-imposed) padding + * Total size = align((Y_Stride * Y_Scanlines + * + UV_Stride * UV_Scanlines + * + max(Extradata, Y_Stride * 8), 4096) + */ + COLOR_FMT_NV21, + /* Venus NV12_MVTB: + * Two YUV 4:2:0 images/views one after the other + * in a top-bottom layout, same as NV12 + * with a plane of 8 bit Y samples followed + * by an interleaved U/V plane containing 8 bit 2x2 subsampled + * colour difference samples. + * + * + * <-------- Y/UV_Stride --------> + * <------- Width -------> + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^ ^ + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | Y_Scanlines | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . V | | + * . . . . . . . . . . . . . . . . | View_1 + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . V | + * U V U V U V U V U V U V . . . . ^ | + * U V U V U V U V U V U V . . . . | | + * U V U V U V U V U V U V . . . . | | + * U V U V U V U V U V U V . . . . UV_Scanlines | + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . V V + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^ ^ + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | Y_Scanlines | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . V | | + * . . . . . . . . . . . . . . . . | View_2 + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . V | + * U V U V U V U V U V U V . . . . ^ | + * U V U V U V U V U V U V . . . . | | + * U V U V U V U V U V U V . . . . | | + * U V U V U V U V U V U V . . . . UV_Scanlines | + * . . . . . . . . . . . . . . . . | | + * . . . . . . . . . . . . . . . . V V + * . . . . . . . . . . . . . . . . --> Buffer size alignment + * + * Y_Stride : Width aligned to 128 + * UV_Stride : Width aligned to 128 + * Y_Scanlines: Height aligned to 32 + * UV_Scanlines: Height/2 aligned to 16 + * View_1 begin at: 0 (zero) + * View_2 begin at: Y_Stride * Y_Scanlines + UV_Stride * UV_Scanlines + * Extradata: Arbitrary (software-imposed) padding + * Total size = align((2*(Y_Stride * Y_Scanlines) + * + 2*(UV_Stride * UV_Scanlines) + Extradata), 4096) + */ + COLOR_FMT_NV12_MVTB, + /* + * The buffer can be of 2 types: + * (1) Venus NV12 UBWC Progressive + * (2) Venus NV12 UBWC Interlaced + * + * (1) Venus NV12 UBWC Progressive Buffer Format: + * Compressed Macro-tile format for NV12. + * Contains 4 planes in the following order - + * (A) Y_Meta_Plane + * (B) Y_UBWC_Plane + * (C) UV_Meta_Plane + * (D) UV_UBWC_Plane + * + * Y_Meta_Plane consists of meta information to decode compressed + * tile data in Y_UBWC_Plane. + * Y_UBWC_Plane consists of Y data in compressed macro-tile format. + * UBWC decoder block will use the Y_Meta_Plane data together with + * Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples. + * + * UV_Meta_Plane consists of meta information to decode compressed + * tile data in UV_UBWC_Plane. + * UV_UBWC_Plane consists of UV data in compressed macro-tile format. + * UBWC decoder block will use UV_Meta_Plane data together with + * UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2 + * subsampled color difference samples. + * + * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable + * and randomly accessible. There is no dependency between tiles. + * + * <----- Y_Meta_Stride ----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_Y_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <--Compressed tile Y Stride---> + * <------- Width -------> + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^ + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Height | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile_Y_Scanlines + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * <----- UV_Meta_Stride ----> + * M M M M M M M M M M M M . . ^ + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . M_UV_Scanlines + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <--Compressed tile UV Stride---> + * U* V* U* V* U* V* U* V* . . . . ^ + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * + * Y_Stride = align(Width, 128) + * UV_Stride = align(Width, 128) + * Y_Scanlines = align(Height, 32) + * UV_Scanlines = align(Height/2, 16) + * Y_UBWC_Plane_size = align(Y_Stride * Y_Scanlines, 4096) + * UV_UBWC_Plane_size = align(UV_Stride * UV_Scanlines, 4096) + * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64) + * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16) + * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096) + * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64) + * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16) + * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align( Y_UBWC_Plane_size + UV_UBWC_Plane_size + + * Y_Meta_Plane_size + UV_Meta_Plane_size + * + max(Extradata, Y_Stride * 48), 4096) + * + * + * (2) Venus NV12 UBWC Interlaced Buffer Format: + * Compressed Macro-tile format for NV12 interlaced. + * Contains 8 planes in the following order - + * (A) Y_Meta_Top_Field_Plane + * (B) Y_UBWC_Top_Field_Plane + * (C) UV_Meta_Top_Field_Plane + * (D) UV_UBWC_Top_Field_Plane + * (E) Y_Meta_Bottom_Field_Plane + * (F) Y_UBWC_Bottom_Field_Plane + * (G) UV_Meta_Bottom_Field_Plane + * (H) UV_UBWC_Bottom_Field_Plane + * Y_Meta_Top_Field_Plane consists of meta information to decode + * compressed tile data for Y_UBWC_Top_Field_Plane. + * Y_UBWC_Top_Field_Plane consists of Y data in compressed macro-tile + * format for top field of an interlaced frame. + * UBWC decoder block will use the Y_Meta_Top_Field_Plane data together + * with Y_UBWC_Top_Field_Plane data to produce loss-less uncompressed + * 8 bit Y samples for top field of an interlaced frame. + * + * UV_Meta_Top_Field_Plane consists of meta information to decode + * compressed tile data in UV_UBWC_Top_Field_Plane. + * UV_UBWC_Top_Field_Plane consists of UV data in compressed macro-tile + * format for top field of an interlaced frame. + * UBWC decoder block will use UV_Meta_Top_Field_Plane data together + * with UV_UBWC_Top_Field_Plane data to produce loss-less uncompressed + * 8 bit subsampled color difference samples for top field of an + * interlaced frame. + * + * Each tile in Y_UBWC_Top_Field_Plane/UV_UBWC_Top_Field_Plane is + * independently decodable and randomly accessible. There is no + * dependency between tiles. + * + * Y_Meta_Bottom_Field_Plane consists of meta information to decode + * compressed tile data for Y_UBWC_Bottom_Field_Plane. + * Y_UBWC_Bottom_Field_Plane consists of Y data in compressed macro-tile + * format for bottom field of an interlaced frame. + * UBWC decoder block will use the Y_Meta_Bottom_Field_Plane data + * together with Y_UBWC_Bottom_Field_Plane data to produce loss-less + * uncompressed 8 bit Y samples for bottom field of an interlaced frame. + * + * UV_Meta_Bottom_Field_Plane consists of meta information to decode + * compressed tile data in UV_UBWC_Bottom_Field_Plane. + * UV_UBWC_Bottom_Field_Plane consists of UV data in compressed + * macro-tile format for bottom field of an interlaced frame. + * UBWC decoder block will use UV_Meta_Bottom_Field_Plane data together + * with UV_UBWC_Bottom_Field_Plane data to produce loss-less + * uncompressed 8 bit subsampled color difference samples for bottom + * field of an interlaced frame. + * + * Each tile in Y_UBWC_Bottom_Field_Plane/UV_UBWC_Bottom_Field_Plane is + * independently decodable and randomly accessible. There is no + * dependency between tiles. + * + * <-----Y_TF_Meta_Stride----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Half_height | + * M M M M M M M M M M M M . . | Meta_Y_TF_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <-Compressed tile Y_TF Stride-> + * <------- Width -------> + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^ + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile_Y_TF_Scanlines + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * <----UV_TF_Meta_Stride----> + * M M M M M M M M M M M M . . ^ + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . M_UV_TF_Scanlines + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <-Compressed tile UV_TF Stride-> + * U* V* U* V* U* V* U* V* . . . . ^ + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . UV_TF_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <-----Y_BF_Meta_Stride----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Half_height | + * M M M M M M M M M M M M . . | Meta_Y_BF_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <-Compressed tile Y_BF Stride-> + * <------- Width -------> + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^ + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile_Y_BF_Scanlines + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * <----UV_BF_Meta_Stride----> + * M M M M M M M M M M M M . . ^ + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . M_UV_BF_Scanlines + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <-Compressed tile UV_BF Stride-> + * U* V* U* V* U* V* U* V* . . . . ^ + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . UV_BF_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * + * Half_height = (Height+1)>>1 + * Y_TF_Stride = align(Width, 128) + * UV_TF_Stride = align(Width, 128) + * Y_TF_Scanlines = align(Half_height, 32) + * UV_TF_Scanlines = align((Half_height+1)/2, 32) + * Y_UBWC_TF_Plane_size = align(Y_TF_Stride * Y_TF_Scanlines, 4096) + * UV_UBWC_TF_Plane_size = align(UV_TF_Stride * UV_TF_Scanlines, 4096) + * Y_TF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64) + * Y_TF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16) + * Y_TF_Meta_Plane_size = + * align(Y_TF_Meta_Stride * Y_TF_Meta_Scanlines, 4096) + * UV_TF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64) + * UV_TF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16) + * UV_TF_Meta_Plane_size = + * align(UV_TF_Meta_Stride * UV_TF_Meta_Scanlines, 4096) + * Y_BF_Stride = align(Width, 128) + * UV_BF_Stride = align(Width, 128) + * Y_BF_Scanlines = align(Half_height, 32) + * UV_BF_Scanlines = align((Half_height+1)/2, 32) + * Y_UBWC_BF_Plane_size = align(Y_BF_Stride * Y_BF_Scanlines, 4096) + * UV_UBWC_BF_Plane_size = align(UV_BF_Stride * UV_BF_Scanlines, 4096) + * Y_BF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64) + * Y_BF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16) + * Y_BF_Meta_Plane_size = + * align(Y_BF_Meta_Stride * Y_BF_Meta_Scanlines, 4096) + * UV_BF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64) + * UV_BF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16) + * UV_BF_Meta_Plane_size = + * align(UV_BF_Meta_Stride * UV_BF_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align( Y_UBWC_TF_Plane_size + UV_UBWC_TF_Plane_size + + * Y_TF_Meta_Plane_size + UV_TF_Meta_Plane_size + + * Y_UBWC_BF_Plane_size + UV_UBWC_BF_Plane_size + + * Y_BF_Meta_Plane_size + UV_BF_Meta_Plane_size + + * + max(Extradata, Y_TF_Stride * 48), 4096) + */ + COLOR_FMT_NV12_UBWC, + /* Venus NV12 10-bit UBWC: + * Compressed Macro-tile format for NV12. + * Contains 4 planes in the following order - + * (A) Y_Meta_Plane + * (B) Y_UBWC_Plane + * (C) UV_Meta_Plane + * (D) UV_UBWC_Plane + * + * Y_Meta_Plane consists of meta information to decode compressed + * tile data in Y_UBWC_Plane. + * Y_UBWC_Plane consists of Y data in compressed macro-tile format. + * UBWC decoder block will use the Y_Meta_Plane data together with + * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples. + * + * UV_Meta_Plane consists of meta information to decode compressed + * tile data in UV_UBWC_Plane. + * UV_UBWC_Plane consists of UV data in compressed macro-tile format. + * UBWC decoder block will use UV_Meta_Plane data together with + * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2 + * subsampled color difference samples. + * + * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable + * and randomly accessible. There is no dependency between tiles. + * + * <----- Y_Meta_Stride -----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_Y_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <--Compressed tile Y Stride---> + * <------- Width -------> + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^ + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Height | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile_Y_Scanlines + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * <----- UV_Meta_Stride ----> + * M M M M M M M M M M M M . . ^ + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . M_UV_Scanlines + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <--Compressed tile UV Stride---> + * U* V* U* V* U* V* U* V* . . . . ^ + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * + * + * Y_Stride = align(Width * 4/3, 128) + * UV_Stride = align(Width * 4/3, 128) + * Y_Scanlines = align(Height, 32) + * UV_Scanlines = align(Height/2, 16) + * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096) + * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096) + * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64) + * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16) + * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096) + * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64) + * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16) + * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size + + * Y_Meta_Plane_size + UV_Meta_Plane_size + * + max(Extradata, Y_Stride * 48), 4096) + */ + COLOR_FMT_NV12_BPP10_UBWC, + /* Venus RGBA8888 format: + * Contains 1 plane in the following order - + * (A) RGBA plane + * + * <-------- RGB_Stride --------> + * <------- Width -------> + * R R R R R R R R R R R R . . . . ^ ^ + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . Height | + * R R R R R R R R R R R R . . . . | RGB_Scanlines + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * + * RGB_Stride = align(Width * 4, 128) + * RGB_Scanlines = align(Height, 32) + * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(RGB_Plane_size + Extradata, 4096) + */ + COLOR_FMT_RGBA8888, + /* Venus RGBA8888 UBWC format: + * Contains 2 planes in the following order - + * (A) Meta plane + * (B) RGBA plane + * + * <--- RGB_Meta_Stride ----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_RGB_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <-------- RGB_Stride --------> + * <------- Width -------> + * R R R R R R R R R R R R . . . . ^ ^ + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . Height | + * R R R R R R R R R R R R . . . . | RGB_Scanlines + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * + * RGB_Stride = align(Width * 4, 128) + * RGB_Scanlines = align(Height, 32) + * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096) + * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64) + * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16) + * RGB_Meta_Plane_size = align(RGB_Meta_Stride * + * RGB_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size + + * Extradata, 4096) + */ + COLOR_FMT_RGBA8888_UBWC, + /* Venus RGBA1010102 UBWC format: + * Contains 2 planes in the following order - + * (A) Meta plane + * (B) RGBA plane + * + * <--- RGB_Meta_Stride ----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_RGB_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <-------- RGB_Stride --------> + * <------- Width -------> + * R R R R R R R R R R R R . . . . ^ ^ + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . Height | + * R R R R R R R R R R R R . . . . | RGB_Scanlines + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * + * RGB_Stride = align(Width * 4, 256) + * RGB_Scanlines = align(Height, 16) + * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096) + * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64) + * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16) + * RGB_Meta_Plane_size = align(RGB_Meta_Stride * + * RGB_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size + + * Extradata, 4096) + */ + COLOR_FMT_RGBA1010102_UBWC, + /* Venus RGB565 UBWC format: + * Contains 2 planes in the following order - + * (A) Meta plane + * (B) RGB plane + * + * <--- RGB_Meta_Stride ----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_RGB_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <-------- RGB_Stride --------> + * <------- Width -------> + * R R R R R R R R R R R R . . . . ^ ^ + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . Height | + * R R R R R R R R R R R R . . . . | RGB_Scanlines + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . | | + * R R R R R R R R R R R R . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * + * RGB_Stride = align(Width * 2, 128) + * RGB_Scanlines = align(Height, 16) + * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096) + * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64) + * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16) + * RGB_Meta_Plane_size = align(RGB_Meta_Stride * + * RGB_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size + + * Extradata, 4096) + */ + COLOR_FMT_RGB565_UBWC, + /* P010 UBWC: + * Compressed Macro-tile format for NV12. + * Contains 4 planes in the following order - + * (A) Y_Meta_Plane + * (B) Y_UBWC_Plane + * (C) UV_Meta_Plane + * (D) UV_UBWC_Plane + * + * Y_Meta_Plane consists of meta information to decode compressed + * tile data in Y_UBWC_Plane. + * Y_UBWC_Plane consists of Y data in compressed macro-tile format. + * UBWC decoder block will use the Y_Meta_Plane data together with + * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples. + * + * UV_Meta_Plane consists of meta information to decode compressed + * tile data in UV_UBWC_Plane. + * UV_UBWC_Plane consists of UV data in compressed macro-tile format. + * UBWC decoder block will use UV_Meta_Plane data together with + * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2 + * subsampled color difference samples. + * + * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable + * and randomly accessible. There is no dependency between tiles. + * + * <----- Y_Meta_Stride -----> + * <-------- Width ------> + * M M M M M M M M M M M M . . ^ ^ + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . Height | + * M M M M M M M M M M M M . . | Meta_Y_Scanlines + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . | | + * M M M M M M M M M M M M . . V | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . V + * <--Compressed tile Y Stride---> + * <------- Width -------> + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^ + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Height | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile_Y_Scanlines + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . | | + * Y* Y* Y* Y* Y* Y* Y* Y* . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * . . . . . . . . . . . . . . . . V + * <----- UV_Meta_Stride ----> + * M M M M M M M M M M M M . . ^ + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . | + * M M M M M M M M M M M M . . M_UV_Scanlines + * . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * <--Compressed tile UV Stride---> + * U* V* U* V* U* V* U* V* . . . . ^ + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . | + * U* V* U* V* U* V* U* V* . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k + * + * + * Y_Stride = align(Width * 2, 256) + * UV_Stride = align(Width * 2, 256) + * Y_Scanlines = align(Height, 16) + * UV_Scanlines = align(Height/2, 16) + * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096) + * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096) + * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64) + * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16) + * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096) + * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64) + * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16) + * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096) + * Extradata = 8k + * + * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size + + * Y_Meta_Plane_size + UV_Meta_Plane_size + * + max(Extradata, Y_Stride * 48), 4096) + */ + COLOR_FMT_P010_UBWC, + /* Venus P010: + * YUV 4:2:0 image with a plane of 10 bit Y samples followed + * by an interleaved U/V plane containing 10 bit 2x2 subsampled + * colour difference samples. + * + * <-------- Y/UV_Stride --------> + * <------- Width -------> + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^ + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | Y_Scanlines + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . | | + * Y Y Y Y Y Y Y Y Y Y Y Y . . . . V | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * U V U V U V U V U V U V . . . . ^ + * U V U V U V U V U V U V . . . . | + * U V U V U V U V U V U V . . . . | + * U V U V U V U V U V U V . . . . UV_Scanlines + * . . . . . . . . . . . . . . . . | + * . . . . . . . . . . . . . . . . V + * . . . . . . . . . . . . . . . . --> Buffer size alignment + * + * Y_Stride : Width * 2 aligned to 128 + * UV_Stride : Width * 2 aligned to 128 + * Y_Scanlines: Height aligned to 32 + * UV_Scanlines: Height/2 aligned to 16 + * Extradata: Arbitrary (software-imposed) padding + * Total size = align((Y_Stride * Y_Scanlines + * + UV_Stride * UV_Scanlines + * + max(Extradata, Y_Stride * 8), 4096) + */ + COLOR_FMT_P010, +}; + +#define COLOR_FMT_RGBA1010102_UBWC COLOR_FMT_RGBA1010102_UBWC +#define COLOR_FMT_RGB565_UBWC COLOR_FMT_RGB565_UBWC +#define COLOR_FMT_P010_UBWC COLOR_FMT_P010_UBWC +#define COLOR_FMT_P010 COLOR_FMT_P010 + +static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height) +{ + (void)height; + (void)width; + + /* + * In the future, calculate the size based on the w/h but just + * hardcode it for now since 16K satisfies all current usecases. + */ + return 16 * 1024; +} + +/* + * Function arguments: + * @color_fmt + * @width + * Progressive: width + * Interlaced: width + */ +static inline unsigned int VENUS_Y_STRIDE(int color_fmt, int width) +{ + unsigned int alignment, stride = 0; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV21: + case COLOR_FMT_NV12: + case COLOR_FMT_NV12_MVTB: + case COLOR_FMT_NV12_UBWC: + alignment = 128; + stride = MSM_MEDIA_ALIGN(width, alignment); + break; + case COLOR_FMT_NV12_BPP10_UBWC: + alignment = 256; + stride = MSM_MEDIA_ALIGN(width, 192); + stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment); + break; + case COLOR_FMT_P010_UBWC: + alignment = 256; + stride = MSM_MEDIA_ALIGN(width * 2, alignment); + break; + case COLOR_FMT_P010: + alignment = 128; + stride = MSM_MEDIA_ALIGN(width*2, alignment); + break; + default: + break; + } +invalid_input: + return stride; +} + +/* + * Function arguments: + * @color_fmt + * @width + * Progressive: width + * Interlaced: width + */ +static inline unsigned int VENUS_UV_STRIDE(int color_fmt, int width) +{ + unsigned int alignment, stride = 0; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV21: + case COLOR_FMT_NV12: + case COLOR_FMT_NV12_MVTB: + case COLOR_FMT_NV12_UBWC: + alignment = 128; + stride = MSM_MEDIA_ALIGN(width, alignment); + break; + case COLOR_FMT_NV12_BPP10_UBWC: + alignment = 256; + stride = MSM_MEDIA_ALIGN(width, 192); + stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment); + break; + case COLOR_FMT_P010_UBWC: + alignment = 256; + stride = MSM_MEDIA_ALIGN(width * 2, alignment); + break; + case COLOR_FMT_P010: + alignment = 128; + stride = MSM_MEDIA_ALIGN(width*2, alignment); + break; + default: + break; + } +invalid_input: + return stride; +} + +/* + * Function arguments: + * @color_fmt + * @height + * Progressive: height + * Interlaced: (height+1)>>1 + */ +static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height) +{ + unsigned int alignment, sclines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV21: + case COLOR_FMT_NV12: + case COLOR_FMT_NV12_MVTB: + case COLOR_FMT_NV12_UBWC: + case COLOR_FMT_P010: + alignment = 32; + break; + case COLOR_FMT_NV12_BPP10_UBWC: + case COLOR_FMT_P010_UBWC: + alignment = 16; + break; + default: + return 0; + } + sclines = MSM_MEDIA_ALIGN(height, alignment); +invalid_input: + return sclines; +} + +/* + * Function arguments: + * @color_fmt + * @height + * Progressive: height + * Interlaced: (height+1)>>1 + */ +static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height) +{ + unsigned int alignment, sclines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV21: + case COLOR_FMT_NV12: + case COLOR_FMT_NV12_MVTB: + case COLOR_FMT_NV12_BPP10_UBWC: + case COLOR_FMT_P010_UBWC: + case COLOR_FMT_P010: + alignment = 16; + break; + case COLOR_FMT_NV12_UBWC: + alignment = 32; + break; + default: + goto invalid_input; + } + + sclines = MSM_MEDIA_ALIGN((height+1)>>1, alignment); + +invalid_input: + return sclines; +} + +/* + * Function arguments: + * @color_fmt + * @width + * Progressive: width + * Interlaced: width + */ +static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width) +{ + int y_tile_width = 0, y_meta_stride = 0; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV12_UBWC: + case COLOR_FMT_P010_UBWC: + y_tile_width = 32; + break; + case COLOR_FMT_NV12_BPP10_UBWC: + y_tile_width = 48; + break; + default: + goto invalid_input; + } + + y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width); + y_meta_stride = MSM_MEDIA_ALIGN(y_meta_stride, 64); + +invalid_input: + return y_meta_stride; +} + +/* + * Function arguments: + * @color_fmt + * @height + * Progressive: height + * Interlaced: (height+1)>>1 + */ +static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height) +{ + int y_tile_height = 0, y_meta_scanlines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV12_UBWC: + y_tile_height = 8; + break; + case COLOR_FMT_NV12_BPP10_UBWC: + case COLOR_FMT_P010_UBWC: + y_tile_height = 4; + break; + default: + goto invalid_input; + } + + y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height); + y_meta_scanlines = MSM_MEDIA_ALIGN(y_meta_scanlines, 16); + +invalid_input: + return y_meta_scanlines; +} + +/* + * Function arguments: + * @color_fmt + * @width + * Progressive: width + * Interlaced: width + */ +static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width) +{ + int uv_tile_width = 0, uv_meta_stride = 0; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV12_UBWC: + case COLOR_FMT_P010_UBWC: + uv_tile_width = 16; + break; + case COLOR_FMT_NV12_BPP10_UBWC: + uv_tile_width = 24; + break; + default: + goto invalid_input; + } + + uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width); + uv_meta_stride = MSM_MEDIA_ALIGN(uv_meta_stride, 64); + +invalid_input: + return uv_meta_stride; +} + +/* + * Function arguments: + * @color_fmt + * @height + * Progressive: height + * Interlaced: (height+1)>>1 + */ +static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height) +{ + int uv_tile_height = 0, uv_meta_scanlines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_NV12_UBWC: + uv_tile_height = 8; + break; + case COLOR_FMT_NV12_BPP10_UBWC: + case COLOR_FMT_P010_UBWC: + uv_tile_height = 4; + break; + default: + goto invalid_input; + } + + uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height); + uv_meta_scanlines = MSM_MEDIA_ALIGN(uv_meta_scanlines, 16); + +invalid_input: + return uv_meta_scanlines; +} + +static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width) +{ + unsigned int alignment = 0, stride = 0, bpp = 4; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_RGBA8888: + alignment = 128; + break; + case COLOR_FMT_RGB565_UBWC: + alignment = 256; + bpp = 2; + break; + case COLOR_FMT_RGBA8888_UBWC: + case COLOR_FMT_RGBA1010102_UBWC: + alignment = 256; + break; + default: + goto invalid_input; + } + + stride = MSM_MEDIA_ALIGN(width * bpp, alignment); + +invalid_input: + return stride; +} + +static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height) +{ + unsigned int alignment = 0, scanlines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_RGBA8888: + alignment = 32; + break; + case COLOR_FMT_RGBA8888_UBWC: + case COLOR_FMT_RGBA1010102_UBWC: + case COLOR_FMT_RGB565_UBWC: + alignment = 16; + break; + default: + goto invalid_input; + } + + scanlines = MSM_MEDIA_ALIGN(height, alignment); + +invalid_input: + return scanlines; +} + +static inline unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width) +{ + int rgb_tile_width = 0, rgb_meta_stride = 0; + + if (!width) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_RGBA8888_UBWC: + case COLOR_FMT_RGBA1010102_UBWC: + case COLOR_FMT_RGB565_UBWC: + rgb_tile_width = 16; + break; + default: + goto invalid_input; + } + + rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, rgb_tile_width); + rgb_meta_stride = MSM_MEDIA_ALIGN(rgb_meta_stride, 64); + +invalid_input: + return rgb_meta_stride; +} + +static inline unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height) +{ + int rgb_tile_height = 0, rgb_meta_scanlines = 0; + + if (!height) + goto invalid_input; + + switch (color_fmt) { + case COLOR_FMT_RGBA8888_UBWC: + case COLOR_FMT_RGBA1010102_UBWC: + case COLOR_FMT_RGB565_UBWC: + rgb_tile_height = 4; + break; + default: + goto invalid_input; + } + + rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, rgb_tile_height); + rgb_meta_scanlines = MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16); + +invalid_input: + return rgb_meta_scanlines; +} + +/* + * Function arguments: + * @color_fmt + * @width + * Progressive: width + * Interlaced: width + * @height + * Progressive: height + * Interlaced: height + */ +static inline unsigned int VENUS_BUFFER_SIZE( + int color_fmt, int width, int height) +{ + const unsigned int extra_size = VENUS_EXTRADATA_SIZE(width, height); + unsigned int uv_alignment = 0, size = 0; + unsigned int y_plane, uv_plane, y_stride, + uv_stride, y_sclines, uv_sclines; + unsigned int y_ubwc_plane = 0, uv_ubwc_plane = 0; + unsigned int y_meta_stride = 0, y_meta_scanlines = 0; + unsigned int uv_meta_stride = 0, uv_meta_scanlines = 0; + unsigned int y_meta_plane = 0, uv_meta_plane = 0; + unsigned int rgb_stride = 0, rgb_scanlines = 0; + unsigned int rgb_plane = 0, rgb_ubwc_plane = 0, rgb_meta_plane = 0; + unsigned int rgb_meta_stride = 0, rgb_meta_scanlines = 0; + + if (!width || !height) + goto invalid_input; + + y_stride = VENUS_Y_STRIDE(color_fmt, width); + uv_stride = VENUS_UV_STRIDE(color_fmt, width); + y_sclines = VENUS_Y_SCANLINES(color_fmt, height); + uv_sclines = VENUS_UV_SCANLINES(color_fmt, height); + rgb_stride = VENUS_RGB_STRIDE(color_fmt, width); + rgb_scanlines = VENUS_RGB_SCANLINES(color_fmt, height); + + switch (color_fmt) { + case COLOR_FMT_NV21: + case COLOR_FMT_NV12: + case COLOR_FMT_P010: + uv_alignment = 4096; + y_plane = y_stride * y_sclines; + uv_plane = uv_stride * uv_sclines + uv_alignment; + size = y_plane + uv_plane + + MSM_MEDIA_MAX(extra_size, 8 * y_stride); + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_NV12_MVTB: + uv_alignment = 4096; + y_plane = y_stride * y_sclines; + uv_plane = uv_stride * uv_sclines + uv_alignment; + size = y_plane + uv_plane; + size = 2 * size + extra_size; + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_NV12_UBWC: + y_sclines = VENUS_Y_SCANLINES(color_fmt, (height+1)>>1); + y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096); + uv_sclines = VENUS_UV_SCANLINES(color_fmt, (height+1)>>1); + uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096); + y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width); + y_meta_scanlines = + VENUS_Y_META_SCANLINES(color_fmt, (height+1)>>1); + y_meta_plane = MSM_MEDIA_ALIGN( + y_meta_stride * y_meta_scanlines, 4096); + uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width); + uv_meta_scanlines = + VENUS_UV_META_SCANLINES(color_fmt, (height+1)>>1); + uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride * + uv_meta_scanlines, 4096); + + size = (y_ubwc_plane + uv_ubwc_plane + y_meta_plane + + uv_meta_plane)*2 + + MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride); + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_NV12_BPP10_UBWC: + y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096); + uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096); + y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width); + y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height); + y_meta_plane = MSM_MEDIA_ALIGN( + y_meta_stride * y_meta_scanlines, 4096); + uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width); + uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height); + uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride * + uv_meta_scanlines, 4096); + + size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane + + uv_meta_plane + + MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride); + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_P010_UBWC: + y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096); + uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096); + y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width); + y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height); + y_meta_plane = MSM_MEDIA_ALIGN( + y_meta_stride * y_meta_scanlines, 4096); + uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width); + uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height); + uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride * + uv_meta_scanlines, 4096); + + size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane + + uv_meta_plane; + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_RGBA8888: + rgb_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines, 4096); + size = rgb_plane; + size = MSM_MEDIA_ALIGN(size, 4096); + break; + case COLOR_FMT_RGBA8888_UBWC: + case COLOR_FMT_RGBA1010102_UBWC: + case COLOR_FMT_RGB565_UBWC: + rgb_ubwc_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines, + 4096); + rgb_meta_stride = VENUS_RGB_META_STRIDE(color_fmt, width); + rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color_fmt, + height); + rgb_meta_plane = MSM_MEDIA_ALIGN(rgb_meta_stride * + rgb_meta_scanlines, 4096); + size = rgb_ubwc_plane + rgb_meta_plane; + size = MSM_MEDIA_ALIGN(size, 4096); + break; + default: + break; + } +invalid_input: + return size; +} + +static inline unsigned int VENUS_VIEW2_OFFSET( + int color_fmt, int width, int height) +{ + unsigned int offset = 0; + unsigned int y_plane, uv_plane, y_stride, + uv_stride, y_sclines, uv_sclines; + if (!width || !height) + goto invalid_input; + + y_stride = VENUS_Y_STRIDE(color_fmt, width); + uv_stride = VENUS_UV_STRIDE(color_fmt, width); + y_sclines = VENUS_Y_SCANLINES(color_fmt, height); + uv_sclines = VENUS_UV_SCANLINES(color_fmt, height); + switch (color_fmt) { + case COLOR_FMT_NV12_MVTB: + y_plane = y_stride * y_sclines; + uv_plane = uv_stride * uv_sclines; + offset = y_plane + uv_plane; + break; + default: + break; + } +invalid_input: + return offset; +} + +#endif diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index 4b646bf9c214..44d1cda56974 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -125,6 +125,8 @@ static void mdp4_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; + drm_atomic_helper_wait_for_vblanks(mdp4_kms->dev, state); + /* see 119ecb7fd */ for_each_new_crtc_in_state(state, crtc, crtc_state, i) drm_crtc_vblank_put(crtc); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 24e00274844b..b1da9ce54379 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -65,7 +65,7 @@ struct mdp5_crtc { struct drm_gem_object *scanout_bo; uint64_t iova; uint32_t width, height; - uint32_t x, y; + int x, y; } cursor; }; #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base) @@ -760,20 +760,31 @@ static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h) * Cursor Region Of Interest (ROI) is a plane read from cursor * buffer to render. The ROI region is determined by the visibility of * the cursor point. In the default Cursor image the cursor point will - * be at the top left of the cursor image, unless it is specified - * otherwise using hotspot feature. + * be at the top left of the cursor image. * + * Without rotation: * If the cursor point reaches the right (xres - x < cursor.width) or * bottom (yres - y < cursor.height) boundary of the screen, then ROI * width and ROI height need to be evaluated to crop the cursor image * accordingly. * (xres-x) will be new cursor width when x > (xres - cursor.width) * (yres-y) will be new cursor height when y > (yres - cursor.height) + * + * With rotation: + * We get negative x and/or y coordinates. + * (cursor.width - abs(x)) will be new cursor width when x < 0 + * (cursor.height - abs(y)) will be new cursor width when y < 0 */ - *roi_w = min(mdp5_crtc->cursor.width, xres - + if (mdp5_crtc->cursor.x >= 0) + *roi_w = min(mdp5_crtc->cursor.width, xres - mdp5_crtc->cursor.x); - *roi_h = min(mdp5_crtc->cursor.height, yres - + else + *roi_w = mdp5_crtc->cursor.width - abs(mdp5_crtc->cursor.x); + if (mdp5_crtc->cursor.y >= 0) + *roi_h = min(mdp5_crtc->cursor.height, yres - mdp5_crtc->cursor.y); + else + *roi_h = mdp5_crtc->cursor.height - abs(mdp5_crtc->cursor.y); } static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc) @@ -783,7 +794,7 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc) struct mdp5_kms *mdp5_kms = get_kms(crtc); const enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL; uint32_t blendcfg, stride; - uint32_t x, y, width, height; + uint32_t x, y, src_x, src_y, width, height; uint32_t roi_w, roi_h; int lm; @@ -800,6 +811,26 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc) get_roi(crtc, &roi_w, &roi_h); + /* If cusror buffer overlaps due to rotation on the + * upper or left screen border the pixel offset inside + * the cursor buffer of the ROI is the positive overlap + * distance. + */ + if (mdp5_crtc->cursor.x < 0) { + src_x = abs(mdp5_crtc->cursor.x); + x = 0; + } else { + src_x = 0; + } + if (mdp5_crtc->cursor.y < 0) { + src_y = abs(mdp5_crtc->cursor.y); + y = 0; + } else { + src_y = 0; + } + DBG("%s: x=%d, y=%d roi_w=%d roi_h=%d src_x=%d src_y=%d", + crtc->name, x, y, roi_w, roi_h, src_x, src_y); + mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm), MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888)); @@ -812,6 +843,9 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc) mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_START_XY(lm), MDP5_LM_CURSOR_START_XY_Y_START(y) | MDP5_LM_CURSOR_START_XY_X_START(x)); + mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_XY(lm), + MDP5_LM_CURSOR_XY_SRC_Y(src_y) | + MDP5_LM_CURSOR_XY_SRC_X(src_x)); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm), mdp5_crtc->cursor.iova); @@ -932,8 +966,9 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) if (unlikely(!crtc->state->enable)) return 0; - mdp5_crtc->cursor.x = x = max(x, 0); - mdp5_crtc->cursor.y = y = max(y, 0); + /* accept negative x/y coordinates up to maximum cursor overlap */ + mdp5_crtc->cursor.x = x = max(x, -(int)mdp5_crtc->cursor.width); + mdp5_crtc->cursor.y = y = max(y, -(int)mdp5_crtc->cursor.height); get_roi(crtc, &roi_w, &roi_h); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c index 9af94e35f678..fcd44d1d1068 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c @@ -319,7 +319,17 @@ static int mdp5_encoder_atomic_check(struct drm_encoder *encoder, mdp5_cstate->ctl = ctl; mdp5_cstate->pipeline.intf = intf; - mdp5_cstate->defer_start = true; + + /* + * This is a bit awkward, but we want to flush the CTL and hit the + * START bit at most once for an atomic update. In the non-full- + * modeset case, this is done from crtc->atomic_flush(), but that + * is too early in the case of full modeset, in which case we + * defer to encoder->enable(). But we need to *know* whether + * encoder->enable() will be called to do this: + */ + if (drm_atomic_crtc_needs_modeset(crtc_state)) + mdp5_cstate->defer_start = true; return 0; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 6e12e275deba..bddd625ab91b 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -170,6 +170,8 @@ static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s struct device *dev = &mdp5_kms->pdev->dev; struct mdp5_global_state *global_state; + drm_atomic_helper_wait_for_vblanks(mdp5_kms->dev, state); + global_state = mdp5_get_existing_global_state(mdp5_kms); if (mdp5_kms->smp) diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c index f2a0db7a8a03..1cc4e57f0226 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c @@ -20,12 +20,10 @@ #include "msm_drv.h" #include "mdp5_kms.h" -/* - * If needed, this can become more specific: something like struct mdp5_mdss, - * which contains a 'struct msm_mdss base' member. - */ -struct msm_mdss { - struct drm_device *dev; +#define to_mdp5_mdss(x) container_of(x, struct mdp5_mdss, base) + +struct mdp5_mdss { + struct msm_mdss base; void __iomem *mmio, *vbif; @@ -41,22 +39,22 @@ struct msm_mdss { } irqcontroller; }; -static inline void mdss_write(struct msm_mdss *mdss, u32 reg, u32 data) +static inline void mdss_write(struct mdp5_mdss *mdp5_mdss, u32 reg, u32 data) { - msm_writel(data, mdss->mmio + reg); + msm_writel(data, mdp5_mdss->mmio + reg); } -static inline u32 mdss_read(struct msm_mdss *mdss, u32 reg) +static inline u32 mdss_read(struct mdp5_mdss *mdp5_mdss, u32 reg) { - return msm_readl(mdss->mmio + reg); + return msm_readl(mdp5_mdss->mmio + reg); } static irqreturn_t mdss_irq(int irq, void *arg) { - struct msm_mdss *mdss = arg; + struct mdp5_mdss *mdp5_mdss = arg; u32 intr; - intr = mdss_read(mdss, REG_MDSS_HW_INTR_STATUS); + intr = mdss_read(mdp5_mdss, REG_MDSS_HW_INTR_STATUS); VERB("intr=%08x", intr); @@ -64,7 +62,7 @@ static irqreturn_t mdss_irq(int irq, void *arg) irq_hw_number_t hwirq = fls(intr) - 1; generic_handle_irq(irq_find_mapping( - mdss->irqcontroller.domain, hwirq)); + mdp5_mdss->irqcontroller.domain, hwirq)); intr &= ~(1 << hwirq); } @@ -84,19 +82,19 @@ static irqreturn_t mdss_irq(int irq, void *arg) static void mdss_hw_mask_irq(struct irq_data *irqd) { - struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd); + struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd); smp_mb__before_atomic(); - clear_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask); + clear_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask); smp_mb__after_atomic(); } static void mdss_hw_unmask_irq(struct irq_data *irqd) { - struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd); + struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd); smp_mb__before_atomic(); - set_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask); + set_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask); smp_mb__after_atomic(); } @@ -109,13 +107,13 @@ static struct irq_chip mdss_hw_irq_chip = { static int mdss_hw_irqdomain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { - struct msm_mdss *mdss = d->host_data; + struct mdp5_mdss *mdp5_mdss = d->host_data; if (!(VALID_IRQS & (1 << hwirq))) return -EPERM; irq_set_chip_and_handler(irq, &mdss_hw_irq_chip, handle_level_irq); - irq_set_chip_data(irq, mdss); + irq_set_chip_data(irq, mdp5_mdss); return 0; } @@ -126,90 +124,99 @@ static const struct irq_domain_ops mdss_hw_irqdomain_ops = { }; -static int mdss_irq_domain_init(struct msm_mdss *mdss) +static int mdss_irq_domain_init(struct mdp5_mdss *mdp5_mdss) { - struct device *dev = mdss->dev->dev; + struct device *dev = mdp5_mdss->base.dev->dev; struct irq_domain *d; d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops, - mdss); + mdp5_mdss); if (!d) { dev_err(dev, "mdss irq domain add failed\n"); return -ENXIO; } - mdss->irqcontroller.enabled_mask = 0; - mdss->irqcontroller.domain = d; + mdp5_mdss->irqcontroller.enabled_mask = 0; + mdp5_mdss->irqcontroller.domain = d; return 0; } -int msm_mdss_enable(struct msm_mdss *mdss) +static int mdp5_mdss_enable(struct msm_mdss *mdss) { + struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss); DBG(""); - clk_prepare_enable(mdss->ahb_clk); - if (mdss->axi_clk) - clk_prepare_enable(mdss->axi_clk); - if (mdss->vsync_clk) - clk_prepare_enable(mdss->vsync_clk); + clk_prepare_enable(mdp5_mdss->ahb_clk); + if (mdp5_mdss->axi_clk) + clk_prepare_enable(mdp5_mdss->axi_clk); + if (mdp5_mdss->vsync_clk) + clk_prepare_enable(mdp5_mdss->vsync_clk); return 0; } -int msm_mdss_disable(struct msm_mdss *mdss) +static int mdp5_mdss_disable(struct msm_mdss *mdss) { + struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss); DBG(""); - if (mdss->vsync_clk) - clk_disable_unprepare(mdss->vsync_clk); - if (mdss->axi_clk) - clk_disable_unprepare(mdss->axi_clk); - clk_disable_unprepare(mdss->ahb_clk); + if (mdp5_mdss->vsync_clk) + clk_disable_unprepare(mdp5_mdss->vsync_clk); + if (mdp5_mdss->axi_clk) + clk_disable_unprepare(mdp5_mdss->axi_clk); + clk_disable_unprepare(mdp5_mdss->ahb_clk); return 0; } -static int msm_mdss_get_clocks(struct msm_mdss *mdss) +static int msm_mdss_get_clocks(struct mdp5_mdss *mdp5_mdss) { - struct platform_device *pdev = to_platform_device(mdss->dev->dev); + struct platform_device *pdev = + to_platform_device(mdp5_mdss->base.dev->dev); - mdss->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(mdss->ahb_clk)) - mdss->ahb_clk = NULL; + mdp5_mdss->ahb_clk = msm_clk_get(pdev, "iface"); + if (IS_ERR(mdp5_mdss->ahb_clk)) + mdp5_mdss->ahb_clk = NULL; - mdss->axi_clk = msm_clk_get(pdev, "bus"); - if (IS_ERR(mdss->axi_clk)) - mdss->axi_clk = NULL; + mdp5_mdss->axi_clk = msm_clk_get(pdev, "bus"); + if (IS_ERR(mdp5_mdss->axi_clk)) + mdp5_mdss->axi_clk = NULL; - mdss->vsync_clk = msm_clk_get(pdev, "vsync"); - if (IS_ERR(mdss->vsync_clk)) - mdss->vsync_clk = NULL; + mdp5_mdss->vsync_clk = msm_clk_get(pdev, "vsync"); + if (IS_ERR(mdp5_mdss->vsync_clk)) + mdp5_mdss->vsync_clk = NULL; return 0; } -void msm_mdss_destroy(struct drm_device *dev) +static void mdp5_mdss_destroy(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; - struct msm_mdss *mdss = priv->mdss; + struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(priv->mdss); - if (!mdss) + if (!mdp5_mdss) return; - irq_domain_remove(mdss->irqcontroller.domain); - mdss->irqcontroller.domain = NULL; + irq_domain_remove(mdp5_mdss->irqcontroller.domain); + mdp5_mdss->irqcontroller.domain = NULL; - regulator_disable(mdss->vdd); + regulator_disable(mdp5_mdss->vdd); pm_runtime_disable(dev->dev); } -int msm_mdss_init(struct drm_device *dev) +static const struct msm_mdss_funcs mdss_funcs = { + .enable = mdp5_mdss_enable, + .disable = mdp5_mdss_disable, + .destroy = mdp5_mdss_destroy, +}; + +int mdp5_mdss_init(struct drm_device *dev) { struct platform_device *pdev = to_platform_device(dev->dev); struct msm_drm_private *priv = dev->dev_private; - struct msm_mdss *mdss; + struct mdp5_mdss *mdp5_mdss; int ret; DBG(""); @@ -217,40 +224,40 @@ int msm_mdss_init(struct drm_device *dev) if (!of_device_is_compatible(dev->dev->of_node, "qcom,mdss")) return 0; - mdss = devm_kzalloc(dev->dev, sizeof(*mdss), GFP_KERNEL); - if (!mdss) { + mdp5_mdss = devm_kzalloc(dev->dev, sizeof(*mdp5_mdss), GFP_KERNEL); + if (!mdp5_mdss) { ret = -ENOMEM; goto fail; } - mdss->dev = dev; + mdp5_mdss->base.dev = dev; - mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS"); - if (IS_ERR(mdss->mmio)) { - ret = PTR_ERR(mdss->mmio); + mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS"); + if (IS_ERR(mdp5_mdss->mmio)) { + ret = PTR_ERR(mdp5_mdss->mmio); goto fail; } - mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF"); - if (IS_ERR(mdss->vbif)) { - ret = PTR_ERR(mdss->vbif); + mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF"); + if (IS_ERR(mdp5_mdss->vbif)) { + ret = PTR_ERR(mdp5_mdss->vbif); goto fail; } - ret = msm_mdss_get_clocks(mdss); + ret = msm_mdss_get_clocks(mdp5_mdss); if (ret) { dev_err(dev->dev, "failed to get clocks: %d\n", ret); goto fail; } /* Regulator to enable GDSCs in downstream kernels */ - mdss->vdd = devm_regulator_get(dev->dev, "vdd"); - if (IS_ERR(mdss->vdd)) { - ret = PTR_ERR(mdss->vdd); + mdp5_mdss->vdd = devm_regulator_get(dev->dev, "vdd"); + if (IS_ERR(mdp5_mdss->vdd)) { + ret = PTR_ERR(mdp5_mdss->vdd); goto fail; } - ret = regulator_enable(mdss->vdd); + ret = regulator_enable(mdp5_mdss->vdd); if (ret) { dev_err(dev->dev, "failed to enable regulator vdd: %d\n", ret); @@ -258,25 +265,26 @@ int msm_mdss_init(struct drm_device *dev) } ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0), - mdss_irq, 0, "mdss_isr", mdss); + mdss_irq, 0, "mdss_isr", mdp5_mdss); if (ret) { dev_err(dev->dev, "failed to init irq: %d\n", ret); goto fail_irq; } - ret = mdss_irq_domain_init(mdss); + ret = mdss_irq_domain_init(mdp5_mdss); if (ret) { dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret); goto fail_irq; } - priv->mdss = mdss; + mdp5_mdss->base.funcs = &mdss_funcs; + priv->mdss = &mdp5_mdss->base; pm_runtime_enable(dev->dev); return 0; fail_irq: - regulator_disable(mdss->vdd); + regulator_disable(mdp5_mdss->vdd); fail: return ret; } diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index b744bcc7d8ad..ff8164cc6738 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -208,6 +208,9 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev, goto fail; } + if (!msm_dsi_manager_validate_current_config(msm_dsi->id)) + goto fail; + msm_dsi->encoder = encoder; msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id); diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 70d9a9a47acd..08f3fc6771b7 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -100,6 +100,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len); void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags); int msm_dsi_manager_register(struct msm_dsi *msm_dsi); void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi); +bool msm_dsi_manager_validate_current_config(u8 id); /* msm dsi */ static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi) @@ -149,6 +150,7 @@ static inline int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll, #endif /* dsi host */ +struct msm_dsi_host; int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host, const struct mipi_dsi_msg *msg); void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host, @@ -162,7 +164,8 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host, int msm_dsi_host_enable(struct mipi_dsi_host *host); int msm_dsi_host_disable(struct mipi_dsi_host *host); int msm_dsi_host_power_on(struct mipi_dsi_host *host, - struct msm_dsi_phy_shared_timings *phy_shared_timings); + struct msm_dsi_phy_shared_timings *phy_shared_timings, + bool is_dual_dsi); int msm_dsi_host_power_off(struct mipi_dsi_host *host); int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host, struct drm_display_mode *mode); @@ -175,13 +178,29 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host, struct msm_dsi_pll *src_pll); void msm_dsi_host_reset_phy(struct mipi_dsi_host *host); void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host, - struct msm_dsi_phy_clk_request *clk_req); + struct msm_dsi_phy_clk_request *clk_req, + bool is_dual_dsi); void msm_dsi_host_destroy(struct mipi_dsi_host *host); int msm_dsi_host_modeset_init(struct mipi_dsi_host *host, struct drm_device *dev); int msm_dsi_host_init(struct msm_dsi *msm_dsi); int msm_dsi_runtime_suspend(struct device *dev); int msm_dsi_runtime_resume(struct device *dev); +int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host); +int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host); +void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host); +void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host); +int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size); +int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size); +void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host); +void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host); +void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host); +int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova); +int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova); +int dsi_clk_init_v2(struct msm_dsi_host *msm_host); +int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host); +int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi); +int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi); /* dsi phy */ struct msm_dsi_phy; diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index 0327bb54b01b..dcdfb1bb54f9 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -136,20 +136,58 @@ static const struct msm_dsi_config sdm845_dsi_cfg = { .num_dsi = 2, }; +const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = { + .link_clk_enable = dsi_link_clk_enable_v2, + .link_clk_disable = dsi_link_clk_disable_v2, + .clk_init_ver = dsi_clk_init_v2, + .tx_buf_alloc = dsi_tx_buf_alloc_v2, + .tx_buf_get = dsi_tx_buf_get_v2, + .tx_buf_put = NULL, + .dma_base_get = dsi_dma_base_get_v2, + .calc_clk_rate = dsi_calc_clk_rate_v2, +}; + +const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = { + .link_clk_enable = dsi_link_clk_enable_6g, + .link_clk_disable = dsi_link_clk_disable_6g, + .clk_init_ver = NULL, + .tx_buf_alloc = dsi_tx_buf_alloc_6g, + .tx_buf_get = dsi_tx_buf_get_6g, + .tx_buf_put = dsi_tx_buf_put_6g, + .dma_base_get = dsi_dma_base_get_6g, + .calc_clk_rate = dsi_calc_clk_rate_6g, +}; + +const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = { + .link_clk_enable = dsi_link_clk_enable_6g, + .link_clk_disable = dsi_link_clk_disable_6g, + .clk_init_ver = dsi_clk_init_6g_v2, + .tx_buf_alloc = dsi_tx_buf_alloc_6g, + .tx_buf_get = dsi_tx_buf_get_6g, + .tx_buf_put = dsi_tx_buf_put_6g, + .dma_base_get = dsi_dma_base_get_6g, + .calc_clk_rate = dsi_calc_clk_rate_6g, +}; + static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = { - {MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, &apq8064_dsi_cfg}, + {MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, + &apq8064_dsi_cfg, &msm_dsi_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_0, - &msm8974_apq8084_dsi_cfg}, + &msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1, - &msm8974_apq8084_dsi_cfg}, + &msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1_1, - &msm8974_apq8084_dsi_cfg}, + &msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_2, - &msm8974_apq8084_dsi_cfg}, - {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3, &msm8994_dsi_cfg}, - {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1, &msm8916_dsi_cfg}, - {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1, &msm8996_dsi_cfg}, - {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg}, + &msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3, + &msm8994_dsi_cfg, &msm_dsi_6g_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1, + &msm8916_dsi_cfg, &msm_dsi_6g_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1, + &msm8996_dsi_cfg, &msm_dsi_6g_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, + &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, }; const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor) diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index 9cfdcf1c95d5..16c507911110 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -40,10 +40,22 @@ struct msm_dsi_config { const int num_dsi; }; +struct msm_dsi_host_cfg_ops { + int (*link_clk_enable)(struct msm_dsi_host *msm_host); + void (*link_clk_disable)(struct msm_dsi_host *msm_host); + int (*clk_init_ver)(struct msm_dsi_host *msm_host); + int (*tx_buf_alloc)(struct msm_dsi_host *msm_host, int size); + void* (*tx_buf_get)(struct msm_dsi_host *msm_host); + void (*tx_buf_put)(struct msm_dsi_host *msm_host); + int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova); + int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_dual_dsi); +}; + struct msm_dsi_cfg_handler { u32 major; u32 minor; const struct msm_dsi_config *cfg; + const struct msm_dsi_host_cfg_ops *ops; }; const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 29841f440111..96fb5f635314 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -118,6 +118,7 @@ struct msm_dsi_host { struct clk *byte_intf_clk; u32 byte_clk_rate; + u32 pixel_clk_rate; u32 esc_clk_rate; /* DSI v2 specific clocks */ @@ -332,6 +333,54 @@ static int dsi_regulator_init(struct msm_dsi_host *msm_host) return 0; } +int dsi_clk_init_v2(struct msm_dsi_host *msm_host) +{ + struct platform_device *pdev = msm_host->pdev; + int ret = 0; + + msm_host->src_clk = msm_clk_get(pdev, "src"); + + if (IS_ERR(msm_host->src_clk)) { + ret = PTR_ERR(msm_host->src_clk); + pr_err("%s: can't find src clock. ret=%d\n", + __func__, ret); + msm_host->src_clk = NULL; + return ret; + } + + msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk); + if (!msm_host->esc_clk_src) { + ret = -ENODEV; + pr_err("%s: can't get esc clock parent. ret=%d\n", + __func__, ret); + return ret; + } + + msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk); + if (!msm_host->dsi_clk_src) { + ret = -ENODEV; + pr_err("%s: can't get src clock parent. ret=%d\n", + __func__, ret); + } + + return ret; +} + +int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host) +{ + struct platform_device *pdev = msm_host->pdev; + int ret = 0; + + msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf"); + if (IS_ERR(msm_host->byte_intf_clk)) { + ret = PTR_ERR(msm_host->byte_intf_clk); + pr_err("%s: can't find byte_intf clock. ret=%d\n", + __func__, ret); + } + + return ret; +} + static int dsi_clk_init(struct msm_dsi_host *msm_host) { struct platform_device *pdev = msm_host->pdev; @@ -379,19 +428,6 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) goto exit; } - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G && - cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V2_2_1) { - msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf"); - if (IS_ERR(msm_host->byte_intf_clk)) { - ret = PTR_ERR(msm_host->byte_intf_clk); - pr_err("%s: can't find byte_intf clock. ret=%d\n", - __func__, ret); - goto exit; - } - } else { - msm_host->byte_intf_clk = NULL; - } - msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk); if (!msm_host->byte_clk_src) { ret = -ENODEV; @@ -406,31 +442,8 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) goto exit; } - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) { - msm_host->src_clk = msm_clk_get(pdev, "src"); - if (IS_ERR(msm_host->src_clk)) { - ret = PTR_ERR(msm_host->src_clk); - pr_err("%s: can't find src clock. ret=%d\n", - __func__, ret); - msm_host->src_clk = NULL; - goto exit; - } - - msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk); - if (!msm_host->esc_clk_src) { - ret = -ENODEV; - pr_err("%s: can't get esc clock parent. ret=%d\n", - __func__, ret); - goto exit; - } - - msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk); - if (!msm_host->dsi_clk_src) { - ret = -ENODEV; - pr_err("%s: can't get src clock parent. ret=%d\n", - __func__, ret); - } - } + if (cfg_hnd->ops->clk_init_ver) + ret = cfg_hnd->ops->clk_init_ver(msm_host); exit: return ret; } @@ -498,7 +511,7 @@ int msm_dsi_runtime_resume(struct device *dev) return dsi_bus_clk_enable(msm_host); } -static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) +int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) { int ret; @@ -511,7 +524,7 @@ static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) goto error; } - ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000); + ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate); if (ret) { pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret); goto error; @@ -566,7 +579,7 @@ error: return ret; } -static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host) +int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host) { int ret; @@ -592,7 +605,7 @@ static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host) goto error; } - ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000); + ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate); if (ret) { pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret); goto error; @@ -634,98 +647,121 @@ error: return ret; } -static int dsi_link_clk_enable(struct msm_dsi_host *msm_host) +void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host) { - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; + clk_disable_unprepare(msm_host->esc_clk); + clk_disable_unprepare(msm_host->pixel_clk); + if (msm_host->byte_intf_clk) + clk_disable_unprepare(msm_host->byte_intf_clk); + clk_disable_unprepare(msm_host->byte_clk); +} - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) - return dsi_link_clk_enable_6g(msm_host); - else - return dsi_link_clk_enable_v2(msm_host); +void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host) +{ + clk_disable_unprepare(msm_host->pixel_clk); + clk_disable_unprepare(msm_host->src_clk); + clk_disable_unprepare(msm_host->esc_clk); + clk_disable_unprepare(msm_host->byte_clk); } -static void dsi_link_clk_disable(struct msm_dsi_host *msm_host) +static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi) { - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; + struct drm_display_mode *mode = msm_host->mode; + u32 pclk_rate; - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) { - clk_disable_unprepare(msm_host->esc_clk); - clk_disable_unprepare(msm_host->pixel_clk); - if (msm_host->byte_intf_clk) - clk_disable_unprepare(msm_host->byte_intf_clk); - clk_disable_unprepare(msm_host->byte_clk); - } else { - clk_disable_unprepare(msm_host->pixel_clk); - clk_disable_unprepare(msm_host->src_clk); - clk_disable_unprepare(msm_host->esc_clk); - clk_disable_unprepare(msm_host->byte_clk); - } + pclk_rate = mode->clock * 1000; + + /* + * For dual DSI mode, the current DRM mode has the complete width of the + * panel. Since, the complete panel is driven by two DSI controllers, + * the clock rates have to be split between the two dsi controllers. + * Adjust the byte and pixel clock rates for each dsi host accordingly. + */ + if (is_dual_dsi) + pclk_rate /= 2; + + return pclk_rate; } -static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host) +static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi) { - struct drm_display_mode *mode = msm_host->mode; - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; u8 lanes = msm_host->lanes; u32 bpp = dsi_get_bpp(msm_host->format); - u32 pclk_rate; + u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_dual_dsi); + u64 pclk_bpp = (u64)pclk_rate * bpp; - if (!mode) { - pr_err("%s: mode not set\n", __func__); - return -EINVAL; - } - - pclk_rate = mode->clock * 1000; - if (lanes > 0) { - msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes); - } else { + if (lanes == 0) { pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__); - msm_host->byte_clk_rate = (pclk_rate * bpp) / 8; + lanes = 1; } - DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate); + do_div(pclk_bpp, (8 * lanes)); - msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk); + msm_host->pixel_clk_rate = pclk_rate; + msm_host->byte_clk_rate = pclk_bpp; - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) { - unsigned int esc_mhz, esc_div; - unsigned long byte_mhz; + DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate, + msm_host->byte_clk_rate); - msm_host->src_clk_rate = (pclk_rate * bpp) / 8; +} - /* - * esc clock is byte clock followed by a 4 bit divider, - * we need to find an escape clock frequency within the - * mipi DSI spec range within the maximum divider limit - * We iterate here between an escape clock frequencey - * between 20 Mhz to 5 Mhz and pick up the first one - * that can be supported by our divider - */ +int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi) +{ + if (!msm_host->mode) { + pr_err("%s: mode not set\n", __func__); + return -EINVAL; + } + + dsi_calc_pclk(msm_host, is_dual_dsi); + msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk); + return 0; +} - byte_mhz = msm_host->byte_clk_rate / 1000000; +int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi) +{ + u32 bpp = dsi_get_bpp(msm_host->format); + u64 pclk_bpp; + unsigned int esc_mhz, esc_div; + unsigned long byte_mhz; - for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) { - esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz); + dsi_calc_pclk(msm_host, is_dual_dsi); - /* - * TODO: Ideally, we shouldn't know what sort of divider - * is available in mmss_cc, we're just assuming that - * it'll always be a 4 bit divider. Need to come up with - * a better way here. - */ - if (esc_div >= 1 && esc_div <= 16) - break; - } + pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_dual_dsi) * bpp; + do_div(pclk_bpp, 8); + msm_host->src_clk_rate = pclk_bpp; - if (esc_mhz < 5) - return -EINVAL; + /* + * esc clock is byte clock followed by a 4 bit divider, + * we need to find an escape clock frequency within the + * mipi DSI spec range within the maximum divider limit + * We iterate here between an escape clock frequencey + * between 20 Mhz to 5 Mhz and pick up the first one + * that can be supported by our divider + */ + + byte_mhz = msm_host->byte_clk_rate / 1000000; - msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div; + for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) { + esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz); - DBG("esc=%d, src=%d", msm_host->esc_clk_rate, - msm_host->src_clk_rate); + /* + * TODO: Ideally, we shouldn't know what sort of divider + * is available in mmss_cc, we're just assuming that + * it'll always be a 4 bit divider. Need to come up with + * a better way here. + */ + if (esc_div >= 1 && esc_div <= 16) + break; } + if (esc_mhz < 5) + return -EINVAL; + + msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div; + + DBG("esc=%d, src=%d", msm_host->esc_clk_rate, + msm_host->src_clk_rate); + return 0; } @@ -885,7 +921,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable, dsi_write(msm_host, REG_DSI_CTRL, data); } -static void dsi_timing_setup(struct msm_dsi_host *msm_host) +static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi) { struct drm_display_mode *mode = msm_host->mode; u32 hs_start = 0, vs_start = 0; /* take sync start as 0 */ @@ -897,10 +933,26 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host) u32 ha_end = ha_start + mode->hdisplay; u32 va_start = v_total - mode->vsync_start; u32 va_end = va_start + mode->vdisplay; + u32 hdisplay = mode->hdisplay; u32 wc; DBG(""); + /* + * For dual DSI mode, the current DRM mode has + * the complete width of the panel. Since, the complete + * panel is driven by two DSI controllers, the horizontal + * timings have to be split between the two dsi controllers. + * Adjust the DSI host timing values accordingly. + */ + if (is_dual_dsi) { + h_total /= 2; + hs_end /= 2; + ha_start /= 2; + ha_end /= 2; + hdisplay /= 2; + } + if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) { dsi_write(msm_host, REG_DSI_ACTIVE_H, DSI_ACTIVE_H_START(ha_start) | @@ -921,7 +973,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host) DSI_ACTIVE_VSYNC_VPOS_END(vs_end)); } else { /* command mode */ /* image data and 1 byte write_memory_start cmd */ - wc = mode->hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1; + wc = hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1; dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_CTRL, DSI_CMD_MDP_STREAM_CTRL_WORD_COUNT(wc) | @@ -931,7 +983,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host) MIPI_DSI_DCS_LONG_WRITE)); dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_TOTAL, - DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(mode->hdisplay) | + DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(hdisplay) | DSI_CMD_MDP_STREAM_TOTAL_V_TOTAL(mode->vdisplay)); } } @@ -1015,50 +1067,37 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host) } } -/* dsi_cmd */ -static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size) +int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size) { struct drm_device *dev = msm_host->dev; struct msm_drm_private *priv = dev->dev_private; - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; - int ret; uint64_t iova; + u8 *data; - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) { - msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED); - if (IS_ERR(msm_host->tx_gem_obj)) { - ret = PTR_ERR(msm_host->tx_gem_obj); - pr_err("%s: failed to allocate gem, %d\n", - __func__, ret); - msm_host->tx_gem_obj = NULL; - return ret; - } + data = msm_gem_kernel_new(dev, size, MSM_BO_UNCACHED, + priv->kms->aspace, + &msm_host->tx_gem_obj, &iova); - ret = msm_gem_get_iova(msm_host->tx_gem_obj, - priv->kms->aspace, &iova); - if (ret) { - pr_err("%s: failed to get iova, %d\n", __func__, ret); - return ret; - } + if (IS_ERR(data)) { + msm_host->tx_gem_obj = NULL; + return PTR_ERR(data); + } - if (iova & 0x07) { - pr_err("%s: buf NOT 8 bytes aligned\n", __func__); - return -EINVAL; - } + msm_host->tx_size = msm_host->tx_gem_obj->size; - msm_host->tx_size = msm_host->tx_gem_obj->size; - } else { - msm_host->tx_buf = dma_alloc_coherent(dev->dev, size, + return 0; +} + +int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size) +{ + struct drm_device *dev = msm_host->dev; + + msm_host->tx_buf = dma_alloc_coherent(dev->dev, size, &msm_host->tx_buf_paddr, GFP_KERNEL); - if (!msm_host->tx_buf) { - ret = -ENOMEM; - pr_err("%s: failed to allocate tx buf, %d\n", - __func__, ret); - return ret; - } + if (!msm_host->tx_buf) + return -ENOMEM; - msm_host->tx_size = size; - } + msm_host->tx_size = size; return 0; } @@ -1089,6 +1128,21 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host) msm_host->tx_buf_paddr); } +void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host) +{ + return msm_gem_get_vaddr(msm_host->tx_gem_obj); +} + +void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host) +{ + return msm_host->tx_buf; +} + +void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host) +{ + msm_gem_put_vaddr(msm_host->tx_gem_obj); +} + /* * prepare cmd buffer to be txed */ @@ -1113,15 +1167,11 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host, return -EINVAL; } - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) { - data = msm_gem_get_vaddr(msm_host->tx_gem_obj); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - pr_err("%s: get vaddr failed, %d\n", __func__, ret); - return ret; - } - } else { - data = msm_host->tx_buf; + data = cfg_hnd->ops->tx_buf_get(msm_host); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + pr_err("%s: get vaddr failed, %d\n", __func__, ret); + return ret; } /* MSM specific command format in memory */ @@ -1142,8 +1192,8 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host, if (packet.size < len) memset(data + packet.size, 0xff, len - packet.size); - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) - msm_gem_put_vaddr(msm_host->tx_gem_obj); + if (cfg_hnd->ops->tx_buf_put) + cfg_hnd->ops->tx_buf_put(msm_host); return len; } @@ -1190,24 +1240,38 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg) return msg->rx_len; } -static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len) +int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *dma_base) { - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; struct drm_device *dev = msm_host->dev; struct msm_drm_private *priv = dev->dev_private; + + if (!dma_base) + return -EINVAL; + + return msm_gem_get_iova(msm_host->tx_gem_obj, + priv->kms->aspace, dma_base); +} + +int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *dma_base) +{ + if (!dma_base) + return -EINVAL; + + *dma_base = msm_host->tx_buf_paddr; + return 0; +} + +static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len) +{ + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; int ret; uint64_t dma_base; bool triggered; - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) { - ret = msm_gem_get_iova(msm_host->tx_gem_obj, - priv->kms->aspace, &dma_base); - if (ret) { - pr_err("%s: failed to get iova: %d\n", __func__, ret); - return ret; - } - } else { - dma_base = msm_host->tx_buf_paddr; + ret = cfg_hnd->ops->dma_base_get(msm_host, &dma_base); + if (ret) { + pr_err("%s: failed to get iova: %d\n", __func__, ret); + return ret; } reinit_completion(&msm_host->dma_comp); @@ -1845,6 +1909,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host, struct drm_device *dev) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; struct platform_device *pdev = msm_host->pdev; int ret; @@ -1865,7 +1930,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host, } msm_host->dev = dev; - ret = dsi_tx_buf_alloc(msm_host, SZ_4K); + ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K); if (ret) { pr_err("%s: alloc tx gem obj failed, %d\n", __func__, ret); return ret; @@ -1923,6 +1988,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host, const struct mipi_dsi_msg *msg) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; /* TODO: make sure dsi_cmd_mdp is idle. * Since DSI6G v1.2.0, we can set DSI_TRIG_CTRL.BLOCK_DMA_WITHIN_FRAME @@ -1935,7 +2001,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host, * mdp clock need to be enabled to receive dsi interrupt */ pm_runtime_get_sync(&msm_host->pdev->dev); - dsi_link_clk_enable(msm_host); + cfg_hnd->ops->link_clk_enable(msm_host); /* TODO: vote for bus bandwidth */ @@ -1956,6 +2022,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host, const struct mipi_dsi_msg *msg) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_CMD_DMA_DONE, 0); dsi_write(msm_host, REG_DSI_CTRL, msm_host->dma_cmd_ctrl_restore); @@ -1965,7 +2032,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host, /* TODO: unvote for bus bandwidth */ - dsi_link_clk_disable(msm_host); + cfg_hnd->ops->link_clk_disable(msm_host); pm_runtime_put_autosuspend(&msm_host->pdev->dev); } @@ -2129,7 +2196,6 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host, struct msm_dsi_pll *src_pll) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); - const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; struct clk *byte_clk_provider, *pixel_clk_provider; int ret; @@ -2155,14 +2221,16 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host, goto exit; } - if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) { + if (msm_host->dsi_clk_src) { ret = clk_set_parent(msm_host->dsi_clk_src, pixel_clk_provider); if (ret) { pr_err("%s: can't set parent to dsi_clk_src. ret=%d\n", __func__, ret); goto exit; } + } + if (msm_host->esc_clk_src) { ret = clk_set_parent(msm_host->esc_clk_src, byte_clk_provider); if (ret) { pr_err("%s: can't set parent to esc_clk_src. ret=%d\n", @@ -2189,12 +2257,14 @@ void msm_dsi_host_reset_phy(struct mipi_dsi_host *host) } void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host, - struct msm_dsi_phy_clk_request *clk_req) + struct msm_dsi_phy_clk_request *clk_req, + bool is_dual_dsi) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; int ret; - ret = dsi_calc_clk_rate(msm_host); + ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_dual_dsi); if (ret) { pr_err("%s: unable to calc clk rate, %d\n", __func__, ret); return; @@ -2256,9 +2326,11 @@ static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable) } int msm_dsi_host_power_on(struct mipi_dsi_host *host, - struct msm_dsi_phy_shared_timings *phy_shared_timings) + struct msm_dsi_phy_shared_timings *phy_shared_timings, + bool is_dual_dsi) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; int ret = 0; mutex_lock(&msm_host->dev_mutex); @@ -2277,7 +2349,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host, } pm_runtime_get_sync(&msm_host->pdev->dev); - ret = dsi_link_clk_enable(msm_host); + ret = cfg_hnd->ops->link_clk_enable(msm_host); if (ret) { pr_err("%s: failed to enable link clocks. ret=%d\n", __func__, ret); @@ -2291,7 +2363,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host, goto fail_disable_clk; } - dsi_timing_setup(msm_host); + dsi_timing_setup(msm_host, is_dual_dsi); dsi_sw_reset(msm_host); dsi_ctrl_config(msm_host, true, phy_shared_timings); @@ -2304,7 +2376,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host, return 0; fail_disable_clk: - dsi_link_clk_disable(msm_host); + cfg_hnd->ops->link_clk_disable(msm_host); pm_runtime_put_autosuspend(&msm_host->pdev->dev); fail_disable_reg: dsi_host_regulator_disable(msm_host); @@ -2316,6 +2388,7 @@ unlock_ret: int msm_dsi_host_power_off(struct mipi_dsi_host *host) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); + const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; mutex_lock(&msm_host->dev_mutex); if (!msm_host->power_on) { @@ -2330,7 +2403,7 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host) pinctrl_pm_select_sleep_state(&msm_host->pdev->dev); - dsi_link_clk_disable(msm_host); + cfg_hnd->ops->link_clk_disable(msm_host); pm_runtime_put_autosuspend(&msm_host->pdev->dev); dsi_host_regulator_disable(msm_host); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index d5006d6923e0..5224010d90e4 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -134,8 +134,9 @@ static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id, { struct msm_dsi_phy_clk_request clk_req; int ret; + bool is_dual_dsi = IS_DUAL_DSI(); - msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req); + msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi); ret = msm_dsi_phy_enable(msm_dsi->phy, src_pll_id, &clk_req); msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings); @@ -305,102 +306,25 @@ static void dsi_mgr_connector_destroy(struct drm_connector *connector) kfree(dsi_connector); } -static void dsi_dual_connector_fix_modes(struct drm_connector *connector) -{ - struct drm_display_mode *mode, *m; - - /* Only support left-right mode */ - list_for_each_entry_safe(mode, m, &connector->probed_modes, head) { - mode->clock >>= 1; - mode->hdisplay >>= 1; - mode->hsync_start >>= 1; - mode->hsync_end >>= 1; - mode->htotal >>= 1; - drm_mode_set_name(mode); - } -} - -static int dsi_dual_connector_tile_init( - struct drm_connector *connector, int id) -{ - struct drm_display_mode *mode; - /* Fake topology id */ - char topo_id[8] = {'M', 'S', 'M', 'D', 'U', 'D', 'S', 'I'}; - - if (connector->tile_group) { - DBG("Tile property has been initialized"); - return 0; - } - - /* Use the first mode only for now */ - mode = list_first_entry(&connector->probed_modes, - struct drm_display_mode, - head); - if (!mode) - return -EINVAL; - - connector->tile_group = drm_mode_get_tile_group( - connector->dev, topo_id); - if (!connector->tile_group) - connector->tile_group = drm_mode_create_tile_group( - connector->dev, topo_id); - if (!connector->tile_group) { - pr_err("%s: failed to create tile group\n", __func__); - return -ENOMEM; - } - - connector->has_tile = true; - connector->tile_is_single_monitor = true; - - /* mode has been fixed */ - connector->tile_h_size = mode->hdisplay; - connector->tile_v_size = mode->vdisplay; - - /* Only support left-right mode */ - connector->num_h_tile = 2; - connector->num_v_tile = 1; - - connector->tile_v_loc = 0; - connector->tile_h_loc = (id == DSI_RIGHT) ? 1 : 0; - - return 0; -} - static int dsi_mgr_connector_get_modes(struct drm_connector *connector) { int id = dsi_mgr_connector_get_id(connector); struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct drm_panel *panel = msm_dsi->panel; - int ret, num; + int num; if (!panel) return 0; - /* Since we have 2 connectors, but only 1 drm_panel in dual DSI mode, - * panel should not attach to any connector. - * Only temporarily attach panel to the current connector here, - * to let panel set mode to this connector. + /* + * In dual DSI mode, we have one connector that can be + * attached to the drm_panel. */ drm_panel_attach(panel, connector); num = drm_panel_get_modes(panel); - drm_panel_detach(panel); if (!num) return 0; - if (IS_DUAL_DSI()) { - /* report half resolution to user */ - dsi_dual_connector_fix_modes(connector); - ret = dsi_dual_connector_tile_init(connector, id); - if (ret) - return ret; - ret = drm_connector_set_tile_property(connector); - if (ret) { - pr_err("%s: set tile property failed, %d\n", - __func__, ret); - return ret; - } - } - return num; } @@ -454,11 +378,11 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) if (ret) goto phy_en_fail; - /* Do nothing with the host if it is DSI 1 in case of dual DSI */ - if (is_dual_dsi && (DSI_1 == id)) + /* Do nothing with the host if it is slave-DSI in case of dual DSI */ + if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) return; - ret = msm_dsi_host_power_on(host, &phy_shared_timings[id]); + ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi); if (ret) { pr_err("%s: power on host %d failed, %d\n", __func__, id, ret); goto host_on_fail; @@ -466,7 +390,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) if (is_dual_dsi && msm_dsi1) { ret = msm_dsi_host_power_on(msm_dsi1->host, - &phy_shared_timings[DSI_1]); + &phy_shared_timings[DSI_1], is_dual_dsi); if (ret) { pr_err("%s: power on host1 failed, %d\n", __func__, ret); @@ -556,11 +480,11 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) return; /* - * Do nothing with the host if it is DSI 1 in case of dual DSI. + * Do nothing with the host if it is slave-DSI in case of dual DSI. * It is safe to call dsi_mgr_phy_disable() here because a single PHY * won't be diabled until both PHYs request disable. */ - if (is_dual_dsi && (DSI_1 == id)) + if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) goto disable_phy; if (panel) { @@ -621,7 +545,7 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge, mode->vsync_end, mode->vtotal, mode->type, mode->flags); - if (is_dual_dsi && (DSI_1 == id)) + if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) return; msm_dsi_host_set_display_mode(host, adjusted_mode); @@ -689,6 +613,23 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id) return connector; } +bool msm_dsi_manager_validate_current_config(u8 id) +{ + bool is_dual_dsi = IS_DUAL_DSI(); + + /* + * For dual DSI, we only have one drm panel. For this + * use case, we register only one bridge/connector. + * Skip bridge/connector initialisation if it is + * slave-DSI for dual DSI configuration. + */ + if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) { + DBG("Skip bridge registration for slave DSI->id: %d\n", id); + return false; + } + return true; +} + /* initialize bridge */ struct drm_bridge *msm_dsi_manager_bridge_init(u8 id) { @@ -832,6 +773,7 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags) struct msm_drm_private *priv; struct msm_kms *kms; struct drm_encoder *encoder; + bool cmd_mode; /* * drm_device pointer is assigned to msm_dsi only in the modeset_init @@ -846,10 +788,11 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags) priv = dev->dev_private; kms = priv->kms; encoder = msm_dsi_get_encoder(msm_dsi); + cmd_mode = !(device_flags & + MIPI_DSI_MODE_VIDEO); if (encoder && kms->funcs->set_encoder_mode) - if (!(device_flags & MIPI_DSI_MODE_VIDEO)) - kms->funcs->set_encoder_mode(kms, encoder, true); + kms->funcs->set_encoder_mode(kms, encoder, cmd_mode); } int msm_dsi_manager_register(struct msm_dsi *msm_dsi) diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c index c4c37a7df637..4c03f0b7343e 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c @@ -798,6 +798,8 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) return ERR_PTR(-ENOMEM); } + spin_lock_init(&pll_10nm->postdiv_lock); + pll = &pll_10nm->base; pll->min_rate = 1000000000UL; pll->max_rate = 3500000000UL; diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index f0635c3da7f4..c1f1779c980f 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -71,12 +71,15 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) drm_atomic_helper_commit_modeset_enables(dev, state); + if (kms->funcs->commit) { + DRM_DEBUG_ATOMIC("triggering commit\n"); + kms->funcs->commit(kms, state); + } + msm_atomic_wait_for_commit_done(dev, state); kms->funcs->complete_commit(kms, state); - drm_atomic_helper_wait_for_vblanks(dev, state); - drm_atomic_helper_commit_hw_done(state); drm_atomic_helper_cleanup_planes(dev, state); diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 1ff3fda245d1..f0da0d3c8a80 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -16,26 +16,101 @@ */ #ifdef CONFIG_DEBUG_FS +#include <linux/debugfs.h> #include "msm_drv.h" #include "msm_gpu.h" #include "msm_kms.h" #include "msm_debugfs.h" -static int msm_gpu_show(struct drm_device *dev, struct seq_file *m) +struct msm_gpu_show_priv { + struct msm_gpu_state *state; + struct drm_device *dev; +}; + +static int msm_gpu_show(struct seq_file *m, void *arg) +{ + struct drm_printer p = drm_seq_file_printer(m); + struct msm_gpu_show_priv *show_priv = m->private; + struct msm_drm_private *priv = show_priv->dev->dev_private; + struct msm_gpu *gpu = priv->gpu; + int ret; + + ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex); + if (ret) + return ret; + + drm_printf(&p, "%s Status:\n", gpu->name); + gpu->funcs->show(gpu, show_priv->state, &p); + + mutex_unlock(&show_priv->dev->struct_mutex); + + return 0; +} + +static int msm_gpu_release(struct inode *inode, struct file *file) { + struct seq_file *m = file->private_data; + struct msm_gpu_show_priv *show_priv = m->private; + struct msm_drm_private *priv = show_priv->dev->dev_private; + struct msm_gpu *gpu = priv->gpu; + int ret; + + ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex); + if (ret) + return ret; + + gpu->funcs->gpu_state_put(show_priv->state); + mutex_unlock(&show_priv->dev->struct_mutex); + + kfree(show_priv); + + return single_release(inode, file); +} + +static int msm_gpu_open(struct inode *inode, struct file *file) +{ + struct drm_device *dev = inode->i_private; struct msm_drm_private *priv = dev->dev_private; struct msm_gpu *gpu = priv->gpu; + struct msm_gpu_show_priv *show_priv; + int ret; - if (gpu) { - seq_printf(m, "%s Status:\n", gpu->name); - pm_runtime_get_sync(&gpu->pdev->dev); - gpu->funcs->show(gpu, m); - pm_runtime_put_sync(&gpu->pdev->dev); + if (!gpu) + return -ENODEV; + + show_priv = kmalloc(sizeof(*show_priv), GFP_KERNEL); + if (!show_priv) + return -ENOMEM; + + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; + + pm_runtime_get_sync(&gpu->pdev->dev); + show_priv->state = gpu->funcs->gpu_state_get(gpu); + pm_runtime_put_sync(&gpu->pdev->dev); + + mutex_unlock(&dev->struct_mutex); + + if (IS_ERR(show_priv->state)) { + ret = PTR_ERR(show_priv->state); + kfree(show_priv); + return ret; } - return 0; + show_priv->dev = dev; + + return single_open(file, msm_gpu_show, show_priv); } +static const struct file_operations msm_gpu_fops = { + .owner = THIS_MODULE, + .open = msm_gpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = msm_gpu_release, +}; + static int msm_gem_show(struct drm_device *dev, struct seq_file *m) { struct msm_drm_private *priv = dev->dev_private; @@ -105,7 +180,6 @@ static int show_locked(struct seq_file *m, void *arg) } static struct drm_info_list msm_debugfs_list[] = { - {"gpu", show_locked, 0, msm_gpu_show}, {"gem", show_locked, 0, msm_gem_show}, { "mm", show_locked, 0, msm_mm_show }, { "fb", show_locked, 0, msm_fb_show }, @@ -158,6 +232,9 @@ int msm_debugfs_init(struct drm_minor *minor) return ret; } + debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root, + dev, &msm_gpu_fops); + if (priv->kms->funcs->debugfs_init) { ret = priv->kms->funcs->debugfs_init(priv->kms, minor); if (ret) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 021a0b6f9a59..46876bc8b707 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> * @@ -15,6 +16,8 @@ * this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/kthread.h> +#include <uapi/linux/sched/types.h> #include <drm/drm_of.h> #include "msm_drv.h" @@ -149,7 +152,7 @@ struct vblank_event { bool enable; }; -static void vblank_ctrl_worker(struct work_struct *work) +static void vblank_ctrl_worker(struct kthread_work *work) { struct msm_vblank_ctrl *vbl_ctrl = container_of(work, struct msm_vblank_ctrl, work); @@ -197,7 +200,8 @@ static int vblank_ctrl_queue_work(struct msm_drm_private *priv, list_add_tail(&vbl_ev->node, &vbl_ctrl->event_list); spin_unlock_irqrestore(&vbl_ctrl->lock, flags); - queue_work(priv->wq, &vbl_ctrl->work); + kthread_queue_work(&priv->disp_thread[crtc_id].worker, + &vbl_ctrl->work); return 0; } @@ -208,19 +212,36 @@ static int msm_drm_uninit(struct device *dev) struct drm_device *ddev = platform_get_drvdata(pdev); struct msm_drm_private *priv = ddev->dev_private; struct msm_kms *kms = priv->kms; + struct msm_mdss *mdss = priv->mdss; struct msm_vblank_ctrl *vbl_ctrl = &priv->vblank_ctrl; struct vblank_event *vbl_ev, *tmp; + int i; /* We must cancel and cleanup any pending vblank enable/disable * work before drm_irq_uninstall() to avoid work re-enabling an * irq after uninstall has disabled it. */ - cancel_work_sync(&vbl_ctrl->work); + kthread_flush_work(&vbl_ctrl->work); list_for_each_entry_safe(vbl_ev, tmp, &vbl_ctrl->event_list, node) { list_del(&vbl_ev->node); kfree(vbl_ev); } + /* clean up display commit/event worker threads */ + for (i = 0; i < priv->num_crtcs; i++) { + if (priv->disp_thread[i].thread) { + kthread_flush_worker(&priv->disp_thread[i].worker); + kthread_stop(priv->disp_thread[i].thread); + priv->disp_thread[i].thread = NULL; + } + + if (priv->event_thread[i].thread) { + kthread_flush_worker(&priv->event_thread[i].worker); + kthread_stop(priv->event_thread[i].thread); + priv->event_thread[i].thread = NULL; + } + } + msm_gem_shrinker_cleanup(ddev); drm_kms_helper_poll_fini(ddev); @@ -243,9 +264,6 @@ static int msm_drm_uninit(struct device *dev) flush_workqueue(priv->wq); destroy_workqueue(priv->wq); - flush_workqueue(priv->atomic_wq); - destroy_workqueue(priv->atomic_wq); - if (kms && kms->funcs) kms->funcs->destroy(kms); @@ -258,7 +276,8 @@ static int msm_drm_uninit(struct device *dev) component_unbind_all(dev, ddev); - msm_mdss_destroy(ddev); + if (mdss && mdss->funcs) + mdss->funcs->destroy(ddev); ddev->dev_private = NULL; drm_dev_unref(ddev); @@ -268,6 +287,10 @@ static int msm_drm_uninit(struct device *dev) return 0; } +#define KMS_MDP4 4 +#define KMS_MDP5 5 +#define KMS_DPU 3 + static int get_mdp_ver(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -357,7 +380,9 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) struct drm_device *ddev; struct msm_drm_private *priv; struct msm_kms *kms; - int ret; + struct msm_mdss *mdss; + int ret, i; + struct sched_param param; ddev = drm_dev_alloc(drv, dev); if (IS_ERR(ddev)) { @@ -369,53 +394,61 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) { - drm_dev_unref(ddev); - return -ENOMEM; + ret = -ENOMEM; + goto err_unref_drm_dev; } ddev->dev_private = priv; priv->dev = ddev; - ret = msm_mdss_init(ddev); - if (ret) { - kfree(priv); - drm_dev_unref(ddev); - return ret; + switch (get_mdp_ver(pdev)) { + case KMS_MDP5: + ret = mdp5_mdss_init(ddev); + break; + case KMS_DPU: + ret = dpu_mdss_init(ddev); + break; + default: + ret = 0; + break; } + if (ret) + goto err_free_priv; + + mdss = priv->mdss; priv->wq = alloc_ordered_workqueue("msm", 0); - priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0); INIT_LIST_HEAD(&priv->inactive_list); INIT_LIST_HEAD(&priv->vblank_ctrl.event_list); - INIT_WORK(&priv->vblank_ctrl.work, vblank_ctrl_worker); + kthread_init_work(&priv->vblank_ctrl.work, vblank_ctrl_worker); spin_lock_init(&priv->vblank_ctrl.lock); drm_mode_config_init(ddev); /* Bind all our sub-components: */ ret = component_bind_all(dev, ddev); - if (ret) { - msm_mdss_destroy(ddev); - kfree(priv); - drm_dev_unref(ddev); - return ret; - } + if (ret) + goto err_destroy_mdss; ret = msm_init_vram(ddev); if (ret) - goto fail; + goto err_msm_uninit; msm_gem_shrinker_init(ddev); switch (get_mdp_ver(pdev)) { - case 4: + case KMS_MDP4: kms = mdp4_kms_init(ddev); priv->kms = kms; break; - case 5: + case KMS_MDP5: kms = mdp5_kms_init(ddev); break; + case KMS_DPU: + kms = dpu_kms_init(ddev); + priv->kms = kms; + break; default: kms = ERR_PTR(-ENODEV); break; @@ -430,24 +463,100 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) */ dev_err(dev, "failed to load kms\n"); ret = PTR_ERR(kms); - goto fail; + goto err_msm_uninit; } + /* Enable normalization of plane zpos */ + ddev->mode_config.normalize_zpos = true; + if (kms) { ret = kms->funcs->hw_init(kms); if (ret) { dev_err(dev, "kms hw init failed: %d\n", ret); - goto fail; + goto err_msm_uninit; } } ddev->mode_config.funcs = &mode_config_funcs; ddev->mode_config.helper_private = &mode_config_helper_funcs; + /** + * this priority was found during empiric testing to have appropriate + * realtime scheduling to process display updates and interact with + * other real time and normal priority task + */ + param.sched_priority = 16; + for (i = 0; i < priv->num_crtcs; i++) { + + /* initialize display thread */ + priv->disp_thread[i].crtc_id = priv->crtcs[i]->base.id; + kthread_init_worker(&priv->disp_thread[i].worker); + priv->disp_thread[i].dev = ddev; + priv->disp_thread[i].thread = + kthread_run(kthread_worker_fn, + &priv->disp_thread[i].worker, + "crtc_commit:%d", priv->disp_thread[i].crtc_id); + ret = sched_setscheduler(priv->disp_thread[i].thread, + SCHED_FIFO, ¶m); + if (ret) + pr_warn("display thread priority update failed: %d\n", + ret); + + if (IS_ERR(priv->disp_thread[i].thread)) { + dev_err(dev, "failed to create crtc_commit kthread\n"); + priv->disp_thread[i].thread = NULL; + } + + /* initialize event thread */ + priv->event_thread[i].crtc_id = priv->crtcs[i]->base.id; + kthread_init_worker(&priv->event_thread[i].worker); + priv->event_thread[i].dev = ddev; + priv->event_thread[i].thread = + kthread_run(kthread_worker_fn, + &priv->event_thread[i].worker, + "crtc_event:%d", priv->event_thread[i].crtc_id); + /** + * event thread should also run at same priority as disp_thread + * because it is handling frame_done events. A lower priority + * event thread and higher priority disp_thread can causes + * frame_pending counters beyond 2. This can lead to commit + * failure at crtc commit level. + */ + ret = sched_setscheduler(priv->event_thread[i].thread, + SCHED_FIFO, ¶m); + if (ret) + pr_warn("display event thread priority update failed: %d\n", + ret); + + if (IS_ERR(priv->event_thread[i].thread)) { + dev_err(dev, "failed to create crtc_event kthread\n"); + priv->event_thread[i].thread = NULL; + } + + if ((!priv->disp_thread[i].thread) || + !priv->event_thread[i].thread) { + /* clean up previously created threads if any */ + for ( ; i >= 0; i--) { + if (priv->disp_thread[i].thread) { + kthread_stop( + priv->disp_thread[i].thread); + priv->disp_thread[i].thread = NULL; + } + + if (priv->event_thread[i].thread) { + kthread_stop( + priv->event_thread[i].thread); + priv->event_thread[i].thread = NULL; + } + } + goto err_msm_uninit; + } + } + ret = drm_vblank_init(ddev, priv->num_crtcs); if (ret < 0) { dev_err(dev, "failed to initialize vblank\n"); - goto fail; + goto err_msm_uninit; } if (kms) { @@ -456,13 +565,13 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) pm_runtime_put_sync(dev); if (ret < 0) { dev_err(dev, "failed to install IRQ handler\n"); - goto fail; + goto err_msm_uninit; } } ret = drm_dev_register(ddev, 0); if (ret) - goto fail; + goto err_msm_uninit; drm_mode_config_reset(ddev); @@ -473,15 +582,23 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) ret = msm_debugfs_late_init(ddev); if (ret) - goto fail; + goto err_msm_uninit; drm_kms_helper_poll_init(ddev); return 0; -fail: +err_msm_uninit: msm_drm_uninit(dev); return ret; +err_destroy_mdss: + if (mdss && mdss->funcs) + mdss->funcs->destroy(ddev); +err_free_priv: + kfree(priv); +err_unref_drm_dev: + drm_dev_unref(ddev); + return ret; } /* @@ -894,16 +1011,35 @@ static struct drm_driver msm_driver = { static int msm_pm_suspend(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev->dev_private; + struct msm_kms *kms = priv->kms; + + /* TODO: Use atomic helper suspend/resume */ + if (kms && kms->funcs && kms->funcs->pm_suspend) + return kms->funcs->pm_suspend(dev); drm_kms_helper_poll_disable(ddev); + priv->pm_state = drm_atomic_helper_suspend(ddev); + if (IS_ERR(priv->pm_state)) { + drm_kms_helper_poll_enable(ddev); + return PTR_ERR(priv->pm_state); + } + return 0; } static int msm_pm_resume(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev->dev_private; + struct msm_kms *kms = priv->kms; + + /* TODO: Use atomic helper suspend/resume */ + if (kms && kms->funcs && kms->funcs->pm_resume) + return kms->funcs->pm_resume(dev); + drm_atomic_helper_resume(ddev, priv->pm_state); drm_kms_helper_poll_enable(ddev); return 0; @@ -915,11 +1051,12 @@ static int msm_runtime_suspend(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); struct msm_drm_private *priv = ddev->dev_private; + struct msm_mdss *mdss = priv->mdss; DBG(""); - if (priv->mdss) - return msm_mdss_disable(priv->mdss); + if (mdss && mdss->funcs) + return mdss->funcs->disable(mdss); return 0; } @@ -928,11 +1065,12 @@ static int msm_runtime_resume(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); struct msm_drm_private *priv = ddev->dev_private; + struct msm_mdss *mdss = priv->mdss; DBG(""); - if (priv->mdss) - return msm_mdss_enable(priv->mdss); + if (mdss && mdss->funcs) + return mdss->funcs->enable(mdss); return 0; } @@ -1031,12 +1169,13 @@ static int add_display_components(struct device *dev, int ret; /* - * MDP5 based devices don't have a flat hierarchy. There is a top level - * parent: MDSS, and children: MDP5, DSI, HDMI, eDP etc. Populate the - * children devices, find the MDP5 node, and then add the interfaces - * to our components list. + * MDP5/DPU based devices don't have a flat hierarchy. There is a top + * level parent: MDSS, and children: MDP5/DPU, DSI, HDMI, eDP etc. + * Populate the children devices, find the MDP5/DPU node, and then add + * the interfaces to our components list. */ - if (of_device_is_compatible(dev->of_node, "qcom,mdss")) { + if (of_device_is_compatible(dev->of_node, "qcom,mdss") || + of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) { ret = of_platform_populate(dev->of_node, NULL, NULL, dev); if (ret) { dev_err(dev, "failed to populate children devices\n"); @@ -1146,8 +1285,9 @@ static int msm_pdev_remove(struct platform_device *pdev) } static const struct of_device_id dt_match[] = { - { .compatible = "qcom,mdp4", .data = (void *)4 }, /* MDP4 */ - { .compatible = "qcom,mdss", .data = (void *)5 }, /* MDP5 MDSS */ + { .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 }, + { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, + { .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU }, {} }; MODULE_DEVICE_TABLE(of, dt_match); @@ -1169,6 +1309,7 @@ static int __init msm_drm_register(void) DBG("init"); msm_mdp_register(); + msm_dpu_register(); msm_dsi_register(); msm_edp_register(); msm_hdmi_register(); @@ -1185,6 +1326,7 @@ static void __exit msm_drm_unregister(void) msm_edp_unregister(); msm_dsi_unregister(); msm_mdp_unregister(); + msm_dpu_unregister(); } module_init(msm_drm_register); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index b2da1fbf81e0..0cba86ed3f54 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -1,4 +1,5 @@ /* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> * @@ -33,6 +34,7 @@ #include <linux/of_graph.h> #include <linux/of_device.h> #include <asm/sizes.h> +#include <linux/kthread.h> #include <drm/drmP.h> #include <drm/drm_atomic.h> @@ -54,6 +56,12 @@ struct msm_fence_context; struct msm_gem_address_space; struct msm_gem_vma; +#define MAX_CRTCS 8 +#define MAX_PLANES 20 +#define MAX_ENCODERS 8 +#define MAX_BRIDGES 8 +#define MAX_CONNECTORS 8 + struct msm_file_private { rwlock_t queuelock; struct list_head submitqueues; @@ -68,12 +76,77 @@ enum msm_mdp_plane_property { }; struct msm_vblank_ctrl { - struct work_struct work; + struct kthread_work work; struct list_head event_list; spinlock_t lock; }; #define MSM_GPU_MAX_RINGS 4 +#define MAX_H_TILES_PER_DISPLAY 2 + +/** + * enum msm_display_caps - features/capabilities supported by displays + * @MSM_DISPLAY_CAP_VID_MODE: Video or "active" mode supported + * @MSM_DISPLAY_CAP_CMD_MODE: Command mode supported + * @MSM_DISPLAY_CAP_HOT_PLUG: Hot plug detection supported + * @MSM_DISPLAY_CAP_EDID: EDID supported + */ +enum msm_display_caps { + MSM_DISPLAY_CAP_VID_MODE = BIT(0), + MSM_DISPLAY_CAP_CMD_MODE = BIT(1), + MSM_DISPLAY_CAP_HOT_PLUG = BIT(2), + MSM_DISPLAY_CAP_EDID = BIT(3), +}; + +/** + * enum msm_event_wait - type of HW events to wait for + * @MSM_ENC_COMMIT_DONE - wait for the driver to flush the registers to HW + * @MSM_ENC_TX_COMPLETE - wait for the HW to transfer the frame to panel + * @MSM_ENC_VBLANK - wait for the HW VBLANK event (for driver-internal waiters) + */ +enum msm_event_wait { + MSM_ENC_COMMIT_DONE = 0, + MSM_ENC_TX_COMPLETE, + MSM_ENC_VBLANK, +}; + +/** + * struct msm_display_topology - defines a display topology pipeline + * @num_lm: number of layer mixers used + * @num_enc: number of compression encoder blocks used + * @num_intf: number of interfaces the panel is mounted on + */ +struct msm_display_topology { + u32 num_lm; + u32 num_enc; + u32 num_intf; +}; + +/** + * struct msm_display_info - defines display properties + * @intf_type: DRM_MODE_CONNECTOR_ display type + * @capabilities: Bitmask of display flags + * @num_of_h_tiles: Number of horizontal tiles in case of split interface + * @h_tile_instance: Controller instance used per tile. Number of elements is + * based on num_of_h_tiles + * @is_te_using_watchdog_timer: Boolean to indicate watchdog TE is + * used instead of panel TE in cmd mode panels + */ +struct msm_display_info { + int intf_type; + uint32_t capabilities; + uint32_t num_of_h_tiles; + uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY]; + bool is_te_using_watchdog_timer; +}; + +/* Commit/Event thread specific structure */ +struct msm_drm_thread { + struct drm_device *dev; + struct task_struct *thread; + unsigned int crtc_id; + struct kthread_worker worker; +}; struct msm_drm_private { @@ -84,7 +157,7 @@ struct msm_drm_private { /* subordinate devices, if present: */ struct platform_device *gpu_pdev; - /* top level MDSS wrapper device (for MDP5 only) */ + /* top level MDSS wrapper device (for MDP5/DPU only) */ struct msm_mdss *mdss; /* possibly this should be in the kms component, but it is @@ -115,22 +188,24 @@ struct msm_drm_private { struct list_head inactive_list; struct workqueue_struct *wq; - struct workqueue_struct *atomic_wq; unsigned int num_planes; - struct drm_plane *planes[16]; + struct drm_plane *planes[MAX_PLANES]; unsigned int num_crtcs; - struct drm_crtc *crtcs[8]; + struct drm_crtc *crtcs[MAX_CRTCS]; + + struct msm_drm_thread disp_thread[MAX_CRTCS]; + struct msm_drm_thread event_thread[MAX_CRTCS]; unsigned int num_encoders; - struct drm_encoder *encoders[8]; + struct drm_encoder *encoders[MAX_ENCODERS]; unsigned int num_bridges; - struct drm_bridge *bridges[8]; + struct drm_bridge *bridges[MAX_BRIDGES]; unsigned int num_connectors; - struct drm_connector *connectors[8]; + struct drm_connector *connectors[MAX_CONNECTORS]; /* Properties */ struct drm_property *plane_property[PLANE_PROP_MAX_NUM]; @@ -150,6 +225,7 @@ struct msm_drm_private { struct shrinker shrinker; struct msm_vblank_ctrl vblank_ctrl; + struct drm_atomic_state *pm_state; }; struct msm_format { @@ -174,6 +250,9 @@ struct msm_gem_address_space * msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain, const char *name); +int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu); +void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu); + void msm_gem_submit_free(struct msm_gem_submit *submit); int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file); @@ -285,6 +364,8 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, void __init msm_mdp_register(void); void __exit msm_mdp_unregister(void); +void __init msm_dpu_register(void); +void __exit msm_dpu_unregister(void); #ifdef CONFIG_DEBUG_FS void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 1c09acfb4028..f388944c93e2 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -20,10 +20,11 @@ #include "msm_mmu.h" #include "msm_fence.h" +#include <generated/utsrelease.h> #include <linux/string_helpers.h> #include <linux/pm_opp.h> #include <linux/devfreq.h> - +#include <linux/devcoredump.h> /* * Power Management: @@ -273,6 +274,123 @@ int msm_gpu_hw_init(struct msm_gpu *gpu) return ret; } +#ifdef CONFIG_DEV_COREDUMP +static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset, + size_t count, void *data, size_t datalen) +{ + struct msm_gpu *gpu = data; + struct drm_print_iterator iter; + struct drm_printer p; + struct msm_gpu_state *state; + + state = msm_gpu_crashstate_get(gpu); + if (!state) + return 0; + + iter.data = buffer; + iter.offset = 0; + iter.start = offset; + iter.remain = count; + + p = drm_coredump_printer(&iter); + + drm_printf(&p, "---\n"); + drm_printf(&p, "kernel: " UTS_RELEASE "\n"); + drm_printf(&p, "module: " KBUILD_MODNAME "\n"); + drm_printf(&p, "time: %lld.%09ld\n", + state->time.tv_sec, state->time.tv_nsec); + if (state->comm) + drm_printf(&p, "comm: %s\n", state->comm); + if (state->cmd) + drm_printf(&p, "cmdline: %s\n", state->cmd); + + gpu->funcs->show(gpu, state, &p); + + msm_gpu_crashstate_put(gpu); + + return count - iter.remain; +} + +static void msm_gpu_devcoredump_free(void *data) +{ + struct msm_gpu *gpu = data; + + msm_gpu_crashstate_put(gpu); +} + +static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state, + struct msm_gem_object *obj, u64 iova, u32 flags) +{ + struct msm_gpu_state_bo *state_bo = &state->bos[state->nr_bos]; + + /* Don't record write only objects */ + + state_bo->size = obj->base.size; + state_bo->iova = iova; + + /* Only store the data for buffer objects marked for read */ + if ((flags & MSM_SUBMIT_BO_READ)) { + void *ptr; + + state_bo->data = kvmalloc(obj->base.size, GFP_KERNEL); + if (!state_bo->data) + return; + + ptr = msm_gem_get_vaddr_active(&obj->base); + if (IS_ERR(ptr)) { + kvfree(state_bo->data); + return; + } + + memcpy(state_bo->data, ptr, obj->base.size); + msm_gem_put_vaddr(&obj->base); + } + + state->nr_bos++; +} + +static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, + struct msm_gem_submit *submit, char *comm, char *cmd) +{ + struct msm_gpu_state *state; + + /* Only save one crash state at a time */ + if (gpu->crashstate) + return; + + state = gpu->funcs->gpu_state_get(gpu); + if (IS_ERR_OR_NULL(state)) + return; + + /* Fill in the additional crash state information */ + state->comm = kstrdup(comm, GFP_KERNEL); + state->cmd = kstrdup(cmd, GFP_KERNEL); + + if (submit) { + int i; + + state->bos = kcalloc(submit->nr_bos, + sizeof(struct msm_gpu_state_bo), GFP_KERNEL); + + for (i = 0; state->bos && i < submit->nr_bos; i++) + msm_gpu_crashstate_get_bo(state, submit->bos[i].obj, + submit->bos[i].iova, submit->bos[i].flags); + } + + /* Set the active crash state to be dumped on failure */ + gpu->crashstate = state; + + /* FIXME: Release the crashstate if this errors out? */ + dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL, + msm_gpu_devcoredump_read, msm_gpu_devcoredump_free); +} +#else +static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm, + char *cmd) +{ +} +#endif + /* * Hangcheck detection for locked gpu: */ @@ -314,6 +432,7 @@ static void recover_worker(struct work_struct *work) struct msm_drm_private *priv = dev->dev_private; struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); + char *comm = NULL, *cmd = NULL; int i; mutex_lock(&dev->struct_mutex); @@ -327,7 +446,7 @@ static void recover_worker(struct work_struct *work) rcu_read_lock(); task = pid_task(submit->pid, PIDTYPE_PID); if (task) { - char *cmd; + comm = kstrdup(task->comm, GFP_ATOMIC); /* * So slightly annoying, in other paths like @@ -340,22 +459,28 @@ static void recover_worker(struct work_struct *work) * about the submit going away. */ mutex_unlock(&dev->struct_mutex); - cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL); + cmd = kstrdup_quotable_cmdline(task, GFP_ATOMIC); mutex_lock(&dev->struct_mutex); + } + rcu_read_unlock(); + if (comm && cmd) { dev_err(dev->dev, "%s: offending task: %s (%s)\n", - gpu->name, task->comm, cmd); + gpu->name, comm, cmd); msm_rd_dump_submit(priv->hangrd, submit, - "offending task: %s (%s)", task->comm, cmd); - - kfree(cmd); - } else { + "offending task: %s (%s)", comm, cmd); + } else msm_rd_dump_submit(priv->hangrd, submit, NULL); - } - rcu_read_unlock(); } + /* Record the crash state */ + pm_runtime_get_sync(&gpu->pdev->dev); + msm_gpu_crashstate_capture(gpu, submit, comm, cmd); + pm_runtime_put_sync(&gpu->pdev->dev); + + kfree(cmd); + kfree(comm); /* * Update all the rings with the latest and greatest fence.. this diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index b8241179175a..1c6105bc55c7 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -27,6 +27,7 @@ struct msm_gem_submit; struct msm_gpu_perfcntr; +struct msm_gpu_state; struct msm_gpu_config { const char *ioname; @@ -64,11 +65,14 @@ struct msm_gpu_funcs { void (*destroy)(struct msm_gpu *gpu); #ifdef CONFIG_DEBUG_FS /* show GPU status in debugfs: */ - void (*show)(struct msm_gpu *gpu, struct seq_file *m); + void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state, + struct drm_printer *p); /* for generation specific debugfs: */ int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor); #endif int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value); + struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu); + int (*gpu_state_put)(struct msm_gpu_state *state); }; struct msm_gpu { @@ -129,6 +133,8 @@ struct msm_gpu { u64 busy_cycles; ktime_t time; } devfreq; + + struct msm_gpu_state *crashstate; }; /* It turns out that all targets use the same ringbuffer size */ @@ -175,6 +181,38 @@ struct msm_gpu_submitqueue { struct kref ref; }; +struct msm_gpu_state_bo { + u64 iova; + size_t size; + void *data; +}; + +struct msm_gpu_state { + struct kref ref; + struct timespec64 time; + + struct { + u64 iova; + u32 fence; + u32 seqno; + u32 rptr; + u32 wptr; + void *data; + int data_size; + } ring[MSM_GPU_MAX_RINGS]; + + int nr_registers; + u32 *registers; + + u32 rbbm_status; + + char *comm; + char *cmd; + + int nr_bos; + struct msm_gpu_state_bo *bos; +}; + static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data) { msm_writel(data, gpu->mmio + (reg << 2)); @@ -254,4 +292,32 @@ static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue) kref_put(&queue->ref, msm_submitqueue_destroy); } +static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu) +{ + struct msm_gpu_state *state = NULL; + + mutex_lock(&gpu->dev->struct_mutex); + + if (gpu->crashstate) { + kref_get(&gpu->crashstate->ref); + state = gpu->crashstate; + } + + mutex_unlock(&gpu->dev->struct_mutex); + + return state; +} + +static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) +{ + mutex_lock(&gpu->dev->struct_mutex); + + if (gpu->crashstate) { + if (gpu->funcs->gpu_state_put(gpu->crashstate)) + gpu->crashstate = NULL; + } + + mutex_unlock(&gpu->dev->struct_mutex); +} + #endif /* __MSM_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index dfd92947de2c..fd88cebb6adb 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -1,4 +1,5 @@ /* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> * @@ -42,6 +43,7 @@ struct msm_kms_funcs { void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc); /* modeset, bracketing atomic_commit(): */ void (*prepare_commit)(struct msm_kms *kms, struct drm_atomic_state *state); + void (*commit)(struct msm_kms *kms, struct drm_atomic_state *state); void (*complete_commit)(struct msm_kms *kms, struct drm_atomic_state *state); /* functions to wait for atomic commit completed on each CRTC */ void (*wait_for_crtc_commit_done)(struct msm_kms *kms, @@ -50,6 +52,11 @@ struct msm_kms_funcs { const struct msm_format *(*get_format)(struct msm_kms *kms, const uint32_t format, const uint64_t modifiers); + /* do format checking on format modified through fb_cmd2 modifiers */ + int (*check_modified_format)(const struct msm_kms *kms, + const struct msm_format *msm_fmt, + const struct drm_mode_fb_cmd2 *cmd, + struct drm_gem_object **bos); /* misc: */ long (*round_pixclk)(struct msm_kms *kms, unsigned long rate, struct drm_encoder *encoder); @@ -60,6 +67,9 @@ struct msm_kms_funcs { void (*set_encoder_mode)(struct msm_kms *kms, struct drm_encoder *encoder, bool cmd_mode); + /* pm suspend/resume hooks */ + int (*pm_suspend)(struct device *dev); + int (*pm_resume)(struct device *dev); /* cleanup: */ void (*destroy)(struct msm_kms *kms); #ifdef CONFIG_DEBUG_FS @@ -86,9 +96,20 @@ static inline void msm_kms_init(struct msm_kms *kms, struct msm_kms *mdp4_kms_init(struct drm_device *dev); struct msm_kms *mdp5_kms_init(struct drm_device *dev); -int msm_mdss_init(struct drm_device *dev); -void msm_mdss_destroy(struct drm_device *dev); -int msm_mdss_enable(struct msm_mdss *mdss); -int msm_mdss_disable(struct msm_mdss *mdss); +struct msm_kms *dpu_kms_init(struct drm_device *dev); + +struct msm_mdss_funcs { + int (*enable)(struct msm_mdss *mdss); + int (*disable)(struct msm_mdss *mdss); + void (*destroy)(struct drm_device *dev); +}; + +struct msm_mdss { + struct drm_device *dev; + const struct msm_mdss_funcs *funcs; +}; + +int mdp5_mdss_init(struct drm_device *dev); +int dpu_mdss_init(struct drm_device *dev); #endif /* __MSM_KMS_H__ */ diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 501d2d290e9c..70dce544984e 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -55,6 +55,9 @@ nv04_display_create(struct drm_device *dev) nouveau_display(dev)->init = nv04_display_init; nouveau_display(dev)->fini = nv04_display_fini; + /* Pre-nv50 doesn't support atomic, so don't expose the ioctls */ + dev->driver->driver_features &= ~DRIVER_ATOMIC; + nouveau_hw_save_vga_fonts(dev, 1); nv04_crtc_create(dev, 0); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 0190377b02a6..8412119bd940 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1610,8 +1610,9 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe) *****************************************************************************/ static void -nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock) +nv50_disp_atomic_commit_core(struct drm_atomic_state *state, u32 *interlock) { + struct nouveau_drm *drm = nouveau_drm(state->dev); struct nv50_disp *disp = nv50_disp(drm->dev); struct nv50_core *core = disp->core; struct nv50_mstm *mstm; @@ -1643,6 +1644,22 @@ nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock) } static void +nv50_disp_atomic_commit_wndw(struct drm_atomic_state *state, u32 *interlock) +{ + struct drm_plane_state *new_plane_state; + struct drm_plane *plane; + int i; + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + struct nv50_wndw *wndw = nv50_wndw(plane); + if (interlock[wndw->interlock.type] & wndw->interlock.data) { + if (wndw->func->update) + wndw->func->update(wndw, interlock); + } + } +} + +static void nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; @@ -1709,7 +1726,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) help->disable(encoder); interlock[NV50_DISP_INTERLOCK_CORE] |= 1; if (outp->flush_disable) { - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_wndw(state, interlock); + nv50_disp_atomic_commit_core(state, interlock); memset(interlock, 0x00, sizeof(interlock)); } } @@ -1718,15 +1736,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) /* Flush disable. */ if (interlock[NV50_DISP_INTERLOCK_CORE]) { if (atom->flush_disable) { - for_each_new_plane_in_state(state, plane, new_plane_state, i) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (interlock[wndw->interlock.type] & wndw->interlock.data) { - if (wndw->func->update) - wndw->func->update(wndw, interlock); - } - } - - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_wndw(state, interlock); + nv50_disp_atomic_commit_core(state, interlock); memset(interlock, 0x00, sizeof(interlock)); } } @@ -1787,18 +1798,14 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) } /* Flush update. */ - for_each_new_plane_in_state(state, plane, new_plane_state, i) { - struct nv50_wndw *wndw = nv50_wndw(plane); - if (interlock[wndw->interlock.type] & wndw->interlock.data) { - if (wndw->func->update) - wndw->func->update(wndw, interlock); - } - } + nv50_disp_atomic_commit_wndw(state, interlock); if (interlock[NV50_DISP_INTERLOCK_CORE]) { if (interlock[NV50_DISP_INTERLOCK_BASE] || + interlock[NV50_DISP_INTERLOCK_OVLY] || + interlock[NV50_DISP_INTERLOCK_WNDW] || !atom->state.legacy_cursor_update) - nv50_disp_atomic_commit_core(drm, interlock); + nv50_disp_atomic_commit_core(state, interlock); else disp->core->func->update(disp->core, interlock, false); } @@ -1896,7 +1903,7 @@ nv50_disp_atomic_commit(struct drm_device *dev, nv50_disp_atomic_commit_tail(state); drm_for_each_crtc(crtc, dev) { - if (crtc->state->enable) { + if (crtc->state->active) { if (!drm->have_disp_power_ref) { drm->have_disp_power_ref = true; return 0; @@ -2144,10 +2151,6 @@ nv50_display_destroy(struct drm_device *dev) kfree(disp); } -MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)"); -static int nouveau_atomic = 0; -module_param_named(atomic, nouveau_atomic, int, 0400); - int nv50_display_create(struct drm_device *dev) { @@ -2172,8 +2175,6 @@ nv50_display_create(struct drm_device *dev) disp->disp = &nouveau_display(dev)->disp; dev->mode_config.funcs = &nv50_disp_func; dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP; - if (nouveau_atomic) - dev->driver->driver_features |= DRIVER_ATOMIC; /* small shared memory area we use for notifiers and semaphores */ ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM, diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index debbbf0fd4bd..408b955e5c39 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -267,6 +267,7 @@ nouveau_backlight_init(struct drm_device *dev) struct nouveau_drm *drm = nouveau_drm(dev); struct nvif_device *device = &drm->client.device; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; INIT_LIST_HEAD(&drm->bl_connectors); @@ -275,7 +276,8 @@ nouveau_backlight_init(struct drm_device *dev) return 0; } - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && connector->connector_type != DRM_MODE_CONNECTOR_eDP) continue; @@ -292,7 +294,7 @@ nouveau_backlight_init(struct drm_device *dev) break; } } - + drm_connector_list_iter_end(&conn_iter); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 22a15478d23d..51932c72334e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1193,14 +1193,19 @@ nouveau_connector_create(struct drm_device *dev, int index) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_connector *nv_connector = NULL; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; int type, ret = 0; bool dummy; - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { nv_connector = nouveau_connector(connector); - if (nv_connector->index == index) + if (nv_connector->index == index) { + drm_connector_list_iter_end(&conn_iter); return connector; + } } + drm_connector_list_iter_end(&conn_iter); nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL); if (!nv_connector) diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index a4d1a059bd3d..dc7454e7f19a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -33,6 +33,7 @@ #include <drm/drm_encoder.h> #include <drm/drm_dp_helper.h> #include "nouveau_crtc.h" +#include "nouveau_encoder.h" struct nvkm_i2c_port; @@ -60,19 +61,46 @@ static inline struct nouveau_connector *nouveau_connector( return container_of(con, struct nouveau_connector, base); } +static inline bool +nouveau_connector_is_mst(struct drm_connector *connector) +{ + const struct nouveau_encoder *nv_encoder; + const struct drm_encoder *encoder; + + if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort) + return false; + + nv_encoder = find_encoder(connector, DCB_OUTPUT_ANY); + if (!nv_encoder) + return false; + + encoder = &nv_encoder->base.base; + return encoder->encoder_type == DRM_MODE_ENCODER_DPMST; +} + +#define nouveau_for_each_non_mst_connector_iter(connector, iter) \ + drm_for_each_connector_iter(connector, iter) \ + for_each_if(!nouveau_connector_is_mst(connector)) + static inline struct nouveau_connector * nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc) { struct drm_device *dev = nv_crtc->base.dev; struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; + struct nouveau_connector *nv_connector = NULL; struct drm_crtc *crtc = to_drm_crtc(nv_crtc); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - if (connector->encoder && connector->encoder->crtc == crtc) - return nouveau_connector(connector); + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { + if (connector->encoder && connector->encoder->crtc == crtc) { + nv_connector = nouveau_connector(connector); + break; + } } + drm_connector_list_iter_end(&conn_iter); - return NULL; + return nv_connector; } struct drm_connector * diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index dfa236370726..139368b31916 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -404,6 +404,7 @@ nouveau_display_init(struct drm_device *dev) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; int ret; ret = disp->init(dev); @@ -411,10 +412,12 @@ nouveau_display_init(struct drm_device *dev) return ret; /* enable hotplug interrupts */ - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { struct nouveau_connector *conn = nouveau_connector(connector); nvif_notify_get(&conn->hpd); } + drm_connector_list_iter_end(&conn_iter); /* enable flip completion events */ nvif_notify_get(&drm->flip); @@ -427,6 +430,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); struct drm_connector *connector; + struct drm_connector_list_iter conn_iter; if (!suspend) { if (drm_drv_uses_atomic_modeset(dev)) @@ -439,10 +443,12 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) nvif_notify_put(&drm->flip); /* disable hotplug interrupts */ - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { struct nouveau_connector *conn = nouveau_connector(connector); nvif_notify_put(&conn->hpd); } + drm_connector_list_iter_end(&conn_iter); drm_kms_helper_poll_disable(dev); disp->fini(dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index c779ee3c665b..c7ec86d6c3c9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -81,6 +81,10 @@ MODULE_PARM_DESC(modeset, "enable driver (default: auto, " int nouveau_modeset = -1; module_param_named(modeset, nouveau_modeset, int, 0400); +MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)"); +static int nouveau_atomic = 0; +module_param_named(atomic, nouveau_atomic, int, 0400); + MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)"); static int nouveau_runtime_pm = -1; module_param_named(runpm, nouveau_runtime_pm, int, 0400); @@ -509,6 +513,9 @@ static int nouveau_drm_probe(struct pci_dev *pdev, pci_set_master(pdev); + if (nouveau_atomic) + driver_pci.driver_features |= DRIVER_ATOMIC; + ret = drm_get_pci_dev(pdev, pent, &driver_pci); if (ret) { nvkm_device_del(&device); @@ -874,22 +881,11 @@ nouveau_pmops_runtime_resume(struct device *dev) static int nouveau_pmops_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct drm_device *drm_dev = pci_get_drvdata(pdev); - struct nouveau_drm *drm = nouveau_drm(drm_dev); - struct drm_crtc *crtc; - if (!nouveau_pmops_runtime()) { pm_runtime_forbid(dev); return -EBUSY; } - list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) { - if (crtc->enabled) { - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); - return -EBUSY; - } - } pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); /* we don't want the main rpm_idle to call suspend - we want to autosuspend */ diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index df73bec354e8..b56524d343c3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -616,7 +616,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, struct nouveau_bo *nvbo; uint32_t data; - if (unlikely(r->bo_index > req->nr_buffers)) { + if (unlikely(r->bo_index >= req->nr_buffers)) { NV_PRINTK(err, cli, "reloc bo index invalid\n"); ret = -EINVAL; break; @@ -626,7 +626,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, if (b->presumed.valid) continue; - if (unlikely(r->reloc_bo_index > req->nr_buffers)) { + if (unlikely(r->reloc_bo_index >= req->nr_buffers)) { NV_PRINTK(err, cli, "reloc container bo index invalid\n"); ret = -EINVAL; break; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c index 73b5d46104bd..434d2fc5bb1c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c @@ -140,6 +140,9 @@ nvkm_fb_init(struct nvkm_subdev *subdev) if (fb->func->init) fb->func->init(fb); + if (fb->func->init_remapper) + fb->func->init_remapper(fb); + if (fb->func->init_page) { ret = fb->func->init_page(fb); if (WARN_ON(ret)) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c index dffe1f5e1071..8205ce436b3e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c @@ -37,6 +37,14 @@ gp100_fb_init_unkn(struct nvkm_fb *base) } void +gp100_fb_init_remapper(struct nvkm_fb *fb) +{ + struct nvkm_device *device = fb->subdev.device; + /* Disable address remapper. */ + nvkm_mask(device, 0x100c14, 0x00040000, 0x00000000); +} + +void gp100_fb_init(struct nvkm_fb *base) { struct gf100_fb *fb = gf100_fb(base); @@ -56,6 +64,7 @@ gp100_fb = { .dtor = gf100_fb_dtor, .oneinit = gf100_fb_oneinit, .init = gp100_fb_init, + .init_remapper = gp100_fb_init_remapper, .init_page = gm200_fb_init_page, .init_unkn = gp100_fb_init_unkn, .ram_new = gp100_ram_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c index b84b9861ef26..b4d74e815674 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c @@ -31,6 +31,7 @@ gp102_fb = { .dtor = gf100_fb_dtor, .oneinit = gf100_fb_oneinit, .init = gp100_fb_init, + .init_remapper = gp100_fb_init_remapper, .init_page = gm200_fb_init_page, .ram_new = gp100_ram_new, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index 2857f31466bf..1e4ad61c19e1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -11,6 +11,7 @@ struct nvkm_fb_func { u32 (*tags)(struct nvkm_fb *); int (*oneinit)(struct nvkm_fb *); void (*init)(struct nvkm_fb *); + void (*init_remapper)(struct nvkm_fb *); int (*init_page)(struct nvkm_fb *); void (*init_unkn)(struct nvkm_fb *); void (*intr)(struct nvkm_fb *); @@ -69,5 +70,6 @@ int gf100_fb_init_page(struct nvkm_fb *); int gm200_fb_init_page(struct nvkm_fb *); +void gp100_fb_init_remapper(struct nvkm_fb *); void gp100_fb_init_unkn(struct nvkm_fb *); #endif diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile index b04ea0f3da75..0eb38ac8e86e 100644 --- a/drivers/gpu/drm/sun4i/Makefile +++ b/drivers/gpu/drm/sun4i/Makefile @@ -32,7 +32,10 @@ obj-$(CONFIG_DRM_SUN4I) += sun4i-tcon.o obj-$(CONFIG_DRM_SUN4I) += sun4i_tv.o obj-$(CONFIG_DRM_SUN4I) += sun6i_drc.o -obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o sun4i-frontend.o +obj-$(CONFIG_DRM_SUN4I_BACKEND) += sun4i-backend.o +ifdef CONFIG_DRM_SUN4I_BACKEND +obj-$(CONFIG_DRM_SUN4I) += sun4i-frontend.o +endif obj-$(CONFIG_DRM_SUN4I_HDMI) += sun4i-drm-hdmi.o obj-$(CONFIG_DRM_SUN6I_DSI) += sun6i-dsi.o obj-$(CONFIG_DRM_SUN8I_DW_HDMI) += sun8i-drm-hdmi.o diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 776c1513e582..a2bd5876c633 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -398,7 +398,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, * unaligned offset is malformed and cause commands stream * corruption on the buffer address relocation. */ - if (offset & 3 || offset >= obj->gem.size) { + if (offset & 3 || offset > obj->gem.size) { err = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index 072582570a4f..e9e9b1ff678e 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -113,7 +113,7 @@ udl_fb_user_fb_create(struct drm_device *dev, struct drm_file *file, const struct drm_mode_fb_cmd2 *mode_cmd); -int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr, +int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr, const char *front, char **urb_buf_ptr, u32 byte_offset, u32 device_byte_offset, u32 byte_width, int *ident_ptr, int *sent_ptr); diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index 2ebdc6d5a76e..dbb62f6eb48a 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -90,7 +90,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y, int bytes_identical = 0; struct urb *urb; int aligned_x; - int bpp = fb->base.format->cpp[0]; + int log_bpp; + + BUG_ON(!is_power_of_2(fb->base.format->cpp[0])); + log_bpp = __ffs(fb->base.format->cpp[0]); if (!fb->active_16) return 0; @@ -125,19 +128,22 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y, for (i = y; i < y + height ; i++) { const int line_offset = fb->base.pitches[0] * i; - const int byte_offset = line_offset + (x * bpp); - const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp); - if (udl_render_hline(dev, bpp, &urb, + const int byte_offset = line_offset + (x << log_bpp); + const int dev_byte_offset = (fb->base.width * i + x) << log_bpp; + if (udl_render_hline(dev, log_bpp, &urb, (char *) fb->obj->vmapping, &cmd, byte_offset, dev_byte_offset, - width * bpp, + width << log_bpp, &bytes_identical, &bytes_sent)) goto error; } if (cmd > (char *) urb->transfer_buffer) { /* Send partial buffer remaining before exiting */ - int len = cmd - (char *) urb->transfer_buffer; + int len; + if (cmd < (char *) urb->transfer_buffer + urb->transfer_buffer_length) + *cmd++ = 0xAF; + len = cmd - (char *) urb->transfer_buffer; ret = udl_submit_urb(dev, urb, len); bytes_sent += len; } else @@ -146,7 +152,7 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y, error: atomic_add(bytes_sent, &udl->bytes_sent); atomic_add(bytes_identical, &udl->bytes_identical); - atomic_add(width*height*bpp, &udl->bytes_rendered); + atomic_add((width * height) << log_bpp, &udl->bytes_rendered); end_cycles = get_cycles(); atomic_add(((unsigned int) ((end_cycles - start_cycles) >> 10)), /* Kcycles */ @@ -172,7 +178,7 @@ static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) pos = (unsigned long)info->fix.smem_start + offset; - pr_notice("mmap() framebuffer addr:%lu size:%lu\n", + pr_debug("mmap() framebuffer addr:%lu size:%lu\n", pos, size); /* We don't want the framebuffer to be mapped encrypted */ @@ -218,7 +224,7 @@ static int udl_fb_open(struct fb_info *info, int user) struct fb_deferred_io *fbdefio; - fbdefio = kmalloc(sizeof(struct fb_deferred_io), GFP_KERNEL); + fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL); if (fbdefio) { fbdefio->delay = DL_DEFIO_WRITE_DELAY; @@ -230,7 +236,7 @@ static int udl_fb_open(struct fb_info *info, int user) } #endif - pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n", + pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d\n", info->node, user, info, ufbdev->fb_count); return 0; @@ -255,7 +261,7 @@ static int udl_fb_release(struct fb_info *info, int user) } #endif - pr_warn("released /dev/fb%d user=%d count=%d\n", + pr_debug("released /dev/fb%d user=%d count=%d\n", info->node, user, ufbdev->fb_count); return 0; diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index d518de8f496b..f455f095a146 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -170,25 +170,19 @@ static void udl_free_urb_list(struct drm_device *dev) struct list_head *node; struct urb_node *unode; struct urb *urb; - int ret; - unsigned long flags; DRM_DEBUG("Waiting for completes and freeing all render urbs\n"); /* keep waiting and freeing, until we've got 'em all */ while (count--) { + down(&udl->urbs.limit_sem); - /* Getting interrupted means a leak, but ok at shutdown*/ - ret = down_interruptible(&udl->urbs.limit_sem); - if (ret) - break; - - spin_lock_irqsave(&udl->urbs.lock, flags); + spin_lock_irq(&udl->urbs.lock); node = udl->urbs.list.next; /* have reserved one with sem */ list_del_init(node); - spin_unlock_irqrestore(&udl->urbs.lock, flags); + spin_unlock_irq(&udl->urbs.lock); unode = list_entry(node, struct urb_node, entry); urb = unode->urb; @@ -205,17 +199,22 @@ static void udl_free_urb_list(struct drm_device *dev) static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size) { struct udl_device *udl = dev->dev_private; - int i = 0; struct urb *urb; struct urb_node *unode; char *buf; + size_t wanted_size = count * size; spin_lock_init(&udl->urbs.lock); +retry: udl->urbs.size = size; INIT_LIST_HEAD(&udl->urbs.list); - while (i < count) { + sema_init(&udl->urbs.limit_sem, 0); + udl->urbs.count = 0; + udl->urbs.available = 0; + + while (udl->urbs.count * size < wanted_size) { unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL); if (!unode) break; @@ -231,11 +230,16 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size) } unode->urb = urb; - buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL, + buf = usb_alloc_coherent(udl->udev, size, GFP_KERNEL, &urb->transfer_dma); if (!buf) { kfree(unode); usb_free_urb(urb); + if (size > PAGE_SIZE) { + size /= 2; + udl_free_urb_list(dev); + goto retry; + } break; } @@ -246,16 +250,14 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size) list_add_tail(&unode->entry, &udl->urbs.list); - i++; + up(&udl->urbs.limit_sem); + udl->urbs.count++; + udl->urbs.available++; } - sema_init(&udl->urbs.limit_sem, i); - udl->urbs.count = i; - udl->urbs.available = i; - - DRM_DEBUG("allocated %d %d byte urbs\n", i, (int) size); + DRM_DEBUG("allocated %d %d byte urbs\n", udl->urbs.count, (int) size); - return i; + return udl->urbs.count; } struct urb *udl_get_urb(struct drm_device *dev) @@ -265,7 +267,6 @@ struct urb *udl_get_urb(struct drm_device *dev) struct list_head *entry; struct urb_node *unode; struct urb *urb = NULL; - unsigned long flags; /* Wait for an in-flight buffer to complete and get re-queued */ ret = down_timeout(&udl->urbs.limit_sem, GET_URB_TIMEOUT); @@ -276,14 +277,14 @@ struct urb *udl_get_urb(struct drm_device *dev) goto error; } - spin_lock_irqsave(&udl->urbs.lock, flags); + spin_lock_irq(&udl->urbs.lock); BUG_ON(list_empty(&udl->urbs.list)); /* reserved one with limit_sem */ entry = udl->urbs.list.next; list_del_init(entry); udl->urbs.available--; - spin_unlock_irqrestore(&udl->urbs.lock, flags); + spin_unlock_irq(&udl->urbs.lock); unode = list_entry(entry, struct urb_node, entry); urb = unode->urb; diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c index 5bcae7649795..7e37765cf5ac 100644 --- a/drivers/gpu/drm/udl/udl_modeset.c +++ b/drivers/gpu/drm/udl/udl_modeset.c @@ -243,7 +243,7 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc) memcpy(buf, udl->mode_buf, udl->mode_buf_len); retval = udl_submit_urb(dev, urb, udl->mode_buf_len); - DRM_INFO("write mode info %d\n", udl->mode_buf_len); + DRM_DEBUG("write mode info %d\n", udl->mode_buf_len); return retval; } @@ -366,7 +366,6 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc, { struct udl_framebuffer *ufb = to_udl_fb(fb); struct drm_device *dev = crtc->dev; - unsigned long flags; struct drm_framebuffer *old_fb = crtc->primary->fb; if (old_fb) { @@ -377,10 +376,10 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc, udl_handle_damage(ufb, 0, 0, fb->width, fb->height); - spin_lock_irqsave(&dev->event_lock, flags); + spin_lock_irq(&dev->event_lock); if (event) drm_crtc_send_vblank_event(crtc, event); - spin_unlock_irqrestore(&dev->event_lock, flags); + spin_unlock_irq(&dev->event_lock); crtc->primary->fb = fb; return 0; diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c index 0c87b1ac6b68..ce87661e544f 100644 --- a/drivers/gpu/drm/udl/udl_transfer.c +++ b/drivers/gpu/drm/udl/udl_transfer.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/fb.h> -#include <linux/prefetch.h> #include <asm/unaligned.h> #include <drm/drmP.h> @@ -51,9 +50,6 @@ static int udl_trim_hline(const u8 *bback, const u8 **bfront, int *width_bytes) int start = width; int end = width; - prefetch((void *) front); - prefetch((void *) back); - for (j = 0; j < width; j++) { if (back[j] != front[j]) { start = j; @@ -83,12 +79,12 @@ static inline u16 pixel32_to_be16(const uint32_t pixel) ((pixel >> 8) & 0xf800)); } -static inline u16 get_pixel_val16(const uint8_t *pixel, int bpp) +static inline u16 get_pixel_val16(const uint8_t *pixel, int log_bpp) { - u16 pixel_val16 = 0; - if (bpp == 2) + u16 pixel_val16; + if (log_bpp == 1) pixel_val16 = *(const uint16_t *)pixel; - else if (bpp == 4) + else pixel_val16 = pixel32_to_be16(*(const uint32_t *)pixel); return pixel_val16; } @@ -125,8 +121,9 @@ static void udl_compress_hline16( const u8 *const pixel_end, uint32_t *device_address_ptr, uint8_t **command_buffer_ptr, - const uint8_t *const cmd_buffer_end, int bpp) + const uint8_t *const cmd_buffer_end, int log_bpp) { + const int bpp = 1 << log_bpp; const u8 *pixel = *pixel_start_ptr; uint32_t dev_addr = *device_address_ptr; uint8_t *cmd = *command_buffer_ptr; @@ -139,8 +136,6 @@ static void udl_compress_hline16( const u8 *cmd_pixel_start, *cmd_pixel_end = NULL; uint16_t pixel_val16; - prefetchw((void *) cmd); /* pull in one cache line at least */ - *cmd++ = 0xaf; *cmd++ = 0x6b; *cmd++ = (uint8_t) ((dev_addr >> 16) & 0xFF); @@ -153,12 +148,11 @@ static void udl_compress_hline16( raw_pixels_count_byte = cmd++; /* we'll know this later */ raw_pixel_start = pixel; - cmd_pixel_end = pixel + (min(MAX_CMD_PIXELS + 1, - min((int)(pixel_end - pixel) / bpp, - (int)(cmd_buffer_end - cmd) / 2))) * bpp; + cmd_pixel_end = pixel + (min3(MAX_CMD_PIXELS + 1UL, + (unsigned long)(pixel_end - pixel) >> log_bpp, + (unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp); - prefetch_range((void *) pixel, (cmd_pixel_end - pixel) * bpp); - pixel_val16 = get_pixel_val16(pixel, bpp); + pixel_val16 = get_pixel_val16(pixel, log_bpp); while (pixel < cmd_pixel_end) { const u8 *const start = pixel; @@ -170,7 +164,7 @@ static void udl_compress_hline16( pixel += bpp; while (pixel < cmd_pixel_end) { - pixel_val16 = get_pixel_val16(pixel, bpp); + pixel_val16 = get_pixel_val16(pixel, log_bpp); if (pixel_val16 != repeating_pixel_val16) break; pixel += bpp; @@ -179,10 +173,10 @@ static void udl_compress_hline16( if (unlikely(pixel > start + bpp)) { /* go back and fill in raw pixel count */ *raw_pixels_count_byte = (((start - - raw_pixel_start) / bpp) + 1) & 0xFF; + raw_pixel_start) >> log_bpp) + 1) & 0xFF; /* immediately after raw data is repeat byte */ - *cmd++ = (((pixel - start) / bpp) - 1) & 0xFF; + *cmd++ = (((pixel - start) >> log_bpp) - 1) & 0xFF; /* Then start another raw pixel span */ raw_pixel_start = pixel; @@ -192,11 +186,14 @@ static void udl_compress_hline16( if (pixel > raw_pixel_start) { /* finalize last RAW span */ - *raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF; + *raw_pixels_count_byte = ((pixel - raw_pixel_start) >> log_bpp) & 0xFF; + } else { + /* undo unused byte */ + cmd--; } - *cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF; - dev_addr += ((pixel - cmd_pixel_start) / bpp) * 2; + *cmd_pixels_count_byte = ((pixel - cmd_pixel_start) >> log_bpp) & 0xFF; + dev_addr += ((pixel - cmd_pixel_start) >> log_bpp) * 2; } if (cmd_buffer_end <= MIN_RLX_CMD_BYTES + cmd) { @@ -219,19 +216,19 @@ static void udl_compress_hline16( * (that we can only write to, slowly, and can never read), and (optionally) * our shadow copy that tracks what's been sent to that hardware buffer. */ -int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr, +int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr, const char *front, char **urb_buf_ptr, u32 byte_offset, u32 device_byte_offset, u32 byte_width, int *ident_ptr, int *sent_ptr) { const u8 *line_start, *line_end, *next_pixel; - u32 base16 = 0 + (device_byte_offset / bpp) * 2; + u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2; struct urb *urb = *urb_ptr; u8 *cmd = *urb_buf_ptr; u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length; - BUG_ON(!(bpp == 2 || bpp == 4)); + BUG_ON(!(log_bpp == 1 || log_bpp == 2)); line_start = (u8 *) (front + byte_offset); next_pixel = line_start; @@ -241,7 +238,7 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr, udl_compress_hline16(&next_pixel, line_end, &base16, - (u8 **) &cmd, (u8 *) cmd_end, bpp); + (u8 **) &cmd, (u8 *) cmd_end, log_bpp); if (cmd >= cmd_end) { int len = cmd - (u8 *) urb->transfer_buffer; diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 37aa2ef33b21..6e728b825259 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -44,6 +44,7 @@ static void vkms_release(struct drm_device *dev) struct vkms_device *vkms = container_of(dev, struct vkms_device, drm); platform_device_unregister(vkms->platform); + drm_atomic_helper_shutdown(&vkms->drm); drm_mode_config_cleanup(&vkms->drm); drm_dev_fini(&vkms->drm); } diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index f1d5f76e9c33..d88073e7d22d 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -218,6 +218,9 @@ static int host1x_probe(struct platform_device *pdev) return err; } + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + goto skip_iommu; + host->group = iommu_group_get(&pdev->dev); if (host->group) { struct iommu_domain_geometry *geometry; diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index e2f4a4d93d20..527a1cddb14f 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -569,7 +569,8 @@ void host1x_job_unpin(struct host1x_job *job) for (i = 0; i < job->num_unpins; i++) { struct host1x_job_unpin_data *unpin = &job->unpins[i]; - if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) { + if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && + unpin->size && host->domain) { iommu_unmap(host->domain, job->addr_phys[i], unpin->size); free_iova(&host->iova, diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 48685cddbad1..474b00e19697 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -122,6 +122,8 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat) case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_NV61: return IPUV3_COLORSPACE_YUV; + case V4L2_PIX_FMT_XRGB32: + case V4L2_PIX_FMT_XBGR32: case V4L2_PIX_FMT_RGB32: case V4L2_PIX_FMT_BGR32: case V4L2_PIX_FMT_RGB24: @@ -190,6 +192,8 @@ int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat) return (24 * pixel_stride) >> 3; case V4L2_PIX_FMT_BGR32: case V4L2_PIX_FMT_RGB32: + case V4L2_PIX_FMT_XBGR32: + case V4L2_PIX_FMT_XRGB32: return (32 * pixel_stride) >> 3; default: break; @@ -1401,6 +1405,8 @@ static int ipu_probe(struct platform_device *pdev) return -ENODEV; ipu->id = of_alias_get_id(np, "ipu"); + if (ipu->id < 0) + ipu->id = 0; if (of_device_is_compatible(np, "fsl,imx6qp-ipu") && IS_ENABLED(CONFIG_DRM)) { diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c index 125721a7f8b6..a9d2501500a1 100644 --- a/drivers/gpu/ipu-v3/ipu-cpmem.c +++ b/drivers/gpu/ipu-v3/ipu-cpmem.c @@ -188,6 +188,12 @@ static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat) case V4L2_PIX_FMT_RGB32: /* R G B A <=> [32:0] A:B:G:R */ return DRM_FORMAT_XBGR8888; + case V4L2_PIX_FMT_XBGR32: + /* B G R X <=> [32:0] X:R:G:B */ + return DRM_FORMAT_XRGB8888; + case V4L2_PIX_FMT_XRGB32: + /* X R G B <=> [32:0] B:G:R:X */ + return DRM_FORMAT_BGRX8888; case V4L2_PIX_FMT_UYVY: return DRM_FORMAT_UYVY; case V4L2_PIX_FMT_YUYV: @@ -541,17 +547,17 @@ static const struct ipu_rgb def_bgra_16 = { #define Y_OFFSET(pix, x, y) ((x) + pix->width * (y)) #define U_OFFSET(pix, x, y) ((pix->width * pix->height) + \ - (pix->width * (y) / 4) + (x) / 2) + (pix->width * ((y) / 2) / 2) + (x) / 2) #define V_OFFSET(pix, x, y) ((pix->width * pix->height) + \ (pix->width * pix->height / 4) + \ - (pix->width * (y) / 4) + (x) / 2) + (pix->width * ((y) / 2) / 2) + (x) / 2) #define U2_OFFSET(pix, x, y) ((pix->width * pix->height) + \ (pix->width * (y) / 2) + (x) / 2) #define V2_OFFSET(pix, x, y) ((pix->width * pix->height) + \ (pix->width * pix->height / 2) + \ (pix->width * (y) / 2) + (x) / 2) #define UV_OFFSET(pix, x, y) ((pix->width * pix->height) + \ - (pix->width * (y) / 2) + (x)) + (pix->width * ((y) / 2)) + (x)) #define UV2_OFFSET(pix, x, y) ((pix->width * pix->height) + \ (pix->width * y) + (x)) @@ -787,6 +793,8 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image) break; case V4L2_PIX_FMT_RGB32: case V4L2_PIX_FMT_BGR32: + case V4L2_PIX_FMT_XRGB32: + case V4L2_PIX_FMT_XBGR32: offset = image->rect.left * 4 + image->rect.top * pix->bytesperline; break; diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c index 524a717ab28e..f4081962784c 100644 --- a/drivers/gpu/ipu-v3/ipu-image-convert.c +++ b/drivers/gpu/ipu-v3/ipu-image-convert.c @@ -227,6 +227,12 @@ static const struct ipu_image_pixfmt image_convert_formats[] = { .fourcc = V4L2_PIX_FMT_BGR32, .bpp = 32, }, { + .fourcc = V4L2_PIX_FMT_XRGB32, + .bpp = 32, + }, { + .fourcc = V4L2_PIX_FMT_XBGR32, + .bpp = 32, + }, { .fourcc = V4L2_PIX_FMT_YUYV, .bpp = 16, .uv_width_dec = 2, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index f858cc72011d..3942ee61bd1c 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1952,6 +1952,8 @@ static int hid_device_probe(struct device *dev) } hdev->io_started = false; + clear_bit(ffs(HID_STAT_REPROBED), &hdev->status); + if (!hdev->driver) { id = hid_match_device(hdev, hdrv); if (id == NULL) { @@ -2215,7 +2217,8 @@ static int __hid_bus_reprobe_drivers(struct device *dev, void *data) struct hid_device *hdev = to_hid_device(dev); if (hdev->driver == hdrv && - !hdrv->match(hdev, hid_ignore_special_drivers)) + !hdrv->match(hdev, hid_ignore_special_drivers) && + !test_and_set_bit(ffs(HID_STAT_REPROBED), &hdev->status)) return device_reprobe(dev); return 0; diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 8469b6964ff6..b48100236df8 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1154,6 +1154,8 @@ copy_rest: goto out; if (list->tail > list->head) { len = list->tail - list->head; + if (len > count) + len = count; if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) { ret = -EFAULT; @@ -1163,6 +1165,8 @@ copy_rest: list->head += len; } else { len = HID_DEBUG_BUFSIZE - list->head; + if (len > count) + len = count; if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) { ret = -EFAULT; @@ -1170,7 +1174,9 @@ copy_rest: } list->head = 0; ret += len; - goto copy_rest; + count -= len; + if (count > 0) + goto copy_rest; } } diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index c1652bb7bd15..eae0cb3ddec6 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -484,7 +484,7 @@ static void i2c_hid_get_input(struct i2c_hid *ihid) return; } - if ((ret_size > size) || (ret_size <= 2)) { + if ((ret_size > size) || (ret_size < 2)) { dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n", __func__, size, ret_size); return; diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index e3ce233f8bdc..23872d08308c 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -36,6 +36,7 @@ #include <linux/hiddev.h> #include <linux/compat.h> #include <linux/vmalloc.h> +#include <linux/nospec.h> #include "usbhid.h" #ifdef CONFIG_USB_DYNAMIC_MINORS @@ -469,10 +470,14 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, if (uref->field_index >= report->maxfield) goto inval; + uref->field_index = array_index_nospec(uref->field_index, + report->maxfield); field = report->field[uref->field_index]; if (uref->usage_index >= field->maxusage) goto inval; + uref->usage_index = array_index_nospec(uref->usage_index, + field->maxusage); uref->usage_code = field->usage[uref->usage_index].hid; @@ -499,6 +504,8 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, if (uref->field_index >= report->maxfield) goto inval; + uref->field_index = array_index_nospec(uref->field_index, + report->maxfield); field = report->field[uref->field_index]; @@ -753,6 +760,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (finfo.field_index >= report->maxfield) break; + finfo.field_index = array_index_nospec(finfo.field_index, + report->maxfield); field = report->field[finfo.field_index]; memset(&finfo, 0, sizeof(finfo)); @@ -797,6 +806,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (cinfo.index >= hid->maxcollection) break; + cinfo.index = array_index_nospec(cinfo.index, + hid->maxcollection); cinfo.type = hid->collection[cinfo.index].type; cinfo.usage = hid->collection[cinfo.index].usage; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 0bb44d0088ed..ad7afa74d365 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -3365,8 +3365,14 @@ void wacom_setup_device_quirks(struct wacom *wacom) if (features->type >= INTUOSHT && features->type <= BAMBOO_PT) features->device_type |= WACOM_DEVICETYPE_PAD; - features->x_max = 4096; - features->y_max = 4096; + if (features->type == INTUOSHT2) { + features->x_max = features->x_max / 10; + features->y_max = features->y_max / 10; + } + else { + features->x_max = 4096; + features->y_max = 4096; + } } else if (features->pktlen == WACOM_PKGLEN_BBTOUCH) { features->device_type |= WACOM_DEVICETYPE_PAD; diff --git a/drivers/i2c/busses/i2c-cht-wc.c b/drivers/i2c/busses/i2c-cht-wc.c index 44cffad43701..c4d176f5ed79 100644 --- a/drivers/i2c/busses/i2c-cht-wc.c +++ b/drivers/i2c/busses/i2c-cht-wc.c @@ -234,7 +234,8 @@ static const struct irq_chip cht_wc_i2c_irq_chip = { .name = "cht_wc_ext_chrg_irq_chip", }; -static const char * const bq24190_suppliers[] = { "fusb302-typec-source" }; +static const char * const bq24190_suppliers[] = { + "tcpm-source-psy-i2c-fusb302" }; static const struct property_entry bq24190_props[] = { PROPERTY_ENTRY_STRING_ARRAY("supplied-from", bq24190_suppliers), diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index 75d6ab177055..7379043711df 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) /* * It's not always possible to have 1 to 2 ratio when d=7, so fall back * to minimal possible clkh in this case. + * + * Note: + * CLKH is not allowed to be 0, in this case I2C clock is not generated + * at all */ - if (clk >= clkl + d) { + if (clk > clkl + d) { clkh = clk - clkl - d; clkl -= d; } else { - clkh = 0; + clkh = 1; clkl = clk - (d << 1); } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 0207e194f84b..498c5e891649 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx, goto err_desc; } + reinit_completion(&dma->cmd_complete); txdesc->callback = i2c_imx_dma_callback; txdesc->callback_param = i2c_imx; if (dma_submit_error(dmaengine_submit(txdesc))) { @@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx, * The first byte must be transmitted by the CPU. */ imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR); - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, if (result) return result; - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); - rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH); + rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER || PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) { diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 5e310efd9446..3c1c817f6968 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -32,6 +32,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <linux/slab.h> /* register offsets */ @@ -111,8 +112,9 @@ #define ID_ARBLOST (1 << 3) #define ID_NACK (1 << 4) /* persistent flags */ +#define ID_P_NO_RXDMA (1 << 30) /* HW forbids RXDMA sometimes */ #define ID_P_PM_BLOCKED (1 << 31) -#define ID_P_MASK ID_P_PM_BLOCKED +#define ID_P_MASK (ID_P_PM_BLOCKED | ID_P_NO_RXDMA) enum rcar_i2c_type { I2C_RCAR_GEN1, @@ -141,6 +143,8 @@ struct rcar_i2c_priv { struct dma_chan *dma_rx; struct scatterlist sg; enum dma_data_direction dma_direction; + + struct reset_control *rstc; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv) dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg), sg_dma_len(&priv->sg), priv->dma_direction); + /* Gen3 can only do one RXDMA per transfer and we just completed it */ + if (priv->devtype == I2C_RCAR_GEN3 && + priv->dma_direction == DMA_FROM_DEVICE) + priv->flags |= ID_P_NO_RXDMA; + priv->dma_direction = DMA_NONE; } @@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv) unsigned char *buf; int len; - /* Do not use DMA if it's not available or for messages < 8 bytes */ - if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE)) + /* Do various checks to see if DMA is feasible at all */ + if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) || + (read && priv->flags & ID_P_NO_RXDMA)) return; if (read) { @@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv) } } +/* I2C is a special case, we need to poll the status of a reset */ +static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv) +{ + int i, ret; + + ret = reset_control_reset(priv->rstc); + if (ret) + return ret; + + for (i = 0; i < LOOP_TIMEOUT; i++) { + ret = reset_control_status(priv->rstc); + if (ret == 0) + return 0; + udelay(1); + } + + return -ETIMEDOUT; +} + static int rcar_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) @@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, pm_runtime_get_sync(dev); + /* Gen3 needs a reset before allowing RXDMA once */ + if (priv->devtype == I2C_RCAR_GEN3) { + priv->flags |= ID_P_NO_RXDMA; + if (!IS_ERR(priv->rstc)) { + ret = rcar_i2c_do_reset(priv); + if (ret == 0) + priv->flags &= ~ID_P_NO_RXDMA; + } + } + rcar_i2c_init(priv); ret = rcar_i2c_bus_barrier(priv); @@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + if (priv->devtype == I2C_RCAR_GEN3) { + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (!IS_ERR(priv->rstc)) { + ret = reset_control_status(priv->rstc); + if (ret < 0) + priv->rstc = ERR_PTR(-ENOTSUPP); + } + } + /* Stay always active when multi-master to keep arbitration working */ if (of_property_read_bool(dev->of_node, "multi-master")) priv->flags |= ID_P_PM_BLOCKED; diff --git a/drivers/i2c/busses/i2c-stu300.c b/drivers/i2c/busses/i2c-stu300.c index e866c481bfc3..fce52bdab2b7 100644 --- a/drivers/i2c/busses/i2c-stu300.c +++ b/drivers/i2c/busses/i2c-stu300.c @@ -127,7 +127,7 @@ enum stu300_error { /* * The number of address send athemps tried before giving up. - * If the first one failes it seems like 5 to 8 attempts are required. + * If the first one fails it seems like 5 to 8 attempts are required. */ #define NUM_ADDR_RESEND_ATTEMPTS 12 diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 5fccd1f1bca8..797def5319f1 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -545,6 +545,14 @@ static int tegra_i2c_disable_packet_mode(struct tegra_i2c_dev *i2c_dev) { u32 cnfg; + /* + * NACK interrupt is generated before the I2C controller generates + * the STOP condition on the bus. So wait for 2 clock periods + * before disabling the controller so that the STOP condition has + * been delivered properly. + */ + udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate)); + cnfg = i2c_readl(i2c_dev, I2C_CNFG); if (cnfg & I2C_CNFG_PACKET_MODE_EN) i2c_writel(i2c_dev, cnfg & ~I2C_CNFG_PACKET_MODE_EN, I2C_CNFG); @@ -706,15 +714,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (likely(i2c_dev->msg_err == I2C_ERR_NONE)) return 0; - /* - * NACK interrupt is generated before the I2C controller generates - * the STOP condition on the bus. So wait for 2 clock periods - * before resetting the controller so that the STOP condition has - * been delivered properly. - */ - if (i2c_dev->msg_err == I2C_ERR_NO_ACK) - udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate)); - tegra_i2c_init(i2c_dev); if (i2c_dev->msg_err == I2C_ERR_NO_ACK) { if (msg->flags & I2C_M_IGNORE_NAK) diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 31d16ada6e7d..301285c54603 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -198,7 +198,16 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap) val = !val; bri->set_scl(adap, val); - ndelay(RECOVERY_NDELAY); + + /* + * If we can set SDA, we will always create STOP here to ensure + * the additional pulses will do no harm. This is achieved by + * letting SDA follow SCL half a cycle later. + */ + ndelay(RECOVERY_NDELAY / 2); + if (bri->set_sda) + bri->set_sda(adap, val); + ndelay(RECOVERY_NDELAY / 2); } /* check if recovery actually succeeded */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 3e90b6a1d9d2..cc06e8404e9b 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3488,8 +3488,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, struct ib_flow_attr *flow_attr; struct ib_qp *qp; struct ib_uflow_resources *uflow_res; + struct ib_uverbs_flow_spec_hdr *kern_spec; int err = 0; - void *kern_spec; void *ib_spec; int i; @@ -3538,8 +3538,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, if (!kern_flow_attr) return -ENOMEM; - memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr)); - err = ib_copy_from_udata(kern_flow_attr + 1, ucore, + *kern_flow_attr = cmd.flow_attr; + err = ib_copy_from_udata(&kern_flow_attr->flow_specs, ucore, cmd.flow_attr.size); if (err) goto err_free_attr; @@ -3559,6 +3559,11 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, goto err_uobj; } + if (qp->qp_type != IB_QPT_UD && qp->qp_type != IB_QPT_RAW_PACKET) { + err = -EINVAL; + goto err_put; + } + flow_attr = kzalloc(struct_size(flow_attr, flows, cmd.flow_attr.num_of_specs), GFP_KERNEL); if (!flow_attr) { @@ -3578,21 +3583,22 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, flow_attr->flags = kern_flow_attr->flags; flow_attr->size = sizeof(*flow_attr); - kern_spec = kern_flow_attr + 1; + kern_spec = kern_flow_attr->flow_specs; ib_spec = flow_attr + 1; for (i = 0; i < flow_attr->num_of_specs && - cmd.flow_attr.size > offsetof(struct ib_uverbs_flow_spec, reserved) && - cmd.flow_attr.size >= - ((struct ib_uverbs_flow_spec *)kern_spec)->size; i++) { - err = kern_spec_to_ib_spec(file->ucontext, kern_spec, ib_spec, - uflow_res); + cmd.flow_attr.size >= sizeof(*kern_spec) && + cmd.flow_attr.size >= kern_spec->size; + i++) { + err = kern_spec_to_ib_spec( + file->ucontext, (struct ib_uverbs_flow_spec *)kern_spec, + ib_spec, uflow_res); if (err) goto err_free; flow_attr->size += ((union ib_flow_spec *) ib_spec)->size; - cmd.flow_attr.size -= ((struct ib_uverbs_flow_spec *)kern_spec)->size; - kern_spec += ((struct ib_uverbs_flow_spec *) kern_spec)->size; + cmd.flow_attr.size -= kern_spec->size; + kern_spec = ((void *)kern_spec) + kern_spec->size; ib_spec += ((union ib_flow_spec *) ib_spec)->size; } if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) { diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 1445918e3239..7b76e6f81aeb 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -774,7 +774,7 @@ static int c4iw_set_page(struct ib_mr *ibmr, u64 addr) { struct c4iw_mr *mhp = to_c4iw_mr(ibmr); - if (unlikely(mhp->mpl_len == mhp->max_mpl_len)) + if (unlikely(mhp->mpl_len == mhp->attr.pbl_size)) return -ENOMEM; mhp->mpl[mhp->mpl_len++] = addr; diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 1a1a47ac53c6..f15c93102081 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -271,7 +271,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) lockdep_assert_held(&qp->s_lock); ps->s_txreq = get_txreq(ps->dev, qp); - if (IS_ERR(ps->s_txreq)) + if (!ps->s_txreq) goto bail_no_tx; if (priv->hdr_type == HFI1_PKT_TYPE_9B) { diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c index b7b671017e59..e254dcec6f64 100644 --- a/drivers/infiniband/hw/hfi1/uc.c +++ b/drivers/infiniband/hw/hfi1/uc.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -72,7 +72,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) int middle = 0; ps->s_txreq = get_txreq(ps->dev, qp); - if (IS_ERR(ps->s_txreq)) + if (!ps->s_txreq) goto bail_no_tx; if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) { diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 1ab332f1866e..70d39fc450a1 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2015, 2016 Intel Corporation. + * Copyright(c) 2015 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -503,7 +503,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps) u32 lid; ps->s_txreq = get_txreq(ps->dev, qp); - if (IS_ERR(ps->s_txreq)) + if (!ps->s_txreq) goto bail_no_tx; if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) { diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c index 873e48ea923f..c4ab2d5b4502 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.c +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c @@ -1,5 +1,5 @@ /* - * Copyright(c) 2016 - 2017 Intel Corporation. + * Copyright(c) 2016 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -94,7 +94,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev, struct rvt_qp *qp) __must_hold(&qp->s_lock) { - struct verbs_txreq *tx = ERR_PTR(-EBUSY); + struct verbs_txreq *tx = NULL; write_seqlock(&dev->txwait_lock); if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) { diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h index 729244c3086c..1c19bbc764b2 100644 --- a/drivers/infiniband/hw/hfi1/verbs_txreq.h +++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h @@ -1,5 +1,5 @@ /* - * Copyright(c) 2016 Intel Corporation. + * Copyright(c) 2016 - 2018 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. @@ -83,7 +83,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev, if (unlikely(!tx)) { /* call slow path to get the lock */ tx = __get_txreq(dev, qp); - if (IS_ERR(tx)) + if (!tx) return tx; } tx->qp = qp; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e3e330f59c2c..b3ba9a222550 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -6113,7 +6113,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); - if (MLX5_VPORT_MANAGER(mdev) && + if (MLX5_ESWITCH_MANAGER(mdev) && mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 0af7b7905550..f5de5adc9b1a 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -266,18 +266,24 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, desc_size = sizeof(struct mlx5_wqe_srq_next_seg) + srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg); - if (desc_size == 0 || srq->msrq.max_gs > desc_size) - return ERR_PTR(-EINVAL); + if (desc_size == 0 || srq->msrq.max_gs > desc_size) { + err = -EINVAL; + goto err_srq; + } desc_size = roundup_pow_of_two(desc_size); desc_size = max_t(size_t, 32, desc_size); - if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) - return ERR_PTR(-EINVAL); + if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) { + err = -EINVAL; + goto err_srq; + } srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) / sizeof(struct mlx5_wqe_data_seg); srq->msrq.wqe_shift = ilog2(desc_size); buf_size = srq->msrq.max * desc_size; - if (buf_size < desc_size) - return ERR_PTR(-EINVAL); + if (buf_size < desc_size) { + err = -EINVAL; + goto err_srq; + } in.type = init_attr->srq_type; if (pd->uobject) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 1f9cd7d8b7ad..f5ae24865355 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1346,6 +1346,8 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0611", 0 }, { "ELAN0612", 0 }, { "ELAN0618", 0 }, + { "ELAN061D", 0 }, + { "ELAN0622", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index b353d494ad40..136f6e7bf797 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), }, }, + { + /* Lenovo LaVie Z */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + }, + }, { } }; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e055d228bfb9..689ffe538370 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -142,7 +142,6 @@ config DMAR_TABLE config INTEL_IOMMU bool "Support for Intel IOMMU using DMA Remapping Devices" depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC) - select DMA_DIRECT_OPS select IOMMU_API select IOMMU_IOVA select NEED_DMA_MAP_STATE diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 14e4b3722428..115ff26e9ced 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -31,7 +31,6 @@ #include <linux/pci.h> #include <linux/dmar.h> #include <linux/dma-mapping.h> -#include <linux/dma-direct.h> #include <linux/mempool.h> #include <linux/memory.h> #include <linux/cpu.h> @@ -485,14 +484,37 @@ static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int intel_iommu_ecs = 1; +static int intel_iommu_pasid28; static int iommu_identity_mapping; #define IDENTMAP_ALL 1 #define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 -#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap)) -#define pasid_enabled(iommu) (ecs_enabled(iommu) && ecap_pasid(iommu->ecap)) +/* Broadwell and Skylake have broken ECS support — normal so-called "second + * level" translation of DMA requests-without-PASID doesn't actually happen + * unless you also set the NESTE bit in an extended context-entry. Which of + * course means that SVM doesn't work because it's trying to do nested + * translation of the physical addresses it finds in the process page tables, + * through the IOVA->phys mapping found in the "second level" page tables. + * + * The VT-d specification was retroactively changed to change the definition + * of the capability bits and pretend that Broadwell/Skylake never happened... + * but unfortunately the wrong bit was changed. It's ECS which is broken, but + * for some reason it was the PASID capability bit which was redefined (from + * bit 28 on BDW/SKL to bit 40 in future). + * + * So our test for ECS needs to eschew those implementations which set the old + * PASID capabiity bit 28, since those are the ones on which ECS is broken. + * Unless we are working around the 'pasid28' limitations, that is, by putting + * the device into passthrough mode for normal DMA and thus masking the bug. + */ +#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \ + (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap))) +/* PASID support is thus enabled if ECS is enabled and *either* of the old + * or new capability bits are set. */ +#define pasid_enabled(iommu) (ecs_enabled(iommu) && \ + (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap))) int intel_iommu_gfx_mapped; EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); @@ -555,6 +577,11 @@ static int __init intel_iommu_setup(char *str) printk(KERN_INFO "Intel-IOMMU: disable extended context table support\n"); intel_iommu_ecs = 0; + } else if (!strncmp(str, "pasid28", 7)) { + printk(KERN_INFO + "Intel-IOMMU: enable pre-production PASID support\n"); + intel_iommu_pasid28 = 1; + iommu_identity_mapping |= IDENTMAP_GFX; } else if (!strncmp(str, "tboot_noforce", 13)) { printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); @@ -3713,30 +3740,61 @@ static void *intel_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) { - void *vaddr; + struct page *page = NULL; + int order; - vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs); - if (iommu_no_mapping(dev) || !vaddr) - return vaddr; + size = PAGE_ALIGN(size); + order = get_order(size); - *dma_handle = __intel_map_single(dev, virt_to_phys(vaddr), - PAGE_ALIGN(size), DMA_BIDIRECTIONAL, - dev->coherent_dma_mask); - if (!*dma_handle) - goto out_free_pages; - return vaddr; + if (!iommu_no_mapping(dev)) + flags &= ~(GFP_DMA | GFP_DMA32); + else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) { + if (dev->coherent_dma_mask < DMA_BIT_MASK(32)) + flags |= GFP_DMA; + else + flags |= GFP_DMA32; + } + + if (gfpflags_allow_blocking(flags)) { + unsigned int count = size >> PAGE_SHIFT; + + page = dma_alloc_from_contiguous(dev, count, order, flags); + if (page && iommu_no_mapping(dev) && + page_to_phys(page) + size > dev->coherent_dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } + + if (!page) + page = alloc_pages(flags, order); + if (!page) + return NULL; + memset(page_address(page), 0, size); + + *dma_handle = __intel_map_single(dev, page_to_phys(page), size, + DMA_BIDIRECTIONAL, + dev->coherent_dma_mask); + if (*dma_handle) + return page_address(page); + if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT)) + __free_pages(page, order); -out_free_pages: - dma_direct_free(dev, size, vaddr, *dma_handle, attrs); return NULL; } static void intel_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs) { - if (!iommu_no_mapping(dev)) - intel_unmap(dev, dma_handle, PAGE_ALIGN(size)); - dma_direct_free(dev, size, vaddr, dma_handle, attrs); + int order; + struct page *page = virt_to_page(vaddr); + + size = PAGE_ALIGN(size); + order = get_order(size); + + intel_unmap(dev, dma_handle, size); + if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT)) + __free_pages(page, order); } static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist, diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 07ea6a48aac6..87107c995cb5 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -136,6 +136,7 @@ struct dm_writecache { struct dm_target *ti; struct dm_dev *dev; struct dm_dev *ssd_dev; + sector_t start_sector; void *memory_map; uint64_t memory_map_size; size_t metadata_sectors; @@ -293,6 +294,10 @@ static int persistent_memory_claim(struct dm_writecache *wc) } dax_read_unlock(id); + + wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT; + wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT; + return 0; err3: kvfree(pages); @@ -311,7 +316,7 @@ static int persistent_memory_claim(struct dm_writecache *wc) static void persistent_memory_release(struct dm_writecache *wc) { if (wc->memory_vmapped) - vunmap(wc->memory_map); + vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT)); } static struct page *persistent_memory_page(void *addr) @@ -359,7 +364,7 @@ static void *memory_data(struct dm_writecache *wc, struct wc_entry *e) static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e) { - return wc->metadata_sectors + + return wc->start_sector + wc->metadata_sectors + ((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT)); } @@ -471,6 +476,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc) if (unlikely(region.sector + region.count > wc->metadata_sectors)) region.count = wc->metadata_sectors - region.sector; + region.sector += wc->start_sector; atomic_inc(&endio.count); req.bi_op = REQ_OP_WRITE; req.bi_op_flags = REQ_SYNC; @@ -1946,14 +1952,6 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) } wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode); - if (WC_MODE_PMEM(wc)) { - r = persistent_memory_claim(wc); - if (r) { - ti->error = "Unable to map persistent memory for cache"; - goto bad; - } - } - /* * Parse the cache block size */ @@ -1982,7 +1980,16 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) while (opt_params) { string = dm_shift_arg(&as), opt_params--; - if (!strcasecmp(string, "high_watermark") && opt_params >= 1) { + if (!strcasecmp(string, "start_sector") && opt_params >= 1) { + unsigned long long start_sector; + string = dm_shift_arg(&as), opt_params--; + if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1) + goto invalid_optional; + wc->start_sector = start_sector; + if (wc->start_sector != start_sector || + wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT) + goto invalid_optional; + } else if (!strcasecmp(string, "high_watermark") && opt_params >= 1) { string = dm_shift_arg(&as), opt_params--; if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1) goto invalid_optional; @@ -2039,12 +2046,20 @@ invalid_optional: goto bad; } - if (!WC_MODE_PMEM(wc)) { + if (WC_MODE_PMEM(wc)) { + r = persistent_memory_claim(wc); + if (r) { + ti->error = "Unable to map persistent memory for cache"; + goto bad; + } + } else { struct dm_io_region region; struct dm_io_request req; size_t n_blocks, n_metadata_blocks; uint64_t n_bitmap_bits; + wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT; + bio_list_init(&wc->flush_list); wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush"); if (IS_ERR(wc->flush_thread)) { @@ -2097,7 +2112,7 @@ invalid_optional: } region.bdev = wc->ssd_dev->bdev; - region.sector = 0; + region.sector = wc->start_sector; region.count = wc->metadata_sectors; req.bi_op = REQ_OP_READ; req.bi_op_flags = REQ_SYNC; @@ -2265,7 +2280,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type, static struct target_type writecache_target = { .name = "writecache", - .version = {1, 0, 0}, + .version = {1, 1, 0}, .module = THIS_MODULE, .ctr = writecache_ctr, .dtr = writecache_dtr, diff --git a/drivers/md/md.c b/drivers/md/md.c index 29b0cd9ec951..994aed2f9dff 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5547,7 +5547,8 @@ int md_run(struct mddev *mddev) else pr_warn("md: personality for level %s is not loaded!\n", mddev->clevel); - return -EINVAL; + err = -EINVAL; + goto abort; } spin_unlock(&pers_lock); if (mddev->level != pers->level) { @@ -5560,7 +5561,8 @@ int md_run(struct mddev *mddev) pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ module_put(pers->owner); - return -EINVAL; + err = -EINVAL; + goto abort; } if (pers->sync_request) { @@ -5629,7 +5631,7 @@ int md_run(struct mddev *mddev) mddev->private = NULL; module_put(pers->owner); bitmap_destroy(mddev); - return err; + goto abort; } if (mddev->queue) { bool nonrot = true; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 478cf446827f..35bd3a62451b 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3893,6 +3893,13 @@ static int raid10_run(struct mddev *mddev) disk->rdev->saved_raid_disk < 0) conf->fullsync = 1; } + + if (disk->replacement && + !test_bit(In_sync, &disk->replacement->flags) && + disk->replacement->saved_raid_disk < 0) { + conf->fullsync = 1; + } + disk->recovery_disabled = mddev->recovery_disabled - 1; } diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 40826bba06b6..fcfab6635f9c 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -207,29 +207,19 @@ void lirc_bpf_free(struct rc_dev *rcdev) bpf_prog_array_free(rcdev->raw->progs); } -int lirc_prog_attach(const union bpf_attr *attr) +int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { - struct bpf_prog *prog; struct rc_dev *rcdev; int ret; if (attr->attach_flags) return -EINVAL; - prog = bpf_prog_get_type(attr->attach_bpf_fd, - BPF_PROG_TYPE_LIRC_MODE2); - if (IS_ERR(prog)) - return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); - if (IS_ERR(rcdev)) { - bpf_prog_put(prog); + if (IS_ERR(rcdev)) return PTR_ERR(rcdev); - } ret = lirc_bpf_attach(rcdev, prog); - if (ret) - bpf_prog_put(prog); put_device(&rcdev->dev); diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c index 753b1a698fc4..6b16946f9b05 100644 --- a/drivers/misc/cxl/api.c +++ b/drivers/misc/cxl/api.c @@ -103,15 +103,15 @@ static struct file *cxl_getfile(const char *name, d_instantiate(path.dentry, inode); file = alloc_file(&path, OPEN_FMODE(flags), fops); - if (IS_ERR(file)) - goto err_dput; + if (IS_ERR(file)) { + path_put(&path); + goto err_fs; + } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; return file; -err_dput: - path_put(&path); err_inode: iput(inode); err_fs: diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c index e05c3245930a..fa840666bdd1 100644 --- a/drivers/misc/ibmasm/ibmasmfs.c +++ b/drivers/misc/ibmasm/ibmasmfs.c @@ -507,35 +507,14 @@ static int remote_settings_file_close(struct inode *inode, struct file *file) static ssize_t remote_settings_file_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { void __iomem *address = (void __iomem *)file->private_data; - unsigned char *page; - int retval; int len = 0; unsigned int value; - - if (*offset < 0) - return -EINVAL; - if (count == 0 || count > 1024) - return 0; - if (*offset != 0) - return 0; - - page = (unsigned char *)__get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; + char lbuf[20]; value = readl(address); - len = sprintf(page, "%d\n", value); - - if (copy_to_user(buf, page, len)) { - retval = -EFAULT; - goto exit; - } - *offset += len; - retval = len; + len = snprintf(lbuf, sizeof(lbuf), "%d\n", value); -exit: - free_page((unsigned long)page); - return retval; + return simple_read_from_buffer(buf, count, offset, lbuf, len); } static ssize_t remote_settings_file_write(struct file *file, const char __user *ubuff, size_t count, loff_t *offset) diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index b0b8f18a85e3..6649f0d56d2f 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -310,8 +310,11 @@ int mei_irq_read_handler(struct mei_device *dev, if (&cl->link == &dev->file_list) { /* A message for not connected fixed address clients * should be silently discarded + * On power down client may be force cleaned, + * silently discard such messages */ - if (hdr_is_fixed(mei_hdr)) { + if (hdr_is_fixed(mei_hdr) || + dev->dev_state == MEI_DEV_POWER_DOWN) { mei_irq_discard_msg(dev, mei_hdr); ret = 0; goto reset_slots; diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index efd733472a35..56c6f79a5c5a 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -467,7 +467,7 @@ static int vmballoon_send_batched_lock(struct vmballoon *b, unsigned int num_pages, bool is_2m_pages, unsigned int *target) { unsigned long status; - unsigned long pfn = page_to_pfn(b->page); + unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page)); STATS_INC(b->stats.lock[is_2m_pages]); @@ -515,7 +515,7 @@ static bool vmballoon_send_batched_unlock(struct vmballoon *b, unsigned int num_pages, bool is_2m_pages, unsigned int *target) { unsigned long status; - unsigned long pfn = page_to_pfn(b->page); + unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page)); STATS_INC(b->stats.unlock[is_2m_pages]); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index ef05e0039378..2a833686784b 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -27,8 +27,8 @@ struct mmc_gpio { bool override_cd_active_level; irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id); char *ro_label; - char cd_label[0]; u32 cd_debounce_delay_ms; + char cd_label[]; }; static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 623f4d27fa01..80dc2fd6576c 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1065,8 +1065,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data) * It's used when HS400 mode is enabled. */ if (data->flags & MMC_DATA_WRITE && - !(host->timing != MMC_TIMING_MMC_HS400)) - return; + host->timing != MMC_TIMING_MMC_HS400) + goto disable; if (data->flags & MMC_DATA_WRITE) enable = SDMMC_CARD_WR_THR_EN; @@ -1074,7 +1074,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data) enable = SDMMC_CARD_RD_THR_EN; if (host->timing != MMC_TIMING_MMC_HS200 && - host->timing != MMC_TIMING_UHS_SDR104) + host->timing != MMC_TIMING_UHS_SDR104 && + host->timing != MMC_TIMING_MMC_HS400) goto disable; blksz_depth = blksz / (1 << host->data_shift); diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c index f7f9773d161f..d032bd63444d 100644 --- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c @@ -139,8 +139,7 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) { renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST, RST_RESERVED_BITS | val); - if (host->data && host->data->flags & MMC_DATA_READ) - clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags); + clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags); renesas_sdhi_internal_dmac_enable_dma(host, true); } @@ -164,17 +163,14 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, goto force_pio; /* This DMAC cannot handle if buffer is not 8-bytes alignment */ - if (!IS_ALIGNED(sg_dma_address(sg), 8)) { - dma_unmap_sg(&host->pdev->dev, sg, host->sg_len, - mmc_get_dma_dir(data)); - goto force_pio; - } + if (!IS_ALIGNED(sg_dma_address(sg), 8)) + goto force_pio_with_unmap; if (data->flags & MMC_DATA_READ) { dtran_mode |= DTRAN_MODE_CH_NUM_CH1; if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) && test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags)) - goto force_pio; + goto force_pio_with_unmap; } else { dtran_mode |= DTRAN_MODE_CH_NUM_CH0; } @@ -189,6 +185,9 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host, return; +force_pio_with_unmap: + dma_unmap_sg(&host->pdev->dev, sg, host->sg_len, mmc_get_dma_dir(data)); + force_pio: host->force_pio = true; renesas_sdhi_internal_dmac_enable_dma(host, false); diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d6aef70d34fa..4eb3d29ecde1 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -312,6 +312,15 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg) if (imx_data->socdata->flags & ESDHC_FLAG_HS400) val |= SDHCI_SUPPORT_HS400; + + /* + * Do not advertise faster UHS modes if there are no + * pinctrl states for 100MHz/200MHz. + */ + if (IS_ERR_OR_NULL(imx_data->pins_100mhz) || + IS_ERR_OR_NULL(imx_data->pins_200mhz)) + val &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50 + | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_HS400); } } @@ -1158,18 +1167,6 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, ESDHC_PINCTRL_STATE_100MHZ); imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl, ESDHC_PINCTRL_STATE_200MHZ); - if (IS_ERR(imx_data->pins_100mhz) || - IS_ERR(imx_data->pins_200mhz)) { - dev_warn(mmc_dev(host->mmc), - "could not get ultra high speed state, work on normal mode\n"); - /* - * fall back to not supporting uhs by specifying no - * 1.8v quirk - */ - host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V; - } - } else { - host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V; } /* call to generic mmc_of_parse to support additional capabilities */ diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index e7472590f2ed..8e7f3e35ee3d 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1446,6 +1446,7 @@ static int sunxi_mmc_runtime_resume(struct device *dev) sunxi_mmc_init_host(host); sunxi_mmc_set_bus_width(host, mmc->ios.bus_width); sunxi_mmc_set_clk(host, &mmc->ios); + enable_irq(host->irq); return 0; } @@ -1455,6 +1456,12 @@ static int sunxi_mmc_runtime_suspend(struct device *dev) struct mmc_host *mmc = dev_get_drvdata(dev); struct sunxi_mmc_host *host = mmc_priv(mmc); + /* + * When clocks are off, it's possible receiving + * fake interrupts, which will stall the system. + * Disabling the irq will prevent this. + */ + disable_irq(host->irq); sunxi_mmc_reset_host(host); sunxi_mmc_disable(host); diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index c3f7aaa5d18f..d7e10b36a0b9 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -926,10 +926,12 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to, if (ret) return ret; - if (f_pdata->use_direct_mode) + if (f_pdata->use_direct_mode) { memcpy_toio(cqspi->ahb_base + to, buf, len); - else + ret = cqspi_wait_idle(cqspi); + } else { ret = cqspi_indirect_write_execute(nor, to, buf, len); + } if (ret) return ret; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 98663c50ded0..4d5d01cb8141 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option) static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { - if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) { - netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", - newval->string); - /* disable arp monitoring */ - bond->params.arp_interval = 0; - /* set miimon to default value */ - bond->params.miimon = BOND_DEFAULT_MIIMON; - netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", - bond->params.miimon); + if (!bond_mode_uses_arp(newval->value)) { + if (bond->params.arp_interval) { + netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", + newval->string); + /* disable arp monitoring */ + bond->params.arp_interval = 0; + } + + if (!bond->params.miimon) { + /* set miimon to default value */ + bond->params.miimon = BOND_DEFAULT_MIIMON; + netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", + bond->params.miimon); + } } if (newval->value == BOND_MODE_ALB) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b397a33f3d32..9b449400376b 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv) int err; err = pm_runtime_get_sync(priv->device); - if (err) + if (err < 0) { pm_runtime_put_noidle(priv->device); + return err; + } - return err; + return 0; } static void m_can_clk_stop(struct m_can_priv *priv) @@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev) } else { /* Version 3.1.x or 3.2.x */ - cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE); + cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE | + CCCR_NISO); /* Only 3.2.x has NISO Bit implemented */ if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) @@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev) priv->can.clock.freq = clk_get_rate(cclk); priv->mram_base = mram_addr; - m_can_of_parse_mram(priv, mram_config_vals); - platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); @@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev) goto clk_disable; } + m_can_of_parse_mram(priv, mram_config_vals); + devm_can_led_init(dev); of_can_transceiver(dev); @@ -1687,8 +1690,6 @@ failed_ret: return ret; } -/* TODO: runtime PM with power down or sleep mode */ - static __maybe_unused int m_can_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); @@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - m_can_init_ram(priv); - priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { @@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev) if (ret) return ret; + m_can_init_ram(priv); m_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index c7427bdd3a4b..2949a381a94d 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev, return 0; } cdm = of_iomap(np_cdm, 0); + if (!cdm) { + of_node_put(np_cdm); + dev_err(&ofdev->dev, "can't map clock node!\n"); + return 0; + } if (in_8(&cdm->ipb_clk_sel) & 0x1) freq *= 2; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index b9e28578bc7b..455a3797a200 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2"); #define PCIEFD_REG_SYS_VER1 0x0040 /* version reg #1 */ #define PCIEFD_REG_SYS_VER2 0x0044 /* version reg #2 */ +#define PCIEFD_FW_VERSION(x, y, z) (((u32)(x) << 24) | \ + ((u32)(y) << 16) | \ + ((u32)(z) << 8)) + /* System Control Registers Bits */ #define PCIEFD_SYS_CTL_TS_RST 0x00000001 /* timestamp clock */ #define PCIEFD_SYS_CTL_CLK_EN 0x00000002 /* system clock */ @@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev, "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count, hw_ver_major, hw_ver_minor, hw_ver_sub); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + /* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and + * 64-bit logical addresses: this workaround forces usage of 32-bit + * DMA addresses only when such a fw is detected. + */ + if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) < + PCIEFD_FW_VERSION(3, 3, 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + dev_warn(&pdev->dev, + "warning: can't set DMA mask %llxh (err %d)\n", + DMA_BIT_MASK(32), err); + } +#endif + /* stop system clock */ pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN, PCIEFD_REG_SYS_CTL_CLR); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 89aec07c225f..5a24039733ef 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -2,6 +2,7 @@ * * Copyright (C) 2012 - 2014 Xilinx, Inc. * Copyright (C) 2009 PetaLogix. All rights reserved. + * Copyright (C) 2017 Sandvik Mining and Construction Oy * * Description: * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. @@ -25,8 +26,10 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/skbuff.h> +#include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/can/dev.h> @@ -101,7 +104,7 @@ enum xcan_reg { #define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK) + XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK) /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ @@ -118,6 +121,7 @@ enum xcan_reg { /** * struct xcan_priv - This definition define CAN driver instance * @can: CAN private data structure. + * @tx_lock: Lock for synchronizing TX interrupt handling * @tx_head: Tx CAN packets ready to send on the queue * @tx_tail: Tx CAN packets successfully sended on the queue * @tx_max: Maximum number packets the driver can send @@ -132,6 +136,7 @@ enum xcan_reg { */ struct xcan_priv { struct can_priv can; + spinlock_t tx_lock; unsigned int tx_head; unsigned int tx_tail; unsigned int tx_max; @@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +#define XCAN_CAP_WATERMARK 0x0001 +struct xcan_devtype_data { + unsigned int caps; +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev) usleep_range(500, 10000); } + /* reset clears FIFOs */ + priv->tx_head = 0; + priv->tx_tail = 0; + return 0; } @@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf = (struct can_frame *)skb->data; u32 id, dlc, data[2] = {0, 0}; + unsigned long flags; if (can_dropped_invalid_skb(ndev, skb)) return NETDEV_TX_OK; @@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); + + spin_lock_irqsave(&priv->tx_lock, flags); + priv->tx_head++; /* Write the Frame to Xilinx CAN TX FIFO */ @@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) stats->tx_bytes += cf->can_dlc; } + /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */ + if (priv->tx_max > 1) + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK); + /* Check if the TX buffer is full */ if ((priv->tx_head - priv->tx_tail) == priv->tx_max) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return NETDEV_TX_OK; } @@ -530,6 +554,123 @@ static int xcan_rx(struct net_device *ndev) } /** + * xcan_current_error_state - Get current error state from HW + * @ndev: Pointer to net_device structure + * + * Checks the current CAN error state from the HW. Note that this + * only checks for ERROR_PASSIVE and ERROR_WARNING. + * + * Return: + * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE + * otherwise. + */ +static enum can_state xcan_current_error_state(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 status = priv->read_reg(priv, XCAN_SR_OFFSET); + + if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) + return CAN_STATE_ERROR_PASSIVE; + else if (status & XCAN_SR_ERRWRN_MASK) + return CAN_STATE_ERROR_WARNING; + else + return CAN_STATE_ERROR_ACTIVE; +} + +/** + * xcan_set_error_state - Set new CAN error state + * @ndev: Pointer to net_device structure + * @new_state: The new CAN state to be set + * @cf: Error frame to be populated or NULL + * + * Set new CAN error state for the device, updating statistics and + * populating the error frame if given. + */ +static void xcan_set_error_state(struct net_device *ndev, + enum can_state new_state, + struct can_frame *cf) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET); + u32 txerr = ecr & XCAN_ECR_TEC_MASK; + u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT; + + priv->can.state = new_state; + + if (cf) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[6] = txerr; + cf->data[7] = rxerr; + } + + switch (new_state) { + case CAN_STATE_ERROR_PASSIVE: + priv->can.can_stats.error_passive++; + if (cf) + cf->data[1] = (rxerr > 127) ? + CAN_ERR_CRTL_RX_PASSIVE : + CAN_ERR_CRTL_TX_PASSIVE; + break; + case CAN_STATE_ERROR_WARNING: + priv->can.can_stats.error_warning++; + if (cf) + cf->data[1] |= (txerr > rxerr) ? + CAN_ERR_CRTL_TX_WARNING : + CAN_ERR_CRTL_RX_WARNING; + break; + case CAN_STATE_ERROR_ACTIVE: + if (cf) + cf->data[1] |= CAN_ERR_CRTL_ACTIVE; + break; + default: + /* non-ERROR states are handled elsewhere */ + WARN_ON(1); + break; + } +} + +/** + * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX + * @ndev: Pointer to net_device structure + * + * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if + * the performed RX/TX has caused it to drop to a lesser state and set + * the interface state accordingly. + */ +static void xcan_update_error_state_after_rxtx(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + enum can_state old_state = priv->can.state; + enum can_state new_state; + + /* changing error state due to successful frame RX/TX can only + * occur from these states + */ + if (old_state != CAN_STATE_ERROR_WARNING && + old_state != CAN_STATE_ERROR_PASSIVE) + return; + + new_state = xcan_current_error_state(ndev); + + if (new_state != old_state) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(ndev, &cf); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); + + if (skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } + } +} + +/** * xcan_err_interrupt - error frame Isr * @ndev: net_device pointer * @isr: interrupt status register value @@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; - u32 err_status, status, txerr = 0, rxerr = 0; + u32 err_status; skb = alloc_can_err_skb(ndev, &cf); err_status = priv->read_reg(priv, XCAN_ESR_OFFSET); priv->write_reg(priv, XCAN_ESR_OFFSET, err_status); - txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK; - rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) & - XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT); - status = priv->read_reg(priv, XCAN_SR_OFFSET); if (isr & XCAN_IXR_BSOFF_MASK) { priv->can.state = CAN_STATE_BUS_OFF; @@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) can_bus_off(ndev); if (skb) cf->can_id |= CAN_ERR_BUSOFF; - } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - priv->can.can_stats.error_passive++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (rxerr > 127) ? - CAN_ERR_CRTL_RX_PASSIVE : - CAN_ERR_CRTL_TX_PASSIVE; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - priv->can.can_stats.error_warning++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] |= (txerr > rxerr) ? - CAN_ERR_CRTL_TX_WARNING : - CAN_ERR_CRTL_RX_WARNING; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } + } else { + enum can_state new_state = xcan_current_error_state(ndev); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); } /* Check for Arbitration lost interrupt */ @@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) if (isr & XCAN_IXR_RXOFLW_MASK) { stats->rx_over_errors++; stats->rx_errors++; - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); if (skb) { cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; @@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) { - if (isr & XCAN_IXR_RXOK_MASK) { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXOK_MASK); - work_done += xcan_rx(ndev); - } else { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXNEMP_MASK); - break; - } + work_done += xcan_rx(ndev); priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK); isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - if (work_done) + if (work_done) { can_led_event(ndev, CAN_LED_EVENT_RX); + xcan_update_error_state_after_rxtx(ndev); + } if (work_done < quota) { napi_complete_done(napi, work_done); ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK); + ier |= XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); } return work_done; @@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + unsigned int frames_in_fifo; + int frames_sent = 1; /* TXOK => at least 1 frame was sent */ + unsigned long flags; + int retries = 0; + + /* Synchronize with xmit as we need to know the exact number + * of frames in the FIFO to stay in sync due to the TXFEMP + * handling. + * This also prevents a race between netif_wake_queue() and + * netif_stop_queue(). + */ + spin_lock_irqsave(&priv->tx_lock, flags); + + frames_in_fifo = priv->tx_head - priv->tx_tail; + + if (WARN_ON_ONCE(frames_in_fifo == 0)) { + /* clear TXOK anyway to avoid getting back here */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return; + } + + /* Check if 2 frames were sent (TXOK only means that at least 1 + * frame was sent). + */ + if (frames_in_fifo > 1) { + WARN_ON(frames_in_fifo > priv->tx_max); + + /* Synchronize TXOK and isr so that after the loop: + * (1) isr variable is up-to-date at least up to TXOK clear + * time. This avoids us clearing a TXOK of a second frame + * but not noticing that the FIFO is now empty and thus + * marking only a single frame as sent. + * (2) No TXOK is left. Having one could mean leaving a + * stray TXOK as we might process the associated frame + * via TXFEMP handling as we read TXFEMP *after* TXOK + * clear to satisfy (1). + */ + while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + } - while ((priv->tx_head - priv->tx_tail > 0) && - (isr & XCAN_IXR_TXOK_MASK)) { + if (isr & XCAN_IXR_TXFEMP_MASK) { + /* nothing in FIFO anymore */ + frames_sent = frames_in_fifo; + } + } else { + /* single frame in fifo, just clear TXOK */ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + } + + while (frames_sent--) { can_get_echo_skb(ndev, priv->tx_tail % priv->tx_max); priv->tx_tail++; stats->tx_packets++; - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - can_led_event(ndev, CAN_LED_EVENT_TX); + netif_wake_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + + can_led_event(ndev, CAN_LED_EVENT_TX); + xcan_update_error_state_after_rxtx(ndev); } /** @@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct xcan_priv *priv = netdev_priv(ndev); u32 isr, ier; + u32 isr_errors; /* Get the interrupt status from Xilinx CAN */ isr = priv->read_reg(priv, XCAN_ISR_OFFSET); @@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) xcan_tx_interrupt(ndev, isr); /* Check for the type of error interrupt and Processing it */ - if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | - XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK | - XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK | - XCAN_IXR_ARBLST_MASK)); + isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK); + if (isr_errors) { + priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors); xcan_err_interrupt(ndev, isr); } /* Check for the type of receive interrupt and Processing it */ - if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) { + if (isr & XCAN_IXR_RXNEMP_MASK) { ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK); + ier &= ~XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); napi_schedule(&priv->napi); } @@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) static void xcan_chip_stop(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 ier; /* Disable interrupts and leave the can in configuration mode */ - ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~XCAN_INTR_ALL; - priv->write_reg(priv, XCAN_IER_OFFSET, ier); - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); + set_reset_mode(ndev); priv->can.state = CAN_STATE_STOPPED; } @@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = { */ static int __maybe_unused xcan_suspend(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_suspend(dev); + struct net_device *ndev = dev_get_drvdata(dev); - return 0; + if (netif_running(ndev)) { + netif_stop_queue(ndev); + netif_device_detach(ndev); + xcan_chip_stop(ndev); + } + + return pm_runtime_force_suspend(dev); } /** @@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev) */ static int __maybe_unused xcan_resume(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_resume(dev); + struct net_device *ndev = dev_get_drvdata(dev); + int ret; - return 0; + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } + + if (netif_running(ndev)) { + ret = xcan_chip_start(ndev); + if (ret) { + dev_err(dev, "xcan_chip_start failed on resume\n"); + return ret; + } + + netif_device_attach(ndev); + netif_start_queue(ndev); + } + return 0; } /** @@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } - - priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK); - priv->can.state = CAN_STATE_SLEEPING; - clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); @@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); int ret; - u32 isr, status; ret = clk_prepare_enable(priv->bus_clk); if (ret) { @@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) return ret; } - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - status = priv->read_reg(priv, XCAN_SR_OFFSET); - - if (netif_running(ndev)) { - if (isr & XCAN_IXR_BSOFF_MASK) { - priv->can.state = CAN_STATE_BUS_OFF; - priv->write_reg(priv, XCAN_SRR_OFFSET, - XCAN_SRR_RESET_MASK); - } else if ((status & XCAN_SR_ESTAT_MASK) == - XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - } else { - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - netif_device_attach(ndev); - netif_start_queue(ndev); - } - return 0; } @@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL) }; +static const struct xcan_devtype_data xcan_zynq_data = { + .caps = XCAN_CAP_WATERMARK, +}; + +/* Match table for OF platform binding */ +static const struct of_device_id xcan_of_match[] = { + { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data }, + { .compatible = "xlnx,axi-can-1.00.a", }, + { /* end of list */ }, +}; +MODULE_DEVICE_TABLE(of, xcan_of_match); + /** * xcan_probe - Platform registration call * @pdev: Handle to the platform device structure @@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev) struct resource *res; /* IO mem resources */ struct net_device *ndev; struct xcan_priv *priv; + const struct of_device_id *of_id; + int caps = 0; void __iomem *addr; - int ret, rx_max, tx_max; + int ret, rx_max, tx_max, tx_fifo_depth; /* Get the virtual base address for the device */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max); + ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", + &tx_fifo_depth); if (ret < 0) goto err; @@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev) if (ret < 0) goto err; + of_id = of_match_device(xcan_of_match, &pdev->dev); + if (of_id) { + const struct xcan_devtype_data *devtype_data = of_id->data; + + if (devtype_data) + caps = devtype_data->caps; + } + + /* There is no way to directly figure out how many frames have been + * sent when the TXOK interrupt is processed. If watermark programming + * is supported, we can have 2 frames in the FIFO and use TXFEMP + * to determine if 1 or 2 frames have been sent. + * Theoretically we should be able to use TXFWMEMP to determine up + * to 3 frames, but it seems that after putting a second frame in the + * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less + * than 2 frames in FIFO) is set anyway with no TXOK (a frame was + * sent), which is not a sensible state - possibly TXFWMEMP is not + * completely synchronized with the rest of the bits? + */ + if (caps & XCAN_CAP_WATERMARK) + tx_max = min(tx_fifo_depth, 2); + else + tx_max = 1; + /* Create a CAN device instance */ ndev = alloc_candev(sizeof(struct xcan_priv), tx_max); if (!ndev) @@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev) CAN_CTRLMODE_BERR_REPORTING; priv->reg_base = addr; priv->tx_max = tx_max; + spin_lock_init(&priv->tx_lock); /* Get IRQ for the device */ ndev->irq = platform_get_irq(pdev, 0); @@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); - netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n", + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, - priv->tx_max); + tx_fifo_depth, priv->tx_max); return 0; @@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev) return 0; } -/* Match table for OF platform binding */ -static const struct of_device_id xcan_of_match[] = { - { .compatible = "xlnx,zynq-can-1.0", }, - { .compatible = "xlnx,axi-can-1.00.a", }, - { /* end of list */ }, -}; -MODULE_DEVICE_TABLE(of, xcan_of_match); - static struct platform_driver xcan_driver = { .probe = xcan_probe, .remove = xcan_remove, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 437cd6eb4faa..9ef07a06aceb 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; +/* To be called with reg_lock held */ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; @@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - + /* + * free_irq must be called without reg_lock taken because the irq + * handler takes this lock, too. + */ free_irq(chip->irq, chip); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) @@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - kthread_cancel_delayed_work_sync(&chip->irq_poll_work); kthread_destroy_worker(chip->kworker); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) @@ -4506,12 +4515,10 @@ out_g2_irq: if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); out: if (pdata) dev_put(pdata->netdev); @@ -4539,12 +4546,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); } static const struct of_device_id mv88e6xxx_of_match[] = { diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 5b7658bcf020..5c3ef9fc8207 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -32,7 +32,7 @@ config EL3 config 3C515 tristate "3c515 ISA \"Fast EtherLink\"" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !PPC32 ---help--- If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet network card, say Y here. diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index f273af136fc7..9e5cf5583c87 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -44,7 +44,7 @@ config AMD8111_ETH config LANCE tristate "AMD LANCE and PCnet (AT1500 and NE2100) support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. Some LinkSys cards are of this type. @@ -138,7 +138,7 @@ config PCMCIA_NMCLAN config NI65 tristate "NI6510 support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index fc7383106946..91eb8910b1c9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -63,8 +63,6 @@ #define AQ_CFG_NAPI_WEIGHT 64U -#define AQ_CFG_MULTICAST_ADDRESS_MAX 32U - /*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/ #define AQ_NIC_FC_OFF 0U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index a2d416b24ffc..2c6ebd91a9f2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -98,6 +98,8 @@ struct aq_stats_s { #define AQ_HW_MEDIA_TYPE_TP 1U #define AQ_HW_MEDIA_TYPE_FIBRE 2U +#define AQ_HW_MULTICAST_ADDRESS_MAX 32U + struct aq_hw_s { atomic_t flags; u8 rbl_enabled:1; @@ -177,7 +179,7 @@ struct aq_hw_ops { unsigned int packet_filter); int (*hw_multicast_list_set)(struct aq_hw_s *self, - u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX] + u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index ba5fe8c4125d..e3ae29e523f0 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -135,17 +135,10 @@ err_exit: static void aq_ndev_set_multicast_settings(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); - int err = 0; - err = aq_nic_set_packet_filter(aq_nic, ndev->flags); - if (err < 0) - return; + aq_nic_set_packet_filter(aq_nic, ndev->flags); - if (netdev_mc_count(ndev)) { - err = aq_nic_set_multicast_list(aq_nic, ndev); - if (err < 0) - return; - } + aq_nic_set_multicast_list(aq_nic, ndev); } static const struct net_device_ops aq_ndev_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 1a1a6380c128..7a22d0257e04 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -563,34 +563,41 @@ err_exit: int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) { + unsigned int packet_filter = self->packet_filter; struct netdev_hw_addr *ha = NULL; unsigned int i = 0U; - self->mc_list.count = 0U; - - netdev_for_each_mc_addr(ha, ndev) { - ether_addr_copy(self->mc_list.ar[i++], ha->addr); - ++self->mc_list.count; + self->mc_list.count = 0; + if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_PROMISC; + } else { + netdev_for_each_uc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], ha->addr); - if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) - break; + if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) + break; + } } - if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) { - /* Number of filters is too big: atlantic does not support this. - * Force all multi filter to support this. - * With this we disable all UC filters and setup "all pass" - * multicast mask - */ - self->packet_filter |= IFF_ALLMULTI; - self->aq_nic_cfg.mc_list_count = 0; - return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw, - self->packet_filter); + if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_ALLMULTI; } else { - return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + netdev_for_each_mc_addr(ha, ndev) { + ether_addr_copy(self->mc_list.ar[i++], ha->addr); + + if (i >= AQ_HW_MULTICAST_ADDRESS_MAX) + break; + } + } + + if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) { + packet_filter |= IFF_MULTICAST; + self->mc_list.count = i; + self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, + self->mc_list.ar, + self->mc_list.count); } + return aq_nic_set_packet_filter(self, packet_filter); } int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index faa533a0ec47..fecfc401f95d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -75,7 +75,7 @@ struct aq_nic_s { struct aq_hw_link_status_s link_status; struct { u32 count; - u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN]; + u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN]; } mc_list; struct pci_dev *pdev; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 67e2f9fb9402..8cc6abadc03b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -765,7 +765,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self, static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self, u8 ar_mac - [AQ_CFG_MULTICAST_ADDRESS_MAX] + [AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 819f6bcf9b4e..956860a69797 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -784,7 +784,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self, u8 ar_mac - [AQ_CFG_MULTICAST_ADDRESS_MAX] + [AQ_HW_MULTICAST_ADDRESS_MAX] [ETH_ALEN], u32 count) { @@ -812,7 +812,7 @@ static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self, hw_atl_rpfl2_uc_flr_en_set(self, (self->aq_nic_cfg->is_mc_list_enabled), - HW_ATL_B0_MAC_MIN + i); + HW_ATL_B0_MAC_MIN + i); } err = aq_hw_err_from_flags(self); diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 567ee54504bc..5e5022fa1d04 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct alx_priv *alx = pci_get_drvdata(pdev); struct alx_hw *hw = &alx->hw; + int err; alx_reset_phy(hw); if (!netif_running(alx->dev)) return 0; netif_device_attach(alx->dev); - return __alx_open(alx, true); + + rtnl_lock(); + err = __alx_open(alx, true); + rtnl_unlock(); + + return err; } static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 94270f654b3b..7087b88550db 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter) skb = build_skb(page_address(page) + adapter->rx_page_offset, adapter->rx_frag_size); if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); adapter->rx_page_offset += adapter->rx_frag_size; if (adapter->rx_page_offset >= PAGE_SIZE) adapter->rx_page = NULL; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index d5fca2e5a9bc..a1f60f89e059 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1946,8 +1946,8 @@ static int bcm_sysport_open(struct net_device *dev) if (!priv->is_lite) priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD); else - priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) & - GIB_FCS_STRIP); + priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) & + GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT); phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link, 0, priv->phy_interface); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index d6e5d0cbf3a3..cf440b91fd04 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -278,7 +278,8 @@ struct bcm_rsb { #define GIB_GTX_CLK_EXT_CLK (0 << GIB_GTX_CLK_SEL_SHIFT) #define GIB_GTX_CLK_125MHZ (1 << GIB_GTX_CLK_SEL_SHIFT) #define GIB_GTX_CLK_250MHZ (2 << GIB_GTX_CLK_SEL_SHIFT) -#define GIB_FCS_STRIP (1 << 6) +#define GIB_FCS_STRIP_SHIFT 6 +#define GIB_FCS_STRIP (1 << GIB_FCS_STRIP_SHIFT) #define GIB_LCL_LOOP_EN (1 << 7) #define GIB_LCL_LOOP_TXEN (1 << 8) #define GIB_RMT_LOOP_EN (1 << 9) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index d847e1b9c37b..be1506169076 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1533,6 +1533,7 @@ struct bnx2x { struct link_vars link_vars; u32 link_cnt; struct bnx2x_link_report_data last_reported_link; + bool force_link_down; struct mdio_if_info mdio; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 8cd73ff5debc..af7b5a4d8ba0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1261,6 +1261,11 @@ void __bnx2x_link_report(struct bnx2x *bp) { struct bnx2x_link_report_data cur_data; + if (bp->force_link_down) { + bp->link_vars.link_up = 0; + return; + } + /* reread mf_cfg */ if (IS_PF(bp) && !CHIP_IS_E1(bp)) bnx2x_read_mf_cfg(bp); @@ -2817,6 +2822,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) bp->pending_max = 0; } + bp->force_link_down = false; if (bp->port.pmf) { rc = bnx2x_initial_phy_init(bp, load_mode); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index da18aa239acb..a4a90b6cdb46 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } else if ((info->flow_type == UDP_V6_FLOW) && (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested; DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } return 0; @@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir, bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id; } - return bnx2x_config_rss_eth(bp, false); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_config_rss_eth(bp, false); + + return 0; } /** diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 5b1ed240bf18..57348f2b49a3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10279,6 +10279,12 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work) bp->sp_rtnl_state = 0; smp_mb(); + /* Immediately indicate link as down */ + bp->link_vars.link_up = 0; + bp->force_link_down = true; + netif_carrier_off(bp->dev); + BNX2X_ERR("Indicating link is down due to Tx-timeout\n"); + bnx2x_nic_unload(bp, UNLOAD_NORMAL, true); /* When ret value shows failure of allocation failure, * the nic is rebooted again. If open still fails, a error diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 176fc9f4d7de..4394c1162be4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5712,7 +5712,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) } vnic->uc_filter_count = 1; - vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; + vnic->rx_mask = 0; + if (bp->dev->flags & IFF_BROADCAST) + vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp)) vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; @@ -5917,7 +5919,7 @@ unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings); } -void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs) +static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs) { bp->hw_resc.max_irqs = max_irqs; } @@ -6888,7 +6890,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) rc = bnxt_request_irq(bp); if (rc) { netdev_err(bp->dev, "bnxt_request_irq err: %x\n", rc); - goto open_err; + goto open_err_irq; } } @@ -6928,6 +6930,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) open_err: bnxt_debug_dev_exit(bp); bnxt_disable_napi(bp); + +open_err_irq: bnxt_del_napi(bp); open_err_free_mem: @@ -7214,13 +7218,16 @@ static void bnxt_set_rx_mode(struct net_device *dev) mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS | CFA_L2_SET_RX_MASK_REQ_MASK_MCAST | - CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST); + CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST | + CFA_L2_SET_RX_MASK_REQ_MASK_BCAST); if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp)) mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; uc_update = bnxt_uc_list_updated(bp); + if (dev->flags & IFF_BROADCAST) + mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; if (dev->flags & IFF_ALLMULTI) { mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; vnic->mc_list_count = 0; @@ -8502,11 +8509,11 @@ int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared) int rx, tx, cp; _bnxt_get_max_rings(bp, &rx, &tx, &cp); + *max_rx = rx; + *max_tx = tx; if (!rx || !tx || !cp) return -ENOMEM; - *max_rx = rx; - *max_tx = tx; return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared); } @@ -8520,8 +8527,11 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx, /* Not enough rings, try disabling agg rings. */ bp->flags &= ~BNXT_FLAG_AGG_RINGS; rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared); - if (rc) + if (rc) { + /* set BNXT_FLAG_AGG_RINGS back for consistency */ + bp->flags |= BNXT_FLAG_AGG_RINGS; return rc; + } bp->flags |= BNXT_FLAG_NO_AGG_RINGS; bp->dev->hw_features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); bp->dev->features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9b14eb610b9f..91575ef97c8c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1470,7 +1470,6 @@ void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp); void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_irqs(struct bnxt *bp); -void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max); int bnxt_get_avail_msix(struct bnxt *bp, int num); int bnxt_reserve_rings(struct bnxt *bp); void bnxt_tx_disable(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 795f45024c20..491bd40a254d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -27,6 +27,15 @@ #define BNXT_FID_INVALID 0xffff #define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT)) +#define is_vlan_pcp_wildcarded(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == 0x0000) +#define is_vlan_pcp_exactmatch(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == VLAN_PRIO_MASK) +#define is_vlan_pcp_zero(vlan_tci) \ + ((ntohs(vlan_tci) & VLAN_PRIO_MASK) == 0x0000) +#define is_vid_exactmatch(vlan_tci_mask) \ + ((ntohs(vlan_tci_mask) & VLAN_VID_MASK) == VLAN_VID_MASK) + /* Return the dst fid of the func for flow forwarding * For PFs: src_fid is the fid of the PF * For VF-reps: src_fid the fid of the VF @@ -389,6 +398,21 @@ static bool is_exactmatch(void *mask, int len) return true; } +static bool is_vlan_tci_allowed(__be16 vlan_tci_mask, + __be16 vlan_tci) +{ + /* VLAN priority must be either exactly zero or fully wildcarded and + * VLAN id must be exact match. + */ + if (is_vid_exactmatch(vlan_tci_mask) && + ((is_vlan_pcp_exactmatch(vlan_tci_mask) && + is_vlan_pcp_zero(vlan_tci)) || + is_vlan_pcp_wildcarded(vlan_tci_mask))) + return true; + + return false; +} + static bool bits_set(void *key, int len) { const u8 *p = key; @@ -803,9 +827,9 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) /* Currently VLAN fields cannot be partial wildcard */ if (bits_set(&flow->l2_key.inner_vlan_tci, sizeof(flow->l2_key.inner_vlan_tci)) && - !is_exactmatch(&flow->l2_mask.inner_vlan_tci, - sizeof(flow->l2_mask.inner_vlan_tci))) { - netdev_info(bp->dev, "Wildcard match unsupported for VLAN TCI\n"); + !is_vlan_tci_allowed(flow->l2_mask.inner_vlan_tci, + flow->l2_key.inner_vlan_tci)) { + netdev_info(bp->dev, "Unsupported VLAN TCI\n"); return false; } if (bits_set(&flow->l2_key.inner_vlan_tpid, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 347e4f946eb2..840f6e505f73 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, edev->ulp_tbl[ulp_id].msix_requested = avail_msix; } bnxt_fill_msix_vecs(bp, ent); - bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) - avail_msix); bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; return avail_msix; @@ -192,7 +191,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) msix_requested = edev->ulp_tbl[ulp_id].msix_requested; bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested); edev->ulp_tbl[ulp_id].msix_requested = 0; - bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) + msix_requested); edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; if (netif_running(dev)) { bnxt_close_nic(bp, true, false); diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 30273a7717e2..4fd829b5e65d 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -660,7 +660,7 @@ static int cnic_init_id_tbl(struct cnic_id_tbl *id_tbl, u32 size, u32 start_id, id_tbl->max = size; id_tbl->next = next; spin_lock_init(&id_tbl->lock); - id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL); + id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL); if (!id_tbl->table) return -ENOMEM; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 3be87efdc93d..aa1374d0af93 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6,11 +6,15 @@ * Copyright (C) 2004 Sun Microsystems Inc. * Copyright (C) 2005-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Limited. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. * * Firmware is: * Derived from proprietary unpublished source code, * Copyright (C) 2000-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Ltd. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. * * Permission is hereby granted for the distribution of this firmware * data in hexadecimal or equivalent format, provided this copyright @@ -9290,6 +9294,15 @@ static int tg3_chip_reset(struct tg3 *tp) tg3_restore_clk(tp); + /* Increase the core clock speed to fix tx timeout issue for 5762 + * with 100Mbps link speed. + */ + if (tg3_asic_rev(tp) == ASIC_REV_5762) { + val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE); + tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val | + TG3_CPMU_MAC_ORIDE_ENABLE); + } + /* Reprobe ASF enable state. */ tg3_flag_clear(tp, ENABLE_ASF); tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK | diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 1d61aa3efda1..a772a33b685c 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -7,6 +7,8 @@ * Copyright (C) 2004 Sun Microsystems Inc. * Copyright (C) 2007-2016 Broadcom Corporation. * Copyright (C) 2016-2017 Broadcom Limited. + * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom" + * refers to Broadcom Inc. and/or its subsidiaries. */ #ifndef _T3_H diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 86659823b259..3d45f4c92cf6 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -166,6 +166,7 @@ #define GEM_DCFG6 0x0294 /* Design Config 6 */ #define GEM_DCFG7 0x0298 /* Design Config 7 */ #define GEM_DCFG8 0x029C /* Design Config 8 */ +#define GEM_DCFG10 0x02A4 /* Design Config 10 */ #define GEM_TXBDCTRL 0x04cc /* TX Buffer Descriptor control register */ #define GEM_RXBDCTRL 0x04d0 /* RX Buffer Descriptor control register */ @@ -490,6 +491,12 @@ #define GEM_SCR2CMP_OFFSET 0 #define GEM_SCR2CMP_SIZE 8 +/* Bitfields in DCFG10 */ +#define GEM_TXBD_RDBUFF_OFFSET 12 +#define GEM_TXBD_RDBUFF_SIZE 4 +#define GEM_RXBD_RDBUFF_OFFSET 8 +#define GEM_RXBD_RDBUFF_SIZE 4 + /* Bitfields in TISUBN */ #define GEM_SUBNSINCR_OFFSET 0 #define GEM_SUBNSINCR_SIZE 16 @@ -635,6 +642,7 @@ #define MACB_CAPS_USRIO_DISABLED 0x00000010 #define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_GEM_HAS_PTP 0x00000040 +#define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 @@ -1203,6 +1211,9 @@ struct macb { unsigned int max_tuples; struct tasklet_struct hresp_err_tasklet; + + int rx_bd_rd_prefetch; + int tx_bd_rd_prefetch; }; #ifdef CONFIG_MACB_USE_HWSTAMP diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 3e93df5d4e3b..a6c911bb5ce2 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1811,23 +1811,25 @@ static void macb_free_consistent(struct macb *bp) { struct macb_queue *queue; unsigned int q; + int size; - queue = &bp->queues[0]; bp->macbgem_ops.mog_free_rx_buffers(bp); - if (queue->rx_ring) { - dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp), - queue->rx_ring, queue->rx_ring_dma); - queue->rx_ring = NULL; - } for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { kfree(queue->tx_skb); queue->tx_skb = NULL; if (queue->tx_ring) { - dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp), + size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch; + dma_free_coherent(&bp->pdev->dev, size, queue->tx_ring, queue->tx_ring_dma); queue->tx_ring = NULL; } + if (queue->rx_ring) { + size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch; + dma_free_coherent(&bp->pdev->dev, size, + queue->rx_ring, queue->rx_ring_dma); + queue->rx_ring = NULL; + } } } @@ -1874,7 +1876,7 @@ static int macb_alloc_consistent(struct macb *bp) int size; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - size = TX_RING_BYTES(bp); + size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch; queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size, &queue->tx_ring_dma, GFP_KERNEL); @@ -1890,7 +1892,7 @@ static int macb_alloc_consistent(struct macb *bp) if (!queue->tx_skb) goto out_err; - size = RX_RING_BYTES(bp); + size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch; queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size, &queue->rx_ring_dma, GFP_KERNEL); if (!queue->rx_ring) @@ -3726,6 +3728,8 @@ static int at91ether_init(struct platform_device *pdev) int err; u32 reg; + bp->queues[0].bp = bp; + dev->netdev_ops = &at91ether_netdev_ops; dev->ethtool_ops = &macb_ethtool_ops; @@ -3795,7 +3799,7 @@ static const struct macb_config np4_config = { static const struct macb_config zynqmp_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | - MACB_CAPS_GEM_HAS_PTP, + MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -3856,7 +3860,7 @@ static int macb_probe(struct platform_device *pdev) void __iomem *mem; const char *mac; struct macb *bp; - int err; + int err, val; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); mem = devm_ioremap_resource(&pdev->dev, regs); @@ -3945,6 +3949,18 @@ static int macb_probe(struct platform_device *pdev) else dev->max_mtu = ETH_DATA_LEN; + if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) { + val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10)); + if (val) + bp->rx_bd_rd_prefetch = (2 << (val - 1)) * + macb_dma_desc_get_size(bp); + + val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10)); + if (val) + bp->tx_bd_rd_prefetch = (2 << (val - 1)) * + macb_dma_desc_get_size(bp); + } + mac = of_get_mac_address(np); if (mac) { ether_addr_copy(bp->dev->dev_addr, mac); diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 043e3c11c42b..92d88c5f76fb 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -15,7 +15,7 @@ if NET_VENDOR_CAVIUM config THUNDER_NIC_PF tristate "Thunder Physical function driver" - depends on 64BIT + depends on 64BIT && PCI select THUNDER_NIC_BGX ---help--- This driver supports Thunder's NIC physical function. @@ -28,13 +28,13 @@ config THUNDER_NIC_PF config THUNDER_NIC_VF tristate "Thunder Virtual function driver" imply CAVIUM_PTP - depends on 64BIT + depends on 64BIT && PCI ---help--- This driver supports Thunder's NIC virtual function config THUNDER_NIC_BGX tristate "Thunder MAC interface driver (BGX)" - depends on 64BIT + depends on 64BIT && PCI select PHYLIB select MDIO_THUNDER select THUNDER_NIC_RGX @@ -44,7 +44,7 @@ config THUNDER_NIC_BGX config THUNDER_NIC_RGX tristate "Thunder MAC interface driver (RGX)" - depends on 64BIT + depends on 64BIT && PCI select PHYLIB select MDIO_THUNDER ---help--- @@ -53,7 +53,7 @@ config THUNDER_NIC_RGX config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" - depends on 64BIT + depends on 64BIT && PCI imply PTP_1588_CLOCK default y ---help--- @@ -65,7 +65,7 @@ config CAVIUM_PTP config LIQUIDIO tristate "Cavium LiquidIO support" - depends on 64BIT + depends on 64BIT && PCI depends on MAY_USE_DEVLINK imply PTP_1588_CLOCK select FW_LOADER diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8a815bb57177..7e8454d3b1ad 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -91,6 +91,9 @@ static int octeon_console_debug_enabled(u32 console) */ #define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000 +/* time to wait for possible in-flight requests in milliseconds */ +#define WAIT_INFLIGHT_REQUEST msecs_to_jiffies(1000) + struct lio_trusted_vf_ctx { struct completion complete; int status; @@ -259,7 +262,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct) force_io_queues_off(oct); /* To allow for in-flight requests */ - schedule_timeout_uninterruptible(100); + schedule_timeout_uninterruptible(WAIT_INFLIGHT_REQUEST); if (wait_for_pending_requests(oct)) dev_err(&oct->pci_dev->dev, "There were pending requests\n"); diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 3f6afb54a5eb..bb43ddb7539e 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -643,13 +643,21 @@ static int octeon_mgmt_set_mac_address(struct net_device *netdev, void *addr) static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu) { struct octeon_mgmt *p = netdev_priv(netdev); - int size_without_fcs = new_mtu + OCTEON_MGMT_RX_HEADROOM; + int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN; netdev->mtu = new_mtu; - cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, size_without_fcs); + /* HW lifts the limit if the frame is VLAN tagged + * (+4 bytes per each tag, up to two tags) + */ + cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, max_packet); + /* Set the hardware to truncate packets larger than the MTU. The jabber + * register must be set to a multiple of 8 bytes, so round up. JABBER is + * an unconditional limit, so we need to account for two possible VLAN + * tags. + */ cvmx_write_csr(p->agl + AGL_GMX_RX_JABBER, - (size_without_fcs + 7) & 0xfff8); + (max_packet + 7 + VLAN_HLEN * 2) & 0xfff8); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 7b795edd9d3a..a19172dbe6be 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -51,6 +51,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/nospec.h> #include "common.h" #include "cxgb3_ioctl.h" @@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (t.qset_idx >= nqsets) return -EINVAL; + t.qset_idx = array_index_nospec(t.qset_idx, nqsets); q = &adapter->params.sge.qset[q1 + t.qset_idx]; t.rspq_size = q->rspq_size; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 974a868a4824..3720c3e11ebb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -8702,7 +8702,7 @@ static int t4_get_flash_params(struct adapter *adap) }; unsigned int part, manufacturer; - unsigned int density, size; + unsigned int density, size = 0; u32 flashid = 0; int ret; @@ -8772,11 +8772,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x22: /* 256MB */ size = 1 << 28; break; - - default: - dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8792,10 +8787,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x17: /* 64MB */ size = 1 << 26; break; - default: - dev_err(adap->pdev_dev, "ISSI Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8811,10 +8802,6 @@ static int t4_get_flash_params(struct adapter *adap) case 0x18: /* 16MB */ size = 1 << 24; break; - default: - dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } @@ -8830,17 +8817,21 @@ static int t4_get_flash_params(struct adapter *adap) case 0x18: /* 16MB */ size = 1 << 24; break; - default: - dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n", - flashid, density); - return -EINVAL; } break; } - default: - dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n", - flashid); - return -EINVAL; + } + + /* If we didn't recognize the FLASH part, that's no real issue: the + * Hardware/Software contract says that Hardware will _*ALWAYS*_ + * use a FLASH part which is at least 4MB in size and has 64KB + * sectors. The unrecognized FLASH part is likely to be much larger + * than 4MB, but that's all we really need. + */ + if (size == 0) { + dev_warn(adap->pdev_dev, "Unknown Flash Part, ID = %#x, assuming 4MB\n", + flashid); + size = 1 << 22; } /* Store decoded Flash size and fall through into vetting code. */ diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig index 5ab912937aff..ec0b545197e2 100644 --- a/drivers/net/ethernet/cirrus/Kconfig +++ b/drivers/net/ethernet/cirrus/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS config CS89x0 tristate "CS89x0 support" depends on ISA || EISA || ARM + depends on !PPC32 ---help--- Support for CS89x0 chipset based Ethernet cards. If you have a network (Ethernet) card of this type, say Y and read the file diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 5f4e1ffa7b95..ab02057ac730 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -125,6 +125,9 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); /* Default alignment for start of data in an Rx FD */ #define DPAA_FD_DATA_ALIGNMENT 16 +/* The DPAA requires 256 bytes reserved and mapped for the SGT */ +#define DPAA_SGT_SIZE 256 + /* Values for the L3R field of the FM Parse Results */ /* L3 Type field: First IP Present IPv4 */ @@ -1617,8 +1620,8 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv, if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) { nr_frags = skb_shinfo(skb)->nr_frags; - dma_unmap_single(dev, addr, qm_fd_get_offset(fd) + - sizeof(struct qm_sg_entry) * (1 + nr_frags), + dma_unmap_single(dev, addr, + qm_fd_get_offset(fd) + DPAA_SGT_SIZE, dma_dir); /* The sgt buffer has been allocated with netdev_alloc_frag(), @@ -1903,8 +1906,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, void *sgt_buf; /* get a page frag to store the SGTable */ - sz = SKB_DATA_ALIGN(priv->tx_headroom + - sizeof(struct qm_sg_entry) * (1 + nr_frags)); + sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE); sgt_buf = netdev_alloc_frag(sz); if (unlikely(!sgt_buf)) { netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n", @@ -1972,9 +1974,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, skbh = (struct sk_buff **)buffer_start; *skbh = skb; - addr = dma_map_single(dev, buffer_start, priv->tx_headroom + - sizeof(struct qm_sg_entry) * (1 + nr_frags), - dma_dir); + addr = dma_map_single(dev, buffer_start, + priv->tx_headroom + DPAA_SGT_SIZE, dma_dir); if (unlikely(dma_mapping_error(dev, addr))) { dev_err(dev, "DMA mapping failed"); err = -EINVAL; diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index ce6e24c74978..ecbf6187e13a 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -324,6 +324,10 @@ struct fman_port_qmi_regs { #define HWP_HXS_PHE_REPORT 0x00000800 #define HWP_HXS_PCAC_PSTAT 0x00000100 #define HWP_HXS_PCAC_PSTOP 0x00000001 +#define HWP_HXS_TCP_OFFSET 0xA +#define HWP_HXS_UDP_OFFSET 0xB +#define HWP_HXS_SH_PAD_REM 0x80000000 + struct fman_port_hwp_regs { struct { u32 ssa; /* Soft Sequence Attachment */ @@ -728,6 +732,10 @@ static void init_hwp(struct fman_port *port) iowrite32be(0xffffffff, ®s->pmda[i].lcv); } + /* Short packet padding removal from checksum calculation */ + iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa); + iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa); + start_port_hwp(port); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index e2e5cdc7119c..4c0f7eda1166 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq) { struct hinic_rq *rq = rxq->rq; + irq_set_affinity_hint(rq->irq, NULL); free_irq(rq->irq, rxq); rx_del_napi(rxq); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9128858479c4..2353ec829c04 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) txq->txq_stats.tx_busy++; u64_stats_update_end(&txq->txq_stats.syncp); err = NETDEV_TX_BUSY; + wqe_size = 0; goto flush_skbs; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d0e196bff081..ffe7acbeaa22 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -329,7 +329,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, return; failure: - dev_info(dev, "replenish pools failure\n"); + if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED) + dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n"); pool->free_map[pool->next_free] = index; pool->rx_buff[index].skb = NULL; @@ -1617,7 +1618,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) &tx_crq); } if (lpar_rc != H_SUCCESS) { - dev_err(dev, "tx failed with code %ld\n", lpar_rc); + if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER) + dev_err_ratelimited(dev, "tx: send failed\n"); dev_kfree_skb_any(skb); tx_buff->skb = NULL; @@ -1825,8 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = ibmvnic_login(netdev); if (rc) { - adapter->state = VNIC_PROBED; - return 0; + adapter->state = reset_state; + return rc; } if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || @@ -3204,6 +3206,25 @@ static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter) return crq; } +static void print_subcrq_error(struct device *dev, int rc, const char *func) +{ + switch (rc) { + case H_PARAMETER: + dev_warn_ratelimited(dev, + "%s failed: Send request is malformed or adapter failover pending. (rc=%d)\n", + func, rc); + break; + case H_CLOSED: + dev_warn_ratelimited(dev, + "%s failed: Backing queue closed. Adapter is down or failover pending. (rc=%d)\n", + func, rc); + break; + default: + dev_err_ratelimited(dev, "%s failed: (rc=%d)\n", func, rc); + break; + } +} + static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, union sub_crq *sub_crq) { @@ -3230,11 +3251,8 @@ static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle, cpu_to_be64(u64_crq[2]), cpu_to_be64(u64_crq[3])); - if (rc) { - if (rc == H_CLOSED) - dev_warn(dev, "CRQ Queue closed\n"); - dev_err(dev, "Send error (rc=%d)\n", rc); - } + if (rc) + print_subcrq_error(dev, rc, __func__); return rc; } @@ -3252,11 +3270,8 @@ static int send_subcrq_indirect(struct ibmvnic_adapter *adapter, cpu_to_be64(remote_handle), ioba, num_entries); - if (rc) { - if (rc == H_CLOSED) - dev_warn(dev, "CRQ Queue closed\n"); - dev_err(dev, "Send (indirect) error (rc=%d)\n", rc); - } + if (rc) + print_subcrq_error(dev, rc, __func__); return rc; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index ed6dbcfd4e96..b151ae316546 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, return true; } -#define I40E_XDP_PASS 0 -#define I40E_XDP_CONSUMED 1 -#define I40E_XDP_TX 2 +#define I40E_XDP_PASS 0 +#define I40E_XDP_CONSUMED BIT(0) +#define I40E_XDP_TX BIT(1) +#define I40E_XDP_REDIR BIT(2) static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring); @@ -2248,7 +2249,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED; + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; break; default: bpf_warn_invalid_xdp_action(act); @@ -2311,7 +2312,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); - bool failure = false, xdp_xmit = false; + unsigned int xdp_xmit = 0; + bool failure = false; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2372,8 +2374,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -I40E_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + xdp_xmit |= xdp_res; i40e_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2427,12 +2431,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & I40E_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & I40E_XDP_TX) { struct i40e_ring *xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; i40e_xdp_ring_update_tail(xdp_ring); - xdp_do_flush_map(); } rx_ring->skb = skb; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3f5c350716bb..0bd1294ba517 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1871,7 +1871,12 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, if (enable_addr != 0) rar_high |= IXGBE_RAH_AV; + /* Record lower 32 bits of MAC address and then make + * sure that write is flushed to hardware before writing + * the upper 16 bits and setting the valid bit. + */ IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low); + IXGBE_WRITE_FLUSH(hw); IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); return 0; @@ -1903,8 +1908,13 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index)); rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV); - IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); + /* Clear the address valid bit and upper 16 bits of the address + * before clearing the lower bits. This way we aren't updating + * a live filter. + */ IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); /* clear VMDq pool/queue selection for this RAR */ hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index c116f459945d..da4322e4daed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -839,7 +839,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, } itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; - if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) { netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", __func__, itd->sa_idx, xs->xso.offload_handle); return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3e87dbbc9024..62e57b05a0ae 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2186,9 +2186,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -#define IXGBE_XDP_PASS 0 -#define IXGBE_XDP_CONSUMED 1 -#define IXGBE_XDP_TX 2 +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, struct xdp_frame *xdpf); @@ -2225,7 +2226,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); if (!err) - result = IXGBE_XDP_TX; + result = IXGBE_XDP_REDIR; else result = IXGBE_XDP_CONSUMED; break; @@ -2285,7 +2286,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; struct xdp_buff xdp; xdp.rxq = &rx_ring->xdp_rxq; @@ -2328,8 +2329,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBE_XDP_TX) { - xdp_xmit = true; + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); } else { rx_buffer->pagecnt_bias++; @@ -2401,7 +2404,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } - if (xdp_xmit) { + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; /* Force memory writes to complete before letting h/w @@ -2409,8 +2415,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ wmb(); writel(ring->next_to_use, ring->tail); - - xdp_do_flush_map(); } u64_stats_update_begin(&rx_ring->syncp); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9f54ccbddea7..3360f7b9ee73 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -474,10 +474,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, { const struct mlx4_en_frag_info *frag_info = priv->frag_info; unsigned int truesize = 0; + bool release = true; int nr, frag_size; struct page *page; dma_addr_t dma; - bool release; /* Collect used fragments while replacing them in the HW descriptors */ for (nr = 0;; frags++) { @@ -500,7 +500,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, release = page_count(page) != 1 || page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); - } else { + } else if (!priv->rx_headroom) { + /* rx_headroom for non XDP setup is always 0. + * When XDP is set, the above condition will + * guarantee page is always released. + */ u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES); frags->page_offset += sz_align; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 7b1b5ac986d0..31bd56727022 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, u32 srqn = qp_get_srqn(qpc) & 0xffffff; int use_srq = (qp_get_srqn(qpc) >> 24) & 1; struct res_srq *srq; - int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + int local_qpn = vhcr->in_modifier & 0xffffff; err = adjust_qp_sched_queue(dev, slave, qpc, inbox); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 323ffe8bf7e4..456f30007ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, int i; buf->size = size; - buf->npages = 1 << get_order(size); + buf->npages = DIV_ROUND_UP(size, PAGE_SIZE); buf->page_shift = PAGE_SHIFT; buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 487388aed98f..384c1fa49081 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -807,6 +807,7 @@ static void cmd_work_handler(struct work_struct *work) unsigned long flags; bool poll_cmd = ent->polling; int alloc_ret; + int cmd_mode; sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -853,6 +854,7 @@ static void cmd_work_handler(struct work_struct *work) set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + cmd_mode = cmd->mode; if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); @@ -877,7 +879,7 @@ static void cmd_work_handler(struct work_struct *work) iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell); mmiowb(); /* if not in polling don't use ent after this point */ - if (cmd->mode == CMD_MODE_POLLING || poll_cmd) { + if (cmd_mode == CMD_MODE_POLLING || poll_cmd) { poll_timeout(ent); /* make sure we read the descriptor after ownership is SW */ rmb(); @@ -1276,7 +1278,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, { struct mlx5_core_dev *dev = filp->private_data; struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - char outlen_str[8]; + char outlen_str[8] = {0}; int outlen; void *ptr; int err; @@ -1291,8 +1293,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf, if (copy_from_user(outlen_str, buf, count)) return -EFAULT; - outlen_str[7] = 0; - err = sscanf(outlen_str, "%d", &outlen); if (err < 0) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 75e4308ba786..d258bb679271 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) HLIST_HEAD(del_list); spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { - if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) - break; if (!work_pending(&arfs_rule->arfs_work) && rps_may_expire_flow(priv->netdev, arfs_rule->rxq, arfs_rule->flow_id, arfs_rule->filter_id)) { hlist_del_init(&arfs_rule->hlist); hlist_add_head(&arfs_rule->hlist, &del_list); + if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) + break; } } spin_unlock_bh(&priv->fs.arfs.arfs_lock); @@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, skb->protocol != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); if (!arfs_t) return -EPROTONOSUPPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 0a52f31fef37..86bc9ac99586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) } static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, - struct ieee_ets *ets) + struct ieee_ets *ets, + bool zero_sum_allowed) { bool have_ets_tc = false; int bw_sum = 0; @@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } if (have_ets_tc && bw_sum != 100) { - netdev_err(netdev, - "Failed to validate ETS: BW sum is illegal\n"); + if (bw_sum || (!bw_sum && !zero_sum_allowed)) + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; } return 0; @@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, if (!MLX5_CAP_GEN(priv->mdev, ets)) return -EOPNOTSUPP; - err = mlx5e_dbcnl_validate_ets(netdev, ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets, false); if (err) return err; @@ -642,12 +644,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) ets.prio_tc[i]); } - err = mlx5e_dbcnl_validate_ets(netdev, &ets); - if (err) { - netdev_err(netdev, - "%s, Failed to validate ETS: %d\n", __func__, err); + err = mlx5e_dbcnl_validate_ets(netdev, &ets, true); + if (err) goto out; - } err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 56c1b6f5593e..dae4156a710d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2846,7 +2846,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); @@ -2857,7 +2857,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -4597,7 +4597,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_set_netdev_dev_addr(netdev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) - if (MLX5_VPORT_MANAGER(mdev)) + if (MLX5_ESWITCH_MANAGER(mdev)) netdev->switchdev_ops = &mlx5e_switchdev_ops; #endif @@ -4753,7 +4753,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_enable_async_events(priv); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_register_vport_reps(priv); if (netdev->reg_state != NETREG_REGISTERED) @@ -4788,7 +4788,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); - if (MLX5_VPORT_MANAGER(priv->mdev)) + if (MLX5_ESWITCH_MANAGER(priv->mdev)) mlx5e_unregister_vport_reps(priv); mlx5e_disable_async_events(priv); @@ -4972,7 +4972,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return NULL; #ifdef CONFIG_MLX5_ESWITCH - if (MLX5_VPORT_MANAGER(mdev)) { + if (MLX5_ESWITCH_MANAGER(mdev)) { rpriv = mlx5e_alloc_nic_rep_priv(mdev); if (!rpriv) { mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 57987f6546e8..2b8040a3cdbd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -823,7 +823,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; - if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager)) + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) return false; rep = rpriv->rep; @@ -837,8 +837,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_eswitch_rep *rep; + if (!MLX5_ESWITCH_MANAGER(priv->mdev)) + return false; + + rep = rpriv->rep; if (rep && rep->vport != FDB_UPLINK_VPORT) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0edf4751a8ba..3a2c4e548226 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1957,6 +1957,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv, else actions = flow->nic_attr->action; + if (flow->flags & MLX5E_TC_FLOW_EGRESS && + !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)) + return false; + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index f63dfbcd29fe..dd01ad4c0b54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1594,17 +1594,15 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) } /* Public E-Switch API */ -#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev)) +#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) + int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { int err; int i, enabled_events; - if (!ESW_ALLOWED(esw)) - return 0; - - if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || + if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n"); return -EOPNOTSUPP; @@ -1806,7 +1804,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u64 node_guid; int err = 0; - if (!ESW_ALLOWED(esw)) + if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) return -EPERM; if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac)) return -EINVAL; @@ -1883,7 +1881,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, { struct mlx5_vport *evport; - if (!ESW_ALLOWED(esw)) + if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) return -EPERM; if (!LEGAL_VPORT(esw, vport)) return -EINVAL; @@ -2218,6 +2216,6 @@ free_out: u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) { - return esw->mode; + return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index cecd201f0b73..91f1209886ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1079,8 +1079,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(dev, vport_group_manager)) - return -EOPNOTSUPP; + if(!MLX5_ESWITCH_MANAGER(dev)) + return -EPERM; if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 49a75d31185e..6ddb2565884d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include <linux/mutex.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "fs_core.h" @@ -1886,7 +1887,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); - if (dest) + if (dest_num) return ERR_PTR(-EINVAL); mutex_lock(&root->chain_lock); next_ft = find_next_chained_ft(prio); @@ -2652,7 +2653,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) { err = init_fdb_root_ns(steering); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index afd9f4fa22f4..41ad24f0de2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -32,6 +32,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/cmd.h> +#include <linux/mlx5/eswitch.h> #include <linux/module.h> #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" @@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) } if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_CAP_GEN(dev, eswitch_flow_table)) { + MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; } - if (MLX5_CAP_GEN(dev, eswitch_flow_table)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 1e062e6b2587..3f767cde4c1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, void mlx5_init_clock(struct mlx5_core_dev *mdev) { struct mlx5_clock *clock = &mdev->clock; + u64 overflow_cycles; u64 ns; u64 frac = 0; u32 dev_freq; @@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. + * The period is calculated as the minimum between max HW cycles count + * (The clock source mask) and max amount of cycles that can be + * multiplied by clock multiplier where the result doesn't exceed + * 64bits. */ - ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult); + overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1); + + ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles, frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); + do_div(ns, NSEC_PER_SEC / HZ); clock->overflow_period = ns; mdev->clock_info_page = alloc_page(GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 7cb67122e8b5..98359559c77e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -33,6 +33,7 @@ #include <linux/etherdevice.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/mlx5/eswitch.h> #include "mlx5_core.h" #include "lib/mpfs.h" @@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); @@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) u32 index; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); @@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index fa9d0760dd36..31a9cbd85689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc); static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, int inlen) { - u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; @@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, int outlen) { - u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; if (!MLX5_CAP_GEN(mdev, ets)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 2a8b529ce6dd..a0674962f02c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return -EBUSY; } + if (!MLX5_ESWITCH_MANAGER(dev)) + goto enable_vfs_hca; + err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); if (err) { mlx5_core_warn(dev, @@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } +enable_vfs_hca: for (vf = 0; vf < num_vfs; vf++) { err = mlx5_core_enable_hca(dev, vf + 1); if (err) { @@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) } out: - mlx5_eswitch_disable_sriov(dev->priv.eswitch); + if (MLX5_ESWITCH_MANAGER(dev)) + mlx5_eswitch_disable_sriov(dev->priv.eswitch); if (mlx5_wait_for_vf_pages(dev)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 719cecb182c6..7eecd5b07bb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -549,8 +549,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, return -EINVAL; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return -EACCES; - if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify)) - return -EOPNOTSUPP; in = kvzalloc(inlen, GFP_KERNEL); if (!in) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index b97bb72b4db4..86478a6b99c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -113,35 +113,45 @@ err_db_free: return err; } -static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf, - struct mlx5_wq_qp *qp) +static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf, + struct mlx5_wq_qp *qp) { + struct mlx5_frag_buf_ctrl *sq_fbc; struct mlx5_frag_buf *rqb, *sqb; - rqb = &qp->rq.fbc.frag_buf; + rqb = &qp->rq.fbc.frag_buf; *rqb = *buf; rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - rqb->npages = 1 << get_order(rqb->size); + rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE); - sqb = &qp->sq.fbc.frag_buf; - *sqb = *buf; - sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - sqb->npages = 1 << get_order(sqb->size); + sq_fbc = &qp->sq.fbc; + sqb = &sq_fbc->frag_buf; + *sqb = *buf; + sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq); + sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE); sqb->frags += rqb->npages; /* first part is for the rq */ + if (sq_fbc->strides_offset) + sqb->frags--; } int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u32 sq_strides_offset; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB), - MLX5_GET(qpc, qpc, log_sq_size), - &wq->sq.fbc); + + sq_strides_offset = + ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + + mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), + MLX5_GET(qpc, qpc, log_sq_size), + sq_strides_offset, + &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq); + mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq); wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6aaaf3d9ba31..77b2adb29341 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4756,6 +4756,12 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) kfree(mlxsw_sp_rt6); } +static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt) +{ + /* RTF_CACHE routes are ignored */ + return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; +} + static struct fib6_info * mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) { @@ -4765,11 +4771,11 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct fib6_info *nrt, bool append) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; - if (!append) + if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace) return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { @@ -4784,7 +4790,8 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, break; if (rt->fib6_metric < nrt->fib6_metric) continue; - if (rt->fib6_metric == nrt->fib6_metric) + if (rt->fib6_metric == nrt->fib6_metric && + mlxsw_sp_fib6_rt_can_mp(rt)) return fib6_entry; if (rt->fib6_metric > nrt->fib6_metric) break; @@ -5163,7 +5170,7 @@ static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, const struct fib6_info *nrt, bool replace) { - struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); @@ -5172,13 +5179,18 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, continue; if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (replace && rt->fib6_metric == nrt->fib6_metric) - return fib6_entry; + if (replace && rt->fib6_metric == nrt->fib6_metric) { + if (mlxsw_sp_fib6_rt_can_mp(rt) == + mlxsw_sp_fib6_rt_can_mp(nrt)) + return fib6_entry; + if (mlxsw_sp_fib6_rt_can_mp(nrt)) + fallback = fallback ?: fib6_entry; + } if (rt->fib6_metric > nrt->fib6_metric) - return fib6_entry; + return fallback ?: fib6_entry; } - return NULL; + return fallback; } static int @@ -5304,8 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, - struct fib6_info *rt, bool replace, - bool append) + struct fib6_info *rt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5331,7 +5342,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, /* Before creating a new entry, try to append route to an existing * multipath entry. */ - fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, append); + fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace); if (fib6_entry) { err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt); if (err) @@ -5339,14 +5350,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, return 0; } - /* We received an append event, yet did not find any route to - * append to. - */ - if (WARN_ON(append)) { - err = -EINVAL; - goto err_fib6_entry_append; - } - fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt); if (IS_ERR(fib6_entry)) { err = PTR_ERR(fib6_entry); @@ -5364,7 +5367,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, err_fib6_node_entry_link: mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); err_fib6_entry_create: -err_fib6_entry_append: err_fib6_entry_nexthop_add: mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); return err; @@ -5715,7 +5717,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; - bool replace, append; + bool replace; int err; rtnl_lock(); @@ -5726,10 +5728,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; - append = fib_work->event == FIB_EVENT_ENTRY_APPEND; err = mlxsw_sp_router_fib6_add(mlxsw_sp, - fib_work->fen6_info.rt, replace, - append); + fib_work->fen6_info.rt, replace); if (err) mlxsw_sp_router_fib_abort(mlxsw_sp); mlxsw_sp_rt6_release(fib_work->fen6_info.rt); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index fcdfb8e7fdea..40216d56dddc 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -81,10 +81,10 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn, ret = nfp_net_bpf_offload(nn, prog, running, extack); /* Stop offload if replace not possible */ - if (ret && prog) - nfp_bpf_xdp_offload(app, nn, NULL, extack); + if (ret) + return ret; - nn->dp.bpf_offload_xdp = prog && !ret; + nn->dp.bpf_offload_xdp = !!prog; return ret; } @@ -202,6 +202,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 91935405f586..84f7a5dbea9d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, NFP_FLOWER_MASK_MPLS_Q; frame->mpls_lse = cpu_to_be32(t_mpls); + } else if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC)) { + /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q + * bit, which indicates an mpls ether type but without any + * mpls fields. + */ + struct flow_dissector_key_basic *key_basic; + + key_basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->key); + if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || + key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) + frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index c42e64f32333..525057bee0ed 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, case cpu_to_be16(ETH_P_ARP): return -EOPNOTSUPP; + case cpu_to_be16(ETH_P_MPLS_UC): + case cpu_to_be16(ETH_P_MPLS_MC): + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + key_layer |= NFP_FLOWER_LAYER_MAC; + key_size += sizeof(struct nfp_flower_mac_mpls); + } + break; + /* Will be included in layer 2. */ case cpu_to_be16(ETH_P_8021Q): break; @@ -623,6 +631,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + if (tcf_block_shared(f->block)) + return -EOPNOTSUPP; + switch (f->command) { case TC_BLOCK_BIND: return tcf_block_cb_register(f->block, diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 78afe75129ab..382bb93cb090 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload.dst_ipv4 = flow->daddr; /* If entry has expired send dst IP with all other fields 0. */ - if (!(neigh->nud_state & NUD_VALID)) { + if (!(neigh->nud_state & NUD_VALID) || neigh->dead) { nfp_tun_del_route_from_cache(app, payload.dst_ipv4); /* Trigger ARP to verify invalid neighbour state. */ neigh_event_send(neigh, NULL); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 46b76d5a726c..152283d7e59c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -240,7 +240,6 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf) return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs); pf->limit_vfs = ~0; - pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */ /* Allow any setting for backwards compatibility if symbol not found */ if (err == -ENOENT) return 0; @@ -668,7 +667,7 @@ static int nfp_pci_probe(struct pci_dev *pdev, err = nfp_net_pci_probe(pf); if (err) - goto err_sriov_unlimit; + goto err_fw_unload; err = nfp_hwmon_register(pf); if (err) { @@ -680,8 +679,6 @@ static int nfp_pci_probe(struct pci_dev *pdev, err_net_remove: nfp_net_pci_remove(pf); -err_sriov_unlimit: - pci_sriov_set_totalvfs(pf->pdev, 0); err_fw_unload: kfree(pf->rtbl); nfp_mip_close(pf->mip); @@ -715,7 +712,6 @@ static void nfp_pci_remove(struct pci_dev *pdev) nfp_hwmon_unregister(pf); nfp_pcie_sriov_disable(pdev); - pci_sriov_set_totalvfs(pf->pdev, 0); nfp_net_pci_remove(pf); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c index cd34097b79f1..37a6d7822a38 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c @@ -232,7 +232,7 @@ struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp) err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res), nfp_resource_address(state->res), fwinf, sizeof(*fwinf)); - if (err < sizeof(*fwinf)) + if (err < (int)sizeof(*fwinf)) goto err_release; if (!nffw_res_flg_init_get(fwinf)) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 00db3401b898..1dfaccd151f0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -502,6 +502,7 @@ enum BAR_ID { struct qed_nvm_image_info { u32 num_images; struct bist_nvm_image_att *image_att; + bool valid; }; #define DRV_MODULE_VERSION \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index f0b01385d5cb..e0680ce91328 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -709,9 +709,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn, p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id, - ARRAY_SIZE(p_local->local_chassis_id)); + sizeof(p_local->local_chassis_id)); memcpy(params->lldp_local.local_port_id, p_local->local_port_id, - ARRAY_SIZE(p_local->local_port_id)); + sizeof(p_local->local_port_id)); } static void @@ -723,9 +723,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn, p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE]; memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id, - ARRAY_SIZE(p_remote->peer_chassis_id)); + sizeof(p_remote->peer_chassis_id)); memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id, - ARRAY_SIZE(p_remote->peer_port_id)); + sizeof(p_remote->peer_port_id)); } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index a14e48489029..4340c4c90bcb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -6723,7 +6723,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, format_idx = header & MFW_TRACE_EVENTID_MASK; /* Skip message if its index doesn't exist in the meta data */ - if (format_idx > s_mcp_trace_meta.formats_num) { + if (format_idx >= s_mcp_trace_meta.formats_num) { u8 format_size = (u8)((header & MFW_TRACE_PRM_SIZE_MASK) >> MFW_TRACE_PRM_SIZE_SHIFT); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 329781cda77f..e5249b4741d0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1804,7 +1804,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) DP_INFO(p_hwfn, "Failed to update driver state\n"); rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt, - QED_OV_ESWITCH_VEB); + QED_OV_ESWITCH_NONE); if (rc) DP_INFO(p_hwfn, "Failed to update eswitch mode\n"); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 99973e10b179..5ede6408649d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn, p_ramrod->common.update_approx_mcast_flg = 1; for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { - u32 *p_bins = (u32 *)p_params->bins; + u32 *p_bins = p_params->bins; p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]); } @@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data) { - unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct vport_update_ramrod_data *p_ramrod = NULL; + u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u8 abs_vport_id = 0; @@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, /* explicitly clear out the entire vector */ memset(&p_ramrod->approx_mcast.bins, 0, sizeof(p_ramrod->approx_mcast.bins)); - memset(bins, 0, sizeof(unsigned long) * - ETH_MULTICAST_MAC_BINS_IN_REGS); + memset(bins, 0, sizeof(bins)); /* filter ADD op is explicit set op and it removes * any existing filters for the vport */ if (p_filter_cmd->opcode == QED_FILTER_ADD) { for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) { - u32 bit; + u32 bit, nbits; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, bins); + nbits = sizeof(u32) * BITS_PER_BYTE; + bins[bit / nbits] |= 1 << (bit % nbits); } /* Convert to correct endianity */ for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { struct vport_update_ramrod_mcast *p_ramrod_bins; - u32 *p_bins = (u32 *)bins; p_ramrod_bins = &p_ramrod->approx_mcast; - p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]); + p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 806a8da257e9..8d80f1095d17 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -215,7 +215,7 @@ struct qed_sp_vport_update_params { u8 anti_spoofing_en; u8 update_accept_any_vlan_flg; u8 accept_any_vlan; - unsigned long bins[8]; + u32 bins[8]; struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 5c10fd7210c3..758a9a5127fa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -371,7 +371,7 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev, goto err2; } - DP_INFO(cdev, "qed_probe completed successffuly\n"); + DP_INFO(cdev, "qed_probe completed successfully\n"); return cdev; @@ -789,6 +789,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev, /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; + if (is_kdump_kernel()) { + DP_INFO(cdev, + "Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n", + cdev->int_params.in.min_msix_cnt); + cdev->int_params.in.num_vectors = + cdev->int_params.in.min_msix_cnt; + } + rc = qed_set_int_mode(cdev, false); if (rc) { DP_ERR(cdev, "qed_slowpath_setup_int ERR\n"); diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 4e0b443c9519..cdd645024a32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -592,6 +592,9 @@ int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, *o_mcp_resp = mb_params.mcp_resp; *o_mcp_param = mb_params.mcp_param; + /* nvm_info needs to be updated */ + p_hwfn->nvm_info.valid = false; + return 0; } @@ -1208,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, break; default: p_link->speed = 0; + p_link->link_up = 0; } if (p_link->link_up && p_link->speed) @@ -1305,9 +1309,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0; phy_cfg.adv_speed = params->speed.advertised_speeds; phy_cfg.loopback_mode = params->loopback_mode; - if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { - if (params->eee.enable) - phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; + + /* There are MFWs that share this capability regardless of whether + * this is feasible or not. And given that at the very least adv_caps + * would be set internally by qed, we want to make sure LFA would + * still work. + */ + if ((p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) { + phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; if (params->eee.tx_lpi_enable) phy_cfg.eee_cfg |= EEE_CFG_TX_LPI; if (params->eee.adv_caps & QED_EEE_1G_ADV) @@ -2555,11 +2565,14 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn, int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) { - struct qed_nvm_image_info *nvm_info = &p_hwfn->nvm_info; + struct qed_nvm_image_info nvm_info; struct qed_ptt *p_ptt; int rc; u32 i; + if (p_hwfn->nvm_info.valid) + return 0; + p_ptt = qed_ptt_acquire(p_hwfn); if (!p_ptt) { DP_ERR(p_hwfn, "failed to acquire ptt\n"); @@ -2567,29 +2580,29 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) } /* Acquire from MFW the amount of available images */ - nvm_info->num_images = 0; + nvm_info.num_images = 0; rc = qed_mcp_bist_nvm_get_num_images(p_hwfn, - p_ptt, &nvm_info->num_images); + p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); goto out; - } else if (rc || !nvm_info->num_images) { + } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); goto err0; } - nvm_info->image_att = kmalloc_array(nvm_info->num_images, - sizeof(struct bist_nvm_image_att), - GFP_KERNEL); - if (!nvm_info->image_att) { + nvm_info.image_att = kmalloc_array(nvm_info.num_images, + sizeof(struct bist_nvm_image_att), + GFP_KERNEL); + if (!nvm_info.image_att) { rc = -ENOMEM; goto err0; } /* Iterate over images and get their attributes */ - for (i = 0; i < nvm_info->num_images; i++) { + for (i = 0; i < nvm_info.num_images; i++) { rc = qed_mcp_bist_nvm_get_image_att(p_hwfn, p_ptt, - &nvm_info->image_att[i], i); + &nvm_info.image_att[i], i); if (rc) { DP_ERR(p_hwfn, "Failed getting image index %d attributes\n", i); @@ -2597,14 +2610,22 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) } DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n", i, - nvm_info->image_att[i].len); + nvm_info.image_att[i].len); } out: + /* Update hwfn's nvm_info */ + if (nvm_info.num_images) { + p_hwfn->nvm_info.num_images = nvm_info.num_images; + kfree(p_hwfn->nvm_info.image_att); + p_hwfn->nvm_info.image_att = nvm_info.image_att; + p_hwfn->nvm_info.valid = true; + } + qed_ptt_release(p_hwfn, p_ptt); return 0; err1: - kfree(nvm_info->image_att); + kfree(nvm_info.image_att); err0: qed_ptt_release(p_hwfn, p_ptt); return rc; @@ -2641,6 +2662,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, return -EINVAL; } + qed_mcp_nvm_info_populate(p_hwfn); for (i = 0; i < p_hwfn->nvm_info.num_images; i++) if (type == p_hwfn->nvm_info.image_att[i].image_type) break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f01bf52bc381..26e918d7f2f9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn, p_data->update_approx_mcast_flg = 1; memcpy(p_data->bins, p_mcast_tlv->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); *tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST; } @@ -4513,6 +4513,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn, static int qed_sriov_enable(struct qed_dev *cdev, int num) { struct qed_iov_vf_init_params params; + struct qed_hwfn *hwfn; + struct qed_ptt *ptt; int i, j, rc; if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) { @@ -4525,8 +4527,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) /* Initialize HW for VF access */ for_each_hwfn(cdev, j) { - struct qed_hwfn *hwfn = &cdev->hwfns[j]; - struct qed_ptt *ptt = qed_ptt_acquire(hwfn); + hwfn = &cdev->hwfns[j]; + ptt = qed_ptt_acquire(hwfn); /* Make sure not to use more than 16 queues per VF */ params.num_queues = min_t(int, @@ -4562,6 +4564,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num) goto err; } + hwfn = QED_LEADING_HWFN(cdev); + ptt = qed_ptt_acquire(hwfn); + if (!ptt) { + DP_ERR(hwfn, "Failed to acquire ptt\n"); + rc = -EBUSY; + goto err; + } + + rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB); + if (rc) + DP_INFO(cdev, "Failed to update eswitch mode\n"); + qed_ptt_release(hwfn, ptt); + return num; err: diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 2d7fcd6a0777..be6ddde1a104 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, resp_size += sizeof(struct pfvf_def_resp_tlv); memcpy(p_mcast_tlv->bins, p_params->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); } update_rx = p_params->accept_flags.update_rx_mode_config; @@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn, u32 bit; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, sp_params.bins); + sp_params.bins[bit / 32] |= 1 << (bit % 32); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 4f05d5eb3cf5..033409db86ae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv { struct channel_tlv tl; u8 padding[4]; - u64 bins[8]; + /* There are only 256 approx bins, and in HSI they're divided into + * 32-bit values. As old VFs used to set-bit to the values on its side, + * the upper half of the array is never expected to contain any data. + */ + u64 bins[4]; + u64 obsolete_bins[4]; }; struct vfpf_vport_update_accept_param_tlv { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 02adb513f475..013ff567283c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info) { struct qede_ptp *ptp = edev->ptp; - if (!ptp) - return -EIO; + if (!ptp) { + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; + } info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 891f03a7a33d..8d7b9bb910f2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -1128,6 +1128,8 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, struct qlcnic_adapter *adapter = dev_get_drvdata(dev); ret = kstrtoul(buf, 16, &data); + if (ret) + return ret; switch (data) { case QLC_83XX_FLASH_SECTOR_ERASE_CMD: diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5803cd6db406..206f0266463e 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -658,7 +658,7 @@ qcaspi_netdev_open(struct net_device *dev) return ret; } - netif_start_queue(qca->net_dev); + /* SPI thread takes care of TX queue */ return 0; } @@ -760,6 +760,9 @@ qcaspi_netdev_tx_timeout(struct net_device *dev) qca->net_dev->stats.tx_errors++; /* Trigger tx queue flush and QCA7000 reset */ qca->sync = QCASPI_SYNC_UNKNOWN; + + if (qca->spi_thread) + wake_up_process(qca->spi_thread); } static int @@ -878,22 +881,22 @@ qca_spi_probe(struct spi_device *spi) if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) || (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) { - dev_info(&spi->dev, "Invalid clkspeed: %d\n", - qcaspi_clkspeed); + dev_err(&spi->dev, "Invalid clkspeed: %d\n", + qcaspi_clkspeed); return -EINVAL; } if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) || (qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) { - dev_info(&spi->dev, "Invalid burst len: %d\n", - qcaspi_burst_len); + dev_err(&spi->dev, "Invalid burst len: %d\n", + qcaspi_burst_len); return -EINVAL; } if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) || (qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) { - dev_info(&spi->dev, "Invalid pluggable: %d\n", - qcaspi_pluggable); + dev_err(&spi->dev, "Invalid pluggable: %d\n", + qcaspi_pluggable); return -EINVAL; } @@ -955,8 +958,8 @@ qca_spi_probe(struct spi_device *spi) } if (register_netdev(qcaspi_devs)) { - dev_info(&spi->dev, "Unable to register net device %s\n", - qcaspi_devs->name); + dev_err(&spi->dev, "Unable to register net device %s\n", + qcaspi_devs->name); free_netdev(qcaspi_devs); return -EFAULT; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index f4cae2be0fda..eaedc11ed686 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7734,8 +7734,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } - /* override BIOS settings, use userspace tools to enable WOL */ - __rtl8169_set_wol(tp, 0); + tp->saved_wolopts = __rtl8169_get_wol(tp); if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; @@ -7789,6 +7788,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_RX; dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_HIGHDMA; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; tp->cp_cmd |= RxChkSum | RxVlan; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 68f122140966..0d811c02ff34 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -980,6 +980,13 @@ static void ravb_adjust_link(struct net_device *ndev) struct ravb_private *priv = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; bool new_state = false; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* Disable TX and RX right over here, if E-MAC change is ignored */ + if (priv->no_avb_link) + ravb_rcv_snd_disable(ndev); if (phydev->link) { if (phydev->duplex != priv->duplex) { @@ -997,18 +1004,21 @@ static void ravb_adjust_link(struct net_device *ndev) ravb_modify(ndev, ECMR, ECMR_TXF, 0); new_state = true; priv->link = phydev->link; - if (priv->no_avb_link) - ravb_rcv_snd_enable(ndev); } } else if (priv->link) { new_state = true; priv->link = 0; priv->speed = 0; priv->duplex = -1; - if (priv->no_avb_link) - ravb_rcv_snd_disable(ndev); } + /* Enable TX and RX right over here, if E-MAC change is ignored */ + if (priv->no_avb_link && phydev->link) + ravb_rcv_snd_enable(ndev); + + mmiowb(); + spin_unlock_irqrestore(&priv->lock, flags); + if (new_state && netif_msg_link(priv)) phy_print_status(phydev); } @@ -1096,75 +1106,6 @@ static int ravb_phy_start(struct net_device *ndev) return 0; } -static int ravb_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *cmd) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned long flags; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&priv->lock, flags); - phy_ethtool_ksettings_get(ndev->phydev, cmd); - spin_unlock_irqrestore(&priv->lock, flags); - - return 0; -} - -static int ravb_set_link_ksettings(struct net_device *ndev, - const struct ethtool_link_ksettings *cmd) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned long flags; - int error; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&priv->lock, flags); - - /* Disable TX and RX */ - ravb_rcv_snd_disable(ndev); - - error = phy_ethtool_ksettings_set(ndev->phydev, cmd); - if (error) - goto error_exit; - - if (cmd->base.duplex == DUPLEX_FULL) - priv->duplex = 1; - else - priv->duplex = 0; - - ravb_set_duplex(ndev); - -error_exit: - mdelay(1); - - /* Enable TX and RX */ - ravb_rcv_snd_enable(ndev); - - mmiowb(); - spin_unlock_irqrestore(&priv->lock, flags); - - return error; -} - -static int ravb_nway_reset(struct net_device *ndev) -{ - struct ravb_private *priv = netdev_priv(ndev); - int error = -ENODEV; - unsigned long flags; - - if (ndev->phydev) { - spin_lock_irqsave(&priv->lock, flags); - error = phy_start_aneg(ndev->phydev); - spin_unlock_irqrestore(&priv->lock, flags); - } - - return error; -} - static u32 ravb_get_msglevel(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); @@ -1377,7 +1318,7 @@ static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) } static const struct ethtool_ops ravb_ethtool_ops = { - .nway_reset = ravb_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_msglevel = ravb_get_msglevel, .set_msglevel = ravb_set_msglevel, .get_link = ethtool_op_get_link, @@ -1387,8 +1328,8 @@ static const struct ethtool_ops ravb_ethtool_ops = { .get_ringparam = ravb_get_ringparam, .set_ringparam = ravb_set_ringparam, .get_ts_info = ravb_get_ts_info, - .get_link_ksettings = ravb_get_link_ksettings, - .set_link_ksettings = ravb_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_wol = ravb_get_wol, .set_wol = ravb_set_wol, }; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index e9007b613f17..5614fd231bbe 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1927,8 +1927,15 @@ static void sh_eth_adjust_link(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; + unsigned long flags; int new_state = 0; + spin_lock_irqsave(&mdp->lock, flags); + + /* Disable TX and RX right over here, if E-MAC change is ignored */ + if (mdp->cd->no_psr || mdp->no_ether_link) + sh_eth_rcv_snd_disable(ndev); + if (phydev->link) { if (phydev->duplex != mdp->duplex) { new_state = 1; @@ -1947,18 +1954,21 @@ static void sh_eth_adjust_link(struct net_device *ndev) sh_eth_modify(ndev, ECMR, ECMR_TXF, 0); new_state = 1; mdp->link = phydev->link; - if (mdp->cd->no_psr || mdp->no_ether_link) - sh_eth_rcv_snd_enable(ndev); } } else if (mdp->link) { new_state = 1; mdp->link = 0; mdp->speed = 0; mdp->duplex = -1; - if (mdp->cd->no_psr || mdp->no_ether_link) - sh_eth_rcv_snd_disable(ndev); } + /* Enable TX and RX right over here, if E-MAC change is ignored */ + if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link) + sh_eth_rcv_snd_enable(ndev); + + mmiowb(); + spin_unlock_irqrestore(&mdp->lock, flags); + if (new_state && netif_msg_link(mdp)) phy_print_status(phydev); } @@ -2030,60 +2040,6 @@ static int sh_eth_phy_start(struct net_device *ndev) return 0; } -static int sh_eth_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *cmd) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - phy_ethtool_ksettings_get(ndev->phydev, cmd); - spin_unlock_irqrestore(&mdp->lock, flags); - - return 0; -} - -static int sh_eth_set_link_ksettings(struct net_device *ndev, - const struct ethtool_link_ksettings *cmd) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - int ret; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - - /* disable tx and rx */ - sh_eth_rcv_snd_disable(ndev); - - ret = phy_ethtool_ksettings_set(ndev->phydev, cmd); - if (ret) - goto error_exit; - - if (cmd->base.duplex == DUPLEX_FULL) - mdp->duplex = 1; - else - mdp->duplex = 0; - - if (mdp->cd->set_duplex) - mdp->cd->set_duplex(ndev); - -error_exit: - mdelay(1); - - /* enable tx and rx */ - sh_eth_rcv_snd_enable(ndev); - - spin_unlock_irqrestore(&mdp->lock, flags); - - return ret; -} - /* If it is ever necessary to increase SH_ETH_REG_DUMP_MAX_REGS, the * version must be bumped as well. Just adding registers up to that * limit is fine, as long as the existing register indices don't @@ -2263,22 +2219,6 @@ static void sh_eth_get_regs(struct net_device *ndev, struct ethtool_regs *regs, pm_runtime_put_sync(&mdp->pdev->dev); } -static int sh_eth_nway_reset(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - unsigned long flags; - int ret; - - if (!ndev->phydev) - return -ENODEV; - - spin_lock_irqsave(&mdp->lock, flags); - ret = phy_start_aneg(ndev->phydev); - spin_unlock_irqrestore(&mdp->lock, flags); - - return ret; -} - static u32 sh_eth_get_msglevel(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); @@ -2429,7 +2369,7 @@ static int sh_eth_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) static const struct ethtool_ops sh_eth_ethtool_ops = { .get_regs_len = sh_eth_get_regs_len, .get_regs = sh_eth_get_regs, - .nway_reset = sh_eth_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_msglevel = sh_eth_get_msglevel, .set_msglevel = sh_eth_set_msglevel, .get_link = ethtool_op_get_link, @@ -2438,8 +2378,8 @@ static const struct ethtool_ops sh_eth_ethtool_ops = { .get_sset_count = sh_eth_get_sset_count, .get_ringparam = sh_eth_get_ringparam, .set_ringparam = sh_eth_set_ringparam, - .get_link_ksettings = sh_eth_get_link_ksettings, - .set_link_ksettings = sh_eth_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_wol = sh_eth_get_wol, .set_wol = sh_eth_set_wol, }; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 23f0785c0573..7eeac3d6cfe8 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -4288,9 +4288,9 @@ static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table, return -EPROTONOSUPPORT; } -static s32 efx_ef10_filter_insert(struct efx_nic *efx, - struct efx_filter_spec *spec, - bool replace_equal) +static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx, + struct efx_filter_spec *spec, + bool replace_equal) { DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT); struct efx_ef10_nic_data *nic_data = efx->nic_data; @@ -4307,7 +4307,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx, bool is_mc_recip; s32 rc; - down_read(&efx->filter_sem); + WARN_ON(!rwsem_is_locked(&efx->filter_sem)); table = efx->filter_state; down_write(&table->lock); @@ -4498,10 +4498,22 @@ out_unlock: if (rss_locked) mutex_unlock(&efx->rss_lock); up_write(&table->lock); - up_read(&efx->filter_sem); return rc; } +static s32 efx_ef10_filter_insert(struct efx_nic *efx, + struct efx_filter_spec *spec, + bool replace_equal) +{ + s32 ret; + + down_read(&efx->filter_sem); + ret = efx_ef10_filter_insert_locked(efx, spec, replace_equal); + up_read(&efx->filter_sem); + + return ret; +} + static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx) { /* no need to do anything here on EF10 */ @@ -5285,7 +5297,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID); efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { if (rollback) { netif_info(efx, drv, efx->net_dev, @@ -5314,7 +5326,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, vlan->vid, baddr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { netif_warn(efx, drv, efx->net_dev, "Broadcast filter insert failed rc=%d\n", rc); @@ -5370,7 +5382,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, if (vlan->vid != EFX_FILTER_VID_UNSPEC) efx_filter_set_eth_local(&spec, vlan->vid, NULL); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { const char *um = multicast ? "Multicast" : "Unicast"; const char *encap_name = ""; @@ -5430,7 +5442,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx, filter_flags, 0); eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, vlan->vid, baddr); - rc = efx_ef10_filter_insert(efx, &spec, true); + rc = efx_ef10_filter_insert_locked(efx, &spec, true); if (rc < 0) { netif_warn(efx, drv, efx->net_dev, "Broadcast filter insert failed rc=%d\n", diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 570ec72266f3..ce3a177081a8 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1871,12 +1871,6 @@ static void efx_remove_filters(struct efx_nic *efx) up_write(&efx->filter_sem); } -static void efx_restore_filters(struct efx_nic *efx) -{ - down_read(&efx->filter_sem); - efx->type->filter_table_restore(efx); - up_read(&efx->filter_sem); -} /************************************************************************** * @@ -2688,6 +2682,7 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method) efx_disable_interrupts(efx); mutex_lock(&efx->mac_lock); + down_write(&efx->filter_sem); mutex_lock(&efx->rss_lock); if (efx->port_initialized && method != RESET_TYPE_INVISIBLE && method != RESET_TYPE_DATAPATH) @@ -2745,9 +2740,8 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) if (efx->type->rx_restore_rss_contexts) efx->type->rx_restore_rss_contexts(efx); mutex_unlock(&efx->rss_lock); - down_read(&efx->filter_sem); - efx_restore_filters(efx); - up_read(&efx->filter_sem); + efx->type->filter_table_restore(efx); + up_write(&efx->filter_sem); if (efx->type->sriov_reset) efx->type->sriov_reset(efx); @@ -2764,6 +2758,7 @@ fail: efx->port_initialized = false; mutex_unlock(&efx->rss_lock); + up_write(&efx->filter_sem); mutex_unlock(&efx->mac_lock); return rc; @@ -3473,7 +3468,9 @@ static int efx_pci_probe_main(struct efx_nic *efx) efx_init_napi(efx); + down_write(&efx->filter_sem); rc = efx->type->init(efx); + up_write(&efx->filter_sem); if (rc) { netif_err(efx, probe, efx->net_dev, "failed to initialise NIC\n"); @@ -3765,7 +3762,9 @@ static int efx_pm_resume(struct device *dev) rc = efx->type->reset(efx, RESET_TYPE_ALL); if (rc) return rc; + down_write(&efx->filter_sem); rc = efx->type->init(efx); + up_write(&efx->filter_sem); if (rc) return rc; rc = efx_pm_thaw(dev); diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 8edf20967c82..e045a5d6b938 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx) if (!state) return -ENOMEM; efx->filter_state = state; + init_rwsem(&state->lock); table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP]; table->id = EFX_FARCH_FILTER_TABLE_RX_IP; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 2e6e2a96b4f2..f9a61f90cfbc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -37,7 +37,7 @@ * is done in the "stmmac files" */ -/* struct emac_variant - Descrive dwmac-sun8i hardware variant +/* struct emac_variant - Describe dwmac-sun8i hardware variant * @default_syscon_value: The default value of the EMAC register in syscon * This value is used for disabling properly EMAC * and used as a good starting value in case of the diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index d37f17ca62fe..65bc3556bd8f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -407,6 +407,16 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan) } } +static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) +{ + u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan)); + + value &= ~DMA_RBSZ_MASK; + value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK; + + writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan)); +} + const struct stmmac_dma_ops dwmac4_dma_ops = { .reset = dwmac4_dma_reset, .init = dwmac4_dma_init, @@ -431,6 +441,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .set_bfsize = dwmac4_set_bfsize, }; const struct stmmac_dma_ops dwmac410_dma_ops = { @@ -457,4 +468,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = { .set_rx_tail_ptr = dwmac4_set_rx_tail_ptr, .set_tx_tail_ptr = dwmac4_set_tx_tail_ptr, .enable_tso = dwmac4_enable_tso, + .set_bfsize = dwmac4_set_bfsize, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index c63c1fe3f26b..22a4a6dbb1a4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -120,6 +120,8 @@ /* DMA Rx Channel X Control register defines */ #define DMA_CONTROL_SR BIT(0) +#define DMA_RBSZ_MASK GENMASK(14, 1) +#define DMA_RBSZ_SHIFT 1 /* Interrupt status per channel */ #define DMA_CHAN_STATUS_REB GENMASK(21, 19) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e44e7b26ce82..fe8b536b13f8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -183,6 +183,7 @@ struct stmmac_dma_ops { void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); + void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan); }; #define stmmac_reset(__priv, __args...) \ @@ -235,6 +236,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args) #define stmmac_enable_tso(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, enable_tso, __args) +#define stmmac_set_dma_bfsize(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_bfsize, __args) struct mac_device_info; struct net_device; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cba46b62a1cd..60f59abab009 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1804,6 +1804,8 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz, qmode); + stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz, + chan); } for (chan = 0; chan < tx_channels_count; chan++) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6d141f3931eb..72da77b94ecd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -94,7 +94,6 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) /** * stmmac_axi_setup - parse DT parameters for programming the AXI register * @pdev: platform device - * @priv: driver private struct. * Description: * if required, from device-tree the AXI internal register can be tuned * by using platform parameters. diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 16c3bfbe1992..757a3b37ae8a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -218,6 +218,7 @@ issue: ret = of_mdiobus_register(bus, np1); if (ret) { mdiobus_free(bus); + lp->mii_bus = NULL; return ret; } return 0; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 750eaa53bf0c..ada33c2d9ac2 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -476,7 +476,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 1a924b867b07..4b6e308199d2 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -210,7 +210,7 @@ int netvsc_recv_callback(struct net_device *net, void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); -void rndis_set_subchannel(struct work_struct *w); +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 5d5bd513847f..31c3d77b4733 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -65,6 +65,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) VM_PKT_DATA_INBAND, 0); } +/* Worker to setup sub channels on initial setup + * Initial hotplug event occurs in softirq context + * and can't wait for channels. + */ +static void netvsc_subchan_work(struct work_struct *w) +{ + struct netvsc_device *nvdev = + container_of(w, struct netvsc_device, subchan_work); + struct rndis_device *rdev; + int i, ret; + + /* Avoid deadlock with device removal already under RTNL */ + if (!rtnl_trylock()) { + schedule_work(w); + return; + } + + rdev = nvdev->extension; + if (rdev) { + ret = rndis_set_subchannel(rdev->ndev, nvdev); + if (ret == 0) { + netif_device_attach(rdev->ndev); + } else { + /* fallback to only primary channel */ + for (i = 1; i < nvdev->num_chn; i++) + netif_napi_del(&nvdev->chan_table[i].napi); + + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + rtnl_unlock(); +} + static struct netvsc_device *alloc_net_device(void) { struct netvsc_device *net_device; @@ -81,7 +116,7 @@ static struct netvsc_device *alloc_net_device(void) init_completion(&net_device->channel_init_wait); init_waitqueue_head(&net_device->subchan_open); - INIT_WORK(&net_device->subchan_work, rndis_set_subchannel); + INIT_WORK(&net_device->subchan_work, netvsc_subchan_work); return net_device; } @@ -1239,6 +1274,7 @@ int netvsc_poll(struct napi_struct *napi, int budget) struct hv_device *device = netvsc_channel_to_device(channel); struct net_device *ndev = hv_get_drvdata(device); int work_done = 0; + int ret; /* If starting a new interval */ if (!nvchan->desc) @@ -1250,16 +1286,18 @@ int netvsc_poll(struct napi_struct *napi, int budget) nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc); } - /* If send of pending receive completions suceeded - * and did not exhaust NAPI budget this time - * and not doing busy poll + /* Send any pending receive completions */ + ret = send_recv_completions(ndev, net_device, nvchan); + + /* If it did not exhaust NAPI budget this time + * and not doing busy poll * then re-enable host interrupts - * and reschedule if ring is not empty. + * and reschedule if ring is not empty + * or sending receive completion failed. */ - if (send_recv_completions(ndev, net_device, nvchan) == 0 && - work_done < budget && + if (work_done < budget && napi_complete_done(napi, work_done) && - hv_end_read(&channel->inbound) && + (ret || hv_end_read(&channel->inbound)) && napi_schedule_prep(napi)) { hv_begin_read(&channel->inbound); __napi_schedule(napi); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index fe2256bf1d13..dd1d6e115145 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev, if (IS_ERR(nvdev)) return PTR_ERR(nvdev); - /* Note: enable and attach happen when sub-channels setup */ + if (nvdev->num_chn > 1) { + ret = rndis_set_subchannel(ndev, nvdev); + + /* if unavailable, just proceed with one queue */ + if (ret) { + nvdev->max_chn = 1; + nvdev->num_chn = 1; + } + } + + /* In any case device is now ready */ + netif_device_attach(ndev); + /* Note: enable and attach happen when sub-channels setup */ netif_carrier_off(ndev); if (netif_running(ndev)) { @@ -2089,6 +2101,9 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + if (nvdev->num_chn > 1) + schedule_work(&nvdev->subchan_work); + /* hw_features computed in rndis_netdev_set_hwcaps() */ net->features = net->hw_features | NETIF_F_HIGHDMA | NETIF_F_SG | diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 5428bb261102..408ece27131c 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1062,29 +1062,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) * This breaks overlap of processing the host message for the * new primary channel with the initialization of sub-channels. */ -void rndis_set_subchannel(struct work_struct *w) +int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev) { - struct netvsc_device *nvdev - = container_of(w, struct netvsc_device, subchan_work); struct nvsp_message *init_packet = &nvdev->channel_init_pkt; - struct net_device_context *ndev_ctx; - struct rndis_device *rdev; - struct net_device *ndev; - struct hv_device *hv_dev; + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hv_dev = ndev_ctx->device_ctx; + struct rndis_device *rdev = nvdev->extension; int i, ret; - if (!rtnl_trylock()) { - schedule_work(w); - return; - } - - rdev = nvdev->extension; - if (!rdev) - goto unlock; /* device was removed */ - - ndev = rdev->ndev; - ndev_ctx = netdev_priv(ndev); - hv_dev = ndev_ctx->device_ctx; + ASSERT_RTNL(); memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL; @@ -1100,13 +1086,13 @@ void rndis_set_subchannel(struct work_struct *w) VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret) { netdev_err(ndev, "sub channel allocate send failed: %d\n", ret); - goto failed; + return ret; } wait_for_completion(&nvdev->channel_init_wait); if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) { netdev_err(ndev, "sub channel request failed\n"); - goto failed; + return -EIO; } nvdev->num_chn = 1 + @@ -1125,21 +1111,7 @@ void rndis_set_subchannel(struct work_struct *w) for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; - netif_device_attach(ndev); - rtnl_unlock(); - return; - -failed: - /* fallback to only primary channel */ - for (i = 1; i < nvdev->num_chn; i++) - netif_napi_del(&nvdev->chan_table[i].napi); - - nvdev->max_chn = 1; - nvdev->num_chn = 1; - - netif_device_attach(ndev); -unlock: - rtnl_unlock(); + return 0; } static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, @@ -1360,21 +1332,13 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, netif_napi_add(net, &net_device->chan_table[i].napi, netvsc_poll, NAPI_POLL_WEIGHT); - if (net_device->num_chn > 1) - schedule_work(&net_device->subchan_work); + return net_device; out: - /* if unavailable, just proceed with one queue */ - if (ret) { - net_device->max_chn = 1; - net_device->num_chn = 1; - } - - /* No sub channels, device is ready */ - if (net_device->num_chn == 1) - netif_device_attach(net); - - return net_device; + /* setting up multiple channels failed */ + net_device->max_chn = 1; + net_device->num_chn = 1; + return 0; err_dev_remv: rndis_filter_device_remove(dev, net_device); diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 64f1b1e77bc0..23a52b9293f3 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -275,6 +275,8 @@ struct adf7242_local { struct spi_message stat_msg; struct spi_transfer stat_xfer; struct dentry *debugfs_root; + struct delayed_work work; + struct workqueue_struct *wqueue; unsigned long flags; int tx_stat; bool promiscuous; @@ -575,10 +577,26 @@ static int adf7242_cmd_rx(struct adf7242_local *lp) /* Wait until the ACK is sent */ adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__); adf7242_clear_irqstat(lp); + mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400)); return adf7242_cmd(lp, CMD_RC_RX); } +static void adf7242_rx_cal_work(struct work_struct *work) +{ + struct adf7242_local *lp = + container_of(work, struct adf7242_local, work.work); + + /* Reissuing RC_RX every 400ms - to adjust for offset + * drift in receiver (datasheet page 61, OCL section) + */ + + if (!test_bit(FLAG_XMIT, &lp->flags)) { + adf7242_cmd(lp, CMD_RC_PHY_RDY); + adf7242_cmd_rx(lp); + } +} + static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm) { struct adf7242_local *lp = hw->priv; @@ -686,7 +704,7 @@ static int adf7242_start(struct ieee802154_hw *hw) enable_irq(lp->spi->irq); set_bit(FLAG_START, &lp->flags); - return adf7242_cmd(lp, CMD_RC_RX); + return adf7242_cmd_rx(lp); } static void adf7242_stop(struct ieee802154_hw *hw) @@ -694,6 +712,7 @@ static void adf7242_stop(struct ieee802154_hw *hw) struct adf7242_local *lp = hw->priv; disable_irq(lp->spi->irq); + cancel_delayed_work_sync(&lp->work); adf7242_cmd(lp, CMD_RC_IDLE); clear_bit(FLAG_START, &lp->flags); adf7242_clear_irqstat(lp); @@ -719,7 +738,10 @@ static int adf7242_channel(struct ieee802154_hw *hw, u8 page, u8 channel) adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8); adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16); - return adf7242_cmd(lp, CMD_RC_RX); + if (test_bit(FLAG_START, &lp->flags)) + return adf7242_cmd_rx(lp); + else + return adf7242_cmd(lp, CMD_RC_PHY_RDY); } static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw, @@ -814,6 +836,7 @@ static int adf7242_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) /* ensure existing instances of the IRQ handler have completed */ disable_irq(lp->spi->irq); set_bit(FLAG_XMIT, &lp->flags); + cancel_delayed_work_sync(&lp->work); reinit_completion(&lp->tx_complete); adf7242_cmd(lp, CMD_RC_PHY_RDY); adf7242_clear_irqstat(lp); @@ -952,6 +975,7 @@ static irqreturn_t adf7242_isr(int irq, void *data) unsigned int xmit; u8 irq1; + mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400)); adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1); if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA))) @@ -1241,6 +1265,9 @@ static int adf7242_probe(struct spi_device *spi) spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg); spi_set_drvdata(spi, lp); + INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work); + lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev), + WQ_MEM_RECLAIM); ret = adf7242_hw_init(lp); if (ret) @@ -1284,6 +1311,9 @@ static int adf7242_remove(struct spi_device *spi) if (!IS_ERR_OR_NULL(lp->debugfs_root)) debugfs_remove_recursive(lp->debugfs_root); + cancel_delayed_work_sync(&lp->work); + destroy_workqueue(lp->wqueue); + ieee802154_unregister_hw(lp->hw); mutex_destroy(&lp->bmux); ieee802154_free_hw(lp->hw); diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 77abedf0b524..3d9e91579866 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -940,7 +940,7 @@ at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) static int at86rf230_ed(struct ieee802154_hw *hw, u8 *level) { - BUG_ON(!level); + WARN_ON(!level); *level = 0xbe; return 0; } @@ -1121,8 +1121,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, if (changed & IEEE802154_AFILT_SADDR_CHANGED) { u16 addr = le16_to_cpu(filt->short_addr); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for saddr\n"); + dev_vdbg(&lp->spi->dev, "%s called for saddr\n", __func__); __at86rf230_write(lp, RG_SHORT_ADDR_0, addr); __at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8); } @@ -1130,8 +1129,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, if (changed & IEEE802154_AFILT_PANID_CHANGED) { u16 pan = le16_to_cpu(filt->pan_id); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for pan id\n"); + dev_vdbg(&lp->spi->dev, "%s called for pan id\n", __func__); __at86rf230_write(lp, RG_PAN_ID_0, pan); __at86rf230_write(lp, RG_PAN_ID_1, pan >> 8); } @@ -1140,15 +1138,13 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw, u8 i, addr[8]; memcpy(addr, &filt->ieee_addr, 8); - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for IEEE addr\n"); + dev_vdbg(&lp->spi->dev, "%s called for IEEE addr\n", __func__); for (i = 0; i < 8; i++) __at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]); } if (changed & IEEE802154_AFILT_PANC_CHANGED) { - dev_vdbg(&lp->spi->dev, - "at86rf230_set_hw_addr_filt called for panc change\n"); + dev_vdbg(&lp->spi->dev, "%s called for panc change\n", __func__); if (filt->pan_coord) at86rf230_write_subreg(lp, SR_AACK_I_AM_COORD, 1); else @@ -1252,7 +1248,6 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw, return at86rf230_write_subreg(lp, SR_CCA_MODE, val); } - static int at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm) { diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c index 0d673f7682ee..176395e4b7bb 100644 --- a/drivers/net/ieee802154/fakelb.c +++ b/drivers/net/ieee802154/fakelb.c @@ -49,7 +49,7 @@ struct fakelb_phy { static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level) { - BUG_ON(!level); + WARN_ON(!level); *level = 0xbe; return 0; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index de0d7f28a181..e428277781ac 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -15,10 +15,11 @@ */ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/spi/spi.h> #include <linux/workqueue.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/skbuff.h> #include <linux/of_gpio.h> #include <linux/regmap.h> diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 23c1d6600241..4a949569ec4c 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -75,10 +75,23 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) { struct ipvl_dev *ipvlan; struct net_device *mdev = port->dev; - int err = 0; + unsigned int flags; + int err; ASSERT_RTNL(); if (port->mode != nval) { + list_for_each_entry(ipvlan, &port->ipvlans, pnode) { + flags = ipvlan->dev->flags; + if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { + err = dev_change_flags(ipvlan->dev, + flags | IFF_NOARP); + } else { + err = dev_change_flags(ipvlan->dev, + flags & ~IFF_NOARP); + } + if (unlikely(err)) + goto fail; + } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); @@ -86,21 +99,28 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval) mdev->l3mdev_ops = &ipvl_l3mdev_ops; mdev->priv_flags |= IFF_L3MDEV_MASTER; } else - return err; + goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ mdev->priv_flags &= ~IFF_L3MDEV_MASTER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); mdev->l3mdev_ops = NULL; } - list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) - ipvlan->dev->flags |= IFF_NOARP; - else - ipvlan->dev->flags &= ~IFF_NOARP; - } port->mode = nval; } + return 0; + +fail: + /* Undo the flags changes that have been done so far. */ + list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { + flags = ipvlan->dev->flags; + if (port->mode == IPVLAN_MODE_L3 || + port->mode == IPVLAN_MODE_L3S) + dev_change_flags(ipvlan->dev, flags | IFF_NOARP); + else + dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP); + } + return err; } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 081d99aa3985..49ac678eb2dc 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -222,7 +222,7 @@ static int dp83811_config_intr(struct phy_device *phydev) if (err < 0) return err; - err = phy_write(phydev, MII_DP83811_INT_STAT1, 0); + err = phy_write(phydev, MII_DP83811_INT_STAT2, 0); } return err; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b8f57e9b9379..1cd439bdf608 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -130,8 +130,9 @@ #define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS BIT(12) #define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE BIT(14) -#define MII_88E1121_PHY_LED_CTRL 16 +#define MII_PHY_LED_CTRL 16 #define MII_88E1121_PHY_LED_DEF 0x0030 +#define MII_88E1510_PHY_LED_DEF 0x1177 #define MII_M1011_PHY_STATUS 0x11 #define MII_M1011_PHY_STATUS_1000 0x8000 @@ -632,8 +633,40 @@ error: return err; } +static void marvell_config_led(struct phy_device *phydev) +{ + u16 def_config; + int err; + + switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) { + /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R): + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1318S): + def_config = MII_88E1121_PHY_LED_DEF; + break; + /* Default PHY LED config: + * LED[0] .. 1000Mbps Link + * LED[1] .. 100Mbps Link + * LED[2] .. Blink, Activity + */ + case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510): + def_config = MII_88E1510_PHY_LED_DEF; + break; + default: + return; + } + + err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL, + def_config); + if (err < 0) + pr_warn("Fail to config marvell phy LED.\n"); +} + static int marvell_config_init(struct phy_device *phydev) { + /* Set defalut LED */ + marvell_config_led(phydev); + /* Set registers from marvell,reg-init DT property */ return marvell_of_reg_init(phydev); } @@ -813,21 +846,6 @@ static int m88e1111_config_init(struct phy_device *phydev) return genphy_soft_reset(phydev); } -static int m88e1121_config_init(struct phy_device *phydev) -{ - int err; - - /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ - err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, - MII_88E1121_PHY_LED_CTRL, - MII_88E1121_PHY_LED_DEF); - if (err < 0) - return err; - - /* Set marvell,reg-init configuration from device tree */ - return marvell_config_init(phydev); -} - static int m88e1318_config_init(struct phy_device *phydev) { if (phy_interrupt_is_valid(phydev)) { @@ -841,7 +859,7 @@ static int m88e1318_config_init(struct phy_device *phydev) return err; } - return m88e1121_config_init(phydev); + return marvell_config_init(phydev); } static int m88e1510_config_init(struct phy_device *phydev) @@ -2087,7 +2105,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = &m88e1121_probe, - .config_init = &m88e1121_config_init, + .config_init = &marvell_config_init, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 537297d2b4b4..6c9b24fe3148 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bd0f339f69fd..b9f5f40a7ac1 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1724,11 +1724,8 @@ EXPORT_SYMBOL(genphy_loopback); static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) { - /* The default values for phydev->supported are provided by the PHY - * driver "features" member, we want to reset to sane defaults first - * before supporting higher speeds. - */ - phydev->supported &= PHY_DEFAULT_FEATURES; + phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES | + PHY_10BT_FEATURES); switch (max_speed) { default: diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index d437f4f5ed52..740655261e5b 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -349,7 +349,6 @@ static int sfp_register_bus(struct sfp_bus *bus) } if (bus->started) bus->socket_ops->start(bus->sfp); - bus->netdev->sfp_bus = bus; bus->registered = true; return 0; } @@ -364,7 +363,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } - bus->netdev->sfp_bus = NULL; bus->registered = false; } @@ -436,6 +434,14 @@ void sfp_upstream_stop(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_upstream_stop); +static void sfp_upstream_clear(struct sfp_bus *bus) +{ + bus->upstream_ops = NULL; + bus->upstream = NULL; + bus->netdev->sfp_bus = NULL; + bus->netdev = NULL; +} + /** * sfp_register_upstream() - Register the neighbouring device * @fwnode: firmware node for the SFP bus @@ -461,9 +467,13 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, bus->upstream_ops = ops; bus->upstream = upstream; bus->netdev = ndev; + ndev->sfp_bus = bus; - if (bus->sfp) + if (bus->sfp) { ret = sfp_register_bus(bus); + if (ret) + sfp_upstream_clear(bus); + } rtnl_unlock(); } @@ -488,8 +498,7 @@ void sfp_unregister_upstream(struct sfp_bus *bus) rtnl_lock(); if (bus->sfp) sfp_unregister_bus(bus); - bus->upstream = NULL; - bus->netdev = NULL; + sfp_upstream_clear(bus); rtnl_unlock(); sfp_bus_put(bus); @@ -561,6 +570,13 @@ void sfp_module_remove(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_module_remove); +static void sfp_socket_clear(struct sfp_bus *bus) +{ + bus->sfp_dev = NULL; + bus->sfp = NULL; + bus->socket_ops = NULL; +} + struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp, const struct sfp_socket_ops *ops) { @@ -573,8 +589,11 @@ struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp, bus->sfp = sfp; bus->socket_ops = ops; - if (bus->netdev) + if (bus->netdev) { ret = sfp_register_bus(bus); + if (ret) + sfp_socket_clear(bus); + } rtnl_unlock(); } @@ -592,9 +611,7 @@ void sfp_unregister_socket(struct sfp_bus *bus) rtnl_lock(); if (bus->netdev) sfp_unregister_bus(bus); - bus->sfp_dev = NULL; - bus->sfp = NULL; - bus->socket_ops = NULL; + sfp_socket_clear(bus); rtnl_unlock(); sfp_bus_put(bus); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a192a017cc68..f5727baac84a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1688,7 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_TX: get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (tun_xdp_tx(tun->dev, &xdp)) + if (tun_xdp_tx(tun->dev, &xdp) < 0) goto err_redirect; rcu_read_unlock(); local_bh_enable(); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 3d4f7959dabb..b1b3d8f7e67d 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev) priv->presvd_phy_advertise); /* Restore BMCR */ + if (priv->presvd_phy_bmcr & BMCR_ANENABLE) + priv->presvd_phy_bmcr |= BMCR_ANRESTART; + asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR, priv->presvd_phy_bmcr); - mii_nway_restart(&dev->mii); priv->presvd_phy_advertise = 0; priv->presvd_phy_bmcr = 0; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 8dff87ec6d99..ed10d49eb5e0 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -64,6 +64,7 @@ #define DEFAULT_RX_CSUM_ENABLE (true) #define DEFAULT_TSO_CSUM_ENABLE (true) #define DEFAULT_VLAN_FILTER_ENABLE (true) +#define DEFAULT_VLAN_RX_OFFLOAD (true) #define TX_OVERHEAD (8) #define RXW_PADDING 2 @@ -2298,7 +2299,7 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; - ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN); + ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2364,6 +2365,11 @@ static int lan78xx_set_features(struct net_device *netdev, } if (features & NETIF_F_HW_VLAN_CTAG_RX) + pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_; + else + pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_; + + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; else pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; @@ -2587,7 +2593,8 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf |= FCT_TX_CTL_EN_; ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf); - ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN); + ret = lan78xx_set_rx_max_frame_length(dev, + dev->net->mtu + VLAN_ETH_HLEN); ret = lan78xx_read_reg(dev, MAC_RX, &buf); buf |= MAC_RX_RXEN_; @@ -2975,6 +2982,12 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) if (DEFAULT_TSO_CSUM_ENABLE) dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG; + if (DEFAULT_VLAN_RX_OFFLOAD) + dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX; + + if (DEFAULT_VLAN_FILTER_ENABLE) + dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + dev->net->hw_features = dev->net->features; ret = lan78xx_setup_irq_domain(dev); @@ -3039,8 +3052,13 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, struct sk_buff *skb, u32 rx_cmd_a, u32 rx_cmd_b) { + /* HW Checksum offload appears to be flawed if used when not stripping + * VLAN headers. Drop back to S/W checksums under these conditions. + */ if (!(dev->net->features & NETIF_F_RXCSUM) || - unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) { + unlikely(rx_cmd_a & RX_CMD_A_ICSM_) || + ((rx_cmd_a & RX_CMD_A_FVTG_) && + !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) { skb->ip_summed = CHECKSUM_NONE; } else { skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_)); @@ -3048,6 +3066,16 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, } } +static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev, + struct sk_buff *skb, + u32 rx_cmd_a, u32 rx_cmd_b) +{ + if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) && + (rx_cmd_a & RX_CMD_A_FVTG_)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + (rx_cmd_b & 0xffff)); +} + static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { int status; @@ -3112,6 +3140,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) if (skb->len == size) { lan78xx_rx_csum_offload(dev, skb, rx_cmd_a, rx_cmd_b); + lan78xx_rx_vlan_offload(dev, skb, + rx_cmd_a, rx_cmd_b); skb_trim(skb, skb->len - 4); /* remove fcs */ skb->truesize = size + sizeof(struct sk_buff); @@ -3130,6 +3160,7 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) skb_set_tail_pointer(skb2, size); lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b); + lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b); skb_trim(skb2, skb2->len - 4); /* remove fcs */ skb2->truesize = size + sizeof(struct sk_buff); @@ -3313,6 +3344,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) pkt_cnt = 0; count = 0; length = 0; + spin_lock_irqsave(&tqp->lock, flags); for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { @@ -3321,7 +3353,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) } count = 1; length = skb->len - TX_OVERHEAD; - skb2 = skb_dequeue(tqp); + __skb_unlink(skb, tqp); + spin_unlock_irqrestore(&tqp->lock, flags); goto gso_skb; } @@ -3330,6 +3363,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32)); pkt_cnt++; } + spin_unlock_irqrestore(&tqp->lock, flags); /* copy to a single skb */ skb = alloc_skb(skb_totallen, GFP_ATOMIC); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8fac8e132c5b..cb0cc30c3d6a 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,13 +1246,14 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ - {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 86f7196f9d91..2a58607a6aea 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP unregister_pm_notifier(&tp->pm_notifier); #endif - napi_disable(&tp->napi); + if (!test_bit(RTL8152_UNPLUG, &tp->flags)) + napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 5f565bd574da..48ba80a8ca5c 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -681,7 +681,7 @@ static void rtl8150_set_multicast(struct net_device *netdev) (netdev->flags & IFF_ALLMULTI)) { rx_creg &= 0xfffe; rx_creg |= 0x0002; - dev_info(&netdev->dev, "%s: allmulti set\n", netdev->name); + dev_dbg(&netdev->dev, "%s: allmulti set\n", netdev->name); } else { /* ~RX_MULTICAST, ~RX_PROMISCUOUS */ rx_creg &= 0x00fc; diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 7a6a1fe79309..05553d252446 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -82,6 +82,9 @@ static bool turbo_mode = true; module_param(turbo_mode, bool, 0644); MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction"); +static int smsc75xx_link_ok_nopm(struct usbnet *dev); +static int smsc75xx_phy_gig_workaround(struct usbnet *dev); + static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index, u32 *data, int in_pm) { @@ -852,6 +855,9 @@ static int smsc75xx_phy_initialize(struct usbnet *dev) return -EIO; } + /* phy workaround for gig link */ + smsc75xx_phy_gig_workaround(dev); + smsc75xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM); @@ -987,6 +993,62 @@ static int smsc75xx_wait_ready(struct usbnet *dev, int in_pm) return -EIO; } +static int smsc75xx_phy_gig_workaround(struct usbnet *dev) +{ + struct mii_if_info *mii = &dev->mii; + int ret = 0, timeout = 0; + u32 buf, link_up = 0; + + /* Set the phy in Gig loopback */ + smsc75xx_mdio_write(dev->net, mii->phy_id, MII_BMCR, 0x4040); + + /* Wait for the link up */ + do { + link_up = smsc75xx_link_ok_nopm(dev); + usleep_range(10000, 20000); + timeout++; + } while ((!link_up) && (timeout < 1000)); + + if (timeout >= 1000) { + netdev_warn(dev->net, "Timeout waiting for PHY link up\n"); + return -EIO; + } + + /* phy reset */ + ret = smsc75xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", ret); + return ret; + } + + buf |= PMT_CTL_PHY_RST; + + ret = smsc75xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to write PMT_CTL: %d\n", ret); + return ret; + } + + timeout = 0; + do { + usleep_range(10000, 20000); + ret = smsc75xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) { + netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", + ret); + return ret; + } + timeout++; + } while ((buf & PMT_CTL_PHY_RST) && (timeout < 100)); + + if (timeout >= 100) { + netdev_warn(dev->net, "timeout waiting for PHY Reset\n"); + return -EIO; + } + + return 0; +} + static int smsc75xx_reset(struct usbnet *dev) { struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b6c9a2af3732..53085c63277b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -53,6 +53,10 @@ module_param(napi_tx, bool, 0644); /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */ #define VIRTIO_XDP_HEADROOM 256 +/* Separating two types of XDP xmit */ +#define VIRTIO_XDP_TX BIT(0) +#define VIRTIO_XDP_REDIR BIT(1) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -582,7 +586,7 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -654,14 +658,14 @@ static struct sk_buff *receive_small(struct net_device *dev, trace_xdp_exception(vi->dev, xdp_prog, act); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: err = xdp_do_redirect(dev, &xdp, xdp_prog); if (err) goto err_xdp; - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; rcu_read_unlock(); goto xdp_xmit; default: @@ -723,7 +727,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - bool *xdp_xmit) + unsigned int *xdp_xmit) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -818,7 +822,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_TX; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -830,7 +834,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(xdp_page); goto err_xdp; } - *xdp_xmit = true; + *xdp_xmit |= VIRTIO_XDP_REDIR; if (unlikely(xdp_page != page)) put_page(page); rcu_read_unlock(); @@ -939,7 +943,8 @@ xdp_xmit: } static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, bool *xdp_xmit) + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit) { struct net_device *dev = vi->dev; struct sk_buff *skb; @@ -1232,7 +1237,8 @@ static void refill_work(struct work_struct *work) } } -static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) +static int virtnet_receive(struct receive_queue *rq, int budget, + unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int len, received = 0, bytes = 0; @@ -1321,7 +1327,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget) struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; unsigned int received, qp; - bool xdp_xmit = false; + unsigned int xdp_xmit = 0; virtnet_poll_cleantx(rq); @@ -1331,12 +1337,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget) if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit) { + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & VIRTIO_XDP_TX) { qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); sq = &vi->sq[qp]; virtqueue_kick(sq->vq); - xdp_do_flush_map(); } return received; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index aee0e60471f1..e857cb3335f6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, flush = 0; out: - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } @@ -638,9 +636,62 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } -/* Add new entry to forwarding table -- assumes lock held */ +static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, + const u8 *mac, __u16 state, + __be32 src_vni, __u8 ndm_flags) +{ + struct vxlan_fdb *f; + + f = kmalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return NULL; + f->state = state; + f->flags = ndm_flags; + f->updated = f->used = jiffies; + f->vni = src_vni; + INIT_LIST_HEAD(&f->remotes); + memcpy(f->eth_addr, mac, ETH_ALEN); + + return f; +} + static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, + __u16 state, __be16 port, __be32 src_vni, + __be32 vni, __u32 ifindex, __u8 ndm_flags, + struct vxlan_fdb **fdb) +{ + struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; + int rc; + + if (vxlan->cfg.addrmax && + vxlan->addrcnt >= vxlan->cfg.addrmax) + return -ENOSPC; + + netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); + f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); + if (!f) + return -ENOMEM; + + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } + + ++vxlan->addrcnt; + hlist_add_head_rcu(&f->hlist, + vxlan_fdb_head(vxlan, mac, src_vni)); + + *fdb = f; + + return 0; +} + +/* Add new entry to forwarding table -- assumes lock held */ +static int vxlan_fdb_update(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u8 ndm_flags) @@ -689,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (!(flags & NLM_F_CREATE)) return -ENOENT; - if (vxlan->cfg.addrmax && - vxlan->addrcnt >= vxlan->cfg.addrmax) - return -ENOSPC; - /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); - f = kmalloc(sizeof(*f), GFP_ATOMIC); - if (!f) - return -ENOMEM; - - notify = 1; - f->state = state; - f->flags = ndm_flags; - f->updated = f->used = jiffies; - f->vni = src_vni; - INIT_LIST_HEAD(&f->remotes); - memcpy(f->eth_addr, mac, ETH_ALEN); - - rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); - if (rc < 0) { - kfree(f); + rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, + vni, ifindex, ndm_flags, &f); + if (rc < 0) return rc; - } - - ++vxlan->addrcnt; - hlist_add_head_rcu(&f->hlist, - vxlan_fdb_head(vxlan, mac, src_vni)); + notify = 1; } if (notify) { @@ -743,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head) kfree(f); } -static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) +static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, + bool do_notify) { netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; - vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); + if (do_notify) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); @@ -865,7 +898,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EAFNOSUPPORT; spin_lock_bh(&vxlan->hash_lock); - err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, + err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags); spin_unlock_bh(&vxlan->hash_lock); @@ -899,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan, goto out; } - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); out: return 0; @@ -1008,7 +1041,7 @@ static bool vxlan_snoop(struct net_device *dev, /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) - vxlan_fdb_create(vxlan, src_mac, src_ip, + vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, @@ -2366,7 +2399,7 @@ static void vxlan_cleanup(struct timer_list *t) "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } @@ -2417,7 +2450,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) spin_lock_bh(&vxlan->hash_lock); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); spin_unlock_bh(&vxlan->hash_lock); } @@ -2471,7 +2504,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } } spin_unlock_bh(&vxlan->hash_lock); @@ -3162,6 +3195,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f = NULL; int err; err = vxlan_dev_configure(net, dev, conf, false, extack); @@ -3175,24 +3209,35 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, err = vxlan_fdb_create(vxlan, all_zeros_mac, &vxlan->default_dst.remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_EXCL | NLM_F_CREATE, vxlan->cfg.dst_port, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) return err; } err = register_netdevice(dev); + if (err) + goto errout; + + err = rtnl_configure_link(dev, NULL); if (err) { - vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni); - return err; + unregister_netdevice(dev); + goto errout; } + /* notify default fdb entry */ + if (f) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); + list_add(&vxlan->next, &vn->vxlan_list); return 0; +errout: + if (f) + vxlan_fdb_destroy(vxlan, f, false); + return err; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], @@ -3427,6 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst old_dst; struct vxlan_config conf; + struct vxlan_fdb *f = NULL; int err; err = vxlan_nl2conf(tb, data, @@ -3455,16 +3501,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_CREATE | NLM_F_APPEND, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; } + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); } spin_unlock_bh(&vxlan->hash_lock); } diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index e9c2fb318c03..836e0a47b94a 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6058,8 +6058,19 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk) ath10k_mac_max_vht_nss(vht_mcs_mask))); if (changed & IEEE80211_RC_BW_CHANGED) { - ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d\n", - sta->addr, bw); + enum wmi_phy_mode mode; + + mode = chan_to_phymode(&def); + ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n", + sta->addr, bw, mode); + + err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr, + WMI_PEER_PHYMODE, mode); + if (err) { + ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n", + sta->addr, mode, err); + goto exit; + } err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr, WMI_PEER_CHAN_WIDTH, bw); @@ -6100,6 +6111,7 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk) sta->addr); } +exit: mutex_unlock(&ar->conf_mutex); } diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index b48db54e9865..d68afb65402a 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -6144,6 +6144,7 @@ enum wmi_peer_param { WMI_PEER_NSS = 0x5, WMI_PEER_USE_4ADDR = 0x6, WMI_PEER_DEBUG = 0xa, + WMI_PEER_PHYMODE = 0xd, WMI_PEER_DUMMY_VAR = 0xff, /* dummy parameter for STA PS workaround */ }; diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c index 1279064a3b71..51a038022c8b 100644 --- a/drivers/net/wireless/ath/wcn36xx/testmode.c +++ b/drivers/net/wireless/ath/wcn36xx/testmode.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (c) 2018, The Linux Foundation. All rights reserved. * * Permission to use, copy, modify, and/or distribute this software for any diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index c99a191e8d69..a907d7b065fa 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4296,6 +4296,13 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus) brcmf_dbg(TRACE, "Enter\n"); if (bus) { + /* Stop watchdog task */ + if (bus->watchdog_tsk) { + send_sig(SIGTERM, bus->watchdog_tsk, 1); + kthread_stop(bus->watchdog_tsk); + bus->watchdog_tsk = NULL; + } + /* De-register interrupt handler */ brcmf_sdiod_intr_unregister(bus->sdiodev); diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c index 6e3cf9817730..88f4c89f89ba 100644 --- a/drivers/net/wireless/marvell/mwifiex/usb.c +++ b/drivers/net/wireless/marvell/mwifiex/usb.c @@ -644,11 +644,6 @@ static void mwifiex_usb_disconnect(struct usb_interface *intf) MWIFIEX_FUNC_SHUTDOWN); } - if (adapter->workqueue) - flush_workqueue(adapter->workqueue); - - mwifiex_usb_free(card); - mwifiex_dbg(adapter, FATAL, "%s: removing card\n", __func__); mwifiex_remove_card(adapter); @@ -1356,6 +1351,8 @@ static void mwifiex_unregister_dev(struct mwifiex_adapter *adapter) { struct usb_card_rec *card = (struct usb_card_rec *)adapter->card; + mwifiex_usb_free(card); + mwifiex_usb_cleanup_tx_aggr(adapter); card->adapter = NULL; diff --git a/drivers/net/wireless/mediatek/mt7601u/phy.c b/drivers/net/wireless/mediatek/mt7601u/phy.c index 9d2f9a776ef1..b804abd464ae 100644 --- a/drivers/net/wireless/mediatek/mt7601u/phy.c +++ b/drivers/net/wireless/mediatek/mt7601u/phy.c @@ -986,13 +986,15 @@ static void mt7601u_agc_tune(struct mt7601u_dev *dev) */ spin_lock_bh(&dev->con_mon_lock); avg_rssi = ewma_rssi_read(&dev->avg_rssi); - WARN_ON_ONCE(avg_rssi == 0); + spin_unlock_bh(&dev->con_mon_lock); + if (avg_rssi == 0) + return; + avg_rssi = -avg_rssi; if (avg_rssi <= -70) val -= 0x20; else if (avg_rssi <= -60) val -= 0x10; - spin_unlock_bh(&dev->con_mon_lock); if (val != mt7601u_bbp_rr(dev, 66)) mt7601u_bbp_wr(dev, 66, val); diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 220e2b710208..ae0ca8006849 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -654,8 +654,7 @@ qtnf_disconnect(struct wiphy *wiphy, struct net_device *dev, vif = qtnf_mac_get_base_vif(mac); if (!vif) { pr_err("MAC%u: primary VIF is not configured\n", mac->macid); - ret = -EFAULT; - goto out; + return -EFAULT; } if (vif->wdev.iftype != NL80211_IFTYPE_STATION) { diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index 39c817eddd78..54c9f6ab0c8c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -484,18 +484,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw) } -void rtl_deinit_deferred_work(struct ieee80211_hw *hw) +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq) { struct rtl_priv *rtlpriv = rtl_priv(hw); del_timer_sync(&rtlpriv->works.watchdog_timer); - cancel_delayed_work(&rtlpriv->works.watchdog_wq); - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); - cancel_delayed_work(&rtlpriv->works.ps_work); - cancel_delayed_work(&rtlpriv->works.ps_rfon_wq); - cancel_delayed_work(&rtlpriv->works.fwevt_wq); - cancel_delayed_work(&rtlpriv->works.c2hcmd_wq); + cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq); + if (ips_wq) + cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + else + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ps_work); + cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq); + cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq); + cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq); } EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work); diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h index 912f205779c3..a7ae40eaa3cd 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.h +++ b/drivers/net/wireless/realtek/rtlwifi/base.h @@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw); void rtl_deinit_rfkill(struct ieee80211_hw *hw); void rtl_watch_dog_timer_callback(struct timer_list *t); -void rtl_deinit_deferred_work(struct ieee80211_hw *hw); +void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq); bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx); int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht, diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index cfea57efa7f4..4bf7967590ca 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -130,7 +130,6 @@ found_alt: firmware->size); rtlpriv->rtlhal.wowlan_fwsize = firmware->size; } - rtlpriv->rtlhal.fwsize = firmware->size; release_firmware(firmware); } @@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw) /* reset sec info */ rtl_cam_reset_sec_info(hw); - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); } rtlpriv->intf_ops->adapter_stop(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index ae13bcfb3bf0..5d1fda16fc8c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -2377,7 +2377,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } rtlpriv->cfg->ops->disable_interrupt(hw); diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c index 71af24e2e051..479a4cfc245d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/ps.c +++ b/drivers/net/wireless/realtek/rtlwifi/ps.c @@ -71,7 +71,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); /*<1> Stop all timer */ - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, true); /*<2> Disable Interrupt */ rtlpriv->cfg->ops->disable_interrupt(hw); @@ -292,7 +292,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw) struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); enum rf_pwrstate rtstate; - cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq); + cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq); mutex_lock(&rtlpriv->locks.ips_mutex); if (ppsc->inactiveps) { diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c index f9faffc498bc..2ac5004d7a40 100644 --- a/drivers/net/wireless/realtek/rtlwifi/usb.c +++ b/drivers/net/wireless/realtek/rtlwifi/usb.c @@ -1132,7 +1132,7 @@ void rtl_usb_disconnect(struct usb_interface *intf) ieee80211_unregister_hw(hw); rtlmac->mac80211_registered = 0; } else { - rtl_deinit_deferred_work(hw); + rtl_deinit_deferred_work(hw, false); rtlpriv->intf_ops->adapter_stop(hw); } /*deinit rfkill */ diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index 2e96b34bc936..fb667bf469c7 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -278,6 +278,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns, return -EIO; if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0) return -EIO; + return 0; } if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 46df030b2c3f..bf65501e6ed6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -100,6 +100,22 @@ static struct class *nvme_subsys_class; static void nvme_ns_remove(struct nvme_ns *ns); static int nvme_revalidate_disk(struct gendisk *disk); static void nvme_put_subsystem(struct nvme_subsystem *subsys); +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, + unsigned nsid); + +static void nvme_set_queue_dying(struct nvme_ns *ns) +{ + /* + * Revalidating a dead namespace sets capacity to 0. This will end + * buffered writers dirtying pages that can't be synced. + */ + if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + return; + revalidate_disk(ns->disk); + blk_set_queue_dying(ns->queue); + /* Forcibly unquiesce queues to avoid blocking dispatch */ + blk_mq_unquiesce_queue(ns->queue); +} static void nvme_queue_scan(struct nvme_ctrl *ctrl) { @@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count); static void nvme_enable_aen(struct nvme_ctrl *ctrl) { - u32 result; + u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED; int status; - status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, - ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result); + if (!supported_aens) + return; + + status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens, + NULL, 0, &result); if (status) dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n", - ctrl->oaes & NVME_AEN_SUPPORTED); + supported_aens); } static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) @@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static void nvme_update_formats(struct nvme_ctrl *ctrl) { - struct nvme_ns *ns, *next; - LIST_HEAD(rm_list); + struct nvme_ns *ns; - down_write(&ctrl->namespaces_rwsem); - list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->disk && nvme_revalidate_disk(ns->disk)) { - list_move_tail(&ns->list, &rm_list); - } - } - up_write(&ctrl->namespaces_rwsem); + down_read(&ctrl->namespaces_rwsem); + list_for_each_entry(ns, &ctrl->namespaces, list) + if (ns->disk && nvme_revalidate_disk(ns->disk)) + nvme_set_queue_dying(ns); + up_read(&ctrl->namespaces_rwsem); - list_for_each_entry_safe(ns, next, &rm_list, list) - nvme_ns_remove(ns); + nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL); } static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) @@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, effects = nvme_passthru_start(ctrl, ns, cmd.opcode); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, (void __user *)(uintptr_t)cmd.addr, cmd.data_len, - (void __user *)(uintptr_t)cmd.metadata, cmd.metadata, + (void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len, 0, &cmd.result, timeout); nvme_passthru_end(ctrl, effects); @@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, down_write(&ctrl->namespaces_rwsem); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) + if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags)) list_move_tail(&ns->list, &rm_list); } up_write(&ctrl->namespaces_rwsem); @@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) if (ctrl->admin_q) blk_mq_unquiesce_queue(ctrl->admin_q); - list_for_each_entry(ns, &ctrl->namespaces, list) { - /* - * Revalidating a dead namespace sets capacity to 0. This will - * end buffered writers dirtying pages that can't be synced. - */ - if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags)) - continue; - revalidate_disk(ns->disk); - blk_set_queue_dying(ns->queue); + list_for_each_entry(ns, &ctrl->namespaces, list) + nvme_set_queue_dying(ns); - /* Forcibly unquiesce queues to avoid blocking dispatch */ - blk_mq_unquiesce_queue(ns->queue); - } up_read(&ctrl->namespaces_rwsem); } EXPORT_SYMBOL_GPL(nvme_kill_queues); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 903eb4545e26..f7efe5a58cc7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport( /* * For something we're not in a state to send to the device the default action * is to busy it and retry it after the controller state is recovered. However, - * anything marked for failfast or nvme multipath is immediately failed. + * if the controller is deleting or if anything is marked for failfast or + * nvme multipath it is immediately failed. * * Note: commands used to initialize the controller will be marked for failfast. * Note: nvme cli/ioctl commands are marked for failfast. */ -blk_status_t nvmf_fail_nonready_command(struct request *rq) +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq) { - if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) + if (ctrl->state != NVME_CTRL_DELETING && + ctrl->state != NVME_CTRL_DEAD && + !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index e1818a27aa2d..aa2fdb2a2e8f 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); -blk_status_t nvmf_fail_nonready_command(struct request *rq); +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq); bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 41d45a1b5c62..9bac912173ba 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); ret = nvme_setup_cmd(ns, rq, sqe); if (ret) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ba943f211687..ddd441b1516a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) quirks |= check_vendor_combination_bug(pdev); - result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, - quirks); - if (result) - goto release_pools; - /* * Double check that our mempool alloc size will cover the biggest * command we support. @@ -2578,6 +2573,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto release_pools; } + result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops, + quirks); + if (result) + goto release_mempool; + dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); nvme_get_ctrl(&dev->ctrl); @@ -2585,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; + release_mempool: + mempool_destroy(dev->iod_mempool); release_pools: nvme_release_prp_pools(dev); unmap: diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 518c5b09038c..66ec5985c9f3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, WARN_ON_ONCE(rq->tag < 0); if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index d3f3b3ec4d1a..ebea1373d1b7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, { struct nvmet_ns *ns = to_nvmet_ns(item); struct nvmet_subsys *subsys = ns->subsys; + size_t len; int ret; mutex_lock(&subsys->lock); @@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, if (ns->enabled) goto out_unlock; - kfree(ns->device_path); + ret = -EINVAL; + len = strcspn(page, "\n"); + if (!len) + goto out_unlock; + kfree(ns->device_path); ret = -ENOMEM; - ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL); + ns->device_path = kstrndup(page, len, GFP_KERNEL); if (!ns->device_path) goto out_unlock; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 74d4b785d2da..9838103f2d62 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = nvmet_bdev_ns_enable(ns); - if (ret) + if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); if (ret) goto out_unlock; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 408279cb6f2c..29b4b236afd8 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod { struct work_struct work; } __aligned(sizeof(unsigned long long)); +/* desired maximum for a single sequence - if sg list allows it */ #define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024) -#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE) enum nvmet_fcp_datadir { NVMET_FCP_NODATA, @@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod { struct nvme_fc_cmd_iu cmdiubuf; struct nvme_fc_ersp_iu rspiubuf; dma_addr_t rspdma; + struct scatterlist *next_sg; struct scatterlist *data_sg; int data_sg_cnt; u32 offset; @@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->assoc_list); kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); - newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS, - template->max_sgl_segments); + newrec->max_sg_cnt = template->max_sgl_segments; ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod) ((fod->io_dir == NVMET_FCP_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE)); /* note: write from initiator perspective */ + fod->next_sg = fod->data_sg; return 0; @@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod, u8 op) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; + struct scatterlist *sg = fod->next_sg; unsigned long flags; - u32 tlen; + u32 remaininglen = fod->req.transfer_len - fod->offset; + u32 tlen = 0; int ret; fcpreq->op = op; fcpreq->offset = fod->offset; fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC; - tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE, - (fod->req.transfer_len - fod->offset)); + /* + * for next sequence: + * break at a sg element boundary + * attempt to keep sequence length capped at + * NVMET_FC_MAX_SEQ_LENGTH but allow sequence to + * be longer if a single sg element is larger + * than that amount. This is done to avoid creating + * a new sg list to use for the tgtport api. + */ + fcpreq->sg = sg; + fcpreq->sg_cnt = 0; + while (tlen < remaininglen && + fcpreq->sg_cnt < tgtport->max_sg_cnt && + tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) { + fcpreq->sg_cnt++; + tlen += sg_dma_len(sg); + sg = sg_next(sg); + } + if (tlen < remaininglen && fcpreq->sg_cnt == 0) { + fcpreq->sg_cnt++; + tlen += min_t(u32, sg_dma_len(sg), remaininglen); + sg = sg_next(sg); + } + if (tlen < remaininglen) + fod->next_sg = sg; + else + fod->next_sg = NULL; + fcpreq->transfer_length = tlen; fcpreq->transferred_length = 0; fcpreq->fcp_error = 0; fcpreq->rsplen = 0; - fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE]; - fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE); - /* * If the last READDATA request: check if LLDD supports * combined xfr with response. diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index d8d91f04bd7e..ae7586b8be07 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t ret; if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready)) - return nvmf_fail_nonready_command(req); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req); ret = nvme_setup_cmd(ns, req, &iod->cmd); if (ret) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index b5b0cdc21d01..514d1dfc5630 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -936,6 +936,10 @@ struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *cell_id) return cell; } + /* NULL cell_id only allowed for device tree; invalid otherwise */ + if (!cell_id) + return ERR_PTR(-EINVAL); + return nvmem_cell_get_from_list(cell_id); } EXPORT_SYMBOL_GPL(nvmem_cell_get); diff --git a/drivers/of/base.c b/drivers/of/base.c index 848f549164cd..466e3c8582f0 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -102,7 +102,7 @@ static u32 phandle_cache_mask; * - the phandle lookup overhead reduction provided by the cache * will likely be less */ -static void of_populate_phandle_cache(void) +void of_populate_phandle_cache(void) { unsigned long flags; u32 cache_entries; @@ -134,8 +134,7 @@ out: raw_spin_unlock_irqrestore(&devtree_lock, flags); } -#ifndef CONFIG_MODULES -static int __init of_free_phandle_cache(void) +int of_free_phandle_cache(void) { unsigned long flags; @@ -148,6 +147,7 @@ static int __init of_free_phandle_cache(void) return 0; } +#if !defined(CONFIG_MODULES) late_initcall_sync(of_free_phandle_cache); #endif diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 891d780c076a..216175d11d3d 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -79,6 +79,8 @@ int of_resolve_phandles(struct device_node *tree); #if defined(CONFIG_OF_OVERLAY) void of_overlay_mutex_lock(void); void of_overlay_mutex_unlock(void); +int of_free_phandle_cache(void); +void of_populate_phandle_cache(void); #else static inline void of_overlay_mutex_lock(void) {}; static inline void of_overlay_mutex_unlock(void) {}; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 7baa53e5b1d7..eda57ef12fd0 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -804,6 +804,8 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree, goto err_free_overlay_changeset; } + of_populate_phandle_cache(); + ret = __of_changeset_apply_notify(&ovcs->cset); if (ret) pr_err("overlay changeset entry notify error %d\n", ret); @@ -1046,8 +1048,17 @@ int of_overlay_remove(int *ovcs_id) list_del(&ovcs->ovcs_list); + /* + * Disable phandle cache. Avoids race condition that would arise + * from removing cache entry when the associated node is deleted. + */ + of_free_phandle_cache(); + ret_apply = 0; ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply); + + of_populate_phandle_cache(); + if (ret) { if (ret_apply) devicetree_state_flags |= DTSF_REVERT_FAIL; diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 16f52c626b4b..91b0194240a5 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -58,7 +58,6 @@ config PCIE_DW_PLAT_HOST depends on PCI && PCI_MSI_IRQ_DOMAIN select PCIE_DW_HOST select PCIE_DW_PLAT - default y help Enables support for the PCIe controller in the Designware IP to work in host mode. There are two instances of PCIe controller in diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 781aa03aeede..29a05759a294 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -363,7 +363,8 @@ int dw_pcie_host_init(struct pcie_port *pp) resource_list_for_each_entry_safe(win, tmp, &bridge->windows) { switch (resource_type(win->res)) { case IORESOURCE_IO: - ret = pci_remap_iospace(win->res, pp->io_base); + ret = devm_pci_remap_iospace(dev, win->res, + pp->io_base); if (ret) { dev_warn(dev, "Error %d: failed to map resource %pR\n", ret, win->res); diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index d3172d5d3d35..0fae816fba39 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -849,7 +849,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) 0, 0xF8000000, 0, lower_32_bits(res->start), OB_PCIE_IO); - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index a1ebe9ed441f..bf5ece5d9291 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -355,11 +355,13 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p) irq = of_irq_get(intc, 0); if (irq <= 0) { dev_err(p->dev, "failed to get parent IRQ\n"); + of_node_put(intc); return irq ?: -EINVAL; } p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX, &faraday_pci_irqdomain_ops, p); + of_node_put(intc); if (!p->irqdomain) { dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n"); return -EINVAL; @@ -501,7 +503,7 @@ static int faraday_pci_probe(struct platform_device *pdev) dev_err(dev, "illegal IO mem size\n"); return -EINVAL; } - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", ret, io); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 6cc5036ac83c..f6325f1a89e8 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1073,6 +1073,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; + unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1164,14 +1165,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * the channel callback directly when channel->target_cpu is * the current CPU. When the higher level interrupt code * calls us with interrupt enabled, let's add the - * local_bh_disable()/enable() to avoid race. + * local_irq_save()/restore() to avoid race: + * hv_pci_onchannelcallback() can also run in tasklet. */ - local_bh_disable(); + local_irq_save(flags); if (hbus->hdev->channel->target_cpu == smp_processor_id()) hv_pci_onchannelcallback(hbus); - local_bh_enable(); + local_irq_restore(flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index 68b8bfbdb867..d219404bad92 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -537,7 +537,7 @@ static int v3_pci_setup_resource(struct v3_pci *v3, v3->io_bus_addr = io->start - win->offset; dev_dbg(dev, "I/O window %pR, bus addr %pap\n", io, &v3->io_bus_addr); - ret = pci_remap_iospace(io, io_base); + ret = devm_pci_remap_iospace(dev, io, io_base); if (ret) { dev_warn(dev, "error %d: failed to map resource %pR\n", diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index 994f32061b32..f59ad2728c0b 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -82,7 +82,7 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index d854d67e873c..ffda3e8b4742 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -423,7 +423,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, case IORESOURCE_IO: xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base, res->start - window->offset); - ret = pci_remap_iospace(res, io_base); + ret = devm_pci_remap_iospace(dev, res, io_base); if (ret < 0) return ret; break; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 0baabe30858f..861dda69f366 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -1109,7 +1109,7 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie) if (err < 0) return err; - pci_remap_iospace(&pcie->pio, pcie->io.start); + devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start); return 0; } diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index 874d75c9ee4a..c8febb009454 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -680,7 +680,11 @@ static int rcar_pcie_phy_init_gen3(struct rcar_pcie *pcie) if (err) return err; - return phy_power_on(pcie->phy); + err = phy_power_on(pcie->phy); + if (err) + phy_exit(pcie->phy); + + return err; } static int rcar_msi_alloc(struct rcar_msi *chip) @@ -1165,7 +1169,7 @@ static int rcar_pcie_probe(struct platform_device *pdev) if (rcar_pcie_hw_init(pcie)) { dev_info(dev, "PCIe link down\n"); err = -ENODEV; - goto err_clk_disable; + goto err_phy_shutdown; } data = rcar_pci_read_reg(pcie, MACSR); @@ -1177,7 +1181,7 @@ static int rcar_pcie_probe(struct platform_device *pdev) dev_err(dev, "failed to enable MSI support: %d\n", err); - goto err_clk_disable; + goto err_phy_shutdown; } } @@ -1191,6 +1195,12 @@ err_msi_teardown: if (IS_ENABLED(CONFIG_PCI_MSI)) rcar_pcie_teardown_msi(pcie); +err_phy_shutdown: + if (pcie->phy) { + phy_power_off(pcie->phy); + phy_exit(pcie->phy); + } + err_clk_disable: clk_disable_unprepare(pcie->bus_clk); diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index 6a4bbb5b3de0..fb32840ce8e6 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -559,7 +559,7 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie) PCI_NUM_INTX, &legacy_domain_ops, pcie); - + of_node_put(legacy_intc_node); if (!pcie->legacy_irq_domain) { dev_err(dev, "failed to create IRQ domain\n"); return -ENOMEM; diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index b110a3a814e3..7b1389d8e2a5 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -509,6 +509,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port) port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, &intx_domain_ops, port); + of_node_put(pcie_intc_node); if (!port->leg_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); return -ENODEV; diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 523a8cab3bfb..825fa24427a3 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -137,6 +137,20 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar) } EXPORT_SYMBOL_GPL(pci_epf_alloc_space); +static void pci_epf_remove_cfs(struct pci_epf_driver *driver) +{ + struct config_group *group, *tmp; + + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return; + + mutex_lock(&pci_epf_mutex); + list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry) + pci_ep_cfs_remove_epf_group(group); + list_del(&driver->epf_group); + mutex_unlock(&pci_epf_mutex); +} + /** * pci_epf_unregister_driver() - unregister the PCI EPF driver * @driver: the PCI EPF driver that has to be unregistered @@ -145,17 +159,38 @@ EXPORT_SYMBOL_GPL(pci_epf_alloc_space); */ void pci_epf_unregister_driver(struct pci_epf_driver *driver) { - struct config_group *group; - - mutex_lock(&pci_epf_mutex); - list_for_each_entry(group, &driver->epf_group, group_entry) - pci_ep_cfs_remove_epf_group(group); - list_del(&driver->epf_group); - mutex_unlock(&pci_epf_mutex); + pci_epf_remove_cfs(driver); driver_unregister(&driver->driver); } EXPORT_SYMBOL_GPL(pci_epf_unregister_driver); +static int pci_epf_add_cfs(struct pci_epf_driver *driver) +{ + struct config_group *group; + const struct pci_epf_device_id *id; + + if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS)) + return 0; + + INIT_LIST_HEAD(&driver->epf_group); + + id = driver->id_table; + while (id->name[0]) { + group = pci_ep_cfs_add_epf_group(id->name); + if (IS_ERR(group)) { + pci_epf_remove_cfs(driver); + return PTR_ERR(group); + } + + mutex_lock(&pci_epf_mutex); + list_add_tail(&group->group_entry, &driver->epf_group); + mutex_unlock(&pci_epf_mutex); + id++; + } + + return 0; +} + /** * __pci_epf_register_driver() - register a new PCI EPF driver * @driver: structure representing PCI EPF driver @@ -167,8 +202,6 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner) { int ret; - struct config_group *group; - const struct pci_epf_device_id *id; if (!driver->ops) return -EINVAL; @@ -183,16 +216,7 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, if (ret) return ret; - INIT_LIST_HEAD(&driver->epf_group); - - id = driver->id_table; - while (id->name[0]) { - group = pci_ep_cfs_add_epf_group(id->name); - mutex_lock(&pci_epf_mutex); - list_add_tail(&group->group_entry, &driver->epf_group); - mutex_unlock(&pci_epf_mutex); - id++; - } + pci_epf_add_cfs(driver); return 0; } diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index d0d73dbbd5ca..0f04ae648cf1 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -575,6 +575,22 @@ void pci_iov_release(struct pci_dev *dev) } /** + * pci_iov_remove - clean up SR-IOV state after PF driver is detached + * @dev: the PCI device + */ +void pci_iov_remove(struct pci_dev *dev) +{ + struct pci_sriov *iov = dev->sriov; + + if (!dev->is_physfn) + return; + + iov->driver_max_VFs = iov->total_VFs; + if (iov->num_VFs) + pci_warn(dev, "driver left SR-IOV enabled after remove\n"); +} + +/** * pci_iov_update_resource - update a VF BAR * @dev: the PCI device * @resno: the resource number diff --git a/drivers/pci/of.c b/drivers/pci/of.c index d088c9147f10..69a60d6ebd73 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -612,7 +612,7 @@ int pci_parse_request_of_pci_ranges(struct device *dev, switch (resource_type(res)) { case IORESOURCE_IO: - err = pci_remap_iospace(res, iobase); + err = devm_pci_remap_iospace(dev, res, iobase); if (err) { dev_warn(dev, "error %d: failed to map resource %pR\n", err, res); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 65113b6eed14..89ee6a2b6eb8 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -629,6 +629,18 @@ static bool acpi_pci_need_resume(struct pci_dev *dev) { struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + /* + * In some cases (eg. Samsung 305V4A) leaving a bridge in suspend over + * system-wide suspend/resume confuses the platform firmware, so avoid + * doing that, unless the bridge has a driver that should take care of + * the PM handling. According to Section 16.1.6 of ACPI 6.2, endpoint + * devices are expected to be in D3 before invoking the S3 entry path + * from the firmware, so they should not be affected by this issue. + */ + if (pci_is_bridge(dev) && !dev->driver && + acpi_target_system_state() != ACPI_STATE_S0) + return true; + if (!adev || !acpi_device_power_manageable(adev)) return false; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c125d53033c6..6792292b5fc7 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -445,6 +445,7 @@ static int pci_device_remove(struct device *dev) } pcibios_free_irq(pci_dev); pci_dev->driver = NULL; + pci_iov_remove(pci_dev); } /* Undo the runtime PM settings in local_pci_probe() */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 22adaf35b136..aa1684d99b70 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3579,6 +3579,44 @@ void pci_unmap_iospace(struct resource *res) } EXPORT_SYMBOL(pci_unmap_iospace); +static void devm_pci_unmap_iospace(struct device *dev, void *ptr) +{ + struct resource **res = ptr; + + pci_unmap_iospace(*res); +} + +/** + * devm_pci_remap_iospace - Managed pci_remap_iospace() + * @dev: Generic device to remap IO address for + * @res: Resource describing the I/O space + * @phys_addr: physical address of range to be mapped + * + * Managed pci_remap_iospace(). Map is automatically unmapped on driver + * detach. + */ +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr) +{ + const struct resource **ptr; + int error; + + ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + error = pci_remap_iospace(res, phys_addr); + if (error) { + devres_free(ptr); + } else { + *ptr = res; + devres_add(dev, ptr); + } + + return error; +} +EXPORT_SYMBOL(devm_pci_remap_iospace); + /** * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace() * @dev: Generic device to remap IO address for diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c358e7a07f3f..882f1f9596df 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -311,6 +311,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev) #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); +void pci_iov_remove(struct pci_dev *dev); void pci_iov_update_resource(struct pci_dev *dev, int resno); resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno); void pci_restore_iov_state(struct pci_dev *dev); @@ -325,6 +326,9 @@ static inline void pci_iov_release(struct pci_dev *dev) { } +static inline void pci_iov_remove(struct pci_dev *dev) +{ +} static inline void pci_restore_iov_state(struct pci_dev *dev) { } diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f7ce0cb0b0b7..f02e334beb45 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) parent = udev->subordinate; pci_lock_rescan_remove(); + pci_dev_get(dev); list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, bus_list) { pci_dev_get(pdev); @@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) pci_info(dev, "Device recovery from fatal error failed\n"); } + pci_dev_put(dev); pci_unlock_rescan_remove(); } diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c index 1b7febc43da9..29d2c3b1913a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init.c @@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params) { void __iomem *ctrl = params->ctrl_regs; + USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE); + /* 1 millisecond - for USB clocks to settle down */ + usleep_range(1000, 2000); + if (BRCM_ID(params->family_id) == 0x7366) { /* * The PHY3_SOFT_RESETB bits default to the wrong state. diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 23705e1a0023..0075fb0bef8c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work) ddata = container_of(work, struct phy_mdm6600, status_work.work); dev = ddata->dev; - error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES, + error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES, ddata->status_gpios->desc, values); if (error) return; - for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) { + for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) { val |= values[i] << i; dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n", __func__, i, values[i], val); diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c index 35c17653c694..87618a4e90e4 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c @@ -460,8 +460,8 @@ static int nsp_pinmux_enable(struct pinctrl_dev *pctrl_dev, const struct nsp_pin_function *func; const struct nsp_pin_group *grp; - if (grp_select > pinctrl->num_groups || - func_select > pinctrl->num_functions) + if (grp_select >= pinctrl->num_groups || + func_select >= pinctrl->num_functions) return -EINVAL; func = &pinctrl->functions[func_select]; @@ -577,6 +577,8 @@ static int nsp_pinmux_probe(struct platform_device *pdev) return PTR_ERR(pinctrl->base0); res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) + return -EINVAL; pinctrl->base1 = devm_ioremap_nocache(&pdev->dev, res->start, resource_size(res)); if (!pinctrl->base1) { diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c index e3f1ab2290fc..4c4740ffeb9c 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c @@ -1424,7 +1424,7 @@ static struct pinctrl_desc mtk_desc = { static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); int value, err; err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value); @@ -1436,7 +1436,7 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio) static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value) { - struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent); + struct mtk_pinctrl *hw = gpiochip_get_data(chip); mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value); } @@ -1508,11 +1508,20 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw, struct device_node *np) if (ret < 0) return ret; - ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, - chip->ngpio); - if (ret < 0) { - gpiochip_remove(chip); - return ret; + /* Just for backward compatible for these old pinctrl nodes without + * "gpio-ranges" property. Otherwise, called directly from a + * DeviceTree-supported pinctrl driver is DEPRECATED. + * Please see Section 2.1 of + * Documentation/devicetree/bindings/gpio/gpio.txt on how to + * bind pinctrl and gpio drivers via the "gpio-ranges" property. + */ + if (!of_find_property(np, "gpio-ranges", NULL)) { + ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, + chip->ngpio); + if (ret < 0) { + gpiochip_remove(chip); + return ret; + } } return 0; @@ -1695,15 +1704,16 @@ static int mtk_pinctrl_probe(struct platform_device *pdev) mtk_desc.custom_conf_items = mtk_conf_items; #endif - hw->pctrl = devm_pinctrl_register(&pdev->dev, &mtk_desc, hw); - if (IS_ERR(hw->pctrl)) - return PTR_ERR(hw->pctrl); + err = devm_pinctrl_register_and_init(&pdev->dev, &mtk_desc, hw, + &hw->pctrl); + if (err) + return err; /* Setup groups descriptions per SoC types */ err = mtk_build_groups(hw); if (err) { dev_err(&pdev->dev, "Failed to build groups\n"); - return 0; + return err; } /* Setup functions descriptions per SoC types */ @@ -1713,17 +1723,25 @@ static int mtk_pinctrl_probe(struct platform_device *pdev) return err; } - err = mtk_build_gpiochip(hw, pdev->dev.of_node); - if (err) { - dev_err(&pdev->dev, "Failed to add gpio_chip\n"); + /* For able to make pinctrl_claim_hogs, we must not enable pinctrl + * until all groups and functions are being added one. + */ + err = pinctrl_enable(hw->pctrl); + if (err) return err; - } err = mtk_build_eint(hw, pdev); if (err) dev_warn(&pdev->dev, "Failed to add EINT, but pinctrl still can work\n"); + /* Build gpiochip should be after pinctrl_enable is done */ + err = mtk_build_gpiochip(hw, pdev->dev.of_node); + if (err) { + dev_err(&pdev->dev, "Failed to add gpio_chip\n"); + return err; + } + platform_set_drvdata(pdev, hw); return 0; diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index a1d7156d0a43..6a1b6058b991 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -536,7 +536,7 @@ static int ingenic_pinmux_gpio_set_direction(struct pinctrl_dev *pctldev, ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input); } else { ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false); - ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, input); + ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input); ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, false); } diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c index b02caf316711..eeb58b3bbc9a 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c @@ -21,15 +21,13 @@ #include "core.h" #include "sh_pfc.h" -#define CFG_FLAGS SH_PFC_PIN_CFG_DRIVE_STRENGTH - #define CPU_ALL_PORT(fn, sfx) \ - PORT_GP_CFG_22(0, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_17(2, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_17(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_6(4, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_15(5, fn, sfx, CFG_FLAGS) + PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_28(1, fn, sfx), \ + PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_6(4, fn, sfx), \ + PORT_GP_15(5, fn, sfx) /* * F_() : just information * FM() : macro for FN_xxx / xxx_MARK diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index f1fa8612db40..06978c14c83b 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -2185,7 +2185,7 @@ static int __init dell_init(void) dell_fill_request(&buffer, token->location, 0, 0, 0); ret = dell_send_request(&buffer, CLASS_TOKEN_READ, SELECT_TOKEN_AC); - if (ret) + if (ret == 0) max_intensity = buffer.output[3]; } diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 547dbdac9d54..01b0e2bb3319 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, case PTP_PF_PHYSYNC: if (chan != 0) return -EINVAL; + break; default: return -EINVAL; } diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 6d4012dd6922..bac1eeb3d312 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -265,8 +265,10 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) return err; /* full-function RTCs won't have such missing fields */ - if (rtc_valid_tm(&alarm->time) == 0) + if (rtc_valid_tm(&alarm->time) == 0) { + rtc_add_offset(rtc, &alarm->time); return 0; + } /* get the "after" timestamp, to detect wrapped fields */ err = rtc_read_time(rtc, &now); @@ -409,7 +411,6 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) if (err) return err; - rtc_subtract_offset(rtc, &alarm->time); scheduled = rtc_tm_to_time64(&alarm->time); /* Make sure we're not setting alarms in the past */ @@ -426,6 +427,8 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) * over right here, before we set the alarm. */ + rtc_subtract_offset(rtc, &alarm->time); + if (!rtc->ops) err = -ENODEV; else if (!rtc->ops->set_alarm) @@ -467,7 +470,6 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) mutex_unlock(&rtc->ops_lock); - rtc_add_offset(rtc, &alarm->time); return err; } EXPORT_SYMBOL_GPL(rtc_set_alarm); diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c index 097a4d4e2aba..1925aaf09093 100644 --- a/drivers/rtc/rtc-mrst.c +++ b/drivers/rtc/rtc-mrst.c @@ -367,10 +367,8 @@ static int vrtc_mrst_do_probe(struct device *dev, struct resource *iomem, } retval = rtc_register_device(mrst_rtc.rtc); - if (retval) { - retval = PTR_ERR(mrst_rtc.rtc); + if (retval) goto cleanup0; - } dev_dbg(dev, "initialised\n"); return 0; diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index d3a38c421503..a9f60d0ee02e 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -41,6 +41,15 @@ #define DASD_DIAG_MOD "dasd_diag_mod" +static unsigned int queue_depth = 32; +static unsigned int nr_hw_queues = 4; + +module_param(queue_depth, uint, 0444); +MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices"); + +module_param(nr_hw_queues, uint, 0444); +MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices"); + /* * SECTION: exported variables of dasd.c */ @@ -3115,8 +3124,8 @@ static int dasd_alloc_queue(struct dasd_block *block) block->tag_set.ops = &dasd_mq_ops; block->tag_set.cmd_size = sizeof(struct dasd_ccw_req); - block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES; - block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV; + block->tag_set.nr_hw_queues = nr_hw_queues; + block->tag_set.queue_depth = queue_depth; block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; rc = blk_mq_alloc_tag_set(&block->tag_set); diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 976b6bd4fb05..de6b96036aa4 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -228,14 +228,6 @@ struct dasd_ccw_req { #define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */ #define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */ -/* - * There is no reliable way to determine the number of available CPUs on - * LPAR but there is no big performance difference between 1 and the - * maximum CPU number. - * 64 is a good trade off performance wise. - */ -#define DASD_NR_HW_QUEUES 64 -#define DASD_MAX_LCU_DEV 256 #define DASD_REQ_PER_DEV 4 /* Signature for error recovery functions. */ diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 2a5fec55bf60..a246a618f9a4 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -829,6 +829,17 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, + unsigned int elements) +{ + unsigned int i; + + for (i = 0; i < elements; i++) + memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element)); + buf->element[14].sflags = 0; + buf->element[15].sflags = 0; +} + /** * qeth_get_elements_for_range() - find number of SBALEs to cover range. * @start: Start of the address range. @@ -1029,7 +1040,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, __u16, __u16, enum qeth_prot_versions); int qeth_set_features(struct net_device *, netdev_features_t); -void qeth_recover_features(struct net_device *dev); +void qeth_enable_hw_features(struct net_device *dev); netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); netdev_features_t qeth_features_check(struct sk_buff *skb, struct net_device *dev, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8e1474f1ffac..d01ac29fd986 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, struct qeth_qdio_out_buffer *buf, enum iucv_tx_notify notification); static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); -static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, - struct qeth_qdio_out_buffer *buf, - enum qeth_qdio_buffer_states newbufstate); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); struct workqueue_struct *qeth_wq; @@ -489,6 +486,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob; struct qeth_qdio_out_buffer *buffer; enum iucv_tx_notify notification; + unsigned int i; aob = (struct qaob *) phys_to_virt(phys_aob_addr); QETH_CARD_TEXT(card, 5, "haob"); @@ -513,10 +511,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card, qeth_notify_skbs(buffer->q, buffer, notification); buffer->aob = NULL; - qeth_clear_output_buffer(buffer->q, buffer, - QETH_QDIO_BUF_HANDLED_DELAYED); + /* Free dangling allocations. The attached skbs are handled by + * qeth_cleanup_handled_pending(). + */ + for (i = 0; + i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card); + i++) { + if (aob->sba[i] && buffer->is_header[i]) + kmem_cache_free(qeth_core_header_cache, + (void *) aob->sba[i]); + } + atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED); - /* from here on: do not touch buffer anymore */ qdio_release_aob(aob); } @@ -3759,6 +3765,10 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, QETH_CARD_TEXT(queue->card, 5, "aob"); QETH_CARD_TEXT_(queue->card, 5, "%lx", virt_to_phys(buffer->aob)); + + /* prepare the queue slot for re-use: */ + qeth_scrub_qdio_buffer(buffer->buffer, + QETH_MAX_BUFFER_ELEMENTS(card)); if (qeth_init_qdio_out_buf(queue, bidx)) { QETH_CARD_TEXT(card, 2, "outofbuf"); qeth_schedule_recovery(card); @@ -4834,7 +4844,7 @@ int qeth_vm_request_mac(struct qeth_card *card) goto out; } - ccw_device_get_id(CARD_RDEV(card), &id); + ccw_device_get_id(CARD_DDEV(card), &id); request->resp_buf_len = sizeof(*response); request->resp_version = DIAG26C_VERSION2; request->op_code = DIAG26C_GET_MAC; @@ -6459,28 +6469,27 @@ static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on) #define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \ NETIF_F_IPV6_CSUM) /** - * qeth_recover_features() - Restore device features after recovery - * @dev: the recovering net_device - * - * Caller must hold rtnl lock. + * qeth_enable_hw_features() - (Re-)Enable HW functions for device features + * @dev: a net_device */ -void qeth_recover_features(struct net_device *dev) +void qeth_enable_hw_features(struct net_device *dev) { - netdev_features_t features = dev->features; struct qeth_card *card = dev->ml_priv; + netdev_features_t features; + rtnl_lock(); + features = dev->features; /* force-off any feature that needs an IPA sequence. * netdev_update_features() will restart them. */ dev->features &= ~QETH_HW_FEATURES; netdev_update_features(dev); - - if (features == dev->features) - return; - dev_warn(&card->gdev->dev, - "Device recovery failed to restore all offload features\n"); + if (features != dev->features) + dev_warn(&card->gdev->dev, + "Device recovery failed to restore all offload features\n"); + rtnl_unlock(); } -EXPORT_SYMBOL_GPL(qeth_recover_features); +EXPORT_SYMBOL_GPL(qeth_enable_hw_features); int qeth_set_features(struct net_device *dev, netdev_features_t features) { diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index a7cb37da6a21..2487f0aeb165 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -140,7 +140,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_SETGMAC : IPA_CMD_SETVMAC; int rc; @@ -157,7 +157,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) { - enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? + enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ? IPA_CMD_DELGMAC : IPA_CMD_DELVMAC; int rc; @@ -501,27 +501,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) return -ERESTARTSYS; } + /* avoid racing against concurrent state change: */ + if (!mutex_trylock(&card->conf_mutex)) + return -EAGAIN; + if (!qeth_card_hw_is_reachable(card)) { ether_addr_copy(dev->dev_addr, addr->sa_data); - return 0; + goto out_unlock; } /* don't register the same address twice */ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) && (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) - return 0; + goto out_unlock; /* add the new address, switch over, drop the old */ rc = qeth_l2_send_setmac(card, addr->sa_data); if (rc) - return rc; + goto out_unlock; ether_addr_copy(old_addr, dev->dev_addr); ether_addr_copy(dev->dev_addr, addr->sa_data); if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED) qeth_l2_remove_mac(card, old_addr); card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; - return 0; + +out_unlock: + mutex_unlock(&card->conf_mutex); + return rc; } static void qeth_promisc_to_bridge(struct qeth_card *card) @@ -1112,6 +1119,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) netif_carrier_off(card->dev); qeth_set_allowed_threads(card, 0xffffffff, 0); + + qeth_enable_hw_features(card->dev); if (recover_flag == CARD_STATE_RECOVER) { if (recovery_mode && card->info.type != QETH_CARD_TYPE_OSN) { @@ -1123,9 +1132,6 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) } /* this also sets saved unicast addresses */ qeth_l2_set_rx_mode(card->dev); - rtnl_lock(); - qeth_recover_features(card->dev); - rtnl_unlock(); } /* let user_space know that device is online */ kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index e7fa479adf47..5905dc63e256 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2662,6 +2662,8 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) netif_carrier_on(card->dev); else netif_carrier_off(card->dev); + + qeth_enable_hw_features(card->dev); if (recover_flag == CARD_STATE_RECOVER) { rtnl_lock(); if (recovery_mode) @@ -2669,7 +2671,6 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) else dev_open(card->dev); qeth_l3_set_rx_mode(card->dev); - qeth_recover_features(card->dev); rtnl_unlock(); } qeth_trace_features(card); diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a9831bd37a73..a57f3a7d4748 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -1974,7 +1974,6 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev) u32 lun_count, nexus; u32 i, bus, target; u8 expose_flag, attribs; - u8 devtype; lun_count = aac_get_safw_phys_lun_count(dev); @@ -1992,23 +1991,23 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev) continue; if (expose_flag != 0) { - devtype = AAC_DEVTYPE_RAID_MEMBER; - goto update_devtype; + dev->hba_map[bus][target].devtype = + AAC_DEVTYPE_RAID_MEMBER; + continue; } if (nexus != 0 && (attribs & 8)) { - devtype = AAC_DEVTYPE_NATIVE_RAW; + dev->hba_map[bus][target].devtype = + AAC_DEVTYPE_NATIVE_RAW; dev->hba_map[bus][target].rmw_nexus = nexus; } else - devtype = AAC_DEVTYPE_ARC_RAW; + dev->hba_map[bus][target].devtype = + AAC_DEVTYPE_ARC_RAW; dev->hba_map[bus][target].scan_counter = dev->scan_counter; aac_set_safw_target_qd(dev, bus, target); - -update_devtype: - dev->hba_map[bus][target].devtype = devtype; } } diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h index 2a3977823812..a39be94d110c 100644 --- a/drivers/scsi/cxlflash/main.h +++ b/drivers/scsi/cxlflash/main.h @@ -107,12 +107,12 @@ cxlflash_assign_ops(struct dev_dependent_vals *ddv) { const struct cxlflash_backend_ops *ops = NULL; -#ifdef CONFIG_OCXL +#ifdef CONFIG_OCXL_BASE if (ddv->flags & CXLFLASH_OCXL_DEV) ops = &cxlflash_ocxl_ops; #endif -#ifdef CONFIG_CXL +#ifdef CONFIG_CXL_BASE if (!(ddv->flags & CXLFLASH_OCXL_DEV)) ops = &cxlflash_cxl_ops; #endif diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c index 0a95b5f25380..497a68389461 100644 --- a/drivers/scsi/cxlflash/ocxl_hw.c +++ b/drivers/scsi/cxlflash/ocxl_hw.c @@ -134,15 +134,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name, rc = PTR_ERR(file); dev_err(dev, "%s: alloc_file failed rc=%d\n", __func__, rc); - goto err5; + path_put(&path); + goto err3; } file->f_flags = flags & (O_ACCMODE | O_NONBLOCK); file->private_data = priv; out: return file; -err5: - path_put(&path); err4: iput(inode); err3: diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 15c7f3b6f35e..58bb70b886d7 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3440,11 +3440,11 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h, struct ext_report_lun_entry *rle = &rlep->LUN[rle_index]; u16 bmic_device_index = 0; - bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]); - - encl_dev->sas_address = + encl_dev->eli = hpsa_get_enclosure_logical_identifier(h, scsi3addr); + bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]); + if (encl_dev->target == -1 || encl_dev->lun == -1) { rc = IO_OK; goto out; @@ -9697,7 +9697,24 @@ hpsa_sas_get_linkerrors(struct sas_phy *phy) static int hpsa_sas_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier) { - *identifier = rphy->identify.sas_address; + struct Scsi_Host *shost = phy_to_shost(rphy); + struct ctlr_info *h; + struct hpsa_scsi_dev_t *sd; + + if (!shost) + return -ENXIO; + + h = shost_to_hba(shost); + + if (!h) + return -ENXIO; + + sd = hpsa_find_device_by_sas_rphy(h, rphy); + if (!sd) + return -ENXIO; + + *identifier = sd->eli; + return 0; } diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h index fb9f5e7f8209..59e023696fff 100644 --- a/drivers/scsi/hpsa.h +++ b/drivers/scsi/hpsa.h @@ -68,6 +68,7 @@ struct hpsa_scsi_dev_t { #define RAID_CTLR_LUNID "\0\0\0\0\0\0\0\0" unsigned char device_id[16]; /* from inquiry pg. 0x83 */ u64 sas_address; + u64 eli; /* from report diags. */ unsigned char vendor[8]; /* bytes 8-15 of inquiry data */ unsigned char model[16]; /* bytes 16-31 of inquiry data */ unsigned char rev; /* byte 2 of inquiry data */ diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 90394cef0f41..0a5dd5595dd3 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3295,6 +3295,11 @@ static int __qedf_probe(struct pci_dev *pdev, int mode) init_completion(&qedf->flogi_compl); + status = qed_ops->common->update_drv_state(qedf->cdev, true); + if (status) + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to send drv state to MFW.\n"); + memset(&link_params, 0, sizeof(struct qed_link_params)); link_params.link_up = true; status = qed_ops->common->set_link(qedf->cdev, &link_params); @@ -3343,6 +3348,7 @@ static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id) static void __qedf_remove(struct pci_dev *pdev, int mode) { struct qedf_ctx *qedf; + int rc; if (!pdev) { QEDF_ERR(NULL, "pdev is NULL.\n"); @@ -3437,6 +3443,12 @@ static void __qedf_remove(struct pci_dev *pdev, int mode) qed_ops->common->set_power_state(qedf->cdev, PCI_D0); pci_set_drvdata(pdev, NULL); } + + rc = qed_ops->common->update_drv_state(qedf->cdev, false); + if (rc) + QEDF_ERR(&(qedf->dbg_ctx), + "Failed to send drv state to MFW.\n"); + qed_ops->common->slowpath_stop(qedf->cdev); qed_ops->common->remove(qedf->cdev); diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index cf274a79e77a..091ec1207bea 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -2273,6 +2273,7 @@ kset_free: static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); + int rval; if (qedi->tmf_thread) { flush_workqueue(qedi->tmf_thread); @@ -2302,6 +2303,10 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) if (mode == QEDI_MODE_NORMAL) qedi_free_iscsi_pf_param(qedi); + rval = qedi_ops->common->update_drv_state(qedi->cdev, false); + if (rval) + QEDI_ERR(&qedi->dbg_ctx, "Failed to send drv state to MFW\n"); + if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) { qedi_ops->common->slowpath_stop(qedi->cdev); qedi_ops->common->remove(qedi->cdev); @@ -2576,6 +2581,12 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) if (qedi_setup_boot_info(qedi)) QEDI_ERR(&qedi->dbg_ctx, "No iSCSI boot target configured\n"); + + rc = qedi_ops->common->update_drv_state(qedi->cdev, true); + if (rc) + QEDI_ERR(&qedi->dbg_ctx, + "Failed to send drv state to MFW\n"); + } return 0; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 9442e18aef6f..0f94b1d62d3f 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -361,6 +361,8 @@ struct ct_arg { dma_addr_t rsp_dma; u32 req_size; u32 rsp_size; + u32 req_allocated_size; + u32 rsp_allocated_size; void *req; void *rsp; port_id_t id; diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 4bc2b66b299f..2c35b0b2baa0 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -556,7 +556,7 @@ err2: /* please ignore kernel warning. otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; @@ -564,7 +564,7 @@ err2: if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -617,6 +617,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -627,6 +628,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -712,6 +714,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -722,6 +725,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -802,6 +806,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -812,6 +817,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id, sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -909,6 +915,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "%s: Failed to allocate ct_sns request.\n", @@ -919,6 +926,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "%s: Failed to allocate ct_sns request.\n", @@ -3388,14 +3396,14 @@ void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp) { if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -3596,14 +3604,14 @@ static void qla2x00_async_gpnid_sp_done(void *s, int res) /* please ignore kernel warning. otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -3654,6 +3662,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xd041, "Failed to allocate ct_sns request.\n"); @@ -3663,6 +3672,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xd042, "Failed to allocate ct_sns request.\n"); @@ -4142,14 +4152,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4179,14 +4189,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) /* please ignore kernel warning. Otherwise, we have mem leak. */ if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4281,14 +4291,14 @@ static int qla24xx_async_gnnft(scsi_qla_host_t *vha, struct srb *sp, done_free_sp: if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; @@ -4349,6 +4359,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) sp->u.iocb_cmd.u.ctarg.req = dma_zalloc_coherent( &vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.req) { ql_log(ql_log_warn, vha, 0xffff, "Failed to allocate ct_sns request.\n"); @@ -4366,6 +4377,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) sp->u.iocb_cmd.u.ctarg.rsp = dma_zalloc_coherent( &vha->hw->pdev->dev, rspsz, &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xffff, "Failed to allocate ct_sns request.\n"); @@ -4425,14 +4437,14 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) done_free_sp: if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req_allocated_size, sp->u.iocb_cmd.u.ctarg.req, sp->u.iocb_cmd.u.ctarg.req_dma); sp->u.iocb_cmd.u.ctarg.req = NULL; } if (sp->u.iocb_cmd.u.ctarg.rsp) { dma_free_coherent(&vha->hw->pdev->dev, - sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, sp->u.iocb_cmd.u.ctarg.rsp, sp->u.iocb_cmd.u.ctarg.rsp_dma); sp->u.iocb_cmd.u.ctarg.rsp = NULL; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 7b675243bd16..db0e3279e07a 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -591,12 +591,14 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, conflict_fcport = qla2x00_find_fcport_by_wwpn(vha, e->port_name, 0); - ql_dbg(ql_dbg_disc, vha, 0x20e6, - "%s %d %8phC post del sess\n", - __func__, __LINE__, - conflict_fcport->port_name); - qlt_schedule_sess_for_deletion - (conflict_fcport); + if (conflict_fcport) { + qlt_schedule_sess_for_deletion + (conflict_fcport); + ql_dbg(ql_dbg_disc, vha, 0x20e6, + "%s %d %8phC post del sess\n", + __func__, __LINE__, + conflict_fcport->port_name); + } } /* FW already picked this loop id for another fcport */ diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index e881fce7477a..9f309e572be4 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3180,6 +3180,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) "req->req_q_in=%p req->req_q_out=%p rsp->rsp_q_in=%p rsp->rsp_q_out=%p.\n", req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out); + ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0); + if (ha->isp_ops->initialize_adapter(base_vha)) { ql_log(ql_log_fatal, base_vha, 0x00d6, "Failed to initialize adapter - Adapter flags %x.\n", @@ -3216,8 +3218,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) host->can_queue, base_vha->req, base_vha->mgmt_svr_loop_id, host->sg_tablesize); - ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0); - if (ha->mqenable) { bool mq = false; bool startit = false; diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 8932ae81a15a..2715cdaa669c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) rtn = host->hostt->eh_timed_out(scmd); if (rtn == BLK_EH_DONE) { + /* + * For blk-mq, we must set the request state to complete now + * before sending the request to the scsi error handler. This + * will prevent a use-after-free in the event the LLD manages + * to complete the request before the error handler finishes + * processing this timed out request. + * + * If the request was already completed, then the LLD beat the + * time out handler from transferring the request to the scsi + * error handler. In that case we can return immediately as no + * further action is required. + */ + if (req->q->mq_ops && !blk_mq_mark_complete(req)) + return rtn; if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index a14fef11776e..2bf3bf73886e 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -391,7 +391,8 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) * Check that all zones of the device are equal. The last zone can however * be smaller. The zone size must also be a power of two number of LBAs. * - * Returns the zone size in bytes upon success or an error code upon failure. + * Returns the zone size in number of blocks upon success or an error code + * upon failure. */ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) { @@ -401,7 +402,7 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) unsigned char *rec; unsigned int buf_len; unsigned int list_length; - int ret; + s64 ret; u8 same; /* Get a buffer */ diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 53ae52dbff84..cd2fdac000c9 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -51,6 +51,7 @@ static int sg_version_num = 30536; /* 2 digits for each component */ #include <linux/atomic.h> #include <linux/ratelimit.h> #include <linux/uio.h> +#include <linux/cred.h> /* for sg_check_file_access() */ #include "scsi.h" #include <scsi/scsi_dbg.h> @@ -209,6 +210,33 @@ static void sg_device_destroy(struct kref *kref); sdev_prefix_printk(prefix, (sdp)->device, \ (sdp)->disk->disk_name, fmt, ##a) +/* + * The SCSI interfaces that use read() and write() as an asynchronous variant of + * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways + * to trigger read() and write() calls from various contexts with elevated + * privileges. This can lead to kernel memory corruption (e.g. if these + * interfaces are called through splice()) and privilege escalation inside + * userspace (e.g. if a process with access to such a device passes a file + * descriptor to a SUID binary as stdin/stdout/stderr). + * + * This function provides protection for the legacy API by restricting the + * calling context. + */ +static int sg_check_file_access(struct file *filp, const char *caller) +{ + if (filp->f_cred != current_real_cred()) { + pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", + caller, task_tgid_vnr(current), current->comm); + return -EPERM; + } + if (uaccess_kernel()) { + pr_err_once("%s: process %d (%s) called from kernel context, this is not allowed.\n", + caller, task_tgid_vnr(current), current->comm); + return -EACCES; + } + return 0; +} + static int sg_allow_access(struct file *filp, unsigned char *cmd) { struct sg_fd *sfp = filp->private_data; @@ -393,6 +421,14 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos) struct sg_header *old_hdr = NULL; int retval = 0; + /* + * This could cause a response to be stranded. Close the associated + * file descriptor to free up any resources being held. + */ + retval = sg_check_file_access(filp, __func__); + if (retval) + return retval; + if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, @@ -580,9 +616,11 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) struct sg_header old_hdr; sg_io_hdr_t *hp; unsigned char cmnd[SG_MAX_CDB_SIZE]; + int retval; - if (unlikely(uaccess_kernel())) - return -EINVAL; + retval = sg_check_file_access(filp, __func__); + if (retval) + return retval; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index 32f0748fd067..0097a939487f 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -27,9 +27,16 @@ #define GPC_PGC_SW2ISO_SHIFT 0x8 #define GPC_PGC_SW_SHIFT 0x0 +#define GPC_PGC_PCI_PDN 0x200 +#define GPC_PGC_PCI_SR 0x20c + #define GPC_PGC_GPU_PDN 0x260 #define GPC_PGC_GPU_PUPSCR 0x264 #define GPC_PGC_GPU_PDNSCR 0x268 +#define GPC_PGC_GPU_SR 0x26c + +#define GPC_PGC_DISP_PDN 0x240 +#define GPC_PGC_DISP_SR 0x24c #define GPU_VPU_PUP_REQ BIT(1) #define GPU_VPU_PDN_REQ BIT(0) @@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = { { } }; +static const struct regmap_range yes_ranges[] = { + regmap_reg_range(GPC_CNTR, GPC_CNTR), + regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR), + regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR), + regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR), +}; + +static const struct regmap_access_table access_table = { + .yes_ranges = yes_ranges, + .n_yes_ranges = ARRAY_SIZE(yes_ranges), +}; + static const struct regmap_config imx_gpc_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, + .rd_table = &access_table, + .wr_table = &access_table, .max_register = 0x2ac, }; diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c index 0ecffab52ec2..abdaf7cf8162 100644 --- a/drivers/staging/ks7010/ks_hostif.c +++ b/drivers/staging/ks7010/ks_hostif.c @@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN); if (dev->flags & IFF_PROMISC) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_PROMISC); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_PROMISC); goto spin_unlock; } if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) || (dev->flags & IFF_ALLMULTI)) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCASTALL); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCASTALL); goto spin_unlock; } @@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) ETH_ALEN * mc_count); } else { priv->sme_i.sme_flag |= SME_MULTICAST; - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCAST); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCAST); } spin_unlock: diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c index a3a83424a926..16478fe9e3f8 100644 --- a/drivers/staging/media/omap4iss/iss_video.c +++ b/drivers/staging/media/omap4iss/iss_video.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <asm/cacheflush.h> #include <linux/clk.h> #include <linux/mm.h> #include <linux/pagemap.h> @@ -24,6 +23,8 @@ #include <media/v4l2-ioctl.h> #include <media/v4l2-mc.h> +#include <asm/cacheflush.h> + #include "iss_video.h" #include "iss.h" diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig index 673fdce25530..ff7832798a77 100644 --- a/drivers/staging/rtl8188eu/Kconfig +++ b/drivers/staging/rtl8188eu/Kconfig @@ -7,7 +7,6 @@ config R8188EU select LIB80211 select LIB80211_CRYPT_WEP select LIB80211_CRYPT_CCMP - select LIB80211_CRYPT_TKIP ---help--- This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N. If built as a module, it will be called r8188eu. diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 05936a45eb93..c6857a5be12a 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -23,7 +23,6 @@ #include <mon.h> #include <wifi.h> #include <linux/vmalloc.h> -#include <net/lib80211.h> #define ETHERNET_HEADER_SIZE 14 /* Ethernet Header Length */ #define LLC_HEADER_SIZE 6 /* LLC Header Length */ @@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter) static int recvframe_chkmic(struct adapter *adapter, struct recv_frame *precvframe) { - int res = _SUCCESS; - struct rx_pkt_attrib *prxattrib = &precvframe->attrib; - struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta); + int i, res = _SUCCESS; + u32 datalen; + u8 miccode[8]; + u8 bmic_err = false, brpt_micerror = true; + u8 *pframe, *payload, *pframemic; + u8 *mickey; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &precvframe->attrib; + struct security_priv *psecuritypriv = &adapter->securitypriv; + + struct mlme_ext_priv *pmlmeext = &adapter->mlmeextpriv; + struct mlme_ext_info *pmlmeinfo = &(pmlmeext->mlmext_info); + + stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]); if (prxattrib->encrypt == _TKIP_) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5])); + + /* calculate mic code */ if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - struct sk_buff *skb = precvframe->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - void *crypto_private = NULL; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &adapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv) { res = _FAIL; @@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter, DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0]; + + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: bcmc key\n", __func__)); } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + mickey = &stainfo->dot11tkiprxmickey.skey[0]; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n %s: unicast key\n", __func__)); } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + /* icv_len included the mic code */ + datalen = precvframe->pkt->len-prxattrib->hdrlen - + prxattrib->iv_len-prxattrib->icv_len-8; + pframe = precvframe->pkt->data; + payload = pframe+prxattrib->hdrlen+prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); - memmove(pframe + iv_len, pframe, prxattrib->hdrlen); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len)); + rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0], + (unsigned char)prxattrib->priority); /* care the length of the data */ - skb_pull(skb, iv_len); - skb_trim(skb, skb->len - icv_len); + pframemic = payload+datalen; - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; + bmic_err = false; + + for (i = 0; i < 8; i++) { + if (miccode[i] != *(pframemic+i)) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ", + __func__, i, miccode[i], i, *(pframemic + i))); + bmic_err = true; + } } - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + if (bmic_err) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-8), *(pframemic-7), *(pframemic-6), + *(pframemic-5), *(pframemic-4), *(pframemic-3), + *(pframemic-2), *(pframemic-1))); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-16), *(pframemic-15), *(pframemic-14), + *(pframemic-13), *(pframemic-12), *(pframemic-11), + *(pframemic-10), *(pframemic-9))); + { + uint i; - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n ======demp packet (len=%d)======\n", + precvframe->pkt->len)); + for (i = 0; i < precvframe->pkt->len; i += 8) { + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x", + *(precvframe->pkt->data+i), + *(precvframe->pkt->data+i+1), + *(precvframe->pkt->data+i+2), + *(precvframe->pkt->data+i+3), + *(precvframe->pkt->data+i+4), + *(precvframe->pkt->data+i+5), + *(precvframe->pkt->data+i+6), + *(precvframe->pkt->data+i+7))); + } + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n ====== demp packet end [len=%d]======\n", + precvframe->pkt->len)); + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n hrdlen=%d,\n", + prxattrib->hdrlen)); + } -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ", + prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey)); + + /* double check key_index for some timing issue , */ + /* cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */ + if ((IS_MCAST(prxattrib->ra) == true) && (prxattrib->key_index != pmlmeinfo->key_index)) + brpt_micerror = false; + + if ((prxattrib->bdecrypted) && (brpt_micerror)) { + rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } else { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } + res = _FAIL; + } else { + /* mic checked ok */ + if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) { + psecuritypriv->bcheck_grpkey = true; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true")); + } + } } else { RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("%s: rtw_get_stainfo==NULL!!!\n", __func__)); } + + skb_trim(precvframe->pkt, precvframe->pkt->len - 8); } exit: + return res; } diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c index bfe0b217e679..67a2490f055e 100644 --- a/drivers/staging/rtl8188eu/core/rtw_security.c +++ b/drivers/staging/rtl8188eu/core/rtw_security.c @@ -650,71 +650,71 @@ u32 rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe) return res; } +/* The hlen isn't include the IV */ u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe) -{ - struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; - u32 res = _SUCCESS; +{ /* exclude ICV */ + u16 pnl; + u32 pnh; + u8 rc4key[16]; + u8 ttkey[16]; + u8 crc[4]; + struct arc4context mycontext; + int length; + + u8 *pframe, *payload, *iv, *prwskey; + union pn48 dot11txpn; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; + struct security_priv *psecuritypriv = &padapter->securitypriv; + u32 res = _SUCCESS; + + + pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data; /* 4 start to decrypt recvframe */ if (prxattrib->encrypt == _TKIP_) { - struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta); - + stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]); if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - void *crypto_private = NULL; - struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &padapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv->binstallGrpkey) { res = _FAIL; DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey; } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__)); + prwskey = &stainfo->dot118021x_UncstKey.skey[0]; } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + iv = pframe+prxattrib->hdrlen; + payload = pframe+prxattrib->iv_len+prxattrib->hdrlen; + length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); + GET_TKIP_PN(iv, dot11txpn); - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; - } + pnl = (u16)(dot11txpn.val); + pnh = (u32)(dot11txpn.val>>16); - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh); + phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl); - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + /* 4 decrypt payload include icv */ -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + arcfour_init(&mycontext, rc4key, 16); + arcfour_encrypt(&mycontext, payload, payload, length); + + *((__le32 *)crc) = getcrc32(payload, length-4); + + if (crc[3] != payload[length-1] || + crc[2] != payload[length-2] || + crc[1] != payload[length-3] || + crc[0] != payload[length-4]) { + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, + ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n", + &crc, &payload[length-4])); + res = _FAIL; + } } else { RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n")); res = _FAIL; diff --git a/drivers/staging/rtl8723bs/core/rtw_ap.c b/drivers/staging/rtl8723bs/core/rtw_ap.c index 45c05527a57a..faf4b4158cfa 100644 --- a/drivers/staging/rtl8723bs/core/rtw_ap.c +++ b/drivers/staging/rtl8723bs/core/rtw_ap.c @@ -1051,7 +1051,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf, int len) return _FAIL; - if (len > MAX_IE_SZ) + if (len < 0 || len > MAX_IE_SZ) return _FAIL; pbss_network->IELength = len; diff --git a/drivers/staging/rtlwifi/rtl8822be/hw.c b/drivers/staging/rtlwifi/rtl8822be/hw.c index 7947edb239a1..88ba5b2fea6a 100644 --- a/drivers/staging/rtlwifi/rtl8822be/hw.c +++ b/drivers/staging/rtlwifi/rtl8822be/hw.c @@ -803,7 +803,7 @@ static void _rtl8822be_enable_aspm_back_door(struct ieee80211_hw *hw) return; pci_read_config_byte(rtlpci->pdev, 0x70f, &tmp); - pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | BIT(7)); + pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | ASPM_L1_LATENCY << 3); pci_read_config_byte(rtlpci->pdev, 0x719, &tmp); pci_write_config_byte(rtlpci->pdev, 0x719, tmp | BIT(3) | BIT(4)); diff --git a/drivers/staging/rtlwifi/wifi.h b/drivers/staging/rtlwifi/wifi.h index 012fb618840b..a45f0eb69d3f 100644 --- a/drivers/staging/rtlwifi/wifi.h +++ b/drivers/staging/rtlwifi/wifi.h @@ -88,6 +88,7 @@ #define RTL_USB_MAX_RX_COUNT 100 #define QBSS_LOAD_SIZE 5 #define MAX_WMMELE_LENGTH 64 +#define ASPM_L1_LATENCY 7 #define TOTAL_CAM_ENTRY 32 diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index a61bc41b82d7..947c79532e10 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, int chars_sent = 0; char __user *cp; char *init; + size_t bytes_per_ch = unicode ? 3 : 1; u16 ch; int empty; unsigned long flags; DEFINE_WAIT(wait); + if (count < bytes_per_ch) + return -EINVAL; + spin_lock_irqsave(&speakup_info.spinlock, flags); while (1) { prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE); @@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, init = get_initstring(); /* Keep 3 bytes available for a 16bit UTF-8-encoded character */ - while (chars_sent <= count - 3) { + while (chars_sent <= count - bytes_per_ch) { if (speakup_info.flushing) { speakup_info.flushing = 0; ch = '\x18'; diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 01ac306131c1..10db5656fd5d 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -3727,11 +3727,16 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd) * Check for overflow of 8byte PRI READ_KEYS payload and * next reservation key list descriptor. */ - if ((add_len + 8) > (cmd->data_length - 8)) - break; - - put_unaligned_be64(pr_reg->pr_res_key, &buf[off]); - off += 8; + if (off + 8 <= cmd->data_length) { + put_unaligned_be64(pr_reg->pr_res_key, &buf[off]); + off += 8; + } + /* + * SPC5r17: 6.16.2 READ KEYS service action + * The ADDITIONAL LENGTH field indicates the number of bytes in + * the Reservation key list. The contents of the ADDITIONAL + * LENGTH field are not altered based on the allocation length + */ add_len += 8; } spin_unlock(&dev->t10_pr.registration_lock); diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index 6281266b8ec0..a923ebdeb73c 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -213,6 +213,10 @@ static ssize_t boot_acl_store(struct device *dev, struct device_attribute *attr, goto err_free_acl; } ret = tb->cm_ops->set_boot_acl(tb, acl, tb->nboot_acl); + if (!ret) { + /* Notify userspace about the change */ + kobject_uevent(&tb->dev.kobj, KOBJ_CHANGE); + } mutex_unlock(&tb->lock); err_free_acl: diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index e8f4ac9400ea..5d421d7e8904 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -215,7 +215,20 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct uio_device *idev = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", idev->info->name); + int ret; + + mutex_lock(&idev->info_lock); + if (!idev->info) { + ret = -EINVAL; + dev_err(dev, "the device has been unregistered\n"); + goto out; + } + + ret = sprintf(buf, "%s\n", idev->info->name); + +out: + mutex_unlock(&idev->info_lock); + return ret; } static DEVICE_ATTR_RO(name); @@ -223,7 +236,20 @@ static ssize_t version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct uio_device *idev = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", idev->info->version); + int ret; + + mutex_lock(&idev->info_lock); + if (!idev->info) { + ret = -EINVAL; + dev_err(dev, "the device has been unregistered\n"); + goto out; + } + + ret = sprintf(buf, "%s\n", idev->info->version); + +out: + mutex_unlock(&idev->info_lock); + return ret; } static DEVICE_ATTR_RO(version); @@ -415,11 +441,15 @@ EXPORT_SYMBOL_GPL(uio_event_notify); static irqreturn_t uio_interrupt(int irq, void *dev_id) { struct uio_device *idev = (struct uio_device *)dev_id; - irqreturn_t ret = idev->info->handler(irq, idev->info); + irqreturn_t ret; + mutex_lock(&idev->info_lock); + + ret = idev->info->handler(irq, idev->info); if (ret == IRQ_HANDLED) uio_event_notify(idev->info); + mutex_unlock(&idev->info_lock); return ret; } @@ -433,7 +463,6 @@ static int uio_open(struct inode *inode, struct file *filep) struct uio_device *idev; struct uio_listener *listener; int ret = 0; - unsigned long flags; mutex_lock(&minor_lock); idev = idr_find(&uio_idr, iminor(inode)); @@ -460,10 +489,16 @@ static int uio_open(struct inode *inode, struct file *filep) listener->event_count = atomic_read(&idev->event); filep->private_data = listener; - spin_lock_irqsave(&idev->info_lock, flags); + mutex_lock(&idev->info_lock); + if (!idev->info) { + mutex_unlock(&idev->info_lock); + ret = -EINVAL; + goto err_alloc_listener; + } + if (idev->info && idev->info->open) ret = idev->info->open(idev->info, inode); - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); if (ret) goto err_infoopen; @@ -495,12 +530,11 @@ static int uio_release(struct inode *inode, struct file *filep) int ret = 0; struct uio_listener *listener = filep->private_data; struct uio_device *idev = listener->dev; - unsigned long flags; - spin_lock_irqsave(&idev->info_lock, flags); + mutex_lock(&idev->info_lock); if (idev->info && idev->info->release) ret = idev->info->release(idev->info, inode); - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); module_put(idev->owner); kfree(listener); @@ -513,12 +547,11 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait) struct uio_listener *listener = filep->private_data; struct uio_device *idev = listener->dev; __poll_t ret = 0; - unsigned long flags; - spin_lock_irqsave(&idev->info_lock, flags); + mutex_lock(&idev->info_lock); if (!idev->info || !idev->info->irq) ret = -EIO; - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); if (ret) return ret; @@ -537,12 +570,11 @@ static ssize_t uio_read(struct file *filep, char __user *buf, DECLARE_WAITQUEUE(wait, current); ssize_t retval = 0; s32 event_count; - unsigned long flags; - spin_lock_irqsave(&idev->info_lock, flags); + mutex_lock(&idev->info_lock); if (!idev->info || !idev->info->irq) retval = -EIO; - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); if (retval) return retval; @@ -592,9 +624,13 @@ static ssize_t uio_write(struct file *filep, const char __user *buf, struct uio_device *idev = listener->dev; ssize_t retval; s32 irq_on; - unsigned long flags; - spin_lock_irqsave(&idev->info_lock, flags); + mutex_lock(&idev->info_lock); + if (!idev->info) { + retval = -EINVAL; + goto out; + } + if (!idev->info || !idev->info->irq) { retval = -EIO; goto out; @@ -618,7 +654,7 @@ static ssize_t uio_write(struct file *filep, const char __user *buf, retval = idev->info->irqcontrol(idev->info, irq_on); out: - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); return retval ? retval : sizeof(s32); } @@ -640,10 +676,20 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf) struct page *page; unsigned long offset; void *addr; + int ret = 0; + int mi; - int mi = uio_find_mem_index(vmf->vma); - if (mi < 0) - return VM_FAULT_SIGBUS; + mutex_lock(&idev->info_lock); + if (!idev->info) { + ret = VM_FAULT_SIGBUS; + goto out; + } + + mi = uio_find_mem_index(vmf->vma); + if (mi < 0) { + ret = VM_FAULT_SIGBUS; + goto out; + } /* * We need to subtract mi because userspace uses offset = N*PAGE_SIZE @@ -658,7 +704,11 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf) page = vmalloc_to_page(addr); get_page(page); vmf->page = page; - return 0; + +out: + mutex_unlock(&idev->info_lock); + + return ret; } static const struct vm_operations_struct uio_logical_vm_ops = { @@ -683,6 +733,7 @@ static int uio_mmap_physical(struct vm_area_struct *vma) struct uio_device *idev = vma->vm_private_data; int mi = uio_find_mem_index(vma); struct uio_mem *mem; + if (mi < 0) return -EINVAL; mem = idev->info->mem + mi; @@ -724,30 +775,46 @@ static int uio_mmap(struct file *filep, struct vm_area_struct *vma) vma->vm_private_data = idev; + mutex_lock(&idev->info_lock); + if (!idev->info) { + ret = -EINVAL; + goto out; + } + mi = uio_find_mem_index(vma); - if (mi < 0) - return -EINVAL; + if (mi < 0) { + ret = -EINVAL; + goto out; + } requested_pages = vma_pages(vma); actual_pages = ((idev->info->mem[mi].addr & ~PAGE_MASK) + idev->info->mem[mi].size + PAGE_SIZE -1) >> PAGE_SHIFT; - if (requested_pages > actual_pages) - return -EINVAL; + if (requested_pages > actual_pages) { + ret = -EINVAL; + goto out; + } if (idev->info->mmap) { ret = idev->info->mmap(idev->info, vma); - return ret; + goto out; } switch (idev->info->mem[mi].memtype) { case UIO_MEM_PHYS: - return uio_mmap_physical(vma); + ret = uio_mmap_physical(vma); + break; case UIO_MEM_LOGICAL: case UIO_MEM_VIRTUAL: - return uio_mmap_logical(vma); + ret = uio_mmap_logical(vma); + break; default: - return -EINVAL; + ret = -EINVAL; } + +out: + mutex_unlock(&idev->info_lock); + return 0; } static const struct file_operations uio_fops = { @@ -865,7 +932,7 @@ int __uio_register_device(struct module *owner, idev->owner = owner; idev->info = info; - spin_lock_init(&idev->info_lock); + mutex_init(&idev->info_lock); init_waitqueue_head(&idev->wait); atomic_set(&idev->event, 0); @@ -902,8 +969,9 @@ int __uio_register_device(struct module *owner, * FDs at the time of unregister and therefore may not be * freed until they are released. */ - ret = request_irq(info->irq, uio_interrupt, - info->irq_flags, info->name, idev); + ret = request_threaded_irq(info->irq, NULL, uio_interrupt, + info->irq_flags, info->name, idev); + if (ret) goto err_request_irq; } @@ -928,7 +996,6 @@ EXPORT_SYMBOL_GPL(__uio_register_device); void uio_unregister_device(struct uio_info *info) { struct uio_device *idev; - unsigned long flags; if (!info || !info->uio_dev) return; @@ -937,14 +1004,14 @@ void uio_unregister_device(struct uio_info *info) uio_free_minor(idev); + mutex_lock(&idev->info_lock); uio_dev_del_attributes(idev); if (info->irq && info->irq != UIO_IRQ_CUSTOM) free_irq(info->irq, idev); - spin_lock_irqsave(&idev->info_lock, flags); idev->info = NULL; - spin_unlock_irqrestore(&idev->info_lock, flags); + mutex_unlock(&idev->info_lock); device_unregister(&idev->dev); diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig index 785f0ed037f7..ee34e9046f7e 100644 --- a/drivers/usb/chipidea/Kconfig +++ b/drivers/usb/chipidea/Kconfig @@ -3,6 +3,7 @@ config USB_CHIPIDEA depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA select EXTCON select RESET_CONTROLLER + select USB_ULPI_BUS help Say Y here if your system has a dual role high speed USB controller based on ChipIdea silicon IP. It supports: @@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST help Say Y here to enable host controller functionality of the ChipIdea driver. - -config USB_CHIPIDEA_ULPI - bool "ChipIdea ULPI PHY support" - depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA - help - Say Y here if you have a ULPI PHY attached to your ChipIdea - controller. - endif diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile index e3d5e728fa53..12df94f78f72 100644 --- a/drivers/usb/chipidea/Makefile +++ b/drivers/usb/chipidea/Makefile @@ -1,11 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_USB_CHIPIDEA) += ci_hdrc.o -ci_hdrc-y := core.o otg.o debug.o +ci_hdrc-y := core.o otg.o debug.o ulpi.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC) += udc.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST) += host.o ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o -ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI) += ulpi.o # Glue/Bridge layers go here diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 0bf244d50544..6a2cc5cd0281 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -240,10 +240,8 @@ struct ci_hdrc { struct ci_hdrc_platform_data *platdata; int vbus_active; -#ifdef CONFIG_USB_CHIPIDEA_ULPI struct ulpi *ulpi; struct ulpi_ops ulpi_ops; -#endif struct phy *phy; /* old usb_phy interface */ struct usb_phy *usb_phy; @@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci) #endif } -#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI) int ci_ulpi_init(struct ci_hdrc *ci); void ci_ulpi_exit(struct ci_hdrc *ci); int ci_ulpi_resume(struct ci_hdrc *ci); -#else -static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; } -static inline void ci_ulpi_exit(struct ci_hdrc *ci) { } -static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; } -#endif u32 hw_read_intr_enable(struct ci_hdrc *ci); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 6da42dcd2888..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci) { int cnt = 100000; + if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) + return 0; + while (cnt-- > 0) { if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE)) return 0; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 998b32d0167e..75c4623ad779 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1831,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ }, + { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index fcae521df29b..1fb266809966 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) if (!udev || udev->state == USB_STATE_NOTATTACHED) { /* Tell hub_wq to disconnect the device or - * check for a new connection + * check for a new connection or over current condition. + * Based on USB2.0 Spec Section 11.12.5, + * C_PORT_OVER_CURRENT could be set while + * PORT_OVER_CURRENT is not. So check for any of them. */ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) || - (portstatus & USB_PORT_STAT_OVERCURRENT)) + (portstatus & USB_PORT_STAT_OVERCURRENT) || + (portchange & USB_PORT_STAT_C_OVERCURRENT)) set_bit(port1, hub->change_bits); } else if (portstatus & USB_PORT_STAT_ENABLE) { diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index c55def2f1320..097057d2eacf 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -378,6 +378,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* Corsair K70 RGB */ { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Corsair Strafe */ + { USB_DEVICE(0x1b1c, 0x1b15), .driver_info = USB_QUIRK_DELAY_INIT | + USB_QUIRK_DELAY_CTRL_MSG }, + /* Corsair Strafe RGB */ { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT | USB_QUIRK_DELAY_CTRL_MSG }, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index a0f82cca2d9a..cefc99ae69b2 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_in[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx)); @@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); @@ -3650,7 +3650,7 @@ irq_retry: for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index b1104be3429c..6e2cdd7b93d4 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg, #define DWC2_USB_DMA_ALIGN 4 -struct dma_aligned_buffer { - void *kmalloc_ptr; - void *old_xfer_buffer; - u8 data[0]; -}; - static void dwc2_free_dma_aligned_buffer(struct urb *urb) { - struct dma_aligned_buffer *temp; + void *stored_xfer_buffer; + size_t length; if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER)) return; - temp = container_of(urb->transfer_buffer, - struct dma_aligned_buffer, data); + /* Restore urb->transfer_buffer from the end of the allocated area */ + memcpy(&stored_xfer_buffer, urb->transfer_buffer + + urb->transfer_buffer_length, sizeof(urb->transfer_buffer)); - if (usb_urb_dir_in(urb)) - memcpy(temp->old_xfer_buffer, temp->data, - urb->transfer_buffer_length); - urb->transfer_buffer = temp->old_xfer_buffer; - kfree(temp->kmalloc_ptr); + if (usb_urb_dir_in(urb)) { + if (usb_pipeisoc(urb->pipe)) + length = urb->transfer_buffer_length; + else + length = urb->actual_length; + + memcpy(stored_xfer_buffer, urb->transfer_buffer, length); + } + kfree(urb->transfer_buffer); + urb->transfer_buffer = stored_xfer_buffer; urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER; } static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) { - struct dma_aligned_buffer *temp, *kmalloc_ptr; + void *kmalloc_ptr; size_t kmalloc_size; if (urb->num_sgs || urb->sg || @@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1))) return 0; - /* Allocate a buffer with enough padding for alignment */ + /* + * Allocate a buffer with enough padding for original transfer_buffer + * pointer. This allocation is guaranteed to be aligned properly for + * DMA + */ kmalloc_size = urb->transfer_buffer_length + - sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1; + sizeof(urb->transfer_buffer); kmalloc_ptr = kmalloc(kmalloc_size, mem_flags); if (!kmalloc_ptr) return -ENOMEM; - /* Position our struct dma_aligned_buffer such that data is aligned */ - temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1; - temp->kmalloc_ptr = kmalloc_ptr; - temp->old_xfer_buffer = urb->transfer_buffer; + /* + * Position value of original urb->transfer_buffer pointer to the end + * of allocation for later referencing + */ + memcpy(kmalloc_ptr + urb->transfer_buffer_length, + &urb->transfer_buffer, sizeof(urb->transfer_buffer)); + if (usb_urb_dir_out(urb)) - memcpy(temp->data, urb->transfer_buffer, + memcpy(kmalloc_ptr, urb->transfer_buffer, urb->transfer_buffer_length); - urb->transfer_buffer = temp->data; + urb->transfer_buffer = kmalloc_ptr; urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER; diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index ed7f05cf4906..8ce10caf3e19 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, * avoid interrupt storms we'll wait before retrying if we've got * several NAKs. If we didn't do this we'd retry directly from the * interrupt handler and could end up quickly getting another - * interrupt (another NAK), which we'd retry. + * interrupt (another NAK), which we'd retry. Note that we do not + * delay retries for IN parts of control requests, as those are expected + * to complete fairly quickly, and if we delay them we risk confusing + * the device and cause it issue STALL. * * Note that in DMA mode software only gets involved to re-send NAKed * transfers for split transactions, so we only need to apply this @@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, qtd->error_count = 0; qtd->complete_split = 0; qtd->num_naks++; - qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY; + qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY && + !(chan->ep_type == USB_ENDPOINT_XFER_CONTROL && + chan->ep_is_in); dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK); goto handle_nak_done; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index c77ff50a88a2..8efde178eef4 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, ret = dwc3_ep0_start_trans(dep); } else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) && req->request.length && req->request.zero) { - u32 maxpacket; ret = usb_gadget_map_request_by_dev(dwc->sysdev, &req->request, dep->number); if (ret) return; - maxpacket = dep->endpoint.maxpacket; - /* prepare normal TRB */ dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d2fa071c21b1..b8a15840b4ff 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1819,7 +1819,6 @@ unknown: if (cdev->use_os_string && cdev->os_desc_config && (ctrl->bRequestType & USB_TYPE_VENDOR) && ctrl->bRequest == cdev->b_vendor_code) { - struct usb_request *req; struct usb_configuration *os_desc_cfg; u8 *buf; int interface; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 33e2030503fa..3ada83d81bda 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3263,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return USB_GADGET_DELAYED_STATUS; + return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index d2dc1f00180b..d582921f7257 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = { }; struct cntrl_cur_lay3 { - __u32 dCUR; + __le32 dCUR; }; struct cntrl_range_lay3 { - __u16 wNumSubRanges; - __u32 dMIN; - __u32 dMAX; - __u32 dRES; + __le16 wNumSubRanges; + __le32 dMIN; + __le32 dMAX; + __le32 dRES; } __packed; static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts, @@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc); if (!agdev->out_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc); if (!agdev->in_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep_maxpsize = max_t(u16, @@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr) memset(&c, 0, sizeof(struct cntrl_cur_lay3)); if (entity_id == USB_IN_CLK_ID) - c.dCUR = p_srate; + c.dCUR = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - c.dCUR = c_srate; + c.dCUR = cpu_to_le32(c_srate); value = min_t(unsigned, w_length, sizeof c); memcpy(req->buf, &c, value); @@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr) if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) { if (entity_id == USB_IN_CLK_ID) - r.dMIN = p_srate; + r.dMIN = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - r.dMIN = c_srate; + r.dMIN = cpu_to_le32(c_srate); else return -EOPNOTSUPP; r.dMAX = r.dMIN; r.dRES = 0; - r.wNumSubRanges = 1; + r.wNumSubRanges = cpu_to_le16(1); value = min_t(unsigned, w_length, sizeof r); memcpy(req->buf, &r, value); diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index a72295c953bb..fb5ed97572e5 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -32,9 +32,6 @@ struct uac_req { struct uac_rtd_params { struct snd_uac_chip *uac; /* parent chip */ bool ep_enabled; /* if the ep is enabled */ - /* Size of the ring buffer */ - size_t dma_bytes; - unsigned char *dma_area; struct snd_pcm_substream *ss; @@ -43,8 +40,6 @@ struct uac_rtd_params { void *rbuf; - size_t period_size; - unsigned max_psize; /* MaxPacketSize of endpoint */ struct uac_req *ureq; @@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = { static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) { unsigned pending; - unsigned long flags; + unsigned long flags, flags2; unsigned int hw_ptr; - bool update_alsa = false; int status = req->status; struct uac_req *ur = req->context; struct snd_pcm_substream *substream; + struct snd_pcm_runtime *runtime; struct uac_rtd_params *prm = ur->pp; struct snd_uac_chip *uac = prm->uac; @@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) if (!substream) goto exit; + snd_pcm_stream_lock_irqsave(substream, flags2); + + runtime = substream->runtime; + if (!runtime || !snd_pcm_running(substream)) { + snd_pcm_stream_unlock_irqrestore(substream, flags2); + goto exit; + } + spin_lock_irqsave(&prm->lock, flags); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { @@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) req->actual = req->length; } - pending = prm->hw_ptr % prm->period_size; - pending += req->actual; - if (pending >= prm->period_size) - update_alsa = true; - hw_ptr = prm->hw_ptr; - prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes; spin_unlock_irqrestore(&prm->lock, flags); /* Pack USB load in ALSA ring buffer */ - pending = prm->dma_bytes - hw_ptr; + pending = runtime->dma_bytes - hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (unlikely(pending < req->actual)) { - memcpy(req->buf, prm->dma_area + hw_ptr, pending); - memcpy(req->buf + pending, prm->dma_area, + memcpy(req->buf, runtime->dma_area + hw_ptr, pending); + memcpy(req->buf + pending, runtime->dma_area, req->actual - pending); } else { - memcpy(req->buf, prm->dma_area + hw_ptr, req->actual); + memcpy(req->buf, runtime->dma_area + hw_ptr, + req->actual); } } else { if (unlikely(pending < req->actual)) { - memcpy(prm->dma_area + hw_ptr, req->buf, pending); - memcpy(prm->dma_area, req->buf + pending, + memcpy(runtime->dma_area + hw_ptr, req->buf, pending); + memcpy(runtime->dma_area, req->buf + pending, req->actual - pending); } else { - memcpy(prm->dma_area + hw_ptr, req->buf, req->actual); + memcpy(runtime->dma_area + hw_ptr, req->buf, + req->actual); } } + spin_lock_irqsave(&prm->lock, flags); + /* update hw_ptr after data is copied to memory */ + prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes; + hw_ptr = prm->hw_ptr; + spin_unlock_irqrestore(&prm->lock, flags); + snd_pcm_stream_unlock_irqrestore(substream, flags2); + + if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual) + snd_pcm_period_elapsed(substream); + exit: if (usb_ep_queue(ep, req, GFP_ATOMIC)) dev_err(uac->card->dev, "%d Error!\n", __LINE__); - - if (update_alsa) - snd_pcm_period_elapsed(substream); } static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd) @@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream) static int uac_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *hw_params) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - int err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - err = snd_pcm_lib_malloc_pages(substream, + return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params)); - if (err >= 0) { - prm->dma_bytes = substream->runtime->dma_bytes; - prm->dma_area = substream->runtime->dma_area; - prm->period_size = params_period_bytes(hw_params); - } - - return err; } static int uac_pcm_hw_free(struct snd_pcm_substream *substream) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - prm->dma_area = NULL; - prm->dma_bytes = 0; - prm->period_size = 0; - return snd_pcm_lib_free_pages(substream); } @@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, if (err < 0) goto snd_fail; - strcpy(pcm->name, pcm_name); + strlcpy(pcm->name, pcm_name, sizeof(pcm->name)); pcm->private_data = uac; uac->pcm = pcm; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops); - strcpy(card->driver, card_name); - strcpy(card->shortname, card_name); + strlcpy(card->driver, card_name, sizeof(card->driver)); + strlcpy(card->shortname, card_name, sizeof(card->shortname)); sprintf(card->longname, "%s %i", card_name, card->dev->id); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig index f0cdf89b8503..83ba8a2eb6af 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig +++ b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig @@ -2,6 +2,7 @@ config USB_ASPEED_VHUB tristate "Aspeed vHub UDC driver" depends on ARCH_ASPEED || COMPILE_TEST + depends on USB_LIBCOMPOSITE help USB peripheral controller for the Aspeed AST2500 family SoCs supporting the "vHub" functionality and USB2.0 diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c index 20ffb03ff6ac..e2927fb083cf 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c @@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep) /* Check our state, cancel pending requests if needed */ if (ep->ep0.state != ep0_state_token) { EPDBG(ep, "wrong state\n"); + ast_vhub_nuke(ep, -EIO); + + /* + * Accept the packet regardless, this seems to happen + * when stalling a SETUP packet that has an OUT data + * phase. + */ ast_vhub_nuke(ep, 0); goto stall; } @@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep, if (chunk && req->req.buf) memcpy(ep->buf, req->req.buf + req->req.actual, chunk); + vhub_dma_workaround(ep->buf); + /* Remember chunk size and trigger send */ reg = VHUB_EP0_SET_TX_LEN(chunk); writel(reg, ep->ep0.ctlstat); @@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep) EPVDBG(ep, "rx prime\n"); /* Prime endpoint for receiving data */ - writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL); + writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat); } static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 80c9feac5147..5939eb1e97f2 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req) if (!req->req.dma) { /* For IN transfers, copy data over first */ - if (ep->epn.is_in) + if (ep->epn.is_in) { memcpy(ep->buf, req->req.buf + act, chunk); + vhub_dma_workaround(ep->buf); + } writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE); - } else + } else { + if (ep->epn.is_in) + vhub_dma_workaround(req->req.buf); writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE); + } /* Start DMA */ req->active = true; @@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep) static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, struct ast_vhub_req *req) { + struct ast_vhub_desc *desc = NULL; unsigned int act = req->act_count; unsigned int len = req->req.length; unsigned int chunk; @@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, /* While we can create descriptors */ while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) { - struct ast_vhub_desc *desc; unsigned int d_num; /* Grab next free descriptor */ @@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, req->act_count = act = act + chunk; } + if (likely(desc)) + vhub_dma_workaround(desc); + /* Tell HW about new descriptors */ writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next), ep->epn.regs + AST_VHUB_EP_DESC_STATUS); diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h index 2b040257bc1f..4ed03d33a5a9 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h +++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h @@ -462,6 +462,39 @@ enum std_req_rc { #define DDBG(d, fmt, ...) do { } while(0) #endif +static inline void vhub_dma_workaround(void *addr) +{ + /* + * This works around a confirmed HW issue with the Aspeed chip. + * + * The core uses a different bus to memory than the AHB going to + * the USB device controller. Due to the latter having a higher + * priority than the core for arbitration on that bus, it's + * possible for an MMIO to the device, followed by a DMA by the + * device from memory to all be performed and services before + * a previous store to memory gets completed. + * + * This the following scenario can happen: + * + * - Driver writes to a DMA descriptor (Mbus) + * - Driver writes to the MMIO register to start the DMA (AHB) + * - The gadget sees the second write and sends a read of the + * descriptor to the memory controller (Mbus) + * - The gadget hits memory before the descriptor write + * causing it to read an obsolete value. + * + * Thankfully the problem is limited to the USB gadget device, other + * masters in the SoC all have a lower priority than the core, thus + * ensuring that the store by the core arrives first. + * + * The workaround consists of using a dummy read of the memory before + * doing the MMIO writes. This will ensure that the previous writes + * have been "pushed out". + */ + mb(); + (void)__raw_readl((void __iomem *)addr); +} + /* core.c */ void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req, int status); diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c index a3ecce62662b..11e25a3f4f1f 100644 --- a/drivers/usb/gadget/udc/r8a66597-udc.c +++ b/drivers/usb/gadget/udc/r8a66597-udc.c @@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597) r8a66597_bset(r8a66597, XCKE, SYSCFG0); - msleep(3); + mdelay(3); r8a66597_bset(r8a66597, PLLC, SYSCFG0); - msleep(1); + mdelay(1); r8a66597_bset(r8a66597, SCKE, SYSCFG0); @@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock) r8a66597->ep0_req->length = 2; /* AV: what happens if we get called again before that gets through? */ spin_unlock(&r8a66597->lock); - r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL); + r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC); spin_lock(&r8a66597->lock); } diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index 1fbfd89d0a0f..387f124a8334 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -508,16 +508,18 @@ static int xhci_do_dbc_start(struct xhci_hcd *xhci) return 0; } -static void xhci_do_dbc_stop(struct xhci_hcd *xhci) +static int xhci_do_dbc_stop(struct xhci_hcd *xhci) { struct xhci_dbc *dbc = xhci->dbc; if (dbc->state == DS_DISABLED) - return; + return -1; writel(0, &dbc->regs->control); xhci_dbc_mem_cleanup(xhci); dbc->state = DS_DISABLED; + + return 0; } static int xhci_dbc_start(struct xhci_hcd *xhci) @@ -544,6 +546,7 @@ static int xhci_dbc_start(struct xhci_hcd *xhci) static void xhci_dbc_stop(struct xhci_hcd *xhci) { + int ret; unsigned long flags; struct xhci_dbc *dbc = xhci->dbc; struct dbc_port *port = &dbc->port; @@ -556,10 +559,11 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci) xhci_dbc_tty_unregister_device(xhci); spin_lock_irqsave(&dbc->lock, flags); - xhci_do_dbc_stop(xhci); + ret = xhci_do_dbc_stop(xhci); spin_unlock_irqrestore(&dbc->lock, flags); - pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller); + if (!ret) + pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller); } static void diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 8a62eee9eee1..ef350c33dc4a 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -595,7 +595,7 @@ struct xhci_ring *xhci_stream_id_to_ring( if (!ep->stream_info) return NULL; - if (stream_id > ep->stream_info->num_streams) + if (stream_id >= ep->stream_info->num_streams) return NULL; return ep->stream_info->stream_rings[stream_id]; } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2f4850f25e82..68e6132aa8b2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3051,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd, if (!list_empty(&ep->ring->td_list)) { dev_err(&udev->dev, "EP not empty, refuse reset\n"); spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, cfg_cmd); goto cleanup; } xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0); diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 8abb6cbbd98a..3be40eaa1ac9 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -396,8 +396,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct usb_yurex *dev; - int retval = 0; - int bytes_read = 0; + int len = 0; char in_buffer[20]; unsigned long flags; @@ -405,26 +404,16 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count, mutex_lock(&dev->io_mutex); if (!dev->interface) { /* already disconnected */ - retval = -ENODEV; - goto exit; + mutex_unlock(&dev->io_mutex); + return -ENODEV; } spin_lock_irqsave(&dev->lock, flags); - bytes_read = snprintf(in_buffer, 20, "%lld\n", dev->bbu); + len = snprintf(in_buffer, 20, "%lld\n", dev->bbu); spin_unlock_irqrestore(&dev->lock, flags); - - if (*ppos < bytes_read) { - if (copy_to_user(buffer, in_buffer + *ppos, bytes_read - *ppos)) - retval = -EFAULT; - else { - retval = bytes_read - *ppos; - *ppos += bytes_read; - } - } - -exit: mutex_unlock(&dev->io_mutex); - return retval; + + return simple_read_from_buffer(buffer, count, ppos, in_buffer, len); } static ssize_t yurex_write(struct file *file, const char __user *user_buffer, diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 900875f326d7..f7c96d209eda 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev) if (pdata->init && pdata->init(pdev) != 0) return -EINVAL; +#ifdef CONFIG_PPC32 if (pdata->big_endian_mmio) { _fsl_readl = _fsl_readl_be; _fsl_writel = _fsl_writel_be; @@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev) _fsl_readl = _fsl_readl_le; _fsl_writel = _fsl_writel_le; } +#endif /* request irq */ p_otg->irq = platform_get_irq(pdev, 0); @@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev) /* * state file in sysfs */ -static int show_fsl_usb2_otg_state(struct device *dev, +static ssize_t show_fsl_usb2_otg_state(struct device *dev, struct device_attribute *attr, char *buf) { struct otg_fsm *fsm = &fsl_otg_dev->fsm; diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index bdd7a5ad3bf1..3bb1fff02bed 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -128,7 +128,7 @@ static int ch341_control_in(struct usb_device *dev, r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, value, index, buf, bufsize, DEFAULT_TIMEOUT); - if (r < bufsize) { + if (r < (int)bufsize) { if (r >= 0) { dev_err(&dev->dev, "short control message received (%d < %u)\n", diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index ee0cc1d90b51..626a29d9aa58 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -149,6 +149,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */ { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */ { USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */ + { USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */ { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */ { USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */ { USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */ diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c index 5169624d8b11..38d43c4b7ce5 100644 --- a/drivers/usb/serial/keyspan_pda.c +++ b/drivers/usb/serial/keyspan_pda.c @@ -369,8 +369,10 @@ static int keyspan_pda_get_modem_info(struct usb_serial *serial, 3, /* get pins */ USB_TYPE_VENDOR|USB_RECIP_INTERFACE|USB_DIR_IN, 0, 0, data, 1, 2000); - if (rc >= 0) + if (rc == 1) *value = *data; + else if (rc >= 0) + rc = -EIO; kfree(data); return rc; diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index fdceb46d9fc6..b580b4c7fa48 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -468,6 +468,9 @@ static void mos7840_control_callback(struct urb *urb) } dev_dbg(dev, "%s urb buffer size is %d\n", __func__, urb->actual_length); + if (urb->actual_length < 1) + goto out; + dev_dbg(dev, "%s mos7840_port->MsrLsr is %d port %d\n", __func__, mos7840_port->MsrLsr, mos7840_port->port_num); data = urb->transfer_buffer; diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index d961f1ec0e08..d1d20252bad8 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -725,6 +725,9 @@ static int tcpm_set_current_limit(struct tcpm_port *port, u32 max_ma, u32 mv) tcpm_log(port, "Setting voltage/current limit %u mV %u mA", mv, max_ma); + port->supply_voltage = mv; + port->current_limit = max_ma; + if (port->tcpc->set_current_limit) ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv); @@ -2137,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) * PPS APDO. Again skip the first sink PDO as this will * always be 5V 3A. */ - for (j = i; j < port->nr_snk_pdo; j++) { + for (j = 1; j < port->nr_snk_pdo; j++) { pdo = port->snk_pdo[j]; switch (pdo_type(pdo)) { @@ -2595,8 +2598,6 @@ static void tcpm_reset_port(struct tcpm_port *port) tcpm_set_attached_state(port, false); port->try_src_count = 0; port->try_snk_count = 0; - port->supply_voltage = 0; - port->current_limit = 0; port->usb_type = POWER_SUPPLY_USB_TYPE_C; power_supply_changed(port->psy); diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index 24ee2605b9f0..42dc1d3d71cf 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -28,5 +28,13 @@ config VFIO_PCI_INTX def_bool y if !S390 config VFIO_PCI_IGD - depends on VFIO_PCI - def_bool y if X86 + bool "VFIO PCI extensions for Intel graphics (GVT-d)" + depends on VFIO_PCI && X86 + default y + help + Support for Intel IGD specific extensions to enable direct + assignment to virtual machines. This includes exposing an IGD + specific firmware table and read-only copies of the host bridge + and LPC bridge config space. + + To enable Intel IGD assignment through vfio-pci, say Y. diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index b423a309a6e0..125b58eff936 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -28,6 +28,7 @@ #include <linux/uaccess.h> #include <linux/vfio.h> #include <linux/vgaarb.h> +#include <linux/nospec.h> #include "vfio_pci_private.h" @@ -727,6 +728,9 @@ static long vfio_pci_ioctl(void *device_data, if (info.index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) return -EINVAL; + info.index = array_index_nospec(info.index, + VFIO_PCI_NUM_REGIONS + + vdev->num_regions); i = info.index - VFIO_PCI_NUM_REGIONS; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 759a5bdd40e1..7cd63b0c1a46 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container, } static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container, - unsigned long tce, unsigned long size, + unsigned long tce, unsigned long shift, unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem) { long ret = 0; struct mm_iommu_table_group_mem_t *mem; - mem = mm_iommu_lookup(container->mm, tce, size); + mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift); if (!mem) return -EINVAL; - ret = mm_iommu_ua_to_hpa(mem, tce, phpa); + ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa); if (ret) return -EINVAL; @@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container, if (!pua) return; - ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl), + ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift, &hpa, &mem); if (ret) pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n", @@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container, entry + i); ret = tce_iommu_prereg_ua_to_hpa(container, - tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem); + tce, tbl->it_page_shift, &hpa, &mem); if (ret) break; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 2c75b33db4ac..3e5b17710a4f 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -343,18 +343,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, struct page *page[1]; struct vm_area_struct *vma; struct vm_area_struct *vmas[1]; + unsigned int flags = 0; int ret; + if (prot & IOMMU_WRITE) + flags |= FOLL_WRITE; + + down_read(&mm->mmap_sem); if (mm == current->mm) { - ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE), - page, vmas); + ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas); } else { - unsigned int flags = 0; - - if (prot & IOMMU_WRITE) - flags |= FOLL_WRITE; - - down_read(&mm->mmap_sem); ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page, vmas, NULL); /* @@ -368,8 +366,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, ret = -EOPNOTSUPP; put_page(page[0]); } - up_read(&mm->mmap_sem); } + up_read(&mm->mmap_sem); if (ret == 1) { *pfn = page_to_pfn(page[0]); @@ -1896,6 +1896,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, return ret; } +struct __aio_sigset { + const sigset_t __user *sigmask; + size_t sigsetsize; +}; + SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/autofs/Makefile b/fs/autofs/Makefile index 43fedde15c26..1f85d35ec8b7 100644 --- a/fs/autofs/Makefile +++ b/fs/autofs/Makefile @@ -2,6 +2,6 @@ # Makefile for the linux autofs-filesystem routines. # -obj-$(CONFIG_AUTOFS_FS) += autofs.o +obj-$(CONFIG_AUTOFS_FS) += autofs4.o -autofs-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o +autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index ea4ca1445ab7..86eafda4a652 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -135,6 +135,15 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) cmd); goto out; } + } else { + unsigned int inr = _IOC_NR(cmd); + + if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD || + inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD || + inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) { + err = -EINVAL; + goto out; + } } err = 0; @@ -271,7 +280,8 @@ static int autofs_dev_ioctl_openmount(struct file *fp, dev_t devid; int err, fd; - /* param->path has already been checked */ + /* param->path has been checked in validate_dev_ioctl() */ + if (!param->openmount.devid) return -EINVAL; @@ -433,10 +443,7 @@ static int autofs_dev_ioctl_requester(struct file *fp, dev_t devid; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ devid = sbi->sb->s_dev; @@ -521,10 +528,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp, unsigned int devid, magic; int err = -ENOENT; - if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { - err = -EINVAL; - goto out; - } + /* param->path has been checked in validate_dev_ioctl() */ name = param->path; type = param->ismountpoint.in.type; diff --git a/fs/autofs/init.c b/fs/autofs/init.c index cc9447e1903f..79ae07d9592f 100644 --- a/fs/autofs/init.c +++ b/fs/autofs/init.c @@ -23,7 +23,7 @@ static struct file_system_type autofs_fs_type = { .kill_sb = autofs_kill_sb, }; MODULE_ALIAS_FS("autofs"); -MODULE_ALIAS("autofs4"); +MODULE_ALIAS("autofs"); static int __init init_autofs_fs(void) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0ac456b52bdd..816cc921cf36 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1259,9 +1259,8 @@ static int load_elf_library(struct file *file) goto out_free_ph; } - len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr + - ELF_MIN_ALIGN - 1); - bss = eppnt->p_memsz + eppnt->p_vaddr; + len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr); + bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr); if (bss > len) { error = vm_brk(len, bss - len); if (error) diff --git a/fs/block_dev.c b/fs/block_dev.c index 0dd87aaeb39a..aba25414231a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) - return ret; + goto out; ret = bio.bi_iter.bi_size; if (iov_iter_rw(iter) == READ) { @@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, put_page(bvec->bv_page); } - if (vecs != inline_vecs) - kfree(vecs); - if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); +out: + if (vecs != inline_vecs) + kfree(vecs); + bio_uninit(&bio); return ret; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e55843f536bc..b3e45714d28f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4238,8 +4238,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) struct extent_map *em; u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; - struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree; + struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &btrfs_inode->io_tree; + struct extent_map_tree *map = &btrfs_inode->extent_tree; if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > SZ_16M) { @@ -4262,6 +4263,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) extent_map_end(em) - 1, EXTENT_LOCKED | EXTENT_WRITEBACK, 0, NULL)) { + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &btrfs_inode->runtime_flags); remove_extent_mapping(map, em); /* once for the rb tree */ free_extent_map(em); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 43ecbe620dea..b077544b5232 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3327,11 +3327,13 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) if (pg) { unlock_page(pg); put_page(pg); + cmp->src_pages[i] = NULL; } pg = cmp->dst_pages[i]; if (pg) { unlock_page(pg); put_page(pg); + cmp->dst_pages[i] = NULL; } } } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 572306036477..6702896cdb8f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1151,11 +1151,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) return ret; } - if (sctx->is_dev_replace && !is_metadata && !have_csum) { - sblocks_for_recheck = NULL; - goto nodatasum_case; - } - /* * read all mirrors one after the other. This includes to * re-read the extent or metadata block that failed (that was @@ -1268,13 +1263,19 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) goto out; } - if (!is_metadata && !have_csum) { + /* + * NOTE: Even for nodatasum case, it's still possible that it's a + * compressed data extent, thus scrub_fixup_nodatasum(), which write + * inode page cache onto disk, could cause serious data corruption. + * + * So here we could only read from disk, and hope our recovery could + * reach disk before the newer write. + */ + if (0 && !is_metadata && !have_csum) { struct scrub_fixup_nodatasum *fixup_nodatasum; WARN_ON(sctx->is_dev_replace); -nodatasum_case: - /* * !is_metadata and !have_csum, this means that the data * might not be COWed, that it might be modified diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e034ad9e23b4..1da162928d1a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1146,6 +1146,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, { int ret; + mutex_lock(&uuid_mutex); mutex_lock(&fs_devices->device_list_mutex); if (fs_devices->opened) { fs_devices->opened++; @@ -1155,6 +1156,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, ret = open_fs_devices(fs_devices, flags, holder); } mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&uuid_mutex); return ret; } diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index d9f001078e08..4a717d400807 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) "%s", fsdef->dentry->d_sb->s_id); - fscache_object_init(&fsdef->fscache, NULL, &cache->cache); + fscache_object_init(&fsdef->fscache, &fscache_fsdef_index, + &cache->cache); ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag); if (ret < 0) diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab0bbe93b398..af2b17b21b94 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -186,12 +186,12 @@ try_again: * need to wait for it to be destroyed */ wait_for_old_object: trace_cachefiles_wait_active(object, dentry, xobject); + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); if (fscache_object_is_live(&xobject->fscache)) { pr_err("\n"); pr_err("Error: Unexpected object collision\n"); cachefiles_printk_object(object, xobject); - BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); @@ -248,7 +248,6 @@ wait_for_old_object: goto try_again; requeue: - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 5082c8a49686..40f7595aad10 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_one_read *monitor = container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; + struct fscache_retrieval *op = monitor->op; struct wait_bit_key *key = _key; struct page *page = wait->private; @@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ - ASSERT(monitor->op); + ASSERT(op); - object = container_of(monitor->op->op.object, - struct cachefiles_object, fscache); + /* We need to temporarily bump the usage count as we don't own a ref + * here otherwise cachefiles_read_copier() may free the op between the + * monitor being enqueued on the op->to_do list and the op getting + * enqueued on the work queue. + */ + fscache_get_retrieval(op); + object = container_of(op->op.object, struct cachefiles_object, fscache); spin_lock(&object->work_lock); - list_add_tail(&monitor->op_link, &monitor->op->to_do); + list_add_tail(&monitor->op_link, &op->to_do); spin_unlock(&object->work_lock); - fscache_enqueue_retrieval(monitor->op); + fscache_enqueue_retrieval(op); + fscache_put_retrieval(op); return 0; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index bd78da59a4fd..c923c7854027 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -423,7 +423,7 @@ struct smb_version_operations { void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int, bool *); /* create lease context buffer for CREATE request */ - char * (*create_lease_buf)(u8 *, u8); + char * (*create_lease_buf)(u8 *lease_key, u8 oplock); /* parse lease context buffer and return oplock/epoch info */ __u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey); ssize_t (*copychunk_range)(const unsigned int, @@ -1416,6 +1416,7 @@ typedef int (mid_handle_t)(struct TCP_Server_Info *server, /* one of these for every pending CIFS request to the server */ struct mid_q_entry { struct list_head qhead; /* mids waiting on reply from this server */ + struct kref refcount; struct TCP_Server_Info *server; /* server corresponding to this mid */ __u64 mid; /* multiplex id */ __u32 pid; /* process id */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 03018be17283..1890f534c88b 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -82,6 +82,7 @@ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server); extern void DeleteMidQEntry(struct mid_q_entry *midEntry); extern void cifs_delete_mid(struct mid_q_entry *mid); +extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry); extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index d352da325de3..93408eab92e7 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -157,8 +157,14 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * greater than cifs socket timeout which is 7 seconds */ while (server->tcpStatus == CifsNeedReconnect) { - wait_event_interruptible_timeout(server->response_q, - (server->tcpStatus != CifsNeedReconnect), 10 * HZ); + rc = wait_event_interruptible_timeout(server->response_q, + (server->tcpStatus != CifsNeedReconnect), + 10 * HZ); + if (rc < 0) { + cifs_dbg(FYI, "%s: aborting reconnect due to a received" + " signal by the process\n", __func__); + return -ERESTARTSYS; + } /* are we still trying to reconnect? */ if (server->tcpStatus != CifsNeedReconnect) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a57da1b88bdf..5df2c0698cda 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -924,6 +924,7 @@ next_pdu: server->pdu_size = next_offset; } + mid_entry = NULL; if (server->ops->is_transform_hdr && server->ops->receive_transform && server->ops->is_transform_hdr(buf)) { @@ -938,8 +939,11 @@ next_pdu: length = mid_entry->receive(server, mid_entry); } - if (length < 0) + if (length < 0) { + if (mid_entry) + cifs_mid_q_entry_release(mid_entry); continue; + } if (server->large_buf) buf = server->bigbuf; @@ -956,6 +960,8 @@ next_pdu: if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); + + cifs_mid_q_entry_release(mid_entry); } else if (server->ops->is_oplock_break && server->ops->is_oplock_break(buf, server)) { cifs_dbg(FYI, "Received oplock break\n"); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index aff8ce8ba34d..646dcd149de1 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -107,6 +107,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer) if (compare_mid(mid->mid, buf) && mid->mid_state == MID_REQUEST_SUBMITTED && le16_to_cpu(mid->command) == buf->Command) { + kref_get(&mid->refcount); spin_unlock(&GlobalMid_Lock); return mid; } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 788412675723..4ed10dd086e6 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -41,7 +41,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, int rc; __le16 *smb2_path; struct smb2_file_all_info *smb2_data = NULL; - __u8 smb2_oplock[17]; + __u8 smb2_oplock; struct cifs_fid *fid = oparms->fid; struct network_resiliency_req nr_ioctl_req; @@ -59,12 +59,9 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, } oparms->desired_access |= FILE_READ_ATTRIBUTES; - *smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; + smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; - if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) - memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE); - - rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL, + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, NULL); if (rc) goto out; @@ -101,7 +98,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, move_smb2_info_to_cifs(buf, smb2_data); } - *oplock = *smb2_oplock; + *oplock = smb2_oplock; out: kfree(smb2_data); kfree(smb2_path); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0356b5559c71..ea92a38b2f08 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -203,6 +203,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) if ((mid->mid == wire_mid) && (mid->mid_state == MID_REQUEST_SUBMITTED) && (mid->command == shdr->Command)) { + kref_get(&mid->refcount); spin_unlock(&GlobalMid_Lock); return mid; } @@ -855,6 +856,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea, len); + kfree(ea); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); return rc; @@ -2219,8 +2222,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock) if (!buf) return NULL; - buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key)); - buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8))); + memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseState = map_oplock_to_lease(oplock); buf->ccontext.DataOffset = cpu_to_le16(offsetof @@ -2246,8 +2248,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock) if (!buf) return NULL; - buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key)); - buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8))); + memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseState = map_oplock_to_lease(oplock); buf->ccontext.DataOffset = cpu_to_le16(offsetof @@ -2284,8 +2285,7 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS) return SMB2_OPLOCK_LEVEL_NOCHANGE; if (lease_key) - memcpy(lease_key, &lc->lcontext.LeaseKeyLow, - SMB2_LEASE_KEY_SIZE); + memcpy(lease_key, &lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); return le32_to_cpu(lc->lcontext.LeaseState); } @@ -2521,7 +2521,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, if (!tr_hdr) goto err_free_iov; - orig_len = smb2_rqst_len(old_rq, false); + orig_len = smb_rqst_len(server, old_rq); /* fill the 2nd iov with a transform header */ fill_transform_hdr(tr_hdr, orig_len, old_rq); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 810b85787c91..3c92678cb45b 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -155,7 +155,7 @@ out: static int smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) { - int rc = 0; + int rc; struct nls_table *nls_codepage; struct cifs_ses *ses; struct TCP_Server_Info *server; @@ -166,10 +166,10 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) * for those three - in the calling routine. */ if (tcon == NULL) - return rc; + return 0; if (smb2_command == SMB2_TREE_CONNECT) - return rc; + return 0; if (tcon->tidStatus == CifsExiting) { /* @@ -212,8 +212,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) return -EAGAIN; } - wait_event_interruptible_timeout(server->response_q, - (server->tcpStatus != CifsNeedReconnect), 10 * HZ); + rc = wait_event_interruptible_timeout(server->response_q, + (server->tcpStatus != CifsNeedReconnect), + 10 * HZ); + if (rc < 0) { + cifs_dbg(FYI, "%s: aborting reconnect due to a received" + " signal by the process\n", __func__); + return -ERESTARTSYS; + } /* are we still trying to reconnect? */ if (server->tcpStatus != CifsNeedReconnect) @@ -231,7 +237,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) } if (!tcon->ses->need_reconnect && !tcon->need_reconnect) - return rc; + return 0; nls_codepage = load_nls_default(); @@ -340,7 +346,10 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, return rc; /* BB eventually switch this to SMB2 specific small buf size */ - *request_buf = cifs_small_buf_get(); + if (smb2_command == SMB2_SET_INFO) + *request_buf = cifs_buf_get(); + else + *request_buf = cifs_small_buf_get(); if (*request_buf == NULL) { /* BB should we add a retry in here if not a writepage? */ return -ENOMEM; @@ -1707,12 +1716,12 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, static int add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, - unsigned int *num_iovec, __u8 *oplock) + unsigned int *num_iovec, u8 *lease_key, __u8 *oplock) { struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; - iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock); + iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = server->vals->create_lease_size; @@ -2172,7 +2181,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; else { - rc = add_lease_context(server, iov, &n_iov, oplock); + rc = add_lease_context(server, iov, &n_iov, + oparms->fid->lease_key, oplock); if (rc) { cifs_small_buf_release(req); kfree(copy_path); @@ -3720,7 +3730,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); + cifs_buf_release(req); rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base; if (rc != 0) { diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 824dddeee3f2..a671adcc44a6 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -678,16 +678,14 @@ struct create_context { #define SMB2_LEASE_KEY_SIZE 16 struct lease_context { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; } __packed; struct lease_context_v2 { - __le64 LeaseKeyLow; - __le64 LeaseKeyHigh; + u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; __le32 LeaseFlags; __le64 LeaseDuration; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3ae208ac2a77..6e6a4f2ec890 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -113,8 +113,8 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile, extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); extern void smb2_reconnect_server(struct work_struct *work); extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server); -extern unsigned long -smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker); +extern unsigned long smb_rqst_len(struct TCP_Server_Info *server, + struct smb_rqst *rqst); /* * SMB2 Worker functions - most of protocol specific implementation details diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 51b9437c3c7b..719d55e63d88 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -173,6 +173,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) struct kvec *iov = rqst->rq_iov; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; + struct shash_desc *shash = &server->secmech.sdeschmacsha256->shash; + struct smb_rqst drqst; ses = smb2_find_smb_ses(server, shdr->SessionId); if (!ses) { @@ -190,21 +192,39 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) } rc = crypto_shash_setkey(server->secmech.hmacsha256, - ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); + ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE); if (rc) { cifs_dbg(VFS, "%s: Could not update with response\n", __func__); return rc; } - rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash); + rc = crypto_shash_init(shash); if (rc) { cifs_dbg(VFS, "%s: Could not init sha256", __func__); return rc; } - rc = __cifs_calc_signature(rqst, server, sigptr, - &server->secmech.sdeschmacsha256->shash); + /* + * For SMB2+, __cifs_calc_signature() expects to sign only the actual + * data, that is, iov[0] should not contain a rfc1002 length. + * + * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to + * __cifs_calc_signature(). + */ + drqst = *rqst; + if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) { + rc = crypto_shash_update(shash, iov[0].iov_base, + iov[0].iov_len); + if (rc) { + cifs_dbg(VFS, "%s: Could not update with payload\n", + __func__); + return rc; + } + drqst.rq_iov++; + drqst.rq_nvec--; + } + rc = __cifs_calc_signature(&drqst, server, sigptr, shash); if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); @@ -408,12 +428,14 @@ generate_smb311signingkey(struct cifs_ses *ses) int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int rc = 0; + int rc; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base; struct cifs_ses *ses; + struct shash_desc *shash = &server->secmech.sdesccmacaes->shash; + struct smb_rqst drqst; ses = smb2_find_smb_ses(server, shdr->SessionId); if (!ses) { @@ -425,8 +447,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE); rc = crypto_shash_setkey(server->secmech.cmacaes, - ses->smb3signingkey, SMB2_CMACAES_SIZE); - + ses->smb3signingkey, SMB2_CMACAES_SIZE); if (rc) { cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__); return rc; @@ -437,15 +458,33 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) * so unlike smb2 case we do not have to check here if secmech are * initialized */ - rc = crypto_shash_init(&server->secmech.sdesccmacaes->shash); + rc = crypto_shash_init(shash); if (rc) { cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__); return rc; } - rc = __cifs_calc_signature(rqst, server, sigptr, - &server->secmech.sdesccmacaes->shash); + /* + * For SMB2+, __cifs_calc_signature() expects to sign only the actual + * data, that is, iov[0] should not contain a rfc1002 length. + * + * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to + * __cifs_calc_signature(). + */ + drqst = *rqst; + if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) { + rc = crypto_shash_update(shash, iov[0].iov_base, + iov[0].iov_len); + if (rc) { + cifs_dbg(VFS, "%s: Could not update with payload\n", + __func__); + return rc; + } + drqst.rq_iov++; + drqst.rq_nvec--; + } + rc = __cifs_calc_signature(&drqst, server, sigptr, shash); if (!rc) memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE); @@ -548,6 +587,7 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr, temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); + kref_init(&temp->refcount); temp->mid = le64_to_cpu(shdr->MessageId); temp->pid = current->pid; temp->command = shdr->Command; /* Always LE */ diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 6fd94d9ffac2..c55ea4e6201b 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2083,8 +2083,9 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) * rqst: the data to write * return value: 0 if successfully write, otherwise error code */ -int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) +int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) { + struct smbd_connection *info = server->smbd_conn; struct kvec vec; int nvecs; int size; @@ -2118,7 +2119,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and * ends at page boundary */ - buflen = smb2_rqst_len(rqst, true); + buflen = smb_rqst_len(server, rqst); if (buflen + sizeof(struct smbd_data_transfer) > info->max_fragmented_send_size) { diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index 1e419c21dc60..a11096254f29 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -292,7 +292,7 @@ void smbd_destroy(struct smbd_connection *info); /* Interface for carrying upper layer I/O through send/recv */ int smbd_recv(struct smbd_connection *info, struct msghdr *msg); -int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst); +int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst); enum mr_state { MR_READY, @@ -332,7 +332,7 @@ static inline void *smbd_get_connection( static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; } static inline void smbd_destroy(struct smbd_connection *info) {} static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; } -static inline int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) {return -1; } +static inline int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) {return -1; } #endif #endif diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index fb57dfbfb749..a341ec839c83 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -61,6 +61,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); + kref_init(&temp->refcount); temp->mid = get_mid(smb_buffer); temp->pid = current->pid; temp->command = cpu_to_le16(smb_buffer->Command); @@ -82,6 +83,21 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) return temp; } +static void _cifs_mid_q_entry_release(struct kref *refcount) +{ + struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry, + refcount); + + mempool_free(mid, cifs_mid_poolp); +} + +void cifs_mid_q_entry_release(struct mid_q_entry *midEntry) +{ + spin_lock(&GlobalMid_Lock); + kref_put(&midEntry->refcount, _cifs_mid_q_entry_release); + spin_unlock(&GlobalMid_Lock); +} + void DeleteMidQEntry(struct mid_q_entry *midEntry) { @@ -110,7 +126,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) } } #endif - mempool_free(midEntry, cifs_mid_poolp); + cifs_mid_q_entry_release(midEntry); } void @@ -202,14 +218,15 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, } unsigned long -smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker) +smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst) { unsigned int i; struct kvec *iov; int nvec; unsigned long buflen = 0; - if (skip_rfc1002_marker && rqst->rq_iov[0].iov_len == 4) { + if (server->vals->header_preamble_size == 0 && + rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) { iov = &rqst->rq_iov[1]; nvec = rqst->rq_nvec - 1; } else { @@ -260,7 +277,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, __be32 rfc1002_marker; if (cifs_rdma_enabled(server) && server->smbd_conn) { - rc = smbd_send(server->smbd_conn, rqst); + rc = smbd_send(server, rqst); goto smbd_done; } if (ssocket == NULL) @@ -271,7 +288,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, (char *)&val, sizeof(val)); for (j = 0; j < num_rqst; j++) - send_length += smb2_rqst_len(&rqst[j], true); + send_length += smb_rqst_len(server, &rqst[j]); rfc1002_marker = cpu_to_be32(send_length); /* Generate a rfc1002 marker for SMB2+ */ diff --git a/fs/exec.c b/fs/exec.c index 2d4e0075bd24..bdd0eacefdf5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -290,15 +290,15 @@ static int __bprm_mm_init(struct linux_binprm *bprm) struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; - bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; + vma_set_anonymous(vma); if (down_write_killable(&mm->mmap_sem)) { err = -EINTR; goto err_free; } - vma->vm_mm = mm; /* * Place the stack at the largest stack address the architecture @@ -311,7 +311,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) @@ -326,7 +325,7 @@ err: up_write(&mm->mmap_sem); err_free: bprm->vma = NULL; - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return err; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index b00481c475cb..aa52d87985aa 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -184,7 +184,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, unsigned int bit, bit_max; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; - int flex_bg = 0; J_ASSERT_BH(bh, buffer_locked(bh)); @@ -207,22 +206,19 @@ static int ext4_init_block_bitmap(struct super_block *sb, start = ext4_group_first_block_no(sb, block_group); - if (ext4_has_feature_flex_bg(sb)) - flex_bg = 1; - /* Set bits for block and inode bitmaps, and inode table */ tmp = ext4_block_bitmap(sb, gdp); - if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_bitmap(sb, gdp); - if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_table(sb, gdp); for (; tmp < ext4_inode_table(sb, gdp) + sbi->s_itb_per_group; tmp++) { - if (!flex_bg || ext4_block_in_group(sb, tmp, block_group)) + if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); } @@ -372,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); @@ -390,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } @@ -442,7 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) goto verify; } ext4_lock_group(sb, block_group); - if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + if (ext4_has_group_desc_csum(sb) && + (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { + if (block_group == 0) { + ext4_unlock_group(sb, block_group); + unlock_buffer(bh); + ext4_error(sb, "Block bitmap for bg 0 marked " + "uninitialized"); + err = -EFSCORRUPTED; + goto out; + } err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0b127853c584..7c7123f265c2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1114,6 +1114,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */ #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ +#define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ @@ -1507,11 +1508,6 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || - ino == EXT4_USR_QUOTA_INO || - ino == EXT4_GRP_QUOTA_INO || - ino == EXT4_BOOT_LOADER_INO || - ino == EXT4_JOURNAL_INO || - ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } @@ -3018,9 +3014,6 @@ extern int ext4_inline_data_fiemap(struct inode *inode, struct iomap; extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap); -extern int ext4_try_to_evict_inline_data(handle_t *handle, - struct inode *inode, - int needed); extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline); extern int ext4_convert_inline_data(struct inode *inode); diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 98fb0c119c68..adf6668b596f 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -91,6 +91,7 @@ struct ext4_extent_header { }; #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) +#define EXT4_MAX_EXTENT_DEPTH 5 #define EXT4_EXTENT_TAIL_OFFSET(hdr) \ (sizeof(struct ext4_extent_header) + \ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0057fe3f248d..8ce6fd5b10dd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -869,6 +869,12 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, eh = ext_inode_hdr(inode); depth = ext_depth(inode); + if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) { + EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d", + depth); + ret = -EFSCORRUPTED; + goto err; + } if (path) { ext4_ext_drop_refs(path); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f525f909b559..f336cbc6e932 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8)) { @@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSBADCRC; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } @@ -150,7 +153,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); - if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { + if (ext4_has_group_desc_csum(sb) && + (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { + if (block_group == 0) { + ext4_unlock_group(sb, block_group); + unlock_buffer(bh); + ext4_error(sb, "Inode bitmap for bg 0 marked " + "uninitialized"); + err = -EFSCORRUPTED; + goto out; + } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); @@ -994,7 +1006,8 @@ got: /* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); @@ -1375,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || + ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)) < + EXT4_FIRST_INO(sb)))) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 285ed1588730..3543fe80a3c4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -437,6 +437,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, memset((void *)ext4_raw_inode(&is.iloc)->i_block, 0, EXT4_MIN_INLINE_DATA_SIZE); + memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE); if (ext4_has_feature_extents(inode->i_sb)) { if (S_ISDIR(inode->i_mode) || @@ -681,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto convert; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out; + flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); @@ -709,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: - if (handle) + if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; @@ -751,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); + mark_inode_dirty(inode); out: return copied; } @@ -886,18 +892,17 @@ retry_journal: flags |= AOP_FLAG_NOFS; if (ret == -ENOSPC) { + ext4_journal_stop(handle); ret = ext4_da_convert_inline_data_to_extent(mapping, inode, flags, fsdata); - ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; @@ -915,6 +920,9 @@ retry_journal: if (ret < 0) goto out_release_page; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; @@ -935,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int i_size_changed = 0; int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -953,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { + if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); - i_size_changed = 1; - } unlock_page(page); put_page(page); @@ -966,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) - mark_inode_dirty(inode); + mark_inode_dirty(inode); return copied; } @@ -1890,42 +1894,6 @@ out: return (error < 0 ? error : 0); } -/* - * Called during xattr set, and if we can sparse space 'needed', - * just create the extent tree evict the data to the outer block. - * - * We use jbd2 instead of page cache to move data to the 1st block - * so that the whole transaction can be committed as a whole and - * the data isn't lost because of the delayed page cache write. - */ -int ext4_try_to_evict_inline_data(handle_t *handle, - struct inode *inode, - int needed) -{ - int error; - struct ext4_xattr_entry *entry; - struct ext4_inode *raw_inode; - struct ext4_iloc iloc; - - error = ext4_get_inode_loc(inode, &iloc); - if (error) - return error; - - raw_inode = ext4_raw_inode(&iloc); - entry = (struct ext4_xattr_entry *)((void *)raw_inode + - EXT4_I(inode)->i_inline_off); - if (EXT4_XATTR_LEN(entry->e_name_len) + - EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) { - error = -ENOSPC; - goto out; - } - - error = ext4_convert_inline_data_nolock(handle, inode, &iloc); -out: - brelse(iloc.bh); - return error; -} - int ext4_inline_data_truncate(struct inode *inode, int *has_inline) { handle_t *handle; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2ea07efbe016..4efe77286ecd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -402,9 +402,9 @@ static int __check_block_validity(struct inode *inode, const char *func, if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, - "lblock %lu mapped to illegal pblock " + "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, - map->m_len); + map->m_pblk, map->m_len); return -EFSCORRUPTED; } return 0; @@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) + if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) @@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); - if (size_changed) { + if (size_changed || inline_data) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page, } if (inline_data) { - BUFFER_TRACE(inode_bh, "get write access"); - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - + ret = ext4_mark_inode_dirty(handle, inode); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); @@ -4506,7 +4504,8 @@ static int __ext4_get_inode_loc(struct inode *inode, int inodes_per_block, inode_offset; iloc->bh = NULL; - if (!ext4_valid_inum(sb, inode->i_ino)) + if (inode->i_ino < EXT4_ROOT_INO || + inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) return -EFSCORRUPTED; iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 6eae2b91aafa..f7ab34088162 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2423,7 +2423,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, * initialize bb_free to be able to skip * empty groups without initialization */ - if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + if (ext4_has_group_desc_csum(sb) && + (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { @@ -2989,7 +2990,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, #endif ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 27b9a76a0dfa..638ad4743477 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -186,11 +186,8 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb_rdonly(sb)) { - ext4_warning(sb, "kmmpd being stopped since filesystem " - "has been remounted as readonly."); - goto exit_thread; - } + if (sb_rdonly(sb)) + break; diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0c4c2201b3aa..b7f7922061be 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -405,6 +405,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) static void ext4_handle_error(struct super_block *sb) { + if (test_opt(sb, WARN_ON_ERROR)) + WARN_ON_ONCE(1); + if (sb_rdonly(sb)) return; @@ -740,6 +743,9 @@ __acquires(bitlock) va_end(args); } + if (test_opt(sb, WARN_ON_ERROR)) + WARN_ON_ONCE(1); + if (test_opt(sb, ERRORS_CONT)) { ext4_commit_super(sb, 0); return; @@ -1371,7 +1377,8 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax, - Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit, + Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, + Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, @@ -1438,6 +1445,8 @@ static const match_table_t tokens = { {Opt_dax, "dax"}, {Opt_stripe, "stripe=%u"}, {Opt_delalloc, "delalloc"}, + {Opt_warn_on_error, "warn_on_error"}, + {Opt_nowarn_on_error, "nowarn_on_error"}, {Opt_lazytime, "lazytime"}, {Opt_nolazytime, "nolazytime"}, {Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"}, @@ -1602,6 +1611,8 @@ static const struct mount_opts { MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR}, + {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, + {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, @@ -2331,6 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; + ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; @@ -2363,6 +2375,14 @@ static int ext4_check_descriptors(struct super_block *sb, if (!sb_rdonly(sb)) return 0; } + if (block_bitmap >= sb_block + 1 && + block_bitmap <= last_bg_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Block bitmap for group %u overlaps " + "block group descriptors", i); + if (!sb_rdonly(sb)) + return 0; + } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " @@ -2377,6 +2397,14 @@ static int ext4_check_descriptors(struct super_block *sb, if (!sb_rdonly(sb)) return 0; } + if (inode_bitmap >= sb_block + 1 && + inode_bitmap <= last_bg_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode bitmap for group %u overlaps " + "block group descriptors", i); + if (!sb_rdonly(sb)) + return 0; + } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " @@ -2391,6 +2419,14 @@ static int ext4_check_descriptors(struct super_block *sb, if (!sb_rdonly(sb)) return 0; } + if (inode_table >= sb_block + 1 && + inode_table <= last_bg_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode table for group %u overlaps " + "block group descriptors", i); + if (!sb_rdonly(sb)) + return 0; + } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -3097,6 +3133,9 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; struct ext4_group_desc *gdp = NULL; + if (!ext4_has_group_desc_csum(sb)) + return ngroups; + for (group = 0; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) @@ -3742,6 +3781,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) le32_to_cpu(es->s_log_block_size)); goto failed_mount; } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto failed_mount; + } if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) { ext4_msg(sb, KERN_ERR, @@ -3806,6 +3852,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } else { sbi->s_inode_size = le16_to_cpu(es->s_inode_size); sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { + ext4_msg(sb, KERN_ERR, "invalid first ino: %u", + sbi->s_first_ino); + goto failed_mount; + } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > blocksize)) { @@ -3882,13 +3933,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "block size (%d)", clustersize, blocksize); goto failed_mount; } - if (le32_to_cpu(es->s_log_cluster_size) > - (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Invalid log cluster size: %u", - le32_to_cpu(es->s_log_cluster_size)); - goto failed_mount; - } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); sbi->s_clusters_per_group = @@ -3909,10 +3953,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } else { if (clustersize != blocksize) { - ext4_warning(sb, "fragment/cluster size (%d) != " - "block size (%d)", clustersize, - blocksize); - clustersize = blocksize; + ext4_msg(sb, KERN_ERR, + "fragment/cluster size (%d) != " + "block size (%d)", clustersize, blocksize); + goto failed_mount; } if (sbi->s_blocks_per_group > blocksize * 8) { ext4_msg(sb, KERN_ERR, @@ -3966,6 +4010,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_blocks_count(es)); goto failed_mount; } + if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && + (sbi->s_cluster_ratio == 1)) { + ext4_msg(sb, KERN_WARNING, "bad geometry: first data " + "block is 0 with a 1k block and cluster size"); + goto failed_mount; + } + blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); @@ -4001,6 +4052,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } bgl_lock_init(sbi->s_blockgroup_lock); @@ -4020,14 +4079,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } + sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; } - sbi->s_gdb_count = db_count; - timer_setup(&sbi->s_err_report, print_daily_error_info, 0); /* Register extent status tree shrinker */ @@ -4736,6 +4794,14 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (!sbh || block_device_ejected(sb)) return error; + + /* + * The superblock bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(sbh)) + return error; + /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -5140,6 +5206,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); + if (sbi->s_mmp_tsk) + kthread_stop(sbi->s_mmp_tsk); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index fc4ced59c565..723df14f4084 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -230,12 +230,12 @@ __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, { int error = -EFSCORRUPTED; - if (buffer_verified(bh)) - return 0; - if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) goto errout; + if (buffer_verified(bh)) + return 0; + error = -EFSBADCRC; if (!ext4_xattr_block_csum_verify(inode, bh)) goto errout; @@ -1560,7 +1560,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, handle_t *handle, struct inode *inode, bool is_block) { - struct ext4_xattr_entry *last; + struct ext4_xattr_entry *last, *next; struct ext4_xattr_entry *here = s->here; size_t min_offs = s->end - s->base, name_len = strlen(i->name); int in_inode = i->in_inode; @@ -1595,7 +1595,13 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, /* Compute min_offs and last. */ last = s->first; - for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { + for (; !IS_LAST_ENTRY(last); last = next) { + next = EXT4_XATTR_NEXT(last); + if ((void *)next >= s->end) { + EXT4_ERROR_INODE(inode, "corrupted xattr entries"); + ret = -EFSCORRUPTED; + goto out; + } if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) @@ -2206,23 +2212,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) { - if (error == -ENOSPC && - ext4_has_inline_data(inode)) { - error = ext4_try_to_evict_inline_data(handle, inode, - EXT4_XATTR_LEN(strlen(i->name) + - EXT4_XATTR_SIZE(i->value_len))); - if (error) - return error; - error = ext4_xattr_ibody_find(inode, i, is); - if (error) - return error; - error = ext4_xattr_set_entry(i, s, handle, inode, - false /* is_block */); - } - if (error) - return error; - } + if (error) + return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); @@ -2651,6 +2642,11 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { + /* never move system.data out of the inode */ + if ((last->e_name_len == 4) && + (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) && + !memcmp(last->e_name, "data", 4)) + continue; total_size = EXT4_XATTR_LEN(last->e_name_len); if (!last->e_value_inum) total_size += EXT4_XATTR_SIZE( diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 065dc919a0ce..bfd589ea74c0 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb, brelse(bh); } +static void fat_reset_iocharset(struct fat_mount_options *opts) +{ + if (opts->iocharset != fat_default_iocharset) { + /* Note: opts->iocharset can be NULL here */ + kfree(opts->iocharset); + opts->iocharset = fat_default_iocharset; + } +} + static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); kfree(sbi); } @@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; - opts->iocharset = fat_default_iocharset; + fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; @@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, /* vfat specific */ case Opt_charset: - if (opts->iocharset != fat_default_iocharset) - kfree(opts->iocharset); + fat_reset_iocharset(opts); iocharset = match_strdup(&args[0]); if (!iocharset) return -ENOMEM; @@ -1881,8 +1888,7 @@ out_fail: iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index c184c5a356ff..cdcb376ef8df 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache, { struct fscache_cache_tag *tag; + ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); BUG_ON(!cache->ops); BUG_ON(!ifsdef); @@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache, if (!cache->kobj) goto error; - ifsdef->cookie = &fscache_fsdef_index; ifsdef->cache = cache; cache->fsdef = ifsdef; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 97137d7ec5ee..83bfe04456b6 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache, goto error; } + ASSERTCMP(object->cookie, ==, cookie); fscache_stat(&fscache_n_object_alloc); object->debug_id = atomic_inc_return(&fscache_object_debug_id); @@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); + ASSERTCMP(object->cookie, ==, cookie); + spin_lock(&cookie->lock); /* there may be multiple initial creations of this object, but we only @@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, spin_unlock(&cache->object_list_lock); } - /* attach to the cookie */ - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); + /* Attach to the cookie. The object already has a ref on it. */ hlist_add_head(&object->cookie_link, &cookie->backing_objects); fscache_objlist_add(object); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 20e0d0a4dc8c..9edc920f651f 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object, object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; + fscache_cookie_get(cookie, fscache_cookie_get_attach_object); object->parent = NULL; #ifdef CONFIG_FSCACHE_OBJECT_LIST RB_CLEAR_NODE(&object->objlist_link); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e30c5975ea58..8d265790374c 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op) ASSERT(op->processor != NULL); ASSERT(fscache_object_is_available(op->object)); ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); + ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, + op->state, ==, FSCACHE_OP_ST_CANCELLED); fscache_stat(&fscache_n_op_enqueue); switch (op->flags & FSCACHE_OP_TYPE) { @@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op) struct fscache_cache *cache; _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + op->object ? op->object->debug_id : 0, + op->debug_id, atomic_read(&op->usage)); ASSERTCMP(atomic_read(&op->usage), >, 0); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d508c7844681..40d4c66c7751 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, current->mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pagevec_init(&pvec); next = start; @@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * as input to create an allocation policy. */ memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; diff --git a/fs/inode.c b/fs/inode.c index 2c300e981796..8c86c809ca17 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1999,8 +1999,14 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; + + /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; + else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && + !in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(dir, CAP_FSETID)) + mode &= ~S_ISGID; } else inode->i_gid = current_fsgid(); inode->i_mode = mode; diff --git a/fs/internal.h b/fs/internal.h index 980d005b21b4..5645b4ebf494 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -127,7 +127,6 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); -extern struct file *filp_clone_open(struct file *); /* * inode.c diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 51dd68e67b0f..c0b66a7a795b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1361,6 +1361,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) { jbd_lock_bh_state(bh); + if (jh->b_transaction == transaction && + jh->b_jlist != BJ_Metadata) + pr_err("JBD2: assertion failure: h_type=%u " + "h_line_no=%u block_no=%llu jlist=%u\n", + handle->h_type, handle->h_line_no, + (unsigned long long) bh->b_blocknr, + jh->b_jlist); J_ASSERT_JH(jh, jh->b_transaction != transaction || jh->b_jlist == BJ_Metadata); jbd_unlock_bh_state(bh); @@ -1380,11 +1387,11 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * of the transaction. This needs to be done * once a transaction -bzzz */ - jh->b_modified = 1; if (handle->h_buffer_credits <= 0) { ret = -ENOSPC; goto out_unlock_bh; } + jh->b_modified = 1; handle->h_buffer_credits--; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e9679016271f..dfd73a4616ce 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -831,7 +831,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) SEQ_PUT_DEC(" kB\nSwap: ", mss->swap); SEQ_PUT_DEC(" kB\nSwapPss: ", mss->swap_pss >> PSS_SHIFT); - SEQ_PUT_DEC(" kB\nLocked: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nLocked: ", + mss->pss_locked >> PSS_SHIFT); seq_puts(m, " kB\n"); } if (!rollup_mode) { diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 7e288d97adcb..9fed1c05f1f4 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -76,83 +76,99 @@ static char *le_type(struct reiserfs_key *key) } /* %k */ -static void sprintf_le_key(char *buf, struct reiserfs_key *key) +static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id), - le32_to_cpu(key->k_objectid), le_offset(key), - le_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + le32_to_cpu(key->k_dir_id), + le32_to_cpu(key->k_objectid), le_offset(key), + le_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } /* %K */ -static void sprintf_cpu_key(char *buf, struct cpu_key *key) +static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key) { if (key) - sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id, - key->on_disk_key.k_objectid, reiserfs_cpu_offset(key), - cpu_type(key)); + return scnprintf(buf, size, "[%d %d %s %s]", + key->on_disk_key.k_dir_id, + key->on_disk_key.k_objectid, + reiserfs_cpu_offset(key), cpu_type(key)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh) +static int scnprintf_de_head(char *buf, size_t size, + struct reiserfs_de_head *deh) { if (deh) - sprintf(buf, - "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", - deh_offset(deh), deh_dir_id(deh), deh_objectid(deh), - deh_location(deh), deh_state(deh)); + return scnprintf(buf, size, + "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]", + deh_offset(deh), deh_dir_id(deh), + deh_objectid(deh), deh_location(deh), + deh_state(deh)); else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_item_head(char *buf, struct item_head *ih) +static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih) { if (ih) { - strcpy(buf, - (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*"); - sprintf_le_key(buf + strlen(buf), &(ih->ih_key)); - sprintf(buf + strlen(buf), ", item_len %d, item_location %d, " - "free_space(entry_count) %d", - ih_item_len(ih), ih_location(ih), ih_free_space(ih)); + char *p = buf; + char * const end = buf + size; + + p += scnprintf(p, end - p, "%s", + (ih_version(ih) == KEY_FORMAT_3_6) ? + "*3.6* " : "*3.5*"); + + p += scnprintf_le_key(p, end - p, &ih->ih_key); + + p += scnprintf(p, end - p, + ", item_len %d, item_location %d, free_space(entry_count) %d", + ih_item_len(ih), ih_location(ih), + ih_free_space(ih)); + return p - buf; } else - sprintf(buf, "[NULL]"); + return scnprintf(buf, size, "[NULL]"); } -static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de) +static int scnprintf_direntry(char *buf, size_t size, + struct reiserfs_dir_entry *de) { char name[20]; memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen); name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0; - sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid); + return scnprintf(buf, size, "\"%s\"==>[%d %d]", + name, de->de_dir_id, de->de_objectid); } -static void sprintf_block_head(char *buf, struct buffer_head *bh) +static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ", - B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); + return scnprintf(buf, size, + "level=%d, nr_items=%d, free_space=%d rdkey ", + B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh)); } -static void sprintf_buffer_head(char *buf, struct buffer_head *bh) +static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh) { - sprintf(buf, - "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", - bh->b_bdev, bh->b_size, - (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)), - bh->b_state, bh->b_page, - buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", - buffer_dirty(bh) ? "DIRTY" : "CLEAN", - buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); + return scnprintf(buf, size, + "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", + bh->b_bdev, bh->b_size, + (unsigned long long)bh->b_blocknr, + atomic_read(&(bh->b_count)), + bh->b_state, bh->b_page, + buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", + buffer_dirty(bh) ? "DIRTY" : "CLEAN", + buffer_locked(bh) ? "LOCKED" : "UNLOCKED"); } -static void sprintf_disk_child(char *buf, struct disk_child *dc) +static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc) { - sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc), - dc_size(dc)); + return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]", + dc_block_number(dc), dc_size(dc)); } static char *is_there_reiserfs_struct(char *fmt, int *what) @@ -189,55 +205,60 @@ static void prepare_error_buf(const char *fmt, va_list args) char *fmt1 = fmt_buf; char *k; char *p = error_buf; + char * const end = &error_buf[sizeof(error_buf)]; int what; spin_lock(&error_lock); - strcpy(fmt1, fmt); + if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) { + strscpy(error_buf, "format string too long", end - error_buf); + goto out_unlock; + } while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) { *k = 0; - p += vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); switch (what) { case 'k': - sprintf_le_key(p, va_arg(args, struct reiserfs_key *)); + p += scnprintf_le_key(p, end - p, + va_arg(args, struct reiserfs_key *)); break; case 'K': - sprintf_cpu_key(p, va_arg(args, struct cpu_key *)); + p += scnprintf_cpu_key(p, end - p, + va_arg(args, struct cpu_key *)); break; case 'h': - sprintf_item_head(p, va_arg(args, struct item_head *)); + p += scnprintf_item_head(p, end - p, + va_arg(args, struct item_head *)); break; case 't': - sprintf_direntry(p, - va_arg(args, - struct reiserfs_dir_entry *)); + p += scnprintf_direntry(p, end - p, + va_arg(args, struct reiserfs_dir_entry *)); break; case 'y': - sprintf_disk_child(p, - va_arg(args, struct disk_child *)); + p += scnprintf_disk_child(p, end - p, + va_arg(args, struct disk_child *)); break; case 'z': - sprintf_block_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_block_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'b': - sprintf_buffer_head(p, - va_arg(args, struct buffer_head *)); + p += scnprintf_buffer_head(p, end - p, + va_arg(args, struct buffer_head *)); break; case 'a': - sprintf_de_head(p, - va_arg(args, - struct reiserfs_de_head *)); + p += scnprintf_de_head(p, end - p, + va_arg(args, struct reiserfs_de_head *)); break; } - p += strlen(p); fmt1 = k + 2; } - vsprintf(p, fmt1, args); + p += vscnprintf(p, end - p, fmt1, args); +out_unlock: spin_unlock(&error_lock); } diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 23813c078cc9..0839efa720b3 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer, TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + if (unlikely(length < 0)) + return -EIO; + while (length) { entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); if (entry->error) { diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 13d80947bf9e..fcff2e0487fe 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n, } for (i = 0; i < blocks; i++) { - int size = le32_to_cpu(blist[i]); + int size = squashfs_block_size(blist[i]); + if (size < 0) { + err = size; + goto failure; + } block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size); } n -= blocks; @@ -367,7 +371,7 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) sizeof(size)); if (res < 0) return res; - return le32_to_cpu(size); + return squashfs_block_size(size); } /* Copy data into page cache */ diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c index 0ed6edbc5c71..86ad9a4b8c36 100644 --- a/fs/squashfs/fragment.c +++ b/fs/squashfs/fragment.c @@ -61,9 +61,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, return size; *fragment_block = le64_to_cpu(fragment_entry.start_block); - size = le32_to_cpu(fragment_entry.size); - - return size; + return squashfs_block_size(fragment_entry.size); } diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 24d12fd14177..4e6853f084d0 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -129,6 +129,12 @@ #define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK)) +static inline int squashfs_block_size(__le32 raw) +{ + u32 size = le32_to_cpu(raw); + return (size >> 25) ? -EIO : size; +} + /* * Inode number ops. Inodes consist of a compressed block number, and an * uncompressed offset within that block diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 123bf7d516fc..594d192b2331 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -222,24 +222,26 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, unsigned long reason) { struct mm_struct *mm = ctx->mm; - pte_t *pte; + pte_t *ptep, pte; bool ret = true; VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); - pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); - if (!pte) + ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); + + if (!ptep) goto out; ret = false; + pte = huge_ptep_get(ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. */ - if (huge_pte_none(*pte)) + if (huge_pte_none(pte)) ret = true; - if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP)) + if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index eef466260d43..75dbdc14c45f 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -223,12 +223,13 @@ xfs_alloc_get_rec( error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - if (rec->alloc.ar_blockcount == 0) - goto out_bad_rec; *bno = be32_to_cpu(rec->alloc.ar_startblock); *len = be32_to_cpu(rec->alloc.ar_blockcount); + if (*len == 0) + goto out_bad_rec; + /* check for valid extent range, including overflow */ if (!xfs_verify_agbno(mp, agno, *bno)) goto out_bad_rec; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 33dc34655ac3..30d1d60f1d46 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -731,7 +731,8 @@ xfs_inode_validate_extsize( if ((hint_flag || inherit_flag) && extsize == 0) return __this_address; - if (!(hint_flag || inherit_flag) && extsize != 0) + /* free inodes get flags set to zero but extsize remains */ + if (mode && !(hint_flag || inherit_flag) && extsize != 0) return __this_address; if (extsize_bytes % blocksize_bytes) @@ -777,7 +778,8 @@ xfs_inode_validate_cowextsize( if (hint_flag && cowextsize == 0) return __this_address; - if (!hint_flag && cowextsize != 0) + /* free inodes get flags set to zero but cowextsize remains */ + if (mode && !hint_flag && cowextsize != 0) return __this_address; if (hint_flag && rt_flag) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index faddde44de8c..3063125197ad 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -265,33 +265,41 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ +#ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ __pte_free_tlb(tlb, ptep, address); \ } while (0) +#endif +#ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) +#endif #ifndef __ARCH_HAS_4LEVEL_HACK +#ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif +#endif #ifndef __ARCH_HAS_5LEVEL_HACK +#ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif +#endif #define tlb_migrate_finish(mm) do {} while (0) diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 767c90b654c5..f3e6eed3e79c 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -69,16 +69,21 @@ struct drm_printer { /* private: */ void (*printfn)(struct drm_printer *p, struct va_format *vaf); + void (*puts)(struct drm_printer *p, const char *str); void *arg; const char *prefix; }; +void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf); +void __drm_puts_coredump(struct drm_printer *p, const char *str); void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf); +void __drm_puts_seq_file(struct drm_printer *p, const char *str); void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf); void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf); __printf(2, 3) void drm_printf(struct drm_printer *p, const char *f, ...); +void drm_puts(struct drm_printer *p, const char *str); __printf(2, 0) /** @@ -105,6 +110,71 @@ drm_vprintf(struct drm_printer *p, const char *fmt, va_list *va) drm_printf((printer), "%.*s" fmt, (indent), "\t\t\t\t\tX", ##__VA_ARGS__) /** + * struct drm_print_iterator - local struct used with drm_printer_coredump + * @data: Pointer to the devcoredump output buffer + * @start: The offset within the buffer to start writing + * @remain: The number of bytes to write for this iteration + */ +struct drm_print_iterator { + void *data; + ssize_t start; + ssize_t remain; + /* private: */ + ssize_t offset; +}; + +/** + * drm_coredump_printer - construct a &drm_printer that can output to a buffer + * from the read function for devcoredump + * @iter: A pointer to a struct drm_print_iterator for the read instance + * + * This wrapper extends drm_printf() to work with a dev_coredumpm() callback + * function. The passed in drm_print_iterator struct contains the buffer + * pointer, size and offset as passed in from devcoredump. + * + * For example:: + * + * void coredump_read(char *buffer, loff_t offset, size_t count, + * void *data, size_t datalen) + * { + * struct drm_print_iterator iter; + * struct drm_printer p; + * + * iter.data = buffer; + * iter.start = offset; + * iter.remain = count; + * + * p = drm_coredump_printer(&iter); + * + * drm_printf(p, "foo=%d\n", foo); + * } + * + * void makecoredump(...) + * { + * ... + * dev_coredumpm(dev, THIS_MODULE, data, 0, GFP_KERNEL, + * coredump_read, ...) + * } + * + * RETURNS: + * The &drm_printer object + */ +static inline struct drm_printer +drm_coredump_printer(struct drm_print_iterator *iter) +{ + struct drm_printer p = { + .printfn = __drm_printfn_coredump, + .puts = __drm_puts_coredump, + .arg = iter, + }; + + /* Set the internal offset of the iterator to zero */ + iter->offset = 0; + + return p; +} + +/** * drm_seq_file_printer - construct a &drm_printer that outputs to &seq_file * @f: the &struct seq_file to output to * @@ -115,6 +185,7 @@ static inline struct drm_printer drm_seq_file_printer(struct seq_file *f) { struct drm_printer p = { .printfn = __drm_printfn_seq_file, + .puts = __drm_puts_seq_file, .arg = f, }; return p; diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h index 9564597cbfac..0aa1d9c3e0b9 100644 --- a/include/dt-bindings/clock/imx6ul-clock.h +++ b/include/dt-bindings/clock/imx6ul-clock.h @@ -235,27 +235,25 @@ #define IMX6UL_CLK_CSI_PODF 222 #define IMX6UL_CLK_PLL3_120M 223 #define IMX6UL_CLK_KPP 224 -#define IMX6UL_CLK_CKO1_SEL 225 -#define IMX6UL_CLK_CKO1_PODF 226 -#define IMX6UL_CLK_CKO1 227 -#define IMX6UL_CLK_CKO2_SEL 228 -#define IMX6UL_CLK_CKO2_PODF 229 -#define IMX6UL_CLK_CKO2 230 -#define IMX6UL_CLK_CKO 231 - -/* For i.MX6ULL */ -#define IMX6ULL_CLK_ESAI_PRED 232 -#define IMX6ULL_CLK_ESAI_PODF 233 -#define IMX6ULL_CLK_ESAI_EXTAL 234 -#define IMX6ULL_CLK_ESAI_MEM 235 -#define IMX6ULL_CLK_ESAI_IPG 236 -#define IMX6ULL_CLK_DCP_CLK 237 -#define IMX6ULL_CLK_EPDC_PRE_SEL 238 -#define IMX6ULL_CLK_EPDC_SEL 239 -#define IMX6ULL_CLK_EPDC_PODF 240 -#define IMX6ULL_CLK_EPDC_ACLK 241 -#define IMX6ULL_CLK_EPDC_PIX 242 -#define IMX6ULL_CLK_ESAI_SEL 243 +#define IMX6ULL_CLK_ESAI_PRED 225 +#define IMX6ULL_CLK_ESAI_PODF 226 +#define IMX6ULL_CLK_ESAI_EXTAL 227 +#define IMX6ULL_CLK_ESAI_MEM 228 +#define IMX6ULL_CLK_ESAI_IPG 229 +#define IMX6ULL_CLK_DCP_CLK 230 +#define IMX6ULL_CLK_EPDC_PRE_SEL 231 +#define IMX6ULL_CLK_EPDC_SEL 232 +#define IMX6ULL_CLK_EPDC_PODF 233 +#define IMX6ULL_CLK_EPDC_ACLK 234 +#define IMX6ULL_CLK_EPDC_PIX 235 +#define IMX6ULL_CLK_ESAI_SEL 236 +#define IMX6UL_CLK_CKO1_SEL 237 +#define IMX6UL_CLK_CKO1_PODF 238 +#define IMX6UL_CLK_CKO1 239 +#define IMX6UL_CLK_CKO2_SEL 240 +#define IMX6UL_CLK_CKO2_PODF 241 +#define IMX6UL_CLK_CKO2 242 +#define IMX6UL_CLK_CKO 243 #define IMX6UL_CLK_END 244 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */ diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h new file mode 100644 index 000000000000..4cc40201273e --- /dev/null +++ b/include/linux/ascii85.h @@ -0,0 +1,38 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2008 Intel Corporation + * Copyright (c) 2018 The Linux Foundation. All rights reserved. + */ + +#ifndef _ASCII85_H_ +#define _ASCII85_H_ + +#include <linux/kernel.h> + +#define ASCII85_BUFSZ 6 + +static inline long +ascii85_encode_len(long len) +{ + return DIV_ROUND_UP(len, 4); +} + +static inline const char * +ascii85_encode(u32 in, char *out) +{ + int i; + + if (in == 0) + return "z"; + + out[5] = '\0'; + for (i = 5; i--; ) { + out[i] = '!' + in % 85; + in /= 85; + } + + return out; +} + +#endif diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ca3f2c2edd85 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +/** + * blk_mq_mark_complete() - Set request state to complete + * @rq: request to set to complete state + * + * Returns true if request state was successfully set to complete. If + * successful, the caller is responsibile for seeing this request is ended, as + * blk_mq_complete_request will not work again. + */ +static inline bool blk_mq_mark_complete(struct request *rq) +{ + return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == + MQ_RQ_IN_FLIGHT; +} + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 975fb4cf1bb7..d50c2f0a655a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include <linux/errno.h> #include <linux/jump_label.h> #include <uapi/linux/bpf.h> @@ -188,12 +189,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, \ __ret; \ }) +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog); +int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype); +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); #else +struct bpf_prog; struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EINVAL; +} + +static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} + #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7df32a3200f7..8827e797ff97 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map, { return -EOPNOTSUPP; } + +static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + return -EINVAL; +} #endif #if defined(CONFIG_XDP_SOCKETS) diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h index 5f8a4283092d..9d9ff755ec29 100644 --- a/include/linux/bpf_lirc.h +++ b/include/linux/bpf_lirc.h @@ -5,11 +5,12 @@ #include <uapi/linux/bpf.h> #ifdef CONFIG_BPF_LIRC_MODE2 -int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int lirc_prog_detach(const union bpf_attr *attr); int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -static inline int lirc_prog_attach(const union bpf_attr *attr) +static inline int lirc_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 687b1760bb9f..f02cee0225d4 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -5,10 +5,10 @@ #include <uapi/linux/bpfilter.h> struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, - int *optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen); extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index fd282c7d3e5e..573f5a7d42d4 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,25 +66,40 @@ #endif /* + * Feature detection for gnu_inline (gnu89 extern inline semantics). Either + * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, + * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not + * defined so the gnu89 semantics are the default. + */ +#ifdef __GNUC_STDC_INLINE__ +# define __gnu_inline __attribute__((gnu_inline)) +#else +# define __gnu_inline +#endif + +/* * Force always-inline if the user requests it so via the .config, * or if gcc is too old. * GCC does not warn about unused static inline functions for * -Wunused-function. This turns out to avoid the need for complex #ifdef * directives. Suppress the warning in clang as well by using "unused" * function attribute, which is redundant but not harmful for gcc. + * Prefer gnu_inline, so that extern inline functions do not emit an + * externally visible function. This makes extern inline behave as per gnu89 + * semantics rather than c99. This prevents multiple symbol definition errors + * of extern inline functions at link time. + * A lot of inline functions can cause havoc with function tracing. */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -#define inline inline __attribute__((always_inline,unused)) notrace -#define __inline__ __inline__ __attribute__((always_inline,unused)) notrace -#define __inline __inline __attribute__((always_inline,unused)) notrace +#define inline \ + inline __attribute__((always_inline, unused)) notrace __gnu_inline #else -/* A lot of inline functions can cause havoc with function tracing */ -#define inline inline __attribute__((unused)) notrace -#define __inline__ __inline__ __attribute__((unused)) notrace -#define __inline __inline __attribute__((unused)) notrace +#define inline inline __attribute__((unused)) notrace __gnu_inline #endif +#define __inline__ inline +#define __inline inline #define __always_inline inline __attribute__((always_inline)) #define noinline __attribute__((noinline)) diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index e6c0448ebcc7..31c865d1842e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (current->delays) + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 7094718b653b..ffcc7724ca21 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -11,6 +11,7 @@ #include <linux/fcntl.h> #include <linux/wait.h> +#include <linux/err.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining diff --git a/include/linux/filter.h b/include/linux/filter.h index 20f2659dd829..c73dd7396886 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -470,9 +470,7 @@ struct sock_fprog_kern { }; struct bpf_binary_header { - u16 pages; - u16 locked:1; - + u32 pages; /* Some arches need word alignment for their instructions */ u8 image[] __aligned(4); }; @@ -481,7 +479,7 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - locked:1, /* Program image locked? */ + undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -677,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - fp->locked = 1; - if (set_memory_ro((unsigned long)fp, fp->pages)) - fp->locked = 0; -#endif + fp->undo_set_mem = 1; + set_memory_ro((unsigned long)fp, fp->pages); } static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (fp->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - fp->locked = 0; - } -#endif + if (fp->undo_set_mem) + set_memory_rw((unsigned long)fp, fp->pages); } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - hdr->locked = 1; - if (set_memory_ro((unsigned long)hdr, hdr->pages)) - hdr->locked = 0; -#endif + set_memory_ro((unsigned long)hdr, hdr->pages); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) { -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - if (hdr->locked) { - WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages)); - /* In case set_memory_rw() fails, we want to be the first - * to crash here instead of some random place later on. - */ - hdr->locked = 0; - } -#endif + set_memory_rw((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * @@ -728,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp) return (void *)addr; } -#ifdef CONFIG_ARCH_HAS_SET_MEMORY -static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp) -{ - if (!fp->locked) - return -ENOLCK; - if (fp->jited) { - const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - - if (!hdr->locked) - return -ENOLCK; - } - - return 0; -} -#endif - int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { @@ -805,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); -static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, - struct net_device *fwd) +static inline int xdp_ok_fwd_dev(const struct net_device *fwd, + unsigned int pktlen) { unsigned int len; @@ -814,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) + if (pktlen > len) return -EMSGSIZE; return 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index d78d146a98da..805bf22898cf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2420,6 +2420,7 @@ extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *filp_clone_open(struct file *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index 3efa3b861d44..941b11811f85 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -16,6 +16,7 @@ #define __FSL_GUTS_H__ #include <linux/types.h> +#include <linux/io.h> /** * Global Utility Registers. diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8154f4920fcb..ebb77674be90 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -223,7 +223,6 @@ extern enum ftrace_tracing_type_t ftrace_tracing_type; */ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); -void clear_ftrace_function(void); extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct pt_regs *regs); @@ -239,7 +238,6 @@ static inline int ftrace_nr_registered_ops(void) { return 0; } -static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } diff --git a/include/linux/hid.h b/include/linux/hid.h index 41a3d5775394..773bcb1d4044 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -511,6 +511,7 @@ struct hid_output_fifo { #define HID_STAT_ADDED BIT(0) #define HID_STAT_PARSED BIT(1) #define HID_STAT_DUP_DETECTED BIT(2) +#define HID_STAT_REPROBED BIT(3) struct hid_input { struct list_head list; @@ -579,7 +580,7 @@ struct hid_device { /* device report descriptor */ bool battery_avoid_query; #endif - unsigned int status; /* see STAT flags above */ + unsigned long status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ bool io_started; /* If IO has started */ diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 7843b98e1c6e..c20c7e197d07 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -105,13 +105,13 @@ static inline bool br_vlan_enabled(const struct net_device *dev) static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { - return -1; + return -EINVAL; } static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { - return -1; + return -EINVAL; } #endif diff --git a/include/linux/igmp.h b/include/linux/igmp.h index f8231854b5d6..119f53941c12 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -109,6 +109,8 @@ struct ip_mc_list { extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); +extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 1df940196ab2..ef169d67df92 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -121,6 +121,7 @@ #define ecap_srs(e) ((e >> 31) & 0x1) #define ecap_ers(e) ((e >> 30) & 0x1) #define ecap_prs(e) ((e >> 29) & 0x1) +#define ecap_broken_pasid(e) ((e >> 28) & 0x1) #define ecap_dis(e) ((e >> 27) & 0x1) #define ecap_nest(e) ((e >> 26) & 0x1) #define ecap_mts(e) ((e >> 25) & 0x1) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 2803264c512f..c1961761311d 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -62,7 +62,6 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_park_complete(struct task_struct *k); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/libata.h b/include/linux/libata.h index 8b8946dd63b9..32f247cb5e9e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LPM = (1 << 2), /* host not happy with LPM */ ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ @@ -1495,6 +1496,29 @@ static inline bool ata_tag_valid(unsigned int tag) return tag < ATA_MAX_QUEUE || ata_tag_internal(tag); } +#define __ata_qc_for_each(ap, qc, tag, max_tag, fn) \ + for ((tag) = 0; (tag) < (max_tag) && \ + ({ qc = fn((ap), (tag)); 1; }); (tag)++) \ + +/* + * Internal use only, iterate commands ignoring error handling and + * status of 'qc'. + */ +#define ata_qc_for_each_raw(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, __ata_qc_from_tag) + +/* + * Iterate all potential commands that can be queued + */ +#define ata_qc_for_each(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, ata_qc_from_tag) + +/* + * Like ata_qc_for_each, but with the internal tag included + */ +#define ata_qc_for_each_with_internal(ap, qc, tag) \ + __ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE + 1, ata_qc_from_tag) + /* * device helpers */ diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 4f5f8c21e283..1eb6f244588d 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -27,6 +27,8 @@ */ #define MARVELL_PHY_ID_88E6390 0x01410f90 +#define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4) + /* struct phy_device dev_flags definitions */ #define MARVELL_PHY_M1145_FLAGS_RESISTANCE 0x00000001 #define MARVELL_PHY_M1118_DNS323_LEDS 0x00000002 diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..83957920653a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u32 frag_sz_m1; + u32 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, - struct mlx5_frag_buf_ctrl *fbc) +static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, + u32 strides_offset, + struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; + fbc->strides_offset = strides_offset; +} + +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) +{ + mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); } static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, @@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { - unsigned int frag = (ix >> fbc->log_frag_strides); + unsigned int frag; + + ix += fbc->strides_offset; + frag = ix >> fbc->log_frag_strides; return fbc->frag_buf.frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index d3c9db492b30..fab5121ffb8f 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -8,6 +8,8 @@ #include <linux/mlx5/driver.h> +#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager) + enum { SRIOV_NONE, SRIOV_LEGACY, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 27134c4fcb76..ac281f5ec9b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vnic_env_queue_counters[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 eswitch_flow_table[0x1]; + u8 eswitch_manager[0x1]; u8 device_memory[0x1]; u8 mcam_reg[0x1]; u8 pcam_reg[0x1]; diff --git a/include/linux/mm.h b/include/linux/mm.h index a0fbb9ffe380..7ba6d356d18f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, * mmap() functions). */ -extern struct kmem_cache *vm_area_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *); +struct vm_area_struct *vm_area_dup(struct vm_area_struct *); +void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -450,6 +452,20 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + + vma->vm_mm = mm; + vma->vm_ops = &dummy_vm_ops; + INIT_LIST_HEAD(&vma->anon_vma_chain); +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + struct mmu_gather; struct inode; @@ -2132,7 +2148,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#ifdef CONFIG_HAVE_MEMBLOCK +#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec9850c7936..3d0cc0b5cec2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff **pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/include/linux/pci.h b/include/linux/pci.h index 6e0c0803b241..e04ab6265566 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1243,6 +1243,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); +int devm_pci_remap_iospace(struct device *dev, const struct resource *res, + phys_addr_t phys_addr); void pci_unmap_iospace(struct resource *res); void __iomem *devm_pci_remap_cfgspace(struct device *dev, resource_size_t offset, diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b72ebdff0b77..003d09ab308d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); int ring_buffer_record_is_on(struct ring_buffer *buffer); +int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9256118bd40c..43731fe51c97 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,7 +118,7 @@ struct task_group; * the comment with set_special_state(). */ #define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD)) + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) #define __set_current_state(state_value) \ do { \ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 5be31eb7b266..108ede99e533 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -extern long kernel_wait4(pid_t, int *, int, struct rusage *); +extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); extern void free_task(struct task_struct *tsk); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 164cdedf6012..610a201126ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t; * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @xmit_more: More SKBs are pending for this queue + * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport @@ -735,7 +736,7 @@ struct sk_buff { peeked:1, head_frag:1, xmit_more:1, - __unused:1; /* one bit hole */ + pfmemalloc:1; /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() @@ -754,31 +755,30 @@ struct sk_buff { __u8 __pkt_type_offset[0]; __u8 pkt_type:3; - __u8 pfmemalloc:1; __u8 ignore_df:1; - __u8 nf_trace:1; __u8 ip_summed:2; __u8 ooo_okay:1; + __u8 l4_hash:1; __u8 sw_hash:1; __u8 wifi_acked_valid:1; __u8 wifi_acked:1; - __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; + __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; - __u8 dst_pending_confirm:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif __u8 ipvs_property:1; + __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a368a68cb667..5c1a0933768e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SYSCALLS_H #define _LINUX_SYSCALLS_H +struct __aio_sigset; struct epoll_event; struct iattr; struct inode; diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 6c5f2074e14f..6f8b68cd460f 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -75,7 +75,7 @@ struct uio_device { struct fasync_struct *async_queue; wait_queue_head_t wait; struct uio_info *info; - spinlock_t info_lock; + struct mutex info_lock; struct kobject *map_dir; struct kobject *portio_dir; }; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5fbfe61f41c6..1beb3ead0385 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5835,10 +5835,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, /** * cfg80211_rx_control_port - notification about a received control port frame * @dev: The device the frame matched to - * @buf: control port frame - * @len: length of the frame data - * @addr: The peer from which the frame was received - * @proto: frame protocol, typically PAE or Pre-authentication + * @skb: The skbuf with the control port frame. It is assumed that the skbuf + * is 802.3 formatted (with 802.3 header). The skb can be non-linear. + * This function does not take ownership of the skb, so the caller is + * responsible for any cleanup. The caller must also ensure that + * skb->protocol is set appropriately. * @unencrypted: Whether the frame was received unencrypted * * This function is used to inform userspace about a received control port @@ -5851,8 +5852,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, * Return: %true if the frame was passed to userspace */ bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted); + struct sk_buff *skb, bool unencrypted); /** * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 71b9043aa0e7..3d4930528db0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i) atomic_inc(&f6i->fib6_ref); } +static inline bool fib6_info_hold_safe(struct fib6_info *f6i) +{ + return atomic_inc_not_zero(&f6i->fib6_ref); +} + static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 59656fc580df..7b9c82de11cc 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } +static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) +{ + return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + RTF_GATEWAY; +} + void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 16475c269749..8f73be494503 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -355,14 +355,7 @@ struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, - struct ipv6_opt_hdr __user *newopt, - int newoptlen); -struct ipv6_txoptions * -ipv6_renew_options_kern(struct sock *sk, - struct ipv6_txoptions *opt, - int newtype, - struct ipv6_opt_hdr *newopt, - int newoptlen); + struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); @@ -830,7 +823,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, * to minimize possbility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ - rol32(hash, 16); + hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; @@ -1107,6 +1100,8 @@ void ipv6_sysctl_unregister(void); int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); +int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); #endif /* _NET_IPV6_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 47e35cce3b64..a71264d75d7f 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -128,6 +128,7 @@ struct net { #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag nf_frag; + struct ctl_table_header *nf_frag_frags_hdr; #endif struct sock *nfnl; struct sock *nfnl_stash; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 08c005ce56e9..dc417ef0a0c5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data) * @portid: netlink portID of the original message * @seq: netlink sequence number * @family: protocol family + * @level: depth of the chains * @report: notify via unicast netlink message */ struct nft_ctx { @@ -160,6 +161,7 @@ struct nft_ctx { u32 portid; u32 seq; u8 family; + u8 level; bool report; }; @@ -865,7 +867,6 @@ enum nft_chain_flags { * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @level: length of longest path to this chain * @flags: bitmask of enum nft_chain_flags * @name: name of the chain */ @@ -878,7 +879,6 @@ struct nft_chain { struct nft_table *table; u64 handle; u32 use; - u16 level; u8 flags:6, genmask:2; char *name; @@ -1124,7 +1124,6 @@ struct nft_flowtable { u32 genmask:2, use:30; u64 handle; - char *dev_name[NFT_FLOWTABLE_DEVICE_MAX]; /* runtime data below here */ struct nf_hook_ops *ops ____cacheline_aligned; struct nf_flowtable data; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index e0c0c2558ec4..a05134507e7b 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -65,4 +65,10 @@ extern const struct nft_expr_ops nft_payload_fast_ops; extern struct static_key_false nft_counters_enabled; extern struct static_key_false nft_trace_enabled; +extern struct nft_set_type nft_set_rhash_type; +extern struct nft_set_type nft_set_hash_type; +extern struct nft_set_type nft_set_hash_fast_type; +extern struct nft_set_type nft_set_rbtree_type; +extern struct nft_set_type nft_set_bitmap_type; + #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h index 9754a50ecde9..4cc64c8446eb 100644 --- a/include/net/netfilter/nf_tproxy.h +++ b/include/net/netfilter/nf_tproxy.h @@ -64,7 +64,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * belonging to established connections going through that one. */ struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, @@ -103,7 +103,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, struct sock *sk); struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c978a31b0f84..762ac9931b62 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -109,7 +109,6 @@ struct netns_ipv6 { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct netns_nf_frag { - struct netns_sysctl_ipv6 sysctl; struct netns_frags frags; }; #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3c1a2c47cd4..20b059574e60 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, { } +static inline bool tcf_block_shared(struct tcf_block *block) +{ + return false; +} + static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 9470fd7e4350..32d2454c0479 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -7,7 +7,6 @@ #include <linux/tc_act/tc_csum.h> struct tcf_csum_params { - int action; u32 update_flags; struct rcu_head rcu; }; diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index efef0b4b1b2b..46b8c7f1c8d5 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -18,7 +18,6 @@ struct tcf_tunnel_key_params { struct rcu_head rcu; int tcft_action; - int action; struct metadata_dst *tcft_enc_metadata; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 800582b5dd54..cd3ecda9386a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { @@ -539,6 +540,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -828,6 +830,10 @@ struct tcp_skb_cb { #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, @@ -835,6 +841,11 @@ struct tcp_skb_cb { */ static inline int tcp_v6_iif(const struct sk_buff *skb) { + return TCP_SKB_CB(skb)->header.h6.iif; +} + +static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) +{ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; @@ -908,8 +919,6 @@ enum tcp_ca_event { CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ - CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */ - CA_EVENT_NON_DELAYED_ACK, }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9fe472f2ac95..7161856bcf9c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -60,6 +60,10 @@ struct xdp_sock { bool zc; /* Protects multiple processes in the control path */ struct mutex mutex; + /* Mutual exclusion of NAPI TX thread and sendmsg error paths + * in the SKB destructor callback. + */ + spinlock_t tx_completion_lock; u64 rx_dropped; }; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index d43949b5bb3e..721ab7e54d96 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -299,6 +299,19 @@ extern "C" { */ #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE fourcc_mod_code(SAMSUNG, 1) +/* + * Qualcomm Compressed Format + * + * Refers to a compressed variant of the base format that is compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) + /* Vivante framebuffer modifiers */ /* diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index 3c5038b587ba..d4593a6062ef 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -29,7 +29,6 @@ #include <linux/types.h> #include <linux/fs.h> -#include <linux/signal.h> #include <asm/byteorder.h> typedef __kernel_ulong_t aio_context_t; @@ -110,10 +109,5 @@ struct iocb { #undef IFBIG #undef IFLITTLE -struct __aio_sigset { - const sigset_t __user *sigmask; - size_t sigsetsize; -}; - #endif /* __LINUX__AIO_ABI_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 59b19b6a40d7..b7db3261c62d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1857,7 +1857,8 @@ union bpf_attr { * is resolved), the nexthop address is returned in ipv4_dst * or ipv6_dst based on family, smac is set to mac address of * egress device, dmac is set to nexthop mac address, rt_metric - * is set to metric from route (IPv4/IPv6 only). + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. * * *plen* argument is the size of the passed in struct. * *flags* argument can be a combination of one or more of the @@ -1873,9 +1874,10 @@ union bpf_attr { * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. * Return - * Egress device index on success, 0 if packet needs to continue - * up the stack for further processing or a negative error in case - * of failure. + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_DIRECT BIT(0) #define BPF_FIB_LOOKUP_OUTPUT BIT(1) +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + struct bpf_fib_lookup { /* input: network family for lookup (AF_INET, AF_INET6) * output: network family of egress nexthop @@ -2625,7 +2639,11 @@ struct bpf_fib_lookup { /* total length of packet from network header - used for MTU check */ __u16 tot_len; - __u32 ifindex; /* L3 device index for lookup */ + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; union { /* inputs to lookup */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4ca65b56084f..7363f18e65a5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -226,7 +226,7 @@ enum tunable_id { ETHTOOL_TX_COPYBREAK, ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* - * Add your fresh new tubale attribute above and remember to update + * Add your fresh new tunable attribute above and remember to update * tunable_strings[] in net/core/ethtool.c */ __ETHTOOL_TUNABLE_COUNT, diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index b4f5073dbac2..01674b56e14f 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args { __u32 queue_priority; /* to KFD */ }; +struct kfd_ioctl_set_cu_mask_args { + __u32 queue_id; /* to KFD */ + __u32 num_cu_mask; /* to KFD */ + __u64 cu_mask_ptr; /* to KFD */ +}; + /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ #define KFD_IOC_CACHE_POLICY_COHERENT 0 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 @@ -189,6 +195,15 @@ struct kfd_ioctl_dbg_wave_control_args { #define KFD_SIGNAL_EVENT_LIMIT 4096 +/* For kfd_event_data.hw_exception_data.reset_type. */ +#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET 0 +#define KFD_HW_EXCEPTION_PER_ENGINE_RESET 1 + +/* For kfd_event_data.hw_exception_data.reset_cause. */ +#define KFD_HW_EXCEPTION_GPU_HANG 0 +#define KFD_HW_EXCEPTION_ECC 1 + + struct kfd_ioctl_create_event_args { __u64 event_page_offset; /* from KFD */ __u32 event_trigger_data; /* from KFD - signal events only */ @@ -219,7 +234,7 @@ struct kfd_memory_exception_failure { __u32 NotPresent; /* Page not present or supervisor privilege */ __u32 ReadOnly; /* Write access to a read-only page */ __u32 NoExecute; /* Execute access to a page marked NX */ - __u32 pad; + __u32 imprecise; /* Can't determine the exact fault address */ }; /* memory exception data*/ @@ -230,10 +245,19 @@ struct kfd_hsa_memory_exception_data { __u32 pad; }; -/* Event data*/ +/* hw exception data */ +struct kfd_hsa_hw_exception_data { + uint32_t reset_type; + uint32_t reset_cause; + uint32_t memory_lost; + uint32_t gpu_id; +}; + +/* Event data */ struct kfd_event_data { union { struct kfd_hsa_memory_exception_data memory_exception_data; + struct kfd_hsa_hw_exception_data hw_exception_data; }; /* From KFD */ __u64 kfd_event_data_ext; /* pointer to an extension structure for future exception types */ @@ -448,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args { #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU \ AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args) +#define AMDKFD_IOC_SET_CU_MASK \ + AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x1A +#define AMDKFD_COMMAND_END 0x1B #endif diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index d620fa43756c..9a402fdb60e9 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -10,13 +10,8 @@ * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> */ -#ifdef __KERNEL__ -# include <linux/types.h> -#else -# include <stdint.h> -#endif - -#include <linux/types_32_64.h> +#include <linux/types.h> +#include <asm/byteorder.h> enum rseq_cpu_id_state { RSEQ_CPU_ID_UNINITIALIZED = -1, @@ -52,10 +47,10 @@ struct rseq_cs { __u32 version; /* enum rseq_cs_flags */ __u32 flags; - LINUX_FIELD_u32_u64(start_ip); + __u64 start_ip; /* Offset from start_ip. */ - LINUX_FIELD_u32_u64(post_commit_offset); - LINUX_FIELD_u32_u64(abort_ip); + __u64 post_commit_offset; + __u64 abort_ip; } __attribute__((aligned(4 * sizeof(__u64)))); /* @@ -67,28 +62,30 @@ struct rseq_cs { struct rseq { /* * Restartable sequences cpu_id_start field. Updated by the - * kernel, and read by user-space with single-copy atomicity - * semantics. Aligned on 32-bit. Always contains a value in the - * range of possible CPUs, although the value may not be the - * actual current CPU (e.g. if rseq is not initialized). This - * CPU number value should always be compared against the value - * of the cpu_id field before performing a rseq commit or - * returning a value read from a data structure indexed using - * the cpu_id_start value. + * kernel. Read by user-space with single-copy atomicity + * semantics. This field should only be read by the thread which + * registered this data structure. Aligned on 32-bit. Always + * contains a value in the range of possible CPUs, although the + * value may not be the actual current CPU (e.g. if rseq is not + * initialized). This CPU number value should always be compared + * against the value of the cpu_id field before performing a rseq + * commit or returning a value read from a data structure indexed + * using the cpu_id_start value. */ __u32 cpu_id_start; /* - * Restartable sequences cpu_id field. Updated by the kernel, - * and read by user-space with single-copy atomicity semantics. - * Aligned on 32-bit. Values RSEQ_CPU_ID_UNINITIALIZED and - * RSEQ_CPU_ID_REGISTRATION_FAILED have a special semantic: the - * former means "rseq uninitialized", and latter means "rseq - * initialization failed". This value is meant to be read within - * rseq critical sections and compared with the cpu_id_start - * value previously read, before performing the commit instruction, - * or read and compared with the cpu_id_start value before returning - * a value loaded from a data structure indexed using the - * cpu_id_start value. + * Restartable sequences cpu_id field. Updated by the kernel. + * Read by user-space with single-copy atomicity semantics. This + * field should only be read by the thread which registered this + * data structure. Aligned on 32-bit. Values + * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED + * have a special semantic: the former means "rseq uninitialized", + * and latter means "rseq initialization failed". This value is + * meant to be read within rseq critical sections and compared + * with the cpu_id_start value previously read, before performing + * the commit instruction, or read and compared with the + * cpu_id_start value before returning a value loaded from a data + * structure indexed using the cpu_id_start value. */ __u32 cpu_id; /* @@ -105,27 +102,44 @@ struct rseq { * targeted by the rseq_cs. Also needs to be set to NULL by user-space * before reclaiming memory that contains the targeted struct rseq_cs. * - * Read and set by the kernel with single-copy atomicity semantics. - * Set by user-space with single-copy atomicity semantics. Aligned - * on 64-bit. + * Read and set by the kernel. Set by user-space with single-copy + * atomicity semantics. This field should only be updated by the + * thread which registered this data structure. Aligned on 64-bit. */ - LINUX_FIELD_u32_u64(rseq_cs); + union { + __u64 ptr64; +#ifdef __LP64__ + __u64 ptr; +#else + struct { +#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN) + __u32 padding; /* Initialized to zero. */ + __u32 ptr32; +#else /* LITTLE */ + __u32 ptr32; + __u32 padding; /* Initialized to zero. */ +#endif /* ENDIAN */ + } ptr; +#endif + } rseq_cs; + /* - * - RSEQ_DISABLE flag: + * Restartable sequences flags field. + * + * This field should only be updated by the thread which + * registered this data structure. Read by the kernel. + * Mainly used for single-stepping through rseq critical sections + * with debuggers. * - * Fallback fast-track flag for single-stepping. - * Set by user-space if lack of progress is detected. - * Cleared by user-space after rseq finish. - * Read by the kernel. * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT - * Inhibit instruction sequence block restart and event - * counter increment on preemption for this thread. + * Inhibit instruction sequence block restart on preemption + * for this thread. * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL - * Inhibit instruction sequence block restart and event - * counter increment on signal delivery for this thread. + * Inhibit instruction sequence block restart on signal + * delivery for this thread. * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE - * Inhibit instruction sequence block restart and event - * counter increment on migration for this thread. + * Inhibit instruction sequence block restart on migration for + * this thread. */ __u32 flags; } __attribute__((aligned(4 * sizeof(__u64)))); diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 29eb659aa77a..e3f6ed8a7064 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -127,6 +127,10 @@ enum { #define TCP_CM_INQ TCP_INQ +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + struct tcp_repair_opt { __u32 opt_code; __u32 opt_val; diff --git a/include/uapi/linux/types_32_64.h b/include/uapi/linux/types_32_64.h deleted file mode 100644 index 0a87ace34a57..000000000000 --- a/include/uapi/linux/types_32_64.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -#ifndef _UAPI_LINUX_TYPES_32_64_H -#define _UAPI_LINUX_TYPES_32_64_H - -/* - * linux/types_32_64.h - * - * Integer type declaration for pointers across 32-bit and 64-bit systems. - * - * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - */ - -#ifdef __KERNEL__ -# include <linux/types.h> -#else -# include <stdint.h> -#endif - -#include <asm/byteorder.h> - -#ifdef __BYTE_ORDER -# if (__BYTE_ORDER == __BIG_ENDIAN) -# define LINUX_BYTE_ORDER_BIG_ENDIAN -# else -# define LINUX_BYTE_ORDER_LITTLE_ENDIAN -# endif -#else -# ifdef __BIG_ENDIAN -# define LINUX_BYTE_ORDER_BIG_ENDIAN -# else -# define LINUX_BYTE_ORDER_LITTLE_ENDIAN -# endif -#endif - -#ifdef __LP64__ -# define LINUX_FIELD_u32_u64(field) __u64 field -# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) field = (intptr_t)v -#else -# ifdef LINUX_BYTE_ORDER_BIG_ENDIAN -# define LINUX_FIELD_u32_u64(field) __u32 field ## _padding, field -# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) \ - field ## _padding = 0, field = (intptr_t)v -# else -# define LINUX_FIELD_u32_u64(field) __u32 field, field ## _padding -# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v) \ - field = (intptr_t)v, field ## _padding = 0 -# endif -#endif - -#endif /* _UAPI_LINUX_TYPES_32_64_H */ diff --git a/include/video/mipi_display.h b/include/video/mipi_display.h index 19aa65a35546..49a53ef8da96 100644 --- a/include/video/mipi_display.h +++ b/include/video/mipi_display.h @@ -38,6 +38,9 @@ enum { MIPI_DSI_DCS_READ = 0x06, + MIPI_DSI_DCS_COMPRESSION_MODE = 0x07, + MIPI_DSI_PPS_LONG_WRITE = 0x0A, + MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE = 0x37, MIPI_DSI_END_OF_TRANSMISSION = 0x08, diff --git a/ipc/sem.c b/ipc/sem.c index 5af1943ad782..76e95e4f3aa2 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { - queue.status = -EINTR; + WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; __set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2d49d18b793a..9704934252b3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) */ static bool btf_type_int_is_regular(const struct btf_type *t) { - u16 nr_bits, nr_bytes; + u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); @@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf, void *data, u8 bits_offset, struct seq_file *m) { + u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); - u16 nr_bits = BTF_INT_BITS(int_data); - u16 total_bits_offset; - u16 nr_copy_bytes; - u16 nr_copy_bits; - u8 nr_upper_bits; - union { - u64 u64_num; - u8 u8_nums[8]; - } print_num; + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; + u64 print_num; + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); - print_num.u64_num = 0; - memcpy(&print_num.u64_num, data, nr_copy_bytes); + print_num = 0; + memcpy(&print_num, data, nr_copy_bytes); - /* Ditch the higher order bits */ - nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); - if (nr_upper_bits) { - /* We need to mask out some bits of the upper byte. */ - u8 mask = (1 << nr_upper_bits) - 1; - - print_num.u8_nums[nr_copy_bytes - 1] &= mask; - } +#ifdef __BIG_ENDIAN_BITFIELD + left_shift_bits = bits_offset; +#else + left_shift_bits = BITS_PER_U64 - nr_copy_bits; +#endif + right_shift_bits = BITS_PER_U64 - nr_bits; - print_num.u64_num >>= bits_offset; + print_num <<= left_shift_bits; + print_num >>= right_shift_bits; - seq_printf(m, "0x%llx", print_num.u64_num); + seq_printf(m, "0x%llx", print_num); } static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, @@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; - u32 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bits = BTF_INT_BITS(int_data); if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index f7c00bd6f8e4..3d83ee7df381 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return ret; } +int cgroup_bpf_prog_attach(const union bpf_attr *attr, + enum bpf_prog_type ptype, struct bpf_prog *prog) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + struct bpf_prog *prog; + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + + cgroup_put(cgrp); + return ret; +} + +int cgroup_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + ret = cgroup_bpf_query(cgrp, attr, uattr); + + cgroup_put(cgrp); + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a9e6c04d0f4a..1e5625d46414 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_fill_ill_insns(hdr, size); hdr->pages = size / PAGE_SIZE; - hdr->locked = 0; - hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) return 0; } -static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp) -{ -#ifdef CONFIG_ARCH_HAS_SET_MEMORY - int i, err; - - for (i = 0; i < fp->aux->func_cnt; i++) { - err = bpf_prog_check_pages_ro_single(fp->aux->func[i]); - if (err) - return err; - } - - return bpf_prog_check_pages_ro_single(fp); -#endif - return 0; -} - static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON @@ -1524,17 +1506,7 @@ finalize: * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); - if (*err) - return fp; - - /* Checkpoint: at this point onwards any cBPF -> eBPF or - * native eBPF program is read-only. If we failed to change - * the page attributes (e.g. allocation failure from - * splitting large pages), then reject the whole program - * in order to guarantee not ending up with any W+X pages - * from BPF side in kernel. - */ - *err = bpf_prog_check_pages_ro_locked(fp); + return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 642c97f6d1b8..d361fc1e3bf3 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; struct xdp_frame *xdpf; + int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, { int err; - err = __xdp_generic_ok_fwd_dev(skb, dst->dev); + err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; skb->dev = dst->dev; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3ca2198a6d22..513d9dfcf4ee 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, * old element will be freed immediately. * Otherwise return an error */ - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + l_new = ERR_PTR(-E2BIG); + goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) - return ERR_PTR(-ENOMEM); + if (!l_new) { + l_new = ERR_PTR(-ENOMEM); + goto dec_count; + } } memcpy(l_new->key, key, key_size); @@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); - return ERR_PTR(-ENOMEM); + l_new = ERR_PTR(-ENOMEM); + goto dec_count; } } @@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new->hash = hash; return l_new; +dec_count: + atomic_dec(&htab->count); + return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 52a91d816c0e..98fb7938beea 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -72,6 +72,7 @@ struct bpf_htab { u32 n_buckets; u32 elem_size; struct bpf_sock_progs progs; + struct rcu_head rcu; }; struct htab_elem { @@ -89,8 +90,8 @@ enum smap_psock_state { struct smap_psock_map_entry { struct list_head list; struct sock **entry; - struct htab_elem *hash_link; - struct bpf_htab *htab; + struct htab_elem __rcu *hash_link; + struct bpf_htab __rcu *htab; }; struct smap_psock { @@ -120,6 +121,7 @@ struct smap_psock { struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; struct list_head maps; + spinlock_t maps_lock; /* Back reference used when sock callback trigger sockmap operations */ struct sock *sock; @@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) { @@ -161,7 +164,42 @@ out: return !empty; } -static struct proto tcp_bpf_proto; +enum { + SOCKMAP_IPV4, + SOCKMAP_IPV6, + SOCKMAP_NUM_PROTS, +}; + +enum { + SOCKMAP_BASE, + SOCKMAP_TX, + SOCKMAP_NUM_CONFIGS, +}; + +static struct proto *saved_tcpv6_prot __read_mostly; +static DEFINE_SPINLOCK(tcpv6_prot_lock); +static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; +static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], + struct proto *base) +{ + prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].close = bpf_tcp_close; + prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; + prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; + + prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; + prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; + prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; +} + +static void update_sk_prot(struct sock *sk, struct smap_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; + int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; + + sk->sk_prot = &bpf_tcp_prots[family][conf]; +} + static int bpf_tcp_init(struct sock *sk) { struct smap_psock *psock; @@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk) psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; - if (psock->bpf_tx_msg) { - tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg; - tcp_bpf_proto.sendpage = bpf_tcp_sendpage; - tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg; - tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read; + /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ + if (sk->sk_family == AF_INET6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + spin_lock_bh(&tcpv6_prot_lock); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + spin_unlock_bh(&tcpv6_prot_lock); } - - sk->sk_prot = &tcp_bpf_proto; + update_sk_prot(sk, psock); rcu_read_unlock(); return 0; } @@ -219,24 +260,64 @@ out: rcu_read_unlock(); } +static struct htab_elem *lookup_elem_raw(struct hlist_head *head, + u32 hash, void *key, u32 key_size) +{ + struct htab_elem *l; + + hlist_for_each_entry_rcu(l, head, hash_node) { + if (l->hash == hash && !memcmp(&l->key, key, key_size)) + return l; + } + + return NULL; +} + +static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &htab->buckets[hash & (htab->n_buckets - 1)]; +} + +static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) +{ + return &__select_bucket(htab, hash)->head; +} + static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { atomic_dec(&htab->count); kfree_rcu(l, rcu); } +static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, + struct smap_psock *psock) +{ + struct smap_psock_map_entry *e; + + spin_lock_bh(&psock->maps_lock); + e = list_first_entry_or_null(&psock->maps, + struct smap_psock_map_entry, + list); + if (e) + list_del(&e->list); + spin_unlock_bh(&psock->maps_lock); + return e; +} + static void bpf_tcp_close(struct sock *sk, long timeout) { void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock_map_entry *e, *tmp; + struct smap_psock_map_entry *e; struct sk_msg_buff *md, *mtmp; struct smap_psock *psock; struct sock *osk; + lock_sock(sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (unlikely(!psock)) { rcu_read_unlock(); + release_sock(sk); return sk->sk_prot->close(sk, timeout); } @@ -247,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout) */ close_fun = psock->save_close; - write_lock_bh(&sk->sk_callback_lock); if (psock->cork) { free_start_sg(psock->sock, psock->cork); kfree(psock->cork); @@ -260,21 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout) kfree(md); } - list_for_each_entry_safe(e, tmp, &psock->maps, list) { + e = psock_map_pop(sk, psock); + while (e) { if (e->entry) { osk = cmpxchg(e->entry, sk, NULL); if (osk == sk) { - list_del(&e->list); smap_release_sock(psock, sk); } } else { - hlist_del_rcu(&e->hash_link->hash_node); - smap_release_sock(psock, e->hash_link->sk); - free_htab_elem(e->htab, e->hash_link); + struct htab_elem *link = rcu_dereference(e->hash_link); + struct bpf_htab *htab = rcu_dereference(e->htab); + struct hlist_head *head; + struct htab_elem *l; + struct bucket *b; + + b = __select_bucket(htab, link->hash); + head = &b->head; + raw_spin_lock_bh(&b->lock); + l = lookup_elem_raw(head, + link->hash, link->key, + htab->map.key_size); + /* If another thread deleted this object skip deletion. + * The refcnt on psock may or may not be zero. + */ + if (l) { + hlist_del_rcu(&link->hash_node); + smap_release_sock(psock, link->sk); + free_htab_elem(htab, link); + } + raw_spin_unlock_bh(&b->lock); } + e = psock_map_pop(sk, psock); } - write_unlock_bh(&sk->sk_callback_lock); rcu_read_unlock(); + release_sock(sk); close_fun(sk, timeout); } @@ -472,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) while (sg[i].length) { free += sg[i].length; sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); + if (!md->skb) + put_page(sg_page(&sg[i])); sg[i].length = 0; sg[i].page_link = 0; sg[i].offset = 0; @@ -481,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) if (i == MAX_SKB_FRAGS) i = 0; } + if (md->skb) + consume_skb(md->skb); return free; } @@ -1111,8 +1213,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock, static int bpf_tcp_ulp_register(void) { - tcp_bpf_proto = tcp_prot; - tcp_bpf_proto.close = bpf_tcp_close; + build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); /* Once BPF TX ULP is registered it is never unregistered. It * will be in the ULP list for the lifetime of the system. Doing * duplicate registers is not a problem. @@ -1135,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) */ TCP_SKB_CB(skb)->bpf.sk_redir = NULL; skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); preempt_enable(); @@ -1357,7 +1458,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { tcp_cleanup_ulp(sock); + write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); clear_bit(SMAP_TX_RUNNING, &psock->state); rcu_assign_sk_user_data(sock, NULL); call_rcu_sched(&psock->rcu, smap_destroy_psock); @@ -1388,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_pointers(skb); + bpf_compute_data_end_sk_skb(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); @@ -1508,6 +1611,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node) INIT_LIST_HEAD(&psock->maps); INIT_LIST_HEAD(&psock->ingress); refcount_set(&psock->refcnt, 1); + spin_lock_init(&psock->maps_lock); rcu_assign_sk_user_data(sock, psock); sock_hold(sock); @@ -1564,18 +1668,32 @@ free_stab: return ERR_PTR(err); } -static void smap_list_remove(struct smap_psock *psock, - struct sock **entry, - struct htab_elem *hash_link) +static void smap_list_map_remove(struct smap_psock *psock, + struct sock **entry) { struct smap_psock_map_entry *e, *tmp; + spin_lock_bh(&psock->maps_lock); list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry || e->hash_link == hash_link) { + if (e->entry == entry) + list_del(&e->list); + } + spin_unlock_bh(&psock->maps_lock); +} + +static void smap_list_hash_remove(struct smap_psock *psock, + struct htab_elem *hash_link) +{ + struct smap_psock_map_entry *e, *tmp; + + spin_lock_bh(&psock->maps_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + struct htab_elem *c = rcu_dereference(e->hash_link); + + if (c == hash_link) list_del(&e->list); - break; - } } + spin_unlock_bh(&psock->maps_lock); } static void sock_map_free(struct bpf_map *map) @@ -1601,7 +1719,6 @@ static void sock_map_free(struct bpf_map *map) if (!sock) continue; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get the * sk_callback_lock before this case but after xchg happens @@ -1609,10 +1726,9 @@ static void sock_map_free(struct bpf_map *map) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, &stab->sock_map[i], NULL); + smap_list_map_remove(psock, &stab->sock_map[i]); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); @@ -1661,17 +1777,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) if (!sock) return -EINVAL; - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); if (!psock) goto out; if (psock->bpf_parse) smap_stop_sock(psock, sock); - smap_list_remove(psock, &stab->sock_map[k], NULL); + smap_list_map_remove(psock, &stab->sock_map[k]); smap_release_sock(psock, sock); out: - write_unlock_bh(&sock->sk_callback_lock); return 0; } @@ -1752,7 +1866,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, } } - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* 2. Do not allow inheriting programs if psock exists and has @@ -1789,7 +1902,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); if (!e) { err = -ENOMEM; - goto out_progs; + goto out_free; } } @@ -1809,7 +1922,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, if (err) goto out_free; smap_init_progs(psock, verdict, parse); + write_lock_bh(&sock->sk_callback_lock); smap_start_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); } /* 4. Place psock in sockmap for use and stop any programs on @@ -1819,9 +1934,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, */ if (map_link) { e->entry = map_link; + spin_lock_bh(&psock->maps_lock); list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); } - write_unlock_bh(&sock->sk_callback_lock); return err; out_free: smap_release_sock(psock, sock); @@ -1832,7 +1948,6 @@ out_progs: } if (tx_msg) bpf_prog_put(tx_msg); - write_unlock_bh(&sock->sk_callback_lock); kfree(e); return err; } @@ -1869,10 +1984,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (osock) { struct smap_psock *opsock = smap_psock_sk(osock); - write_lock_bh(&osock->sk_callback_lock); - smap_list_remove(opsock, &stab->sock_map[i], NULL); + smap_list_map_remove(opsock, &stab->sock_map[i]); smap_release_sock(opsock, osock); - write_unlock_bh(&osock->sk_callback_lock); } out: return err; @@ -1915,6 +2028,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) return 0; } +int sockmap_get_from_fd(const union bpf_attr *attr, int type, + struct bpf_prog *prog) +{ + int ufd = attr->target_fd; + struct bpf_map *map; + struct fd f; + int err; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + err = sock_map_prog(map, prog, attr->attach_type); + fdput(f); + return err; +} + static void *sock_map_lookup(struct bpf_map *map, void *key) { return NULL; @@ -1944,7 +2075,13 @@ static int sock_map_update_elem(struct bpf_map *map, return -EOPNOTSUPP; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_map_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2043,14 +2180,13 @@ free_htab: return ERR_PTR(err); } -static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) +static void __bpf_htab_free(struct rcu_head *rcu) { - return &htab->buckets[hash & (htab->n_buckets - 1)]; -} + struct bpf_htab *htab; -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &__select_bucket(htab, hash)->head; + htab = container_of(rcu, struct bpf_htab, rcu); + bpf_map_area_free(htab->buckets); + kfree(htab); } static void sock_hash_free(struct bpf_map *map) @@ -2069,16 +2205,18 @@ static void sock_hash_free(struct bpf_map *map) */ rcu_read_lock(); for (i = 0; i < htab->n_buckets; i++) { - struct hlist_head *head = select_bucket(htab, i); + struct bucket *b = __select_bucket(htab, i); + struct hlist_head *head; struct hlist_node *n; struct htab_elem *l; + raw_spin_lock_bh(&b->lock); + head = &b->head; hlist_for_each_entry_safe(l, n, head, hash_node) { struct sock *sock = l->sk; struct smap_psock *psock; hlist_del_rcu(&l->hash_node); - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get * the sk_callback_lock before this case but after xchg @@ -2086,16 +2224,15 @@ static void sock_hash_free(struct bpf_map *map) * (psock) to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, NULL, l); + smap_list_hash_remove(psock, l); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); - kfree(l); + free_htab_elem(htab, l); } + raw_spin_unlock_bh(&b->lock); } rcu_read_unlock(); - bpf_map_area_free(htab->buckets); - kfree(htab); + call_rcu(&htab->rcu, __bpf_htab_free); } static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, @@ -2122,19 +2259,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, return l_new; } -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, - u32 hash, void *key, u32 key_size) -{ - struct htab_elem *l; - - hlist_for_each_entry_rcu(l, head, hash_node) { - if (l->hash == hash && !memcmp(&l->key, key, key_size)) - return l; - } - - return NULL; -} - static inline u32 htab_map_hash(const void *key, u32 key_len) { return jhash(key, key_len, 0); @@ -2230,7 +2354,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (err) goto err; - /* bpf_map_update_elem() can be called in_irq() */ + /* psock is valid here because otherwise above *ctx_update_elem would + * have thrown an error. It is safe to skip error check. + */ + psock = smap_psock_sk(sock); raw_spin_lock_bh(&b->lock); l_old = lookup_elem_raw(head, hash, key, key_size); if (l_old && map_flags == BPF_NOEXIST) { @@ -2248,15 +2375,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto bucket_err; } - psock = smap_psock_sk(sock); - if (unlikely(!psock)) { - err = -EINVAL; - goto bucket_err; - } - - e->hash_link = l_new; - e->htab = container_of(map, struct bpf_htab, map); + rcu_assign_pointer(e->hash_link, l_new); + rcu_assign_pointer(e->htab, + container_of(map, struct bpf_htab, map)); + spin_lock_bh(&psock->maps_lock); list_add_tail(&e->list, &psock->maps); + spin_unlock_bh(&psock->maps_lock); /* add new element to the head of the list, so that * concurrent search will find it before old elem @@ -2266,19 +2390,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, psock = smap_psock_sk(l_old->sk); hlist_del_rcu(&l_old->hash_node); - smap_list_remove(psock, NULL, l_old); + smap_list_hash_remove(psock, l_old); smap_release_sock(psock, l_old->sk); free_htab_elem(htab, l_old); } raw_spin_unlock_bh(&b->lock); return 0; bucket_err: + smap_release_sock(psock, sock); raw_spin_unlock_bh(&b->lock); err: kfree(e); - psock = smap_psock_sk(sock); - if (psock) - smap_release_sock(psock, sock); return err; } @@ -2300,7 +2422,13 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + lock_sock(skops.sk); + preempt_disable(); + rcu_read_lock(); err = sock_hash_ctx_update_elem(&skops, map, key, flags); + rcu_read_unlock(); + preempt_enable(); + release_sock(skops.sk); fput(socket->file); return err; } @@ -2326,7 +2454,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct smap_psock *psock; hlist_del_rcu(&l->hash_node); - write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); /* This check handles a racing sock event that can get the * sk_callback_lock before this case but after xchg happens @@ -2334,10 +2461,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) * to be null and queued for garbage collection. */ if (likely(psock)) { - smap_list_remove(psock, NULL, l); + smap_list_hash_remove(psock, l); smap_release_sock(psock, sock); } - write_unlock_bh(&sock->sk_callback_lock); free_htab_elem(htab, l); ret = 0; } @@ -2359,10 +2485,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_bh(&b->lock); l = lookup_elem_raw(head, hash, key, key_size); sk = l ? l->sk : NULL; - raw_spin_unlock_bh(&b->lock); return sk; } @@ -2383,6 +2507,7 @@ const struct bpf_map_ops sock_hash_ops = { .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_hash_update_elem, .map_delete_elem = sock_hash_delete_elem, + .map_release_uref = sock_map_release, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 35dc466641f2..a31a1ba0f8ea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_update_elem(map, key, value, attr->flags); goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } @@ -1483,8 +1485,6 @@ out_free_tp: return err; } -#ifdef CONFIG_CGROUP_BPF - static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { @@ -1499,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_PROG_ATTACH_LAST_FIELD attach_flags -static int sockmap_get_from_fd(const union bpf_attr *attr, - int type, bool attach) -{ - struct bpf_prog *prog = NULL; - int ufd = attr->target_fd; - struct bpf_map *map; - struct fd f; - int err; - - f = fdget(ufd); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return PTR_ERR(map); - - if (attach) { - prog = bpf_prog_get_type(attr->attach_bpf_fd, type); - if (IS_ERR(prog)) { - fdput(f); - return PTR_ERR(prog); - } - } - - err = sock_map_prog(map, prog, attr->attach_type); - if (err) { - fdput(f); - if (prog) - bpf_prog_put(prog); - return err; - } - - fdput(f); - return 0; -} - #define BPF_F_ATTACH_MASK \ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) @@ -1540,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; - struct cgroup *cgrp; int ret; if (!capable(CAP_NET_ADMIN)) @@ -1577,12 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true); + ptype = BPF_PROG_TYPE_SK_MSG; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); + ptype = BPF_PROG_TYPE_SK_SKB; + break; case BPF_LIRC_MODE2: - return lirc_prog_attach(attr); + ptype = BPF_PROG_TYPE_LIRC_MODE2; + break; default: return -EINVAL; } @@ -1596,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr) return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) { - bpf_prog_put(prog); - return PTR_ERR(cgrp); + switch (ptype) { + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_SK_MSG: + ret = sockmap_get_from_fd(attr, ptype, prog); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + ret = lirc_prog_attach(attr, prog); + break; + default: + ret = cgroup_bpf_prog_attach(attr, ptype, prog); } - ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, - attr->attach_flags); if (ret) bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; } @@ -1616,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { enum bpf_prog_type ptype; - struct bpf_prog *prog; - struct cgroup *cgrp; - int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1651,29 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); + return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); - if (IS_ERR(prog)) - prog = NULL; - - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); - if (prog) - bpf_prog_put(prog); - cgroup_put(cgrp); - return ret; + return cgroup_bpf_prog_detach(attr, ptype); } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt @@ -1681,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - struct cgroup *cgrp; - int ret; - if (!capable(CAP_NET_ADMIN)) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) @@ -1711,14 +1663,9 @@ static int bpf_prog_query(const union bpf_attr *attr, default: return -EINVAL; } - cgrp = cgroup_get_from_fd(attr->query.target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - ret = cgroup_bpf_query(cgrp, attr, uattr); - cgroup_put(cgrp); - return ret; + + return cgroup_bpf_prog_query(attr, uattr); } -#endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -2365,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; -#ifdef CONFIG_CGROUP_BPF case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; @@ -2375,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr); break; -#endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e2bf834f13a..63aaac52a265 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; + /* Upon error here we cannot fall back to interpreter but + * need a hard reject of the program. Thus -EFAULT is + * propagated in any case. + */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", @@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) - return -ENOMEM; + goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; @@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); - err = -EFAULT; + err = -ENOTSUPP; goto out_free; } cond_resched(); @@ -5552,6 +5556,7 @@ out_free: if (func[i]) bpf_jit_free(func[i]); kfree(func); +out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) err = jit_subprogs(env); if (err == 0) return 0; + if (err == -EFAULT) + return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { diff --git a/kernel/fork.c b/kernel/fork.c index 9440d61b925c..1b27babc4c78 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -303,11 +303,36 @@ struct kmem_cache *files_cachep; struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -struct kmem_cache *vm_area_cachep; +static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) +{ + struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + + if (vma) + vma_init(vma, mm); + return vma; +} + +struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) +{ + struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + + if (new) { + *new = *orig; + INIT_LIST_HEAD(&new->anon_vma_chain); + } + return new; +} + +void vm_area_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vm_area_cachep, vma); +} + static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); @@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; - *tmp = *mpnt; - INIT_LIST_HEAD(&tmp->anon_vma_chain); retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; @@ -539,7 +562,7 @@ fail_uprobe_end: fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: - kmem_cache_free(vm_area_cachep, tmp); + vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); diff --git a/kernel/kthread.c b/kernel/kthread.c index 481951bf091d..486dedbd9af5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task) static void __kthread_parkme(struct kthread *self) { for (;;) { - set_current_state(TASK_PARKED); + /* + * TASK_PARKED is a special state; we must serialize against + * possible pending wakeups to avoid store-store collisions on + * task->state. + * + * Such a collision might possibly result in the task state + * changin from TASK_PARKED and us failing the + * wait_task_inactive() in kthread_park(). + */ + set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; + + complete_all(&self->parked); schedule(); } __set_current_state(TASK_RUNNING); @@ -191,11 +202,6 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -void kthread_park_complete(struct task_struct *k) -{ - complete_all(&to_kthread(k)->parked); -} - static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -319,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; + char name[TASK_COMM_LEN]; - vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + /* + * task is already visible to other tasks, so updating + * COMM must be protected. + */ + vsnprintf(name, sizeof(name), namefmt, args); + set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. @@ -461,6 +473,9 @@ void kthread_unpark(struct task_struct *k) reinit_completion(&kthread->parked); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. + */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); @@ -487,7 +502,16 @@ int kthread_park(struct task_struct *k) set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); + /* + * Wait for __kthread_parkme() to complete(), this means we + * _will_ have TASK_PARKED and are about to call schedule(). + */ wait_for_completion(&kthread->parked); + /* + * Now wait for that schedule() to complete and the task to + * get scheduled out. + */ + WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; diff --git a/kernel/memremap.c b/kernel/memremap.c index 5857267a4af5..38283363da06 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - align_start; + align_end = align_start + align_size - 1; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); @@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) mutex_lock(&pgmap_lock); error = 0; - align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { error = __radix_tree_insert(&pgmap_radix, @@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL_GPL(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); static atomic_t devmap_enable; /* @@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL_GPL(__put_devmap_managed_page); +EXPORT_SYMBOL(__put_devmap_managed_page); #endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/rseq.c b/kernel/rseq.c index 22b6acf1ad63..c6242d8594dc 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t) { u32 cpu_id = raw_smp_processor_id(); - if (__put_user(cpu_id, &t->rseq->cpu_id_start)) + if (put_user(cpu_id, &t->rseq->cpu_id_start)) return -EFAULT; - if (__put_user(cpu_id, &t->rseq->cpu_id)) + if (put_user(cpu_id, &t->rseq->cpu_id)) return -EFAULT; trace_rseq_update(t); return 0; @@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t) /* * Reset cpu_id_start to its initial state (0). */ - if (__put_user(cpu_id_start, &t->rseq->cpu_id_start)) + if (put_user(cpu_id_start, &t->rseq->cpu_id_start)) return -EFAULT; /* * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming * in after unregistration can figure out that rseq needs to be * registered again. */ - if (__put_user(cpu_id, &t->rseq->cpu_id)) + if (put_user(cpu_id, &t->rseq->cpu_id)) return -EFAULT; return 0; } @@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t) static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) { struct rseq_cs __user *urseq_cs; - unsigned long ptr; + u64 ptr; u32 __user *usig; u32 sig; int ret; - ret = __get_user(ptr, &t->rseq->rseq_cs); - if (ret) - return ret; + if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr))) + return -EFAULT; if (!ptr) { memset(rseq_cs, 0, sizeof(*rseq_cs)); return 0; } - urseq_cs = (struct rseq_cs __user *)ptr; + if (ptr >= TASK_SIZE) + return -EINVAL; + urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr; if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs))) return -EFAULT; - if (rseq_cs->version > 0) - return -EINVAL; + if (rseq_cs->start_ip >= TASK_SIZE || + rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE || + rseq_cs->abort_ip >= TASK_SIZE || + rseq_cs->version > 0) + return -EINVAL; + /* Check for overflow. */ + if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip) + return -EINVAL; /* Ensure that abort_ip is not in the critical section. */ if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset) return -EINVAL; - usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32)); + usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32)); ret = get_user(sig, usig); if (ret) return ret; @@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs) printk_ratelimited(KERN_WARNING "Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n", sig, current->rseq_sig, current->pid, usig); - return -EPERM; + return -EINVAL; } return 0; } @@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags) int ret; /* Get thread flags. */ - ret = __get_user(flags, &t->rseq->flags); + ret = get_user(flags, &t->rseq->flags); if (ret) return ret; @@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t) * of code outside of the rseq assembly block. This performs * a lazy clear of the rseq_cs field. * - * Set rseq_cs to NULL with single-copy atomicity. + * Set rseq_cs to NULL. */ - return __put_user(0UL, &t->rseq->rseq_cs); + if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64))) + return -EFAULT; + return 0; } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 78d8facba456..fe365c9a08e9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7,7 +7,6 @@ */ #include "sched.h" -#include <linux/kthread.h> #include <linux/nospec.h> #include <linux/kcov.h> @@ -2724,28 +2723,20 @@ static struct rq *finish_task_switch(struct task_struct *prev) membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); } - if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) { - switch (prev_state) { - case TASK_DEAD: - if (prev->sched_class->task_dead) - prev->sched_class->task_dead(prev); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - - /* Task is done with its stack. */ - put_task_stack(prev); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); - put_task_struct(prev); - break; + /* Task is done with its stack. */ + put_task_stack(prev); - case TASK_PARKED: - kthread_park_complete(prev); - break; - } + put_task_struct(prev); } tick_nohz_task_switch(); @@ -3113,7 +3104,9 @@ static void sched_tick_remote(struct work_struct *work) struct tick_work *twork = container_of(dwork, struct tick_work, work); int cpu = twork->cpu; struct rq *rq = cpu_rq(cpu); + struct task_struct *curr; struct rq_flags rf; + u64 delta; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3122,24 +3115,28 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) { - struct task_struct *curr; - u64 delta; + if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + goto out_requeue; - rq_lock_irq(rq, &rf); - update_rq_clock(rq); - curr = rq->curr; - delta = rq_clock_task(rq) - curr->se.exec_start; + rq_lock_irq(rq, &rf); + curr = rq->curr; + if (is_idle_task(curr)) + goto out_unlock; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); - curr->sched_class->task_tick(rq, curr, 0); - rq_unlock_irq(rq, &rf); - } + update_rq_clock(rq); + delta = rq_clock_task(rq) - curr->se.exec_start; + + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + curr->sched_class->task_tick(rq, curr, 0); + +out_unlock: + rq_unlock_irq(rq, &rf); +out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3cde46483f0a..c907fde01eaa 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -192,7 +192,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - if (rq->rt.rt_nr_running) + if (rt_rq_is_runnable(&rq->rt)) return sg_cpu->max; /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fbfc3f1d368a..10c7b51c0d1f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2290,8 +2290,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) if (task_on_rq_queued(p) && p->dl.dl_runtime) task_non_contending(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + /* + * Inactive timer is armed. However, p is leaving DEADLINE and + * might migrate away from this rq while continuing to run on + * some other class. We need to remove its contribution from + * this rq running_bw now, or sub_rq_bw (below) will complain. + */ + if (p->dl.dl_non_contending) + sub_running_bw(&p->dl, &rq->dl); sub_rq_bw(&p->dl, &rq->dl); + } /* * We cannot use inactive_task_timer() to invoke sub_running_bw() diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1866e64792a7..2f0a0be4d344 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3982,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) if (!sched_feat(UTIL_EST)) return; - /* - * Update root cfs_rq's estimated utilization - * - * If *p is the last task then the root cfs_rq's estimated utilization - * of a CPU is 0 by definition. - */ - ue.enqueued = 0; - if (cfs_rq->nr_running) { - ue.enqueued = cfs_rq->avg.util_est.enqueued; - ue.enqueued -= min_t(unsigned int, ue.enqueued, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); - } + /* Update root cfs_rq's estimated utilization */ + ue.enqueued = cfs_rq->avg.util_est.enqueued; + ue.enqueued -= min_t(unsigned int, ue.enqueued, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); /* @@ -4590,6 +4582,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4612,6 +4605,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); u64 amount = 0, min_amount, expires; + int expires_seq; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4628,6 +4622,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } + expires_seq = cfs_b->expires_seq; expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); @@ -4637,8 +4632,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) * spread between our sched_clock and the one on which runtime was * issued. */ - if ((s64)(expires - cfs_rq->runtime_expires) > 0) + if (cfs_rq->expires_seq != expires_seq) { + cfs_rq->expires_seq = expires_seq; cfs_rq->runtime_expires = expires; + } return cfs_rq->runtime_remaining > 0; } @@ -4664,12 +4661,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. It is valid to compare - * cfs_b->runtime_expires without any locks since we only care about - * exact equality, so a partial write will still work. + * whether the global deadline(cfs_b->expires_seq) has advanced. */ - - if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { + if (cfs_rq->expires_seq == cfs_b->expires_seq) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { @@ -5202,13 +5196,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { + u64 overrun; + lockdep_assert_held(&cfs_b->lock); - if (!cfs_b->period_active) { - cfs_b->period_active = 1; - hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); - } + if (cfs_b->period_active) + return; + + cfs_b->period_active = 1; + overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); + cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); + cfs_b->expires_seq++; + hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 47556b0c9a95..572567078b60 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (!rt_se) + if (!rt_se) { dequeue_top_rt_rq(rt_rq); + /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ + cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); + } else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se, 0); } @@ -1001,8 +1004,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) sub_nr_running(rq, rt_rq->rt_nr_running); rt_rq->rt_queued = 0; - /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_util(rq, 0); } static void @@ -1014,11 +1015,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq) if (rt_rq->rt_queued) return; - if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + + if (rt_rq_throttled(rt_rq)) return; - add_nr_running(rq, rt_rq->rt_nr_running); - rt_rq->rt_queued = 1; + if (rt_rq->rt_nr_running) { + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; + } /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq, 0); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6601baf2361c..c7742dcc136c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -334,9 +334,10 @@ struct cfs_bandwidth { u64 runtime; s64 hierarchical_quota; u64 runtime_expires; + int expires_seq; - int idle; - int period_active; + short idle; + short period_active; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; @@ -551,6 +552,7 @@ struct cfs_rq { #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; + int expires_seq; u64 runtime_expires; s64 runtime_remaining; @@ -609,6 +611,11 @@ struct rt_rq { #endif }; +static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq) +{ + return rt_rq->rt_queued && rt_rq->rt_nr_running; +} + /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ diff --git a/kernel/softirq.c b/kernel/softirq.c index 900dcfee542c..75ffc1d1a2e0 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -79,12 +79,16 @@ static void wakeup_softirqd(void) /* * If ksoftirqd is scheduled, we do not want to process pending softirqs - * right now. Let ksoftirqd handle this at its own rate, to get fairness. + * right now. Let ksoftirqd handle this at its own rate, to get fairness, + * unless we're doing some of the synchronous softirqs. */ -static bool ksoftirqd_running(void) +#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) +static bool ksoftirqd_running(unsigned long pending) { struct task_struct *tsk = __this_cpu_read(ksoftirqd); + if (pending & SOFTIRQ_NOW_MASK) + return false; return tsk && (tsk->state == TASK_RUNNING); } @@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void) pending = local_softirq_pending(); - if (pending && !ksoftirqd_running()) + if (pending && !ksoftirqd_running(pending)) do_softirq_own_stack(); local_irq_restore(flags); @@ -355,7 +359,7 @@ void irq_enter(void) static inline void invoke_softirq(void) { - if (ksoftirqd_running()) + if (ksoftirqd_running(local_softirq_pending())) return; if (!force_irqthreads) { diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index f89014a2c238..1ff523dae6e2 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -270,7 +270,11 @@ unlock: goto retry; } - wake_up_q(&wakeq); + if (!err) { + preempt_disable(); + wake_up_q(&wakeq); + preempt_enable(); + } return err; } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index b7005dd21ec1..14de3727b18e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev, */ return !curdev || newdev->rating > curdev->rating || - (!cpumask_equal(curdev->cpumask, newdev->cpumask) && - !tick_check_percpu(curdev, newdev, smp_processor_id())); + !cpumask_equal(curdev->cpumask, newdev->cpumask); } /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index efed9c1cfb7e..caf9cbf35816 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, op->saved_func(ip, parent_ip, op, regs); } -/** - * clear_ftrace_function - reset the ftrace function - * - * This NULLs the ftrace function and in essence stops - * tracing. There may be lag - */ -void clear_ftrace_function(void) -{ - ftrace_trace_function = ftrace_stub; -} - static void ftrace_sync(struct work_struct *work) { /* @@ -6689,7 +6678,7 @@ void ftrace_kill(void) { ftrace_disabled = 1; ftrace_enabled = 0; - clear_ftrace_function(); + ftrace_trace_function = ftrace_stub; } /** diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6a46af21765c..0b0b688ea166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer) } /** + * ring_buffer_record_is_set_on - return true if the ring buffer is set writable + * @buffer: The ring buffer to see if write is set enabled + * + * Returns true if the ring buffer is set writable by ring_buffer_record_on(). + * Note that this does NOT mean it is in a writable state. + * + * It may return true when the ring buffer has been disabled by + * ring_buffer_record_disable(), as that is a temporary disabling of + * the ring buffer. + */ +int ring_buffer_record_is_set_on(struct ring_buffer *buffer) +{ + return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a0079b4c7a49..823687997b01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); + /* Inherit the recordable setting from trace_buffer */ + if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + ring_buffer_record_on(tr->max_buffer.buffer); + else + ring_buffer_record_off(tr->max_buffer.buffer); + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); @@ -2953,6 +2959,7 @@ out_nobuffer: } EXPORT_SYMBOL_GPL(trace_vbprintk); +__printf(3, 0) static int __trace_array_vprintk(struct ring_buffer *buffer, unsigned long ip, const char *fmt, va_list args) @@ -3007,12 +3014,14 @@ out_nobuffer: return len; } +__printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); } +__printf(3, 0) int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { @@ -3028,6 +3037,7 @@ int trace_array_printk(struct trace_array *tr, return ret; } +__printf(3, 4) int trace_array_printk_buf(struct ring_buffer *buffer, unsigned long ip, const char *fmt, ...) { @@ -3043,6 +3053,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer, return ret; } +__printf(2, 0) int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(&global_trace, ip, fmt, args); @@ -3360,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, print_event_info(buf, m); - seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | | %s | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, @@ -3381,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file tgid ? tgid_space : space); seq_printf(m, "# %s||| / delay\n", tgid ? tgid_space : space); - seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", + seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", tgid ? " TGID " : space); - seq_printf(m, "# | | | %s|||| | |\n", + seq_printf(m, "# | | %s | |||| | |\n", tgid ? " | " : space); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 630c5a24b2b2..f8f86231ad90 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -583,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit) static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { - if (iter->buffer_iter && iter->buffer_iter[cpu]) - return iter->buffer_iter[cpu]; - return NULL; + return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL; } int tracer_init(struct tracer *t, struct trace_array *tr); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 0dceb77d1d42..893a206bcba4 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1701,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe) * @filter_str: filter string * @set_str: remember @filter_str and enable detailed error in filter * @filterp: out param for created filter (always updated on return) + * Must be a pointer that references a NULL pointer. * * Creates a filter for @call with @filter_str. If @set_str is %true, * @filter_str is copied and recorded in the new filter. @@ -1718,6 +1719,10 @@ static int create_filter(struct trace_event_call *call, struct filter_parse_error *pe = NULL; int err; + /* filterp must point to NULL */ + if (WARN_ON(*filterp)) + *filterp = NULL; + err = create_filter_start(filter_string, set_str, &pe, filterp); if (err) return err; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 046c716a6536..aae18af94c94 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var) else if (system) snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event); else - strncpy(err, var, MAX_FILTER_STR_VAL); + strscpy(err, var, MAX_FILTER_STR_VAL); hist_err(str, err); } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d18249683682..5dea177cef53 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops, goto out_free; out_reg: + /* Up the trigger_data count to make sure reg doesn't free it on failure */ + event_trigger_init(trigger_ops, trigger_data); ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); /* * The above returns on success the # of functions enabled, @@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops, * Consider no functions a failure too. */ if (!ret) { + cmd_ops->unreg(glob, trigger_ops, trigger_data, file); ret = -ENOENT; - goto out_free; - } else if (ret < 0) - goto out_free; - ret = 0; + } else if (ret > 0) + ret = 0; + + /* Down the counter of trigger_data or free it if not used anymore */ + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out; } + /* Up the trigger_data count to make sure nothing frees it on failure */ + event_trigger_init(trigger_ops, trigger_data); + if (trigger) { number = strsep(&trigger, ":"); @@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); - kfree(trigger_data); + event_trigger_free(trigger_ops, trigger_data); kfree(enable_data); goto out; } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 23c0b0cb5fb9..169b3c44ee97 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter, struct ftrace_graph_ret *graph_ret; struct ftrace_graph_ent *call; unsigned long long duration; + int cpu = iter->cpu; int i; graph_ret = &ret_entry->ret; @@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter, if (data) { struct fgraph_cpu_data *cpu_data; - int cpu = iter->cpu; cpu_data = per_cpu_ptr(data->cpu_data, cpu); @@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter, trace_seq_printf(s, "%ps();\n", (void *)call->func); + print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET, + cpu, iter->ent->pid, flags); + return trace_handle_return(s); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index daa81571b22a..6b71860f3998 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { + struct event_file_link *link = NULL; int ret = 0; if (file) { - struct event_file_link *link; - link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; @@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) else ret = enable_kprobe(&tk->rp.kp); } + + if (ret) { + if (file) { + /* Notice the if is true on not WARN() */ + if (!WARN_ON_ONCE(!link)) + list_del_rcu(&link->list); + kfree(link); + tk->tp.flags &= ~TP_FLAG_TRACE; + } else { + tk->tp.flags &= ~TP_FLAG_PROFILE; + } + } out: return ret; } @@ -1480,8 +1491,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, } ret = __register_trace_kprobe(tk); - if (ret < 0) + if (ret < 0) { + kfree(tk->tp.call.print_fmt); goto error; + } return &tk->tp.call; error: @@ -1501,6 +1514,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call) } __unregister_trace_kprobe(tk); + + kfree(tk->tp.call.print_fmt); free_trace_kprobe(tk); } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 90db994ac900..1c8e30fda46a 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%16s-%-5d [%03d] ", - comm, entry->pid, iter->cpu); + trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { unsigned int tgid = trace_find_tgid(entry->pid); @@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter) trace_seq_printf(s, "(%5d) ", tgid); } + trace_seq_printf(s, "[%03d] ", iter->cpu); + if (tr->trace_flags & TRACE_ITER_IRQ_INFO) trace_print_lat_fmt(s, entry); diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index c253c1b46c6b..befb127507c0 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" - depends on SLUB || (SLAB && !DEBUG_SLAB) + depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) select SLUB_DEBUG if SLUB select CONSTRUCTORS select STACKDEPOT diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 7e43cd54c84c..8be175df3075 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset, return ret; } +static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, + struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + size_t n, off, xfer = 0; + int idx; + + if (!sanity(i)) + return 0; + + bytes = n = push_pipe(i, bytes, &idx, &off); + if (unlikely(!n)) + return 0; + for ( ; n; idx = next_idx(idx, pipe), off = 0) { + size_t chunk = min_t(size_t, n, PAGE_SIZE - off); + unsigned long rem; + + rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr, + chunk); + i->idx = idx; + i->iov_offset = off + chunk - rem; + xfer += chunk - rem; + if (rem) + break; + n -= chunk; + addr += chunk; + } + i->count -= xfer; + return xfer; +} + +/** + * _copy_to_iter_mcsafe - copy to user with source-read error exception handling + * @addr: source kernel address + * @bytes: total transfer length + * @iter: destination iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_to_iter() for protecting read/write to persistent memory. + * Unless / until an architecture can guarantee identical performance + * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a + * performance regression to switch more users to the mcsafe version. + * + * Otherwise, the main differences between this and typical _copy_to_iter(). + * + * * Typical tail/residue handling after a fault retries the copy + * byte-by-byte until the fault happens again. Re-triggering machine + * checks is potentially fatal so the implementation uses source + * alignment and poison alignment assumptions to avoid re-triggering + * hardware exceptions. + * + * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. + * Compare to copy_to_iter() where only ITER_IOVEC attempts might return + * a short copy. + * + * See MCSAFE_TEST for self-test. + */ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) { - WARN_ON(1); - return 0; - } + if (unlikely(i->type & ITER_PIPE)) + return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, @@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/** + * _copy_from_iter_flushcache - write destination through cpu cache + * @addr: destination kernel address + * @bytes: total transfer length + * @iter: source iterator + * + * The pmem driver arranges for filesystem-dax to use this facility via + * dax_copy_from_iter() for ensuring that writes to persistent memory + * are flushed through the CPU cache. It is differentiated from + * _copy_from_iter_nocache() in that guarantees all data is flushed for + * all iterator types. The _copy_from_iter_nocache() only attempts to + * bypass the cache for the ITER_IOVEC case, and on some archs may use + * instructions that strand dirty-data in the cache. + */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 9427b5766134..e5c8586cf717 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) skip++; if (list == iter->list) { iter->p = p; - skip = skip; + iter->skip = skip; goto found; } } @@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop); static size_t rounded_hashtable_size(const struct rhashtable_params *params) { - return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), - (unsigned long)params->min_size); + size_t retsize; + + if (params->nelem_hint) + retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3), + (unsigned long)params->min_size); + else + retsize = max(HASH_DEFAULT_SIZE, + (unsigned long)params->min_size); + + return retsize; } static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) @@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht, struct bucket_table *tbl; size_t size; - size = HASH_DEFAULT_SIZE; - if ((!params->key_len && !params->obj_hashfn) || (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; @@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht, ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); - if (params->nelem_hint) - size = rounded_hashtable_size(&ht->p); + size = rounded_hashtable_size(&ht->p); if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul); @@ -1143,13 +1148,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg) { - struct bucket_table *tbl; + struct bucket_table *tbl, *next_tbl; unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); +restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; @@ -1166,7 +1172,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, } } + next_tbl = rht_dereference(tbl->future_tbl, ht); bucket_table_free(tbl); + if (next_tbl) { + tbl = next_tbl; + goto restart; + } mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 60aedc879361..08d3d59dca17 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = { { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Ctx heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }, { 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) } }, .fill_helper = bpf_fill_maxinsns6, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Call heavy transformations", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, +#else CLASSIC | FLAG_NO_DATA, +#endif { }, { { 1, 0 }, { 10, 0 } }, .fill_helper = bpf_fill_maxinsns7, + .expected_errcode = -ENOTSUPP, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Jump heavy test", @@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: exec all MSH", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { 0xfa, 0xfb, 0xfc, 0xfd, }, { { 4, 0xababab83 } }, .fill_helper = bpf_fill_maxinsns13, + .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: ld_abs+get_processor_id", { }, +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390) + CLASSIC | FLAG_EXPECTED_FAIL, +#else CLASSIC, +#endif { }, { { 1, 0xbee } }, .fill_helper = bpf_fill_ld_abs_get_processor_id, + .expected_errcode = -ENOTSUPP, }, /* * LD_IND / LD_ABS on fragmented SKBs diff --git a/mm/debug.c b/mm/debug.c index 56e2d9125ea5..38c926520c97 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -43,12 +43,25 @@ const struct trace_print_flags vmaflag_names[] = { void __dump_page(struct page *page, const char *reason) { + bool page_poisoned = PagePoisoned(page); + int mapcount; + + /* + * If struct page is poisoned don't access Page*() functions as that + * leads to recursive loop. Page*() check for poisoned pages, and calls + * dump_page() when detected. + */ + if (page_poisoned) { + pr_emerg("page:%px is uninitialized and poisoned", page); + goto hex_only; + } + /* * Avoid VM_BUG_ON() in page_mapcount(). * page->_mapcount space in struct page is used by sl[aou]b pages to * encode own info. */ - int mapcount = PageSlab(page) ? 0 : page_mapcount(page); + mapcount = PageSlab(page) ? 0 : page_mapcount(page); pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx", page, page_ref_count(page), mapcount, @@ -60,6 +73,7 @@ void __dump_page(struct page *page, const char *reason) pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags); +hex_only: print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, sizeof(struct page), false); @@ -68,7 +82,7 @@ void __dump_page(struct page *page, const char *reason) pr_alert("page dumped because: %s\n", reason); #ifdef CONFIG_MEMCG - if (page->mem_cgroup) + if (!page_poisoned && page->mem_cgroup) pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup); #endif } @@ -1238,8 +1238,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) int locked = 0; long ret = 0; - VM_BUG_ON(start & ~PAGE_MASK); - VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; for (nstart = start; nstart < end; nstart = nend) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cd7c1a57a14..25346bd99364 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (vma_is_dax(vma)) return; page = pmd_page(_pmd); + if (!PageDirty(page) && pmd_dirty(_pmd)) + set_page_dirty(page); if (!PageReferenced(page) && pmd_young(_pmd)) SetPageReferenced(page); page_remove_rmap(page, true); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3612fbb32e9d..039ddbc574e9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2163,6 +2163,7 @@ static void __init gather_bootmem_prealloc(void) */ if (hstate_is_gigantic(h)) adjust_managed_page_count(page, 1 << h->order); + cond_resched(); } } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index f185455b3406..c3bd5209da38 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -619,12 +619,13 @@ void kasan_kfree_large(void *ptr, unsigned long ip) int kasan_module_alloc(void *addr, size_t size) { void *ret; + size_t scaled_size; size_t shadow_size; unsigned long shadow_start; shadow_start = (unsigned long)kasan_mem_to_shadow(addr); - shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT, - PAGE_SIZE); + scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT; + shadow_size = round_up(scaled_size, PAGE_SIZE); if (WARN_ON(!PAGE_ALIGNED(shadow_start))) return -EINVAL; diff --git a/mm/memblock.c b/mm/memblock.c index 03d48d8835ba..4b5d245fafc1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,6 +20,7 @@ #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> +#include <linux/bootmem.h> #include <asm/sections.h> #include <linux/io.h> @@ -227,7 +228,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, * so we use WARN_ONCE() here to see the stack trace if * fail happens. */ - WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n"); + WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE), + "memblock: bottom-up allocation failed, memory hotremove may be affected\n"); } return __memblock_find_range_top_down(start, end, size, align, nid, @@ -1224,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } +#if defined(CONFIG_NO_BOOTMEM) /** * memblock_virt_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes @@ -1431,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid( (u64)max_addr); return NULL; } +#endif /** * __memblock_free_early - free boot memory block diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e6f0d5ef320a..8c0280b3143e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) int nid; int i; - while ((memcg = parent_mem_cgroup(memcg))) { + for (; memcg; memcg = parent_mem_cgroup(memcg)) { for_each_node(nid) { mz = mem_cgroup_nodeinfo(memcg, nid); for (i = 0; i <= DEF_PRIORITY; i++) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9ac49ef17b4e..01f1a14facc4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); + vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ diff --git a/mm/mmap.c b/mm/mmap.c index d1eb87ef4b1a..17bbf4d3e24f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -182,12 +182,12 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return next; } -static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf); - +static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, + struct list_head *uf); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long retval; @@ -245,7 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) goto out; /* Ok, looks good - let it rip. */ - if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0) + if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) goto out; set_brk: @@ -911,7 +911,7 @@ again: anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); - kmem_cache_free(vm_area_cachep, next); + vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter @@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { if (vm_flags & VM_DENYWRITE) { @@ -1780,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, error = shmem_zero_setup(vma); if (error) goto free_vma; + } else { + vma_set_anonymous(vma); } vma_link(mm, vma, prev, rb_link, rb_parent); @@ -1832,7 +1832,7 @@ allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); @@ -2620,15 +2620,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return err; } - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) return -ENOMEM; - /* most fields are the same, copy all, and then fixup */ - *new = *vma; - - INIT_LIST_HEAD(&new->anon_vma_chain); - if (new_below) new->vm_end = addr; else { @@ -2669,7 +2664,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: - kmem_cache_free(vm_area_cachep, new); + vm_area_free(new); return err; } @@ -2929,21 +2924,14 @@ static inline void verify_mm_writelocked(struct mm_struct *mm) * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ -static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf) +static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long len; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; - len = PAGE_ALIGN(request); - if (len < request) - return -ENOMEM; - if (!len) - return 0; - /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; @@ -2991,14 +2979,13 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long /* * create a vma struct for an anonymous mapping */ - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; + vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; @@ -3015,18 +3002,20 @@ out: return 0; } -static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf) -{ - return do_brk_flags(addr, len, 0, uf); -} - -int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags) +int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; + unsigned long len; int ret; bool populate; LIST_HEAD(uf); + len = PAGE_ALIGN(request); + if (len < request) + return -ENOMEM; + if (!len) + return 0; + if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -3207,16 +3196,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { - new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new_vma = vm_area_dup(vma); if (!new_vma) goto out; - *new_vma = *vma; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; - INIT_LIST_HEAD(&new_vma->anon_vma_chain); if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) @@ -3231,7 +3218,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: - kmem_cache_free(vm_area_cachep, new_vma); + vm_area_free(new_vma); out: return NULL; } @@ -3355,12 +3342,10 @@ static struct vm_area_struct *__install_special_mapping( int ret; struct vm_area_struct *vma; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&vma->anon_vma_chain); - vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; @@ -3381,7 +3366,7 @@ static struct vm_area_struct *__install_special_mapping( return vma; out: - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ERR_PTR(ret); } diff --git a/mm/nommu.c b/mm/nommu.c index 4452d8bd9ae4..9fc9e43335b6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); } /* @@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma, if (ret < len) memset(base + ret, 0, len - ret); + } else { + vma_set_anonymous(vma); } return 0; @@ -1204,7 +1206,7 @@ unsigned long do_mmap(struct file *file, if (!region) goto error_getting_region; - vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); + vma = vm_area_alloc(current->mm); if (!vma) goto error_getting_vma; @@ -1212,7 +1214,6 @@ unsigned long do_mmap(struct file *file, region->vm_flags = vm_flags; region->vm_pgoff = pgoff; - INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_flags = vm_flags; vma->vm_pgoff = pgoff; @@ -1368,7 +1369,7 @@ error: kmem_cache_free(vm_region_jar, region); if (vma->vm_file) fput(vma->vm_file); - kmem_cache_free(vm_area_cachep, vma); + vm_area_free(vma); return ret; sharing_violation: @@ -1469,14 +1470,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (!region) return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); + new = vm_area_dup(vma); if (!new) { kmem_cache_free(vm_region_jar, region); return -ENOMEM; } /* most fields are the same, copy all, and then fixup */ - *new = *vma; *region = *vma->vm_region; new->vm_region = region; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1521100f1e63..a790ef4be74e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6383,7 +6383,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -#ifdef CONFIG_HAVE_MEMBLOCK +#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) /* * Only struct pages that are backed by physical memory are zeroed and * initialized by going through __init_single_page(). But, there are some @@ -6421,7 +6421,7 @@ void __paginginit zero_resv_unavail(void) if (pgcnt) pr_info("Reserved but unavailable: %lld pages", pgcnt); } -#endif /* CONFIG_HAVE_MEMBLOCK */ +#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -6847,6 +6847,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); + zero_resv_unavail(); for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); free_area_init_node(nid, NULL, @@ -6857,7 +6858,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) node_set_state(nid, N_MEMORY); check_for_memory(pgdat, nid); } - zero_resv_unavail(); } static int __init cmdline_parse_core(char *p, unsigned long *core, @@ -7033,9 +7033,9 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) void __init free_area_init(unsigned long *zones_size) { + zero_resv_unavail(); free_area_init_node(0, zones_size, __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); - zero_resv_unavail(); } static int page_alloc_cpu_dead(unsigned int cpu) diff --git a/mm/rmap.c b/mm/rmap.c index 6db729dc4c50..eb477809a5c0 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -64,6 +64,7 @@ #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> +#include <linux/userfaultfd_k.h> #include <asm/tlbflush.h> @@ -1481,11 +1482,16 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, set_pte_at(mm, address, pvmw.pte, pteval); } - } else if (pte_unused(pteval)) { + } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. + * A future reference will then fault in a new zero + * page. When userfaultfd is active, we must not drop + * this page though, as its main user (postcopy + * migration) will not expect userfaults on already + * copied pages. */ dec_mm_counter(mm, mm_counter(page)); /* We have to invalidate as we cleared the pte */ diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..41b9bbf24e16 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma, { /* Create a pseudo vma that just contains the policy */ memset(vma, 0, sizeof(*vma)); + vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); diff --git a/mm/zswap.c b/mm/zswap.c index 7d34e69507e3..cd91fd9d96b8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, ret = -ENOMEM; goto reject; } + + /* A second zswap_is_full() check after + * zswap_shrink() to make sure it's now + * under the max_pool_percent + */ + if (zswap_is_full()) { + ret = -ENOMEM; + goto reject; + } } /* allocate entry */ diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 73a65789271b..8ccee3d01822 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/9p/client.c b/net/9p/client.c index 18c5271910dc..5c1343195292 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -225,7 +225,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) } free_and_return: - v9fs_put_trans(clnt->trans_mod); + if (ret) + v9fs_put_trans(clnt->trans_mod); kfree(tmp_options); return ret; } diff --git a/net/Makefile b/net/Makefile index 13ec0d5415c7..bdaf53925acd 100644 --- a/net/Makefile +++ b/net/Makefile @@ -20,11 +20,7 @@ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ -ifneq ($(CC_CAN_LINK),y) -$(warning CC cannot link executables. Skipping bpfilter.) -else obj-$(CONFIG_BPFILTER) += bpfilter/ -endif obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index be09a9883825..73bf6a93a3cf 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -2732,7 +2732,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -2780,6 +2780,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index ec93337ee259..6baec4e68898 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -927,7 +927,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -995,6 +995,8 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 4229b01ac7b5..87479c60670e 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -19,6 +19,7 @@ #include "debugfs.h" #include "main.h" +#include <linux/dcache.h> #include <linux/debugfs.h> #include <linux/err.h> #include <linux/errno.h> @@ -344,6 +345,25 @@ out: } /** + * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif + * @hard_iface: hard interface which was renamed + */ +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ + const char *name = hard_iface->net_dev->name; + struct dentry *dir; + struct dentry *d; + + dir = hard_iface->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_hardif() - delete the base directory for a hard interface * in debugfs. * @hard_iface: hard interface which is deleted. @@ -414,6 +434,26 @@ out: } /** + * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif + * @dev: net_device which was renamed + */ +void batadv_debugfs_rename_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *name = dev->name; + struct dentry *dir; + struct dentry *d; + + dir = bat_priv->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries * @dev: netdev struct of the soft interface */ diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 37b069698b04..08a592ffbee5 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -30,8 +30,10 @@ struct net_device; void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_rename_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #else @@ -49,6 +51,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev) return 0; } +static inline void batadv_debugfs_rename_meshif(struct net_device *dev) +{ +} + static inline void batadv_debugfs_del_meshif(struct net_device *dev) { } @@ -60,6 +66,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) } static inline +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +static inline void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) { } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c405d15befd6..2f0d42f2f913 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -989,6 +989,32 @@ void batadv_hardif_remove_interfaces(void) rtnl_unlock(); } +/** + * batadv_hard_if_event_softif() - Handle events for soft interfaces + * @event: NETDEV_* event to handle + * @net_dev: net_device which generated an event + * + * Return: NOTIFY_* result + */ +static int batadv_hard_if_event_softif(unsigned long event, + struct net_device *net_dev) +{ + struct batadv_priv *bat_priv; + + switch (event) { + case NETDEV_REGISTER: + batadv_sysfs_add_meshif(net_dev); + bat_priv = netdev_priv(net_dev); + batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); + break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_meshif(net_dev); + break; + } + + return NOTIFY_DONE; +} + static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -997,12 +1023,8 @@ static int batadv_hard_if_event(struct notifier_block *this, struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; - if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) { - batadv_sysfs_add_meshif(net_dev); - bat_priv = netdev_priv(net_dev); - batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); - return NOTIFY_DONE; - } + if (batadv_softif_is_valid(net_dev)) + return batadv_hard_if_event_softif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER || @@ -1051,6 +1073,9 @@ static int batadv_hard_if_event(struct notifier_block *this, if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_hardif(hard_iface); + break; default: break; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 3986551397ca..12a2b7d21376 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1705,7 +1705,9 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, ether_addr_copy(common->addr, tt_addr); common->vid = vid; - common->flags = flags; + if (!is_multicast_ether_addr(common->addr)) + common->flags = flags & (~BATADV_TT_SYNC_MASK); + tt_global_entry->roam_at = 0; /* node must store current time in case of roaming. This is * needed to purge this entry out on timeout (if nobody claims @@ -1768,7 +1770,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags & (~BATADV_TT_SYNC_MASK); + if (!is_multicast_ether_addr(common->addr)) + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 68c3578343b4..22a78eedf4b1 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -96,6 +96,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; u32 retval, duration; + int hh_len = ETH_HLEN; struct sk_buff *skb; void *data; int ret; @@ -131,12 +132,22 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reset_network_header(skb); if (is_l2) - __skb_push(skb, ETH_HLEN); + __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); retval = bpf_test_run(prog, skb, repeat, &duration); - if (!is_l2) - __skb_push(skb, ETH_HLEN); + if (!is_l2) { + if (skb_headroom(skb) < hh_len) { + int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); + + if (pskb_expand_head(skb, nhead, 0, GFP_USER)) { + kfree_skb(skb); + return -ENOMEM; + } + } + memset(__skb_push(skb, hh_len), 0, hh_len); + } + size = skb->len; /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index a948b072c28f..76deb6615883 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -1,6 +1,5 @@ menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" - default n depends on NET && BPF && INET help This builds experimental bpfilter framework that is aiming to @@ -9,6 +8,7 @@ menuconfig BPFILTER if BPFILTER config BPFILTER_UMH tristate "bpfilter kernel module with user mode helper" + depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC)) default m help This builds bpfilter kernel module with embedded user mode helper diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index 051dc18b8ccb..39c6980b5d99 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y) HOSTLDFLAGS += -static endif -# a bit of elf magic to convert bpfilter_umh binary into a binary blob -# inside bpfilter_umh.o elf file referenced by -# _binary_net_bpfilter_bpfilter_umh_start symbol -# which bpfilter_kern.c passes further into umh blob loader at run-time -quiet_cmd_copy_umh = GEN $@ - cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ - $(OBJCOPY) -I binary \ - `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \ - |awk -F' |,' '/file format/{print "-O",$$NF} \ - /^architecture:/{print "-B",$$2}'` \ - --rename-section .data=.init.rodata $< $@ - -$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh - $(call cmd,copy_umh) +$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o -bpfilter-objs += bpfilter_kern.o bpfilter_umh.o +bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 09522573f611..f0fc182d3db7 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -10,11 +10,8 @@ #include <linux/file.h> #include "msgfmt.h" -#define UMH_start _binary_net_bpfilter_bpfilter_umh_start -#define UMH_end _binary_net_bpfilter_bpfilter_umh_end - -extern char UMH_start; -extern char UMH_end; +extern char bpfilter_umh_start; +extern char bpfilter_umh_end; static struct umh_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ @@ -93,7 +90,9 @@ static int __init load_umh(void) int err; /* fork usermode process */ - err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info); + err = fork_usermode_blob(&bpfilter_umh_start, + &bpfilter_umh_end - &bpfilter_umh_start, + &info); if (err) return err; pr_info("Loaded bpfilter_umh pid %d\n", info.pid); diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S new file mode 100644 index 000000000000..40311d10d2f2 --- /dev/null +++ b/net/bpfilter/bpfilter_umh_blob.S @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + .section .init.rodata, "a" + .global bpfilter_umh_start +bpfilter_umh_start: + .incbin "net/bpfilter/bpfilter_umh" + .global bpfilter_umh_end +bpfilter_umh_end: diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..711d7156efd8 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb) caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); - if (caifd == NULL) + if (!caifd) { + rcu_read_unlock(); return; + } caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index a04e1e88bf3a..50537ff961a7 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_qlen < 0) return -EINVAL; if (dev->tx_queue_len ^ ifr->ifr_qlen) { - unsigned int orig_len = dev->tx_queue_len; - - dev->tx_queue_len = ifr->ifr_qlen; - err = call_netdevice_notifiers( - NETDEV_CHANGE_TX_QUEUE_LEN, dev); - err = notifier_to_errno(err); - if (err) { - dev->tx_queue_len = orig_len; + err = dev_change_tx_queue_len(dev, ifr->ifr_qlen); + if (err) return err; - } } return 0; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 126ffc5bc630..f64aa13811ea 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->mark && r->mark != rule->mark) continue; + if (rule->suppress_ifgroup != -1 && + r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (rule->suppress_prefixlen != -1 && + r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; @@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; + if (rule->proto && r->proto != rule->proto) + continue; + if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) @@ -645,6 +656,73 @@ errout: return err; } +static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, + struct nlattr **tb, struct fib_rule *rule) +{ + struct fib_rule *r; + + list_for_each_entry(r, &ops->rules_list, list) { + if (r->action != rule->action) + continue; + + if (r->table != rule->table) + continue; + + if (r->pref != rule->pref) + continue; + + if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) + continue; + + if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) + continue; + + if (r->mark != rule->mark) + continue; + + if (r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + + if (r->mark_mask != rule->mark_mask) + continue; + + if (r->tun_id != rule->tun_id) + continue; + + if (r->fr_net != rule->fr_net) + continue; + + if (r->l3mdev != rule->l3mdev) + continue; + + if (!uid_eq(r->uid_range.start, rule->uid_range.start) || + !uid_eq(r->uid_range.end, rule->uid_range.end)) + continue; + + if (r->ip_proto != rule->ip_proto) + continue; + + if (r->proto != rule->proto) + continue; + + if (!fib_rule_port_range_compare(&r->sport_range, + &rule->sport_range)) + continue; + + if (!fib_rule_port_range_compare(&r->dport_range, + &rule->dport_range)) + continue; + + if (!ops->compare(r, frh, tb)) + continue; + return 1; + } + return 0; +} + int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && - rule_find(ops, frh, tb, rule, user_priority)) { + rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } diff --git a/net/core/filter.c b/net/core/filter.c index e7f12e9f598c..06da770f543f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { + bool ldx_off_ok = offset <= S16_MAX; + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); - *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian); - *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, - offset); + *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, + size, 2 + endian + (!ldx_off_ok * 2)); + if (ldx_off_ok) { + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_D, offset); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_TMP, 0); + } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); @@ -1762,6 +1772,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +static inline int sk_skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + int err = __bpf_try_make_writable(skb, write_len); + + bpf_compute_data_end_sk_skb(skb); + return err; +} + +BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto sk_skb_pull_data_proto = { + .func = sk_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -2779,7 +2820,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) static u32 __bpf_skb_max_len(const struct sk_buff *skb) { - return skb->dev->mtu + skb->dev->hard_header_len; + return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : + SKB_MAX_ALLOC; } static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) @@ -2863,8 +2905,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, - u64, flags) +static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); @@ -2900,6 +2942,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; @@ -2914,9 +2963,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, +BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { + int ret = __bpf_skb_change_tail(skb, new_len, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_tail_proto = { + .func = sk_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, + u64 flags) +{ u32 max_len = __bpf_skb_max_len(skb); u32 new_len = skb->len + head_room; int ret; @@ -2941,8 +3008,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + bpf_compute_data_pointers(skb); - return 0; + return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { @@ -2954,6 +3029,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_head_proto = { + .func = sk_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3046,12 +3138,16 @@ static int __bpf_tx_xdp(struct net_device *dev, u32 index) { struct xdp_frame *xdpf; - int sent; + int err, sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -3285,7 +3381,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, goto err; } - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) goto err; skb->dev = fwd; @@ -4073,8 +4170,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + params->ifindex = dev->ifindex; - return dev->ifindex; + return 0; } #endif @@ -4098,7 +4196,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; @@ -4123,7 +4221,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = fib_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { @@ -4135,8 +4233,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } - if (err || res.type != RTN_UNICAST) - return 0; + if (err) { + /* map fib lookup errors to RTN_ type */ + if (err == -EINVAL) + return BPF_FIB_LKUP_RET_BLACKHOLE; + if (err == -EHOSTUNREACH) + return BPF_FIB_LKUP_RET_UNREACHABLE; + if (err == -EACCES) + return BPF_FIB_LKUP_RET_PROHIBIT; + + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + + if (res.type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (res.fi->fib_nhs > 1) fib_select_path(net, &res, &fl4, NULL); @@ -4144,19 +4254,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } nh = &res.fi->fib_nh[res.nh_sel]; /* do not handle lwt encaps right now */ if (nh->nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nh->nh_dev; - if (unlikely(!dev)) - return 0; - if (nh->nh_gw) params->ipv4_dst = nh->nh_gw; @@ -4166,10 +4273,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, * rcu_read_lock_bh is not needed here */ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4190,7 +4297,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -4198,7 +4305,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !net->ipv6.devconf_all->forwarding)) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; @@ -4225,7 +4332,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict); } else { @@ -4238,11 +4345,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, } if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; + + if (unlikely(f6i->fib6_flags & RTF_REJECT)) { + switch (f6i->fib6_type) { + case RTN_BLACKHOLE: + return BPF_FIB_LKUP_RET_BLACKHOLE; + case RTN_UNREACHABLE: + return BPF_FIB_LKUP_RET_UNREACHABLE; + case RTN_PROHIBIT: + return BPF_FIB_LKUP_RET_PROHIBIT; + default: + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + } - if (unlikely(f6i->fib6_flags & RTF_REJECT || - f6i->fib6_type != RTN_UNICAST)) - return 0; + if (f6i->fib6_type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0) f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6, @@ -4252,11 +4371,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } if (f6i->fib6_nh.nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (f6i->fib6_flags & RTF_GATEWAY) *dst = f6i->fib6_nh.nh_gw; @@ -4270,10 +4389,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, */ neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, dst, dev); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4315,7 +4434,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); - int index = -EAFNOSUPPORT; + int rc = -EAFNOSUPPORT; if (plen < sizeof(*params)) return -EINVAL; @@ -4326,25 +4445,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: - index = bpf_ipv4_fib_lookup(net, params, flags, false); + rc = bpf_ipv4_fib_lookup(net, params, flags, false); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - index = bpf_ipv6_fib_lookup(net, params, flags, false); + rc = bpf_ipv6_fib_lookup(net, params, flags, false); break; #endif } - if (index > 0) { + if (!rc) { struct net_device *dev; - dev = dev_get_by_index_rcu(net, index); + dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) - index = 0; + rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; } - return index; + return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { @@ -4417,10 +4536,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = { .arg4_type = ARG_CONST_SIZE }; +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_tlvs, *srh_end, *ptr; @@ -4446,9 +4565,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, memcpy(skb->data + offset, from, len); return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { @@ -4464,7 +4580,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh; @@ -4512,9 +4627,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, default: return -EINVAL; } -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { @@ -4530,7 +4642,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_end, *srh_tlvs, *ptr; @@ -4574,9 +4685,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, srh_state->hdrlen += len; srh_state->valid = 0; return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { @@ -4587,6 +4695,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; +#endif /* CONFIG_IPV6_SEG6_BPF */ bool bpf_helper_changes_pkt_data(void *func) { @@ -4595,9 +4704,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || + func == sk_skb_change_head || func == bpf_skb_change_tail || + func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == bpf_skb_pull_data || + func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || @@ -4605,11 +4717,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || func == bpf_xdp_adjust_tail || - func == bpf_lwt_push_encap || +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || func == bpf_lwt_seg6_adjust_srh || - func == bpf_lwt_seg6_action - ) + func == bpf_lwt_seg6_action || +#endif + func == bpf_lwt_push_encap) return true; return false; @@ -4849,11 +4962,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; + return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: - return &bpf_skb_change_tail_proto; + return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: - return &bpf_skb_change_head_proto; + return &sk_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -4944,12 +5057,14 @@ static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; +#endif default: return lwt_out_func_proto(func_id, prog); } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index b2b2323bdc84..188d693cb251 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, d->lock = lock; spin_lock_bh(lock); } - if (d->tail) - return gnet_stats_copy(d, type, NULL, 0, padattr); + if (d->tail) { + int ret = gnet_stats_copy(d, type, NULL, 0, padattr); + + /* The initial attribute added in gnet_stats_copy() may be + * preceded by a padding attribute, in which case d->tail will + * end up pointing at the padding instead of the real attribute. + * Fix this so gnet_stats_finish_copy() adjusts the length of + * the right attribute. + */ + if (ret == 0 && d->tail->nla_type == padattr) + d->tail = (struct nlattr *)((char *)d->tail + + NLA_ALIGN(d->tail->nla_len)); + return ret; + } return 0; } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 68bf07206744..43a932cb609b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) struct page *page; /* Empty recycle ring */ - while ((page = ptr_ring_consume(&pool->ring))) { + while ((page = ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ if (!(page_ref_count(page) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ef61222fdef..e3f743c141b3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) return err; } - dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - - __dev_notify_flags(dev, old_flags, ~0U); + if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { + __dev_notify_flags(dev, old_flags, 0U); + } else { + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + __dev_notify_flags(dev, old_flags, ~0U); + } return 0; } EXPORT_SYMBOL(rtnl_configure_link); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c642304f178c..fb35b62af272 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->cloned = 1; n->nohdr = 0; n->peeked = 0; + C(pfmemalloc); n->destructor = NULL; C(tail); C(end); @@ -3719,6 +3720,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3752,11 +3754,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = @@ -5276,8 +5277,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, if (npages >= 1 << order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NOWARN, order); if (page) goto fill_page; diff --git a/net/core/sock.c b/net/core/sock.c index bcc41829a16d..bc2d7a37297f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, pfrag->offset += use; sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && - sg->offset + sg->length == orig_offset) { - sg->length += use; + if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; } else { sge = sg + sg_curr; sg_unmark_end(sge); @@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - prot->slab_flags, NULL); + SLAB_ACCOUNT | prot->slab_flags, + NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", @@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab) if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, - SLAB_HWCACHE_ALIGN | prot->slab_flags, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | + prot->slab_flags, prot->useroffset, prot->usersize, NULL); @@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab) kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, + SLAB_ACCOUNT | prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 40c851693f77..0c9478b91fa5 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) opt++; kdebug("options: '%s'", opt); do { + int opt_len, opt_nlen; const char *eq; - int opt_len, opt_nlen, opt_vlen, tmp; + char optval[128]; next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (opt_len <= 0 || opt_len > 128) { + if (opt_len <= 0 || opt_len > sizeof(optval)) { pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", opt_len); return -EINVAL; } - eq = memchr(opt, '=', opt_len) ?: end; - opt_nlen = eq - opt; - eq++; - opt_vlen = next_opt - eq; /* will be -1 if no value */ + eq = memchr(opt, '=', opt_len); + if (eq) { + opt_nlen = eq - opt; + eq++; + memcpy(optval, eq, next_opt - eq); + optval[next_opt - eq] = '\0'; + } else { + opt_nlen = opt_len; + optval[0] = '\0'; + } - tmp = opt_vlen >= 0 ? opt_vlen : 0; - kdebug("option '%*.*s' val '%*.*s'", - opt_nlen, opt_nlen, opt, tmp, tmp, eq); + kdebug("option '%*.*s' val '%s'", + opt_nlen, opt_nlen, opt, optval); /* see if it's an error number representing a DNS error * that's to be recorded as the result in this key */ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 && memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) { kdebug("dns error number option"); - if (opt_vlen <= 0) - goto bad_option_value; - ret = kstrtoul(eq, 10, &derrno); + ret = kstrtoul(optval, 10, &derrno); if (ret < 0) goto bad_option_value; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 275449b0d633..3297e7fa9945 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -90,12 +90,18 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) return 0; } +static int lowpan_get_iflink(const struct net_device *dev) +{ + return lowpan_802154_dev(dev)->wdev->ifindex; +} + static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, + .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b21833651394..e46cdd310e5f 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), .flowi4_scope = scope, diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..c9ec1603666b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -448,9 +448,7 @@ next_proto: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..6a7d980105f6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 85b617b655bc..28fef7d15959 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->crcount; + psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + } else { + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } in_dev_put(pmc->interface); kfree(pmc); @@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) #endif } -static void igmp_group_added(struct ip_mc_list *im) +static void igmp_group_added(struct ip_mc_list *im, unsigned int mode) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should + * not send filter-mode change record as the mode should be from + * IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + igmp_ifc_event(in_dev); #endif } @@ -1381,8 +1387,7 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ - -void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) { struct ip_mc_list *im; #ifdef CONFIG_IP_MULTICAST @@ -1394,7 +1399,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; - ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); + ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } @@ -1408,8 +1413,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ - im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_EXCLUDE] = 1; + im->sfmode = mode; + im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST @@ -1426,12 +1431,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif - igmp_group_added(im); + igmp_group_added(im, mode); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } + +void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +{ + __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) @@ -1688,7 +1698,7 @@ void ip_mc_remap(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -1751,7 +1761,7 @@ void ip_mc_up(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -2130,8 +2140,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) /* Join a multicast group */ - -int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; @@ -2172,15 +2182,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; - iml->sfmode = MCAST_EXCLUDE; + iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - ip_mc_inc_group(in_dev, addr); + __ip_mc_inc_group(in_dev, addr, mode); err = 0; done: return err; } + +/* Join ASM (Any-Source Multicast) group + */ +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +{ + return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_join_group); +/* Join SSM (Source-Specific Multicast) group + */ +int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) +{ + return __ip_mc_join_group(sk, imr, mode); +} + static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9e35b81d093..1e4cf3ab560f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) void inet_frags_exit_net(struct netns_frags *nf) { - nf->low_thresh = 0; /* prevent creation of new frags */ + nf->high_thresh = 0; /* prevent creation of new frags */ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..0e3edd25f881 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index fc32fdbeefa6..c0fe5ad996f2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > (int)skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; @@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr; mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; @@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr = psin->sin_addr; mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; greqs.gsr_interface = mreq.imr_ifindex; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ca0dad90803a..e77872c93c20 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = { .checkentry = icmp_checkentry, .proto = IPPROTO_ICMP, .family = NFPROTO_IPV4, + .me = THIS_MODULE, }, }; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 805e83ec3ad9..164714104965 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr ? laddr : iph->daddr, hp->source, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) EXPORT_SYMBOL_GPL(nf_tproxy_laddr4); struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, @@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet_lookup_listener(net, &tcp_hashinfo, skb, ip_hdrlen(skb) + - __tcp_hdrlen(tcph), + __tcp_hdrlen(hp), saddr, sport, daddr, dport, in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d06247ba08b2..5fa335fd3852 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); high = make_kgid(user_ns, urange[1]); - if (!gid_valid(low) || !gid_valid(high) || - (urange[1] < urange[0]) || gid_lt(high, low)) { + if (!gid_valid(low) || !gid_valid(high)) + return -EINVAL; + if (urange[1] < urange[0] || gid_lt(high, low)) { low = make_kgid(&init_user_ns, 1); high = make_kgid(&init_user_ns, 0); } @@ -265,8 +266,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; - int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + __le32 key[4]; + int ret, i; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) @@ -275,11 +277,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) - memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else - memset(user_key, 0, sizeof(user_key)); + memset(key, 0, sizeof(key)); rcu_read_unlock(); + for (i = 0; i < ARRAY_SIZE(key); i++) + user_key[i] = le32_to_cpu(key[i]); + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", user_key[0], user_key[1], user_key[2], user_key[3]); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); @@ -290,13 +295,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, NULL, user_key, + + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + + tcp_fastopen_reset_cipher(net, NULL, key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], + user_key[0], user_key[1], user_key[2], user_key[3], (char *)tbl.data, ret); kfree(tbl.data); return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e7b53d2a971f..4491faf83f4f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1998,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), - "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; @@ -2013,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), - "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } @@ -2562,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); + tp->copied_seq = tp->rcv_nxt; + tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -2821,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; - else if (val == 1) { + else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; - } else if (val == 0) { + } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); + } else if (val == TCP_REPAIR_OFF_NO_WP) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; @@ -3720,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err) struct request_sock *req = inet_reqsk(sk); local_bh_disable(); - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, - req); + inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 5f5e5936760e..8b637f9f23a2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -55,7 +55,6 @@ struct dctcp { u32 dctcp_alpha; u32 next_seq; u32 ce_state; - u32 delayed_ack_reserved; u32 loss_cwnd; }; @@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); - ca->delayed_ack_reserved = 0; ca->loss_cwnd = 0; ca->ce_state = 0; @@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state) } } -static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev) -{ - struct dctcp *ca = inet_csk_ca(sk); - - switch (ev) { - case CA_EVENT_DELAYED_ACK: - if (!ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 1; - break; - case CA_EVENT_NON_DELAYED_ACK: - if (ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 0; - break; - default: - /* Don't care for the rest. */ - break; - } -} - static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { switch (ev) { @@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ce_state_1_to_0(sk); break; - case CA_EVENT_DELAYED_ACK: - case CA_EVENT_NON_DELAYED_ACK: - dctcp_update_ack_reserved(sk, ev); - break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 355d3dffd021..3bcd30a2ba06 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -265,7 +266,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) * it is probably a retransmit. */ if (tp->ecn_flags & TCP_ECN_SEEN) - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); break; case INET_ECN_CE: if (tcp_ca_needs_ecn(sk)) @@ -273,7 +274,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */ - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } tp->ecn_flags |= TCP_ECN_SEEN; @@ -3181,6 +3182,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); + + /* If any of the cumulatively ACKed segments was + * retransmitted, non-SACK case cannot confirm that + * progress was due to original transmission due to + * lack of TCPCB_SACKED_ACKED bits even if some of + * the packets may have been never retransmitted. + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; @@ -4348,6 +4358,23 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); @@ -4471,8 +4498,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, tp->ooo_last_skb, - skb, &fragstolen)) { + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); @@ -4500,7 +4527,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4519,11 +4546,11 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, skb1, - skb, &fragstolen)) { + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; @@ -4892,6 +4919,7 @@ end: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; @@ -4903,6 +4931,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); @@ -4913,11 +4942,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) @@ -4932,6 +4970,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4939,20 +4978,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); @@ -4987,6 +5032,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bea17f1e8302..3b2711e33e4c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) */ if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + /* In case of repair and re-using TIME-WAIT sockets we still + * want to be sure that it is safe as above but honor the + * sequence numbers and time stamps set as part of the repair + * process. + * + * Without this check re-using a TIME-WAIT socket with TCP + * repair would accumulate a -1 on the repair assigned + * sequence number. The first time it is reused the sequence + * is -1, the second time -2, etc. This fixes that issue + * without appearing to create any others. + */ + if (likely(!tp->repair)) { + tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; + if (tp->write_seq == 0) + tp->write_seq = 1; + tp->rx_opt.ts_recent = tcptw->tw_ts_recent; + tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + } sock_hold(sktw); return 1; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e08b409c71e..c4172c1fb198 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return err; } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk) int ato = icsk->icsk_ack.ato; unsigned long timeout; - tcp_ca_event(sk, CA_EVENT_DELAYED_ACK); - if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; @@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk) if (sk->sk_state == TCP_CLOSE) return; - tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK); - /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. @@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); +} +EXPORT_SYMBOL_GPL(__tcp_send_ack); + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 92dc9e5a7ff3..69c54540d5b4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -394,7 +394,7 @@ unflush: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 0eff75525da1..b3885ca22d6f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -108,6 +108,7 @@ config IPV6_MIP6 config IPV6_ILA tristate "IPv6: Identifier Locator Addressing (ILA)" depends on NETFILTER + select DST_CACHE select LWTUNNEL ---help--- Support for IPv6 Identifier Locator Addressing (ILA). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c134286d6a41..f66a1cae3366 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->fib6_flags & noflags) != 0) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -4528,6 +4529,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags) { struct fib6_info *f6i; + u32 prio; f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, @@ -4536,13 +4538,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, if (!f6i) return -ENOENT; - if (f6i->fib6_metric != ifp->rt_priority) { + prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF; + if (f6i->fib6_metric != prio) { + /* delete old one */ + ip6_del_rt(dev_net(ifp->idev->dev), f6i); + /* add new one */ addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); - /* delete old one */ - ip6_del_rt(dev_net(ifp->idev->dev), f6i); } else { if (!expires) fib6_clean_expires(f6i); diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1323b9679cf7..1c0bb9fb76e6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -799,8 +799,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop) { struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts; - txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS, - hop, hop ? ipv6_optlen(hop) : 0); + txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop); txopt_put(old); if (IS_ERR(txopts)) return PTR_ERR(txopts); @@ -1222,8 +1221,7 @@ static int calipso_req_setattr(struct request_sock *req, if (IS_ERR(new)) return PTR_ERR(new); - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); kfree(new); @@ -1260,8 +1258,7 @@ static void calipso_req_delattr(struct request_sock *req) if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new)) return; /* Nothing to do */ - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); if (!IS_ERR(txopts)) { txopts = xchg(&req_inet->ipv6_opt, txopts); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2ee08b6a86a4..1a1f876f8e28 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= (int)skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5bc2bf3733ab..20291c2036fc 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1015,29 +1015,21 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) } EXPORT_SYMBOL_GPL(ipv6_dup_options); -static int ipv6_renew_option(void *ohdr, - struct ipv6_opt_hdr __user *newopt, int newoptlen, - int inherit, - struct ipv6_opt_hdr **hdr, - char **p) +static void ipv6_renew_option(int renewtype, + struct ipv6_opt_hdr **dest, + struct ipv6_opt_hdr *old, + struct ipv6_opt_hdr *new, + int newtype, char **p) { - if (inherit) { - if (ohdr) { - memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); - *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*hdr)); - } - } else { - if (newopt) { - if (copy_from_user(*p, newopt, newoptlen)) - return -EFAULT; - *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*hdr) > newoptlen) - return -EINVAL; - *p += CMSG_ALIGN(newoptlen); - } - } - return 0; + struct ipv6_opt_hdr *src; + + src = (renewtype == newtype ? new : old); + if (!src) + return; + + memcpy(*p, src, ipv6_optlen(src)); + *dest = (struct ipv6_opt_hdr *)*p; + *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** @@ -1063,13 +1055,11 @@ static int ipv6_renew_option(void *ohdr, */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, - struct ipv6_opt_hdr __user *newopt, int newoptlen) + int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; - int err; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) @@ -1082,8 +1072,8 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } - if (newopt && newoptlen) - tot_len += CMSG_ALIGN(newoptlen); + if (newopt) + tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; @@ -1098,29 +1088,19 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->tot_len = tot_len; p = (char *)(opt2 + 1); - err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen, - newtype != IPV6_HOPOPTS, - &opt2->hopopt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDRDSTOPTS, - &opt2->dst0opt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDR, - (struct ipv6_opt_hdr **)&opt2->srcrt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen, - newtype != IPV6_DSTOPTS, - &opt2->dst1opt, &p); - if (err) - goto out; + ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, + (opt ? opt->hopopt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, + (opt ? opt->dst0opt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDR, + (struct ipv6_opt_hdr **)&opt2->srcrt, + (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, + (opt ? opt->dst1opt : NULL), + newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + @@ -1128,37 +1108,6 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; -out: - sock_kfree_s(sk, opt2, opt2->tot_len); - return ERR_PTR(err); -} - -/** - * ipv6_renew_options_kern - replace a specific ext hdr with a new one. - * - * @sk: sock from which to allocate memory - * @opt: original options - * @newtype: option type to replace in @opt - * @newopt: new option of type @newtype to replace (kernel-mem) - * @newoptlen: length of @newopt - * - * See ipv6_renew_options(). The difference is that @newopt is - * kernel memory, rather than user memory. - */ -struct ipv6_txoptions * -ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, struct ipv6_opt_hdr *newopt, - int newoptlen) -{ - struct ipv6_txoptions *ret_val; - const mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret_val = ipv6_renew_options(sk, opt, newtype, - (struct ipv6_opt_hdr __user *)newopt, - newoptlen); - set_fs(old_fs); - return ret_val; } struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be491bf6ab6e..ef2505aefc15 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb) /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so - * get the real device index. + * get the real device index. Same is needed for replies to a link + * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX)) { + if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1fb2f3118d60..d212738e9d10 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; - struct fib6_info *iter = NULL, *match = NULL; + struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; + struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); - int append = (info->nlh && - (info->nlh->nlmsg_flags & NLM_F_APPEND)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); u16 nlflags = NLM_F_EXCL; int err; - if (append) + if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; @@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, nlflags &= ~NLM_F_EXCL; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { @@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } - - /* first route that matches */ - if (!match) - match = iter; + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) + rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; +next_iter: ins = &iter->fib6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ - if (append && match) { + if (rt->fib6_nsiblings) { + unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; - if (rt->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append a REJECT route"); - return -EINVAL; - } else if (match->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append to a REJECT route"); - return -EINVAL; + /* Find the first route that have the same metric */ + sibling = leaf; + while (sibling) { + if (sibling->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(sibling)) { + list_add_tail(&rt->fib6_siblings, + &sibling->fib6_siblings); + break; + } + sibling = rcu_dereference_protected(sibling->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } - event = FIB_EVENT_ENTRY_APPEND; - rt->fib6_nsiblings = match->fib6_nsiblings; - list_add_tail(&rt->fib6_siblings, &match->fib6_siblings); - match->fib6_nsiblings++; - /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ + fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, - &match->fib6_siblings, fib6_siblings) { + &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; - BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings); + BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); + fib6_nsiblings++; } - - rt6_multipath_rebalance(match); + BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); + rt6_multipath_rebalance(temp_sibling); } /* @@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, add: nlflags |= NLM_F_CREATE; - err = call_fib6_entry_notifiers(info->nl_net, event, rt, - extack); + err = call_fib6_entry_notifiers(info->nl_net, + FIB_EVENT_ENTRY_ADD, + rt, extack); if (err) return err; @@ -1062,7 +1087,7 @@ add: } } else { - struct fib6_info *tmp; + int nsiblings; if (!found) { if (add) @@ -1077,57 +1102,48 @@ add: if (err) return err; - /* if route being replaced has siblings, set tmp to - * last one, otherwise tmp is current route. this is - * used to set fib6_next for new route - */ - if (iter->fib6_nsiblings) - tmp = list_last_entry(&iter->fib6_siblings, - struct fib6_info, - fib6_siblings); - else - tmp = iter; - - /* insert new route */ atomic_inc(&rt->fib6_ref); rcu_assign_pointer(rt->fib6_node, fn); - rt->fib6_next = tmp->fib6_next; + rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); - if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->fib6_nsiblings; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); - /* delete old route */ - rt = iter; - - if (rt->fib6_nsiblings) { - struct fib6_info *tmp; - + if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ - list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings, - fib6_siblings) { - iter->fib6_node = NULL; - fib6_purge_rt(iter, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == iter) - fn->rr_ptr = NULL; - fib6_info_release(iter); - - rt->fib6_nsiblings--; - info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + ins = &rt->fib6_next; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + while (iter) { + if (iter->fib6_metric > rt->fib6_metric) + break; + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->fib6_next; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); + nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + } else { + ins = &iter->fib6_next; + } + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } + WARN_ON(nsiblings != 0); } - - WARN_ON(rt->fib6_nsiblings != 0); - - rt->fib6_node = NULL; - fib6_purge_rt(rt, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == rt) - fn->rr_ptr = NULL; - fib6_info_release(rt); } return 0; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c8cf2fdbb13b..cd2cfb04e5d8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -927,7 +927,6 @@ tx_err: static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device_stats *stats; @@ -1010,6 +1009,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; } } else { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a14fb4fcdf18..3168847c30d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4d780c7f0130..568ca4187cd1 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + struct ipv6_opt_hdr *new = NULL; + + /* hop-by-hop / destination options are privileged option */ + retv = -EPERM; + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) + break; /* remove any sticky options header with a zero option * length, per RFC3542. @@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, else if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) goto e_inval; - - /* hop-by-hop / destination options are privileged option */ - retv = -EPERM; - if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) - break; + else { + new = memdup_user(optval, optlen); + if (IS_ERR(new)) { + retv = PTR_ERR(new); + break; + } + if (unlikely(ipv6_optlen(new) > optlen)) { + kfree(new); + goto e_inval; + } + } opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); - opt = ipv6_renew_options(sk, opt, optname, - (struct ipv6_opt_hdr __user *)optval, - optlen); + opt = ipv6_renew_options(sk, opt, optname, new); + kfree(new); if (IS_ERR(opt)) { retv = PTR_ERR(opt); break; @@ -718,8 +729,9 @@ done: struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; - retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface, + &psin6->sin6_addr, + MCAST_INCLUDE); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index c0c74088f2af..f60f310785fd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ @@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev) return iv > 0 ? iv : 1; } -int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; @@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } mc_lst->ifindex = dev->ifindex; - mc_lst->sfmode = MCAST_EXCLUDE; + mc_lst->sfmode = mode; rwlock_init(&mc_lst->sflock); mc_lst->sflist = NULL; @@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) * now add/increase the group membership on the device */ - err = ipv6_dev_mc_inc(dev, addr); + err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); @@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } + +int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ipv6_sock_mc_join); +int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, mode); +} + /* * socket leave on multicast group */ @@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, return rv; } -static void igmp6_group_added(struct ifmcaddr6 *mc) +static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; @@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) } /* else v2 */ - mc->mca_crcount = mc->idev->mc_qrv; + /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we + * should not send filter-mode change record as the mode + * should be from IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + mc->mca_crcount = mc->idev->mc_qrv; + mld_ifc_event(mc->idev); } @@ -770,13 +790,13 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_lock_bh(&im->mca_lock); if (pmc) { im->idev = pmc->idev; - im->mca_crcount = idev->mc_qrv; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->mca_crcount; + psf->sf_crcount = idev->mc_qrv; + } else { + im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); kfree(pmc); @@ -831,7 +851,8 @@ static void ma_put(struct ifmcaddr6 *mc) } static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, - const struct in6_addr *addr) + const struct in6_addr *addr, + unsigned int mode) { struct ifmcaddr6 *mc; @@ -849,9 +870,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); - /* initial mode is (EX, empty) */ - mc->mca_sfmode = MCAST_EXCLUDE; - mc->mca_sfcount[MCAST_EXCLUDE] = 1; + mc->mca_sfmode = mode; + mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) @@ -863,7 +883,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, /* * device multicast group inc (add if not found) */ -int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; @@ -887,14 +908,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; write_unlock_bh(&idev->lock); - ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0, - NULL, 0); + ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); in6_dev_put(idev); return 0; } } - mc = mca_alloc(idev, addr); + mc = mca_alloc(idev, addr, mode); if (!mc) { write_unlock_bh(&idev->lock); in6_dev_put(idev); @@ -911,11 +931,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); mld_del_delrec(idev, mc); - igmp6_group_added(mc); + igmp6_group_added(mc, mode); ma_put(mc); return 0; } +int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +{ + return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); +} + /* * device multicast group del */ @@ -1751,7 +1776,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, psf_next = psf->sf_next; - if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { + if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } @@ -2066,7 +2091,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev) if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else - type = MLD2_CHANGE_TO_INCLUDE; + type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); spin_unlock_bh(&pmc->mca_lock); } @@ -2546,7 +2571,7 @@ void ipv6_mc_up(struct inet6_dev *idev) ipv6_mc_reset(idev); for (i = idev->mc_list; i; i = i->next) { mld_del_delrec(idev, i); - igmp6_group_added(i); + igmp6_group_added(i, i->mca_sfmode); } read_unlock_bh(&idev->lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index e640d2f3c55c..0ec273997d1d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) return; } } - if (ndopts.nd_opts_nonce) + if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7eab959734bc..daf2e9e9193d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1909,6 +1909,7 @@ static struct xt_match ip6t_builtin_mt[] __read_mostly = { .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, .family = NFPROTO_IPV6, + .me = THIS_MODULE, }, }; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e0332014c17..e4d9e6976d3c 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net) if (hdr == NULL) goto err_reg; - net->nf_frag.sysctl.frags_hdr = hdr; + net->nf_frag_frags_hdr = hdr; return 0; err_reg: @@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct ctl_table *table; - table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg; - unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr); + table = net->nf_frag_frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } @@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) fq->q.meat == fq->q.len && nf_ct_frag6_reasm(fq, skb, dev)) ret = 0; + else + skb_dst_drop(skb); out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c index bf1d6c421e3b..5dfd33af6451 100644 --- a/net/ipv6/netfilter/nf_tproxy_ipv6.c +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -55,7 +55,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto, + sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto, &iph->saddr, nf_tproxy_laddr6(skb, laddr, &iph->daddr), hp->source, @@ -72,7 +72,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6); struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, @@ -80,15 +80,20 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, - thoff + __tcp_hdrlen(tcph), + thoff + __tcp_hdrlen(hp), saddr, sport, daddr, ntohs(dport), in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 86a0e4333d42..ec18b3ce8b6d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.lastuse = jiffies; } +/* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; - fib6_info_hold(from); rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); if (from->fib6_metrics != &dst_default_metrics) { @@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) } } +/* Caller must already hold reference to @ort */ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) { struct net_device *dev = fib6_info_nh_dev(ort); @@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct net_device *dev = rt->fib6_nh.nh_dev; struct rt6_info *nrt; + if (!fib6_info_hold_safe(rt)) + return NULL; + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (nrt) ip6_rt_copy_init(nrt, rt); + else + fib6_info_release(rt); return nrt; } @@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, * Clone the route. */ + if (!fib6_info_hold_safe(ort)) + return NULL; + dev = ip6_rt_get_dev_rcu(ort); rt = ip6_dst_alloc(dev_net(dev), dev, 0); - if (!rt) + if (!rt) { + fib6_info_release(ort); return NULL; + } ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; @@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) struct net_device *dev; struct rt6_info *pcpu_rt; + if (!fib6_info_hold_safe(rt)) + return NULL; + rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); - if (!pcpu_rt) + if (!pcpu_rt) { + fib6_info_release(rt); return NULL; + } ip6_rt_copy_init(pcpu_rt, rt); pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; @@ -2486,7 +2502,7 @@ restart: out: if (ret) - dst_hold(&ret->dst); + ip6_hold_safe(net, &ret, true); else ret = ip6_create_rt_rcu(rt); @@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); + /* This fib6_info_hold() is safe here because we hold reference to rt + * and rt already holds reference to fib6_info. + */ fib6_info_hold(from); rcu_read_unlock(); @@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } - if (rt) - fib6_info_hold(rt); + if (rt && !fib6_info_hold_safe(rt)) + rt = NULL; rcu_read_unlock(); return rt; } @@ -3579,8 +3600,8 @@ restart: struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!idev || idev->cnf.accept_ra != 2)) { - fib6_info_hold(rt); + (!idev || idev->cnf.accept_ra != 2) && + fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt); goto restart; @@ -3842,7 +3863,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && - iter->fib6_nsiblings) + rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); @@ -4388,6 +4409,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, rt = NULL; goto cleanup; } + if (!rt6_qualify_for_ecmp(rt)) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, + "Device only routes can not be added for IPv6 using the multipath API."); + fib6_info_release(rt); + goto cleanup; + } rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1; @@ -4439,7 +4467,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND; nhn++; } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..558fe8cc6d43 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void) return -ENOMEM; for_each_possible_cpu(cpu) { - tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); p_tfm = per_cpu_ptr(algo->tfms, cpu); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 19ccf0dc996c..a8854dd3e9c5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -101,7 +101,7 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, if (do_flowlabel > 0) { hash = skb_get_hash(skb); - rol32(hash, 16); + hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { flowlabel = ip6_flowlabel(inner_hdr); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7efa9fd7e109..03e6b7a2bc53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb), + ntohs(th->source), + tcp_v6_iif_l3_slave(skb), tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1609,7 +1610,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb), + ntohs(th->dest), + tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0a38cc1cbebc..932985ca4e66 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); bool noencrypt = status->flag & RX_FLAG_DECRYPTED; - struct ethhdr *ehdr = eth_hdr(skb); - cfg80211_rx_control_port(dev, skb->data, skb->len, - ehdr->h_source, - be16_to_cpu(skb->protocol), noencrypt); + cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { /* deliver to local stack */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 44b5dfe8727d..fa1f1e63a264 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_reset_network_header(skb); skb_reset_mac_header(skb); + local_bh_disable(); __ieee80211_subif_start_xmit(skb, skb->dev, flags); + local_bh_enable(); return 0; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 5e2e511c4a6f..d02fbfec3783 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!sta->uploaded) continue; - if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + if (sta->sdata->vif.type != NL80211_IFTYPE_AP && + sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN) continue; for (state = IEEE80211_STA_NOTEXIST; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index dbd7d1fad277..f0a1c536ef15 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -460,6 +460,13 @@ config NF_TABLES if NF_TABLES +config NF_TABLES_SET + tristate "Netfilter nf_tables set infrastructure" + help + This option enables the nf_tables set infrastructure that allows to + look up for elements in a set and to build one-way mappings between + matchings and actions. + config NF_TABLES_INET depends on IPV6 select NF_TABLES_IPV4 @@ -493,24 +500,6 @@ config NFT_FLOW_OFFLOAD This option adds the "flow_offload" expression that you can use to choose what flows are placed into the hardware. -config NFT_SET_RBTREE - tristate "Netfilter nf_tables rbtree set module" - help - This option adds the "rbtree" set type (Red Black tree) that is used - to build interval-based sets. - -config NFT_SET_HASH - tristate "Netfilter nf_tables hash set module" - help - This option adds the "hash" set type that is used to build one-way - mappings between matchings and actions. - -config NFT_SET_BITMAP - tristate "Netfilter nf_tables bitmap set module" - help - This option adds the "bitmap" set type that is used to build sets - whose keys are smaller or equal to 16 bits. - config NFT_COUNTER tristate "Netfilter nf_tables counter module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 44449389e527..8a76dced974d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -78,7 +78,11 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o +nf_tables_set-objs := nf_tables_set_core.o \ + nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o + obj-$(CONFIG_NF_TABLES) += nf_tables.o +obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o @@ -91,9 +95,6 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o -obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o -obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o -obj-$(CONFIG_NFT_SET_BITMAP) += nft_set_bitmap.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index d8383609fe28..510039862aa9 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -47,6 +47,8 @@ struct nf_conncount_tuple { struct hlist_node node; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; + int cpu; + u32 jiffies32; }; struct nf_conncount_rb { @@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head, return false; conn->tuple = *tuple; conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; hlist_add_head(&conn->node, head); return true; } EXPORT_SYMBOL_GPL(nf_conncount_add); +static const struct nf_conntrack_tuple_hash * +find_or_evict(struct net *net, struct nf_conncount_tuple *conn) +{ + const struct nf_conntrack_tuple_hash *found; + unsigned long a, b; + int cpu = raw_smp_processor_id(); + __s32 age; + + found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); + if (found) + return found; + b = conn->jiffies32; + a = (u32)jiffies; + + /* conn might have been added just before by another cpu and + * might still be unconfirmed. In this case, nf_conntrack_find() + * returns no result. Thus only evict if this cpu added the + * stale entry or if the entry is older than two jiffies. + */ + age = a - b; + if (conn->cpu == cpu || age >= 2) { + hlist_del(&conn->node); + kmem_cache_free(conncount_conn_cachep, conn); + return ERR_PTR(-ENOENT); + } + + return ERR_PTR(-EAGAIN); +} + unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone, @@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn; - struct hlist_node *n; struct nf_conn *found_ct; + struct hlist_node *n; unsigned int length = 0; *addit = tuple ? true : false; /* check the saved connections */ hlist_for_each_entry_safe(conn, n, head, node) { - found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); - if (found == NULL) { - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + found = find_or_evict(net, conn); + if (IS_ERR(found)) { + /* Not found, but might be about to be confirmed */ + if (PTR_ERR(found) == -EAGAIN) { + length++; + if (!tuple) + continue; + + if (nf_ct_tuple_equal(&conn->tuple, tuple) && + nf_ct_zone_id(&conn->zone, conn->zone.dir) == + nf_ct_zone_id(zone, zone->dir)) + *addit = false; + } continue; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3465da2a98bd..3d5280425027 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2043,7 +2043,7 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) return -EOPNOTSUPP; /* On boot, we can set this without any fancy locking. */ - if (!nf_conntrack_htable_size) + if (!nf_conntrack_hash) return param_set_uint(val, kp); rc = kstrtouint(val, 0, &hashsize); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 551a1eddf0fa..a75b11c39312 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); + + /* Maybe someone has gotten the helper already when unhelp above. + * So need to wait it. + */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abe647d5b8c6..9ce6336d1e55 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { @@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 426457047578..a61d6df6e5f6 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, if (write) { struct ctl_table tmp = *table; + /* proc_dostring() can append to existing strings, so we need to + * initialize it as an empty string. + */ + buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) @@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { + struct ctl_table tmp = *table; + + tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) - table->data = "NONE"; + strlcpy(buf, "NONE", sizeof(buf)); else - table->data = logger->name; - r = proc_dostring(table, write, buffer, lenp, ppos); + strlcpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); + r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..f5745e4c6513 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, { ctx->net = net; ctx->family = family; + ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; @@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_base_chain *basechain; struct nft_stats *stats = NULL; struct nft_chain_hook hook; - const struct nlattr *name; struct nf_hook_ops *ops; struct nft_trans *trans; int err; @@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return PTR_ERR(stats); } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } + if (trans == NULL) + goto err; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, else nft_trans_chain_policy(trans) = -1; - name = nla[NFTA_CHAIN_NAME]; - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_trans *tmp; + char *name; + + err = -ENOMEM; + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + if (!name) + goto err; + + err = -EEXIST; + list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + if (tmp->msg_type == NFT_MSG_NEWCHAIN && + tmp->ctx.table == table && + nft_trans_chain_update(tmp) && + nft_trans_chain_name(tmp) && + strcmp(name, nft_trans_chain_name(tmp)) == 0) { + kfree(name); + goto err; + } } + + nft_trans_chain_name(trans) = name; } list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err: + free_percpu(stats); + kfree(trans); + return err; } static int nf_tables_newchain(struct net *net, struct sock *nlsk, @@ -2254,6 +2271,39 @@ done: return skb->len; } +static int nf_tables_dump_rules_start(struct netlink_callback *cb) +{ + const struct nlattr * const *nla = cb->data; + struct nft_rule_dump_ctx *ctx = NULL; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_ATOMIC); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } + } + + cb->data = ctx; + return 0; +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = cb->data; @@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { - struct nft_rule_dump_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; - - if (nla[NFTA_RULE_TABLE]) { - ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); - return -ENOMEM; - } - } - if (nla[NFTA_RULE_CHAIN]) { - ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_ATOMIC); - if (!ctx->chain) { - kfree(ctx->table); - kfree(ctx); - return -ENOMEM; - } - } - c.data = ctx; - } - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) struct nft_rule *rule; int err; + if (ctx->level == NFT_JUMP_STACK_SIZE) + return -EMLINK; + list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; @@ -3161,6 +3189,18 @@ done: return skb->len; } +static int nf_tables_dump_sets_start(struct netlink_callback *cb) +{ + struct nft_ctx *ctx_dump = NULL; + + ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); + if (ctx_dump == NULL) + return -ENOMEM; + + cb->data = ctx_dump; + return 0; +} + static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .data = &ctx, .module = THIS_MODULE, }; - struct nft_ctx *ctx_dump; - - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); - if (ctx_dump == NULL) - return -ENOMEM; - - *ctx_dump = ctx; - c.data = ctx_dump; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -3849,6 +3883,15 @@ nla_put_failure: return -ENOSPC; } +static int nf_tables_dump_set_start(struct netlink_callback *cb) +{ + struct nft_set_dump_ctx *dump_ctx = cb->data; + + cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); + + return cb->data ? 0 : -ENOMEM; +} + static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); @@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; + struct nft_set_dump_ctx dump_ctx = { + .set = set, + .ctx = ctx, + }; - c.data = dump_ctx; + c.data = &dump_ctx; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -4975,38 +5015,42 @@ done: return skb->len; } -static int nf_tables_dump_obj_done(struct netlink_callback *cb) +static int nf_tables_dump_obj_start(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_obj_filter *filter = NULL; - if (filter) { - kfree(filter->table); - kfree(filter); + if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; + + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + + if (nla[NFTA_OBJ_TYPE]) + filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); } + cb->data = filter; return 0; } -static struct nft_obj_filter * -nft_obj_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter; - - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) - return ERR_PTR(-ENOMEM); + struct nft_obj_filter *filter = cb->data; - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } + if (filter) { + kfree(filter->table); + kfree(filter); } - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - return filter; + return 0; } /* called with rcu_read_lock held */ @@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_OBJ_TABLE] || - nla[NFTA_OBJ_TYPE]) { - struct nft_obj_filter *filter; - - filter = nft_obj_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; - flowtable->dev_name[i] = kstrdup(dev_array[i]->name, - GFP_KERNEL); } return err; @@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, err6: i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) { - kfree(flowtable->dev_name[k]); + for (k = i - 1; k >= 0; k--) nf_unregister_net_hook(net, &flowtable->ops[k]); - } kfree(flowtable->ops); err4: @@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->dev_name[i][0] && - nla_put_string(skb, NFTA_DEVICE_NAME, - flowtable->dev_name[i])) + const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); + + if (dev && + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -5650,37 +5683,39 @@ done: return skb->len; } -static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) +static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_flowtable_filter *filter = NULL; - if (!filter) - return 0; + if (nla[NFTA_FLOWTABLE_TABLE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; - kfree(filter->table); - kfree(filter); + filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], + GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + cb->data = filter; return 0; } -static struct nft_flowtable_filter * -nft_flowtable_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter; + struct nft_flowtable_filter *filter = cb->data; - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) - return ERR_PTR(-ENOMEM); + return 0; - if (nla[NFTA_FLOWTABLE_TABLE]) { - filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } - } - return filter; + kfree(filter->table); + kfree(filter); + + return 0; } /* called with rcu_read_lock held */ @@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_FLOWTABLE_TABLE]) { - struct nft_flowtable_filter *filter; - - filter = nft_flowtable_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); + kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, @@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, continue; nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->dev_name[i][0] = '\0'; flowtable->ops[i].dev = NULL; break; } @@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); break; + case NFT_MSG_NEWCHAIN: + kfree(nft_trans_chain_name(trans)); + break; case NFT_MSG_DELCHAIN: nf_tables_chain_destroy(&trans->ctx); break; @@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: - if (nft_trans_chain_update(trans)) + if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - else + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + /* trans destroyed after rcu grace period */ + } else { nft_clear(net, trans->ctx.chain); - - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); - nft_trans_destroy(trans); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + } break; case NFT_MSG_DELCHAIN: nft_chain_del(trans->ctx.chain); @@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { free_percpu(nft_trans_chain_stats(trans)); - + kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx, err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - - if (ctx->chain->level + 1 > - data->verdict.chain->level) { - if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) - return -EMLINK; - data->verdict.chain->level = ctx->chain->level + 1; - } } return 0; diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c new file mode 100644 index 000000000000..814789644bd3 --- /dev/null +++ b/net/netfilter/nf_tables_set_core.c @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <net/netfilter/nf_tables_core.h> + +static int __init nf_tables_set_module_init(void) +{ + nft_register_set(&nft_set_hash_fast_type); + nft_register_set(&nft_set_hash_type); + nft_register_set(&nft_set_rhash_type); + nft_register_set(&nft_set_bitmap_type); + nft_register_set(&nft_set_rbtree_type); + + return 0; +} + +static void __exit nf_tables_set_module_exit(void) +{ + nft_unregister_set(&nft_set_rbtree_type); + nft_unregister_set(&nft_set_bitmap_type); + nft_unregister_set(&nft_set_rhash_type); + nft_unregister_set(&nft_set_hash_type); + nft_unregister_set(&nft_set_hash_fast_type); +} + +module_init(nf_tables_set_module_init); +module_exit(nf_tables_set_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4ccd2988f9db..ea4ba551abb2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, + [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, + [NFQA_CFG_MASK] = { .type = NLA_U32 }, + [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 8d1ff654e5af..32535eea51b2 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -832,10 +832,18 @@ nft_target_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV])); family = ctx->family; + if (strcmp(tg_name, XT_ERROR_TARGET) == 0 || + strcmp(tg_name, XT_STANDARD_TARGET) == 0 || + strcmp(tg_name, "standard") == 0) + return ERR_PTR(-EINVAL); + /* Re-use the existing target if it's already loaded. */ list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; + if (!target->target) + continue; + if (nft_target_cmp(target, tg_name, rev, family)) return &nft_target->ops; } @@ -844,6 +852,11 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (IS_ERR(target)) return ERR_PTR(-ENOENT); + if (!target->target) { + err = -EINVAL; + goto err; + } + if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { err = -EINVAL; goto err; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 15adf8ca82c3..0777a93211e2 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: + pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; + pctx->level--; break; default: break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 42e6fadf1417..c2a1d84cdfc4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; + int err; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) @@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nft_chain_validate(ctx, data->verdict.chain); + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; default: - return 0; + break; } + + return 0; } static int nft_lookup_validate(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index d6626e01c7ee..128bc16f52dd 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -296,7 +296,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_bitmap_type __read_mostly = { +struct nft_set_type nft_set_bitmap_type __read_mostly = { .owner = THIS_MODULE, .ops = { .privsize = nft_bitmap_privsize, @@ -314,20 +314,3 @@ static struct nft_set_type nft_bitmap_type __read_mostly = { .get = nft_bitmap_get, }, }; - -static int __init nft_bitmap_module_init(void) -{ - return nft_register_set(&nft_bitmap_type); -} - -static void __exit nft_bitmap_module_exit(void) -{ - nft_unregister_set(&nft_bitmap_type); -} - -module_init(nft_bitmap_module_init); -module_exit(nft_bitmap_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6f9a1365a09f..90c3e7e6cacb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set) struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } @@ -654,7 +655,7 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features return true; } -static struct nft_set_type nft_rhash_type __read_mostly = { +struct nft_set_type nft_set_rhash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT | NFT_SET_EVAL, @@ -677,7 +678,7 @@ static struct nft_set_type nft_rhash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_type __read_mostly = { +struct nft_set_type nft_set_hash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -697,7 +698,7 @@ static struct nft_set_type nft_hash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_fast_type __read_mostly = { +struct nft_set_type nft_set_hash_fast_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -716,26 +717,3 @@ static struct nft_set_type nft_hash_fast_type __read_mostly = { .get = nft_hash_get, }, }; - -static int __init nft_hash_module_init(void) -{ - if (nft_register_set(&nft_hash_fast_type) || - nft_register_set(&nft_hash_type) || - nft_register_set(&nft_rhash_type)) - return 1; - return 0; -} - -static void __exit nft_hash_module_exit(void) -{ - nft_unregister_set(&nft_rhash_type); - nft_unregister_set(&nft_hash_type); - nft_unregister_set(&nft_hash_fast_type); -} - -module_init(nft_hash_module_init); -module_exit(nft_hash_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 7f3a9a211034..9873d734b494 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) - goto out; + break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); @@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(prev, struct nft_rbtree_elem, node); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + prev = NULL; } node = rb_next(node); + if (!node) + break; } -out: if (gcb) { for (i = 0; i < gcb->head.cnt; i++) { rbe = gcb->elems[i]; @@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct rb_node *node; cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -462,7 +465,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_rbtree_type __read_mostly = { +struct nft_set_type nft_set_rbtree_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -481,20 +484,3 @@ static struct nft_set_type nft_rbtree_type __read_mostly = { .get = nft_rbtree_get, }, }; - -static int __init nft_rbtree_module_init(void) -{ - return nft_register_set(&nft_rbtree_type); -} - -static void __exit nft_rbtree_module_exit(void) -{ - nft_unregister_set(&nft_rbtree_type); -} - -module_init(nft_rbtree_module_init); -module_exit(nft_rbtree_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 58fce4e749a9..d76550a8b642 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -61,7 +61,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); @@ -77,7 +77,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -150,7 +150,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); @@ -171,7 +171,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, laddr, hp->source, lport, xt_in(par), NF_TPROXY_LOOKUP_LISTENER); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 2ceefa183cee..6a196e438b6c 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); - pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { - pr_err("Could not allocate PDU\n"); - continue; + pr_err("Could not allocate PDU (error=%d)\n", err); + len -= remaining_len; + if (len == 0) + len = err; + break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 9696ef96b719..1a30e165eeb4 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, __skb_pull(skb, nsh_len); skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0; skb->protocol = proto; features &= NETIF_F_SG; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 57634bc3da74..9b27d0cd766d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2878,6 +2878,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); + if (len < reserve) + skb_reset_network_header(skb); } /* Returns -EFAULT on error */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2aa07b547b16..86e1e37eb4e8 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -191,8 +191,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->type = cpu_to_le32(type); hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); - hdr->dst_node_id = cpu_to_le32(to->sq_node); - hdr->dst_port_id = cpu_to_le32(to->sq_port); + if (to->sq_port == QRTR_PORT_CTRL) { + hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST); + } else { + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + } hdr->size = cpu_to_le32(len); hdr->confirm_rx = 0; @@ -764,6 +769,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { enqueue_fn = qrtr_bcast_enqueue; + if (addr->sq_port != QRTR_PORT_CTRL) { + release_sock(sk); + return -ENOTCONN; + } } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { diff --git a/net/rds/connection.c b/net/rds/connection.c index abef75da89a7..cfb05953b0e5 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len, int rds_conn_init(void) { + int ret; + + ret = rds_loop_net_init(); /* register pernet callback */ + if (ret) + return ret; + rds_conn_slab = kmem_cache_create("rds_connection", sizeof(struct rds_connection), 0, 0, NULL); - if (!rds_conn_slab) + if (!rds_conn_slab) { + rds_loop_net_exit(); return -ENOMEM; + } rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info); rds_info_register_func(RDS_INFO_SEND_MESSAGES, @@ -676,6 +684,7 @@ int rds_conn_init(void) void rds_conn_exit(void) { + rds_loop_net_exit(); /* unregister pernet callback */ rds_loop_exit(); WARN_ON(!hlist_empty(rds_conn_hash)); diff --git a/net/rds/loop.c b/net/rds/loop.c index dac6218a460e..feea1f96ee2a 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -33,6 +33,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/in.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include "rds_single_path.h" #include "rds.h" @@ -40,6 +42,17 @@ static DEFINE_SPINLOCK(loop_conns_lock); static LIST_HEAD(loop_conns); +static atomic_t rds_loop_unloading = ATOMIC_INIT(0); + +static void rds_loop_set_unloading(void) +{ + atomic_set(&rds_loop_unloading, 1); +} + +static bool rds_loop_is_unloading(struct rds_connection *conn) +{ + return atomic_read(&rds_loop_unloading) != 0; +} /* * This 'loopback' transport is a special case for flows that originate @@ -165,6 +178,8 @@ void rds_loop_exit(void) struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); + rds_loop_set_unloading(); + synchronize_rcu(); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&loop_conns_lock); list_splice(&loop_conns, &tmp_list); @@ -177,6 +192,46 @@ void rds_loop_exit(void) } } +static void rds_loop_kill_conns(struct net *net) +{ + struct rds_loop_connection *lc, *_lc; + LIST_HEAD(tmp_list); + + spin_lock_irq(&loop_conns_lock); + list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) { + struct net *c_net = read_pnet(&lc->conn->c_net); + + if (net != c_net) + continue; + list_move_tail(&lc->loop_node, &tmp_list); + } + spin_unlock_irq(&loop_conns_lock); + + list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { + WARN_ON(lc->conn->c_passive); + rds_conn_destroy(lc->conn); + } +} + +static void __net_exit rds_loop_exit_net(struct net *net) +{ + rds_loop_kill_conns(net); +} + +static struct pernet_operations rds_loop_net_ops = { + .exit = rds_loop_exit_net, +}; + +int rds_loop_net_init(void) +{ + return register_pernet_device(&rds_loop_net_ops); +} + +void rds_loop_net_exit(void) +{ + unregister_pernet_device(&rds_loop_net_ops); +} + /* * This is missing .xmit_* because loop doesn't go through generic * rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and @@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = { .inc_free = rds_loop_inc_free, .t_name = "loopback", .t_type = RDS_TRANS_LOOP, + .t_unloading = rds_loop_is_unloading, }; diff --git a/net/rds/loop.h b/net/rds/loop.h index 469fa4b2da4f..bbc8cdd030df 100644 --- a/net/rds/loop.h +++ b/net/rds/loop.h @@ -5,6 +5,8 @@ /* loop.c */ extern struct rds_transport rds_loop_transport; +int rds_loop_net_init(void); +void rds_loop_net_exit(void); void rds_loop_exit(void); #endif diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 526a8e491626..6e7124e57918 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -91,7 +91,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } params_old = rtnl_dereference(p->params); - params_new->action = parm->action; + p->tcf_action = parm->action; params_new->update_flags = parm->update_flags; rcu_assign_pointer(p->params, params_new); if (params_old) @@ -561,7 +561,7 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&p->tcf_tm); bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) goto drop_stats; @@ -599,11 +599,11 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, .index = p->tcf_index, .refcnt = p->tcf_refcnt - ref, .bindcnt = p->tcf_bindcnt - bind, + .action = p->tcf_action, }; struct tcf_t t; params = rtnl_dereference(p->params); - opt.action = params->action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 626dac81a48a..9bc6c2ae98a5 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -36,7 +36,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&t->tcf_tm); bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(t->tcf_action); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: @@ -182,7 +182,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, params_old = rtnl_dereference(t->params); - params_new->action = parm->action; + t->tcf_action = parm->action; params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -254,13 +254,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, .index = t->tcf_index, .refcnt = t->tcf_refcnt - ref, .bindcnt = t->tcf_bindcnt - bind, + .action = t->tcf_action, }; struct tcf_t tm; params = rtnl_dereference(t->params); opt.t_action = params->tcft_action; - opt.action = params->action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cdc3c87c53e6..f74513a7c7a8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1053,7 +1053,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, block, - q, parent, 0, event, false); + q, parent, NULL, event, false); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1444,7 +1444,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, block, q, parent, 0, + if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cd2e0e342fb6..6c0a9d5dbf94 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -479,24 +479,28 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, q->cparams.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = fq_codel_change(sch, opt, extack); + err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -509,6 +513,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 445b7ef61677..12cac85da994 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -282,7 +282,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) if (dst) { /* Re-fetch, as under layers may have a higher minimum size */ - pmtu = SCTP_TRUNC4(dst_mtu(dst)); + pmtu = sctp_dst_mtu(dst); change = t->pathmtu != pmtu; } t->pathmtu = pmtu; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 973b4471b532..05e4ffe5aabd 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group */ static void smc_tcp_listen_work(struct work_struct *); +static void smc_connect_work(struct work_struct *); static void smc_set_keepalive(struct sock *sk, int val) { @@ -122,6 +123,12 @@ static int smc_release(struct socket *sock) goto out; smc = smc_sk(sk); + + /* cleanup for a dangling non-blocking connect */ + flush_work(&smc->connect_work); + kfree(smc->connect_info); + smc->connect_info = NULL; + if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires * sock lock for child sockets again @@ -140,7 +147,8 @@ static int smc_release(struct socket *sock) smc->clcsock = NULL; } if (smc->use_fallback) { - sock_put(sk); /* passive closing */ + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } @@ -186,6 +194,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_protocol = protocol; smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); + INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); INIT_LIST_HEAD(&smc->accept_q); spin_lock_init(&smc->accept_q_lock); @@ -409,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) { int rc; - if (reason_code < 0) /* error, fallback is not possible */ + if (reason_code < 0) { /* error, fallback is not possible */ + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return reason_code; + } if (reason_code != SMC_CLC_DECL_REPLY) { rc = smc_clc_send_decline(smc, reason_code); - if (rc < 0) + if (rc < 0) { + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return rc; + } } return smc_connect_fallback(smc); } @@ -427,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, smc_lgr_forget(smc->conn.lgr); mutex_unlock(&smc_create_lgr_pending); smc_conn_free(&smc->conn); - if (reason_code < 0 && smc->sk.sk_state == SMC_INIT) - sock_put(&smc->sk); /* passive closing */ return reason_code; } @@ -576,6 +589,35 @@ static int __smc_connect(struct smc_sock *smc) return 0; } +static void smc_connect_work(struct work_struct *work) +{ + struct smc_sock *smc = container_of(work, struct smc_sock, + connect_work); + int rc; + + lock_sock(&smc->sk); + rc = kernel_connect(smc->clcsock, &smc->connect_info->addr, + smc->connect_info->alen, smc->connect_info->flags); + if (smc->clcsock->sk->sk_err) { + smc->sk.sk_err = smc->clcsock->sk->sk_err; + goto out; + } + if (rc < 0) { + smc->sk.sk_err = -rc; + goto out; + } + + rc = __smc_connect(smc); + if (rc < 0) + smc->sk.sk_err = -rc; + +out: + smc->sk.sk_state_change(&smc->sk); + kfree(smc->connect_info); + smc->connect_info = NULL; + release_sock(&smc->sk); +} + static int smc_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { @@ -605,15 +647,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, smc_copy_sock_settings_to_clc(smc); tcp_sk(smc->clcsock->sk)->syn_smc = 1; - rc = kernel_connect(smc->clcsock, addr, alen, flags); - if (rc) - goto out; + if (flags & O_NONBLOCK) { + if (smc->connect_info) { + rc = -EALREADY; + goto out; + } + smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL); + if (!smc->connect_info) { + rc = -ENOMEM; + goto out; + } + smc->connect_info->alen = alen; + smc->connect_info->flags = flags ^ O_NONBLOCK; + memcpy(&smc->connect_info->addr, addr, alen); + schedule_work(&smc->connect_work); + rc = -EINPROGRESS; + } else { + rc = kernel_connect(smc->clcsock, addr, alen, flags); + if (rc) + goto out; - rc = __smc_connect(smc); - if (rc < 0) - goto out; - else - rc = 0; /* success cases including fallback */ + rc = __smc_connect(smc); + if (rc < 0) + goto out; + else + rc = 0; /* success cases including fallback */ + } out: release_sock(sk); @@ -1279,40 +1338,20 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; struct smc_sock *smc; - int rc; if (!sk) return EPOLLNVAL; smc = smc_sk(sock->sk); - sock_hold(sk); - lock_sock(sk); if ((sk->sk_state == SMC_INIT) || smc->use_fallback) { /* delegate to CLC child sock */ - release_sock(sk); mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); - lock_sock(sk); sk->sk_err = smc->clcsock->sk->sk_err; - if (sk->sk_err) { + if (sk->sk_err) mask |= EPOLLERR; - } else { - /* if non-blocking connect finished ... */ - if (sk->sk_state == SMC_INIT && - mask & EPOLLOUT && - smc->clcsock->sk->sk_state != TCP_CLOSE) { - rc = __smc_connect(smc); - if (rc < 0) - mask |= EPOLLERR; - /* success cases including fallback */ - mask |= EPOLLOUT | EPOLLWRNORM; - } - } } else { - if (sk->sk_state != SMC_CLOSED) { - release_sock(sk); + if (sk->sk_state != SMC_CLOSED) sock_poll_wait(file, sk_sleep(sk), wait); - lock_sock(sk); - } if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || @@ -1338,10 +1377,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, } if (smc->conn.urg_state == SMC_URG_VALID) mask |= EPOLLPRI; - } - release_sock(sk); - sock_put(sk); return mask; } @@ -1421,7 +1457,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; - get_user(val, (int __user *)optval); + if (get_user(val, (int __user *)optval)) + return -EFAULT; lock_sock(sk); switch (optname) { @@ -1489,10 +1526,13 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, return -EBADF; return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); } + lock_sock(&smc->sk); switch (cmd) { case SIOCINQ: /* same as FIONREAD */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1501,8 +1541,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQ: /* output queue size (not send + not acked) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1512,8 +1554,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQNSD: /* output queue size (not send only) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1521,8 +1565,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, answ = smc_tx_prepared_sends(&smc->conn); break; case SIOCATMARK: - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) { answ = 0; @@ -1538,8 +1584,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, } break; default: + release_sock(&smc->sk); return -ENOIOCTLCMD; } + release_sock(&smc->sk); return put_user(answ, (int __user *)arg); } diff --git a/net/smc/smc.h b/net/smc/smc.h index 51ae1f10d81a..d7ca26570482 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -187,11 +187,19 @@ struct smc_connection { struct work_struct close_work; /* peer sent some closing */ }; +struct smc_connect_info { + int flags; + int alen; + struct sockaddr addr; +}; + struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ + struct smc_connect_info *connect_info; /* connect address & flags */ + struct work_struct connect_work; /* handle non-blocking connect*/ struct work_struct tcp_listen_work;/* handle tcp socket accepts */ struct work_struct smc_listen_work;/* prepare new accept socket */ struct list_head accept_q; /* sockets to be accepted */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 717449b1da0b..ae5d168653ce 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -250,6 +250,7 @@ out: int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type) { + long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo; struct sock *clc_sk = smc->clcsock->sk; struct smc_clc_msg_hdr *clcm = buf; struct msghdr msg = {NULL, 0}; @@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, memset(&msg, 0, sizeof(struct msghdr)); iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); krflags = MSG_WAITALL; - smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { smc->sk.sk_err = EPROTO; @@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } out: + smc->clcsock->sk->sk_rcvtimeo = rcvtimeo; return reason_code; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index fa41d9881741..ac961dfb1ea1 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_INIT: + sk->sk_state = SMC_PEERABORTWAIT; + break; case SMC_ACTIVE: sk->sk_state = SMC_PEERABORTWAIT; release_sock(sk); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index cee666400752..f82886b7d1d8 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -495,7 +495,8 @@ out: void smc_tx_consumer_update(struct smc_connection *conn, bool force) { - union smc_host_cursor cfed, cons; + union smc_host_cursor cfed, cons, prod; + int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_write(&cons, @@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) smc_curs_read(&conn->rx_curs_confirmed, conn), conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); + if (to_confirm > conn->rmbe_update_limit) { + smc_curs_write(&prod, + smc_curs_read(&conn->local_rx_ctrl.prod, conn), + conn); + sender_free = conn->rmb_desc->len - + smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && - ((to_confirm > (conn->rmb_desc->len / 2)) || + ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && conn->alert_token_local) { /* connection healthy */ diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 373836615c57..625acb27efcc 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -35,7 +35,6 @@ struct _strp_msg { */ struct strp_msg strp; int accum_len; - int early_eaten; }; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) @@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, head = strp->skb_head; if (head) { /* Message already in progress */ - - stm = _strp_msg(head); - if (unlikely(stm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= stm->early_eaten ? - orig_len : stm->early_eaten; - stm->early_eaten -= eaten; - - return eaten; - } - if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } stm->accum_len += cand_len; + eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 9f666e0650e2..2830709957bd 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -133,6 +133,8 @@ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr, } /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer + * Returns true if message should be dropped by caller, i.e., if it is a + * trial message or we are inside trial period. Otherwise false. */ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, struct tipc_media_addr *maddr, @@ -168,8 +170,9 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } + /* Accept regular link requests/responses only after trial period */ if (mtyp != DSC_TRIAL_MSG) - return false; + return trial; sugg_addr = tipc_node_try_addr(net, peer_id, src); if (sugg_addr) @@ -284,7 +287,6 @@ static void tipc_disc_timeout(struct timer_list *t) { struct tipc_discoverer *d = from_timer(d, t, timer); struct tipc_net *tn = tipc_net(d->net); - u32 self = tipc_own_addr(d->net); struct tipc_media_addr maddr; struct sk_buff *skb = NULL; struct net *net = d->net; @@ -298,12 +300,14 @@ static void tipc_disc_timeout(struct timer_list *t) goto exit; } - /* Did we just leave the address trial period ? */ - if (!self && !time_before(jiffies, tn->addr_trial_end)) { - self = tn->trial_addr; - tipc_net_finalize(net, self); - msg_set_prevnode(buf_msg(d->skb), self); + /* Trial period over ? */ + if (!time_before(jiffies, tn->addr_trial_end)) { + /* Did we just leave it ? */ + if (!tipc_own_addr(net)) + tipc_net_finalize(net, tn->trial_addr); + msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); + msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net)); } /* Adjust timeout interval according to discovery phase */ diff --git a/net/tipc/net.c b/net/tipc/net.c index 4fbaa0464405..a7f6964c3a4b 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -121,12 +121,17 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr) void tipc_net_finalize(struct net *net, u32 addr) { - tipc_set_node_addr(net, addr); - smp_mb(); - tipc_named_reinit(net); - tipc_sk_reinit(net); - tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); + struct tipc_net *tn = tipc_net(net); + + spin_lock_bh(&tn->node_list_lock); + if (!tipc_own_addr(net)) { + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, + TIPC_CLUSTER_SCOPE, 0, addr); + } + spin_unlock_bh(&tn->node_list_lock); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6a44eb812baf..0453bd451ce8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -797,6 +797,7 @@ static u32 tipc_node_suggest_addr(struct net *net, u32 addr) } /* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not + * Returns suggested address if any, otherwise 0 */ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) { @@ -819,12 +820,14 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) if (n) { addr = n->addr; tipc_node_put(n); + return addr; } - /* Even this node may be in trial phase */ + + /* Even this node may be in conflict */ if (tn->trial_addr == addr) return tipc_node_suggest_addr(net, addr); - return addr; + return 0; } void tipc_node_check_dest(struct net *net, u32 addr, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d2380548f8f6..1f3d9789af30 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -440,7 +440,7 @@ alloc_encrypted: ret = tls_push_record(sk, msg->msg_flags, record_type); if (!ret) continue; - if (ret == -EAGAIN) + if (ret < 0) goto send_end; copied -= try_to_copy; @@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + if (sock_flag(sk, SOCK_DONE)) return NULL; @@ -701,6 +704,10 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, nsg = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); + if (nsg < 0) { + ret = nsg; + goto out; + } tls_make_aad(ctx->rx_aad_ciphertext, rxm->full_len - tls_ctx->rx.overhead_size, @@ -712,6 +719,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, rxm->full_len - tls_ctx->rx.overhead_size, skb, sk->sk_allocation); +out: if (sgin != &sgin_arr[0]) kfree(sgin); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c7bbe5f0aae8..80bc986c79e5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info, params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHORIZED); + break; default: return -EINVAL; } @@ -6231,7 +6232,7 @@ do { \ nl80211_check_s32); /* * Check HT operation mode based on - * IEEE 802.11 2012 8.4.2.59 HT Operation element. + * IEEE 802.11-2016 9.4.2.57 HT Operation element. */ if (tb[NL80211_MESHCONF_HT_OPMODE]) { ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]); @@ -6241,22 +6242,9 @@ do { \ IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) return -EINVAL; - if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) && - (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; + /* NON_HT_STA bit is reserved, but some programs set it */ + ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; - switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) { - case IEEE80211_HT_OP_MODE_PROTECTION_NONE: - case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: - if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT) - return -EINVAL; - break; - case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: - case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: - if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; - break; - } cfg->ht_opmode = ht_opmode; mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1)); } @@ -10962,9 +10950,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, - info->extack); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, + info->extack); + if (err) + goto error; + err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -11213,8 +11204,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, NULL); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); + if (err) + return err; + if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; @@ -14930,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, + struct sk_buff *skb, bool unencrypted, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct ethhdr *ehdr = eth_hdr(skb); + const u8 *addr = ehdr->h_source; + u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; + struct nlattr *frame; + u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid); if (!nlportid) return -ENOENT; - msg = nlmsg_new(100 + len, gfp); + msg = nlmsg_new(100 + skb->len, gfp); if (!msg) return -ENOMEM; @@ -14957,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) goto nla_put_failure; + frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len); + if (!frame) + goto nla_put_failure; + + skb_copy_bits(skb, 0, nla_data(frame), skb->len); genlmsg_end(msg, hdr); return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); @@ -14974,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev, } bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted) + struct sk_buff *skb, bool unencrypted) { int ret; - trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted); - ret = __nl80211_rx_control_port(dev, buf, len, addr, proto, - unencrypted, GFP_ATOMIC); + trace_cfg80211_rx_control_port(dev, skb, unencrypted); + ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC); trace_cfg80211_return_bool(ret == 0); return ret == 0; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bbe6298e4bb9..4fc66a117b7d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG && + !(wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED)) reg_call_notifier(wiphy, lr); return; } @@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) } } -static bool reg_only_self_managed_wiphys(void) -{ - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; - bool self_managed_found = false; - - ASSERT_RTNL(); - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) - self_managed_found = true; - else - return false; - } - - /* make sure at least one self-managed wiphy exists */ - return self_managed_found; -} - /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); notify_self_managed_wiphys(reg_request); - if (reg_only_self_managed_wiphys()) { - reg_free_request(reg_request); - return; - } reg_process_hint(reg_request); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2b417a2fe63f..7c73510b161f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, ); TRACE_EVENT(cfg80211_rx_control_port, - TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted), - TP_ARGS(netdev, buf, len, addr, proto, unencrypted), + TP_PROTO(struct net_device *netdev, struct sk_buff *skb, + bool unencrypted), + TP_ARGS(netdev, skb, unencrypted), TP_STRUCT__entry( NETDEV_ENTRY - MAC_ENTRY(addr) + __field(int, len) + MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) ), TP_fast_assign( NETDEV_ASSIGN; - MAC_ASSIGN(addr, addr); - __entry->proto = proto; + __entry->len = skb->len; + MAC_ASSIGN(from, eth_hdr(skb)->h_source); + __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, MAC_PR_ARG(addr), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 59fb7d3c36a3..72335c2e8108 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -199,8 +199,11 @@ static void xsk_destruct_skb(struct sk_buff *skb) { u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg; struct xdp_sock *xs = xdp_sk(skb->sk); + unsigned long flags; + spin_lock_irqsave(&xs->tx_completion_lock, flags); WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr)); + spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); } @@ -215,9 +218,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, struct sk_buff *skb; int err = 0; - if (unlikely(!xs->tx)) - return -ENOBUFS; - mutex_lock(&xs->mutex); while (xskq_peek_desc(xs->tx, &desc)) { @@ -230,22 +230,13 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, goto out; } - if (xskq_reserve_addr(xs->umem->cq)) { - err = -EAGAIN; - goto out; - } - - len = desc.len; - if (unlikely(len > xs->dev->mtu)) { - err = -EMSGSIZE; + if (xskq_reserve_addr(xs->umem->cq)) goto out; - } - if (xs->queue_id >= xs->dev->real_num_tx_queues) { - err = -ENXIO; + if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - } + len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); if (unlikely(!skb)) { err = -EAGAIN; @@ -268,15 +259,15 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, skb->destructor = xsk_destruct_skb; err = dev_direct_xmit(skb, xs->queue_id); + xskq_discard_desc(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { - err = -EAGAIN; - /* SKB consumed by dev_direct_xmit() */ + /* SKB completed but not sent */ + err = -EBUSY; goto out; } sent_frame = true; - xskq_discard_desc(xs->tx); } out: @@ -297,6 +288,8 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; if (need_wait) return -EOPNOTSUPP; @@ -755,6 +748,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, xs = xdp_sk(sk); mutex_init(&xs->mutex); + spin_lock_init(&xs->tx_completion_lock); local_bh_disable(); sock_prot_inuse_add(net, &xsk_proto, 1); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index ef6a6f0ec949..52ecaf770642 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -62,14 +62,9 @@ static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) return (entries > dcnt) ? dcnt : entries; } -static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer) -{ - return q->nentries - (producer - q->cons_tail); -} - static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) { - u32 free_entries = xskq_nb_free_lazy(q, producer); + u32 free_entries = q->nentries - (producer - q->cons_tail); if (free_entries >= dcnt) return free_entries; @@ -129,7 +124,7 @@ static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0) + if (xskq_nb_free(q, q->prod_tail, 1) == 0) return -ENOSPC; ring->desc[q->prod_tail++ & q->ring_mask] = addr; diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore new file mode 100644 index 000000000000..8ae4940025f8 --- /dev/null +++ b/samples/bpf/.gitignore @@ -0,0 +1,49 @@ +cpustat +fds_example +lathist +load_sock_ops +lwt_len_hist +map_perf_test +offwaketime +per_socket_stats_example +sampleip +sock_example +sockex1 +sockex2 +sockex3 +spintest +syscall_nrs.h +syscall_tp +task_fd_query +tc_l2_redirect +test_cgrp2_array_pin +test_cgrp2_attach +test_cgrp2_attach2 +test_cgrp2_sock +test_cgrp2_sock2 +test_current_task_under_cgroup +test_lru_dist +test_map_in_map +test_overhead +test_probe_write_user +trace_event +trace_output +tracex1 +tracex2 +tracex3 +tracex4 +tracex5 +tracex6 +tracex7 +xdp1 +xdp2 +xdp_adjust_tail +xdp_fwd +xdp_monitor +xdp_redirect +xdp_redirect_cpu +xdp_redirect_map +xdp_router_ipv4 +xdp_rxq_info +xdp_tx_iptunnel +xdpsock diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c index 95c16324760c..0b6f22feb2c9 100644 --- a/samples/bpf/parse_varlen.c +++ b/samples/bpf/parse_varlen.c @@ -6,6 +6,7 @@ */ #define KBUILD_MODNAME "foo" #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/in.h> @@ -108,11 +109,6 @@ static int parse_ipv6(void *data, uint64_t nh_off, void *data_end) return 0; } -struct vlan_hdr { - uint16_t h_vlan_TCI; - uint16_t h_vlan_encapsulated_proto; -}; - SEC("varlen") int handle_ingress(struct __sk_buff *skb) { diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c index 6caf47afa635..9d6dcaa9db92 100644 --- a/samples/bpf/test_overhead_user.c +++ b/samples/bpf/test_overhead_user.c @@ -6,6 +6,7 @@ */ #define _GNU_SOURCE #include <sched.h> +#include <errno.h> #include <stdio.h> #include <sys/types.h> #include <asm/unistd.h> @@ -44,8 +45,13 @@ static void test_task_rename(int cpu) exit(1); } start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) - write(fd, buf, sizeof(buf)); + for (i = 0; i < MAX_CNT; i++) { + if (write(fd, buf, sizeof(buf)) < 0) { + printf("task rename failed: %s\n", strerror(errno)); + close(fd); + return; + } + } printf("task_rename:%d: %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); close(fd); @@ -63,8 +69,13 @@ static void test_urandom_read(int cpu) exit(1); } start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) - read(fd, buf, sizeof(buf)); + for (i = 0; i < MAX_CNT; i++) { + if (read(fd, buf, sizeof(buf)) < 0) { + printf("failed to read from /dev/urandom: %s\n", strerror(errno)); + close(fd); + return; + } + } printf("urandom_read:%d: %lld events per sec\n", cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); close(fd); diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 1fa1becfa641..d08046ab81f0 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -122,6 +122,16 @@ static void print_stacks(void) } } +static inline int generate_load(void) +{ + if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) { + printf("failed to generate some load with dd: %s\n", strerror(errno)); + return -1; + } + + return 0; +} + static void test_perf_event_all_cpu(struct perf_event_attr *attr) { int nr_cpus = sysconf(_SC_NPROCESSORS_CONF); @@ -142,7 +152,11 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr) assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0); } - system("dd if=/dev/zero of=/dev/null count=5000k status=none"); + + if (generate_load() < 0) { + error = 1; + goto all_cpu_err; + } print_stacks(); all_cpu_err: for (i--; i >= 0; i--) { @@ -156,7 +170,7 @@ all_cpu_err: static void test_perf_event_task(struct perf_event_attr *attr) { - int pmu_fd; + int pmu_fd, error = 0; /* per task perf event, enable inherit so the "dd ..." command can be traced properly. * Enabling inherit will cause bpf_perf_prog_read_time helper failure. @@ -171,10 +185,17 @@ static void test_perf_event_task(struct perf_event_attr *attr) } assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0); assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0); - system("dd if=/dev/zero of=/dev/null count=5000k status=none"); + + if (generate_load() < 0) { + error = 1; + goto err; + } print_stacks(); +err: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); close(pmu_fd); + if (error) + int_exit(0); } static void test_bpf_perf_event(void) diff --git a/samples/bpf/xdp2skb_meta.sh b/samples/bpf/xdp2skb_meta.sh index b9c9549c4c27..4bde9d066c46 100755 --- a/samples/bpf/xdp2skb_meta.sh +++ b/samples/bpf/xdp2skb_meta.sh @@ -16,8 +16,8 @@ BPF_FILE=xdp2skb_meta_kern.o DIR=$(dirname $0) -export TC=/usr/sbin/tc -export IP=/usr/sbin/ip +[ -z "$TC" ] && TC=tc +[ -z "$IP" ] && IP=ip function usage() { echo "" @@ -53,7 +53,7 @@ function _call_cmd() { local allow_fail="$2" shift 2 if [[ -n "$VERBOSE" ]]; then - echo "$(basename $cmd) $@" + echo "$cmd $@" fi if [[ -n "$DRYRUN" ]]; then return diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c index 6673cdb9f55c..a7e94e7ff87d 100644 --- a/samples/bpf/xdp_fwd_kern.c +++ b/samples/bpf/xdp_fwd_kern.c @@ -48,9 +48,9 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) struct ethhdr *eth = data; struct ipv6hdr *ip6h; struct iphdr *iph; - int out_index; u16 h_proto; u64 nh_off; + int rc; nh_off = sizeof(*eth); if (data + nh_off > data_end) @@ -101,7 +101,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) fib_params.ifindex = ctx->ingress_ifindex; - out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); + rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); /* verify egress index has xdp support * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with @@ -109,7 +109,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) * NOTE: without verification that egress index supports XDP * forwarding packets are dropped. */ - if (out_index > 0) { + if (rc == 0) { if (h_proto == htons(ETH_P_IP)) ip_decrease_ttl(iph); else if (h_proto == htons(ETH_P_IPV6)) @@ -117,7 +117,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); memcpy(eth->h_source, fib_params.smac, ETH_ALEN); - return bpf_redirect_map(&tx_port, out_index, 0); + return bpf_redirect_map(&tx_port, fib_params.ifindex, 0); } return XDP_PASS; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index d69c8d78d3fd..5904b1543831 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -729,7 +729,7 @@ static void kick_tx(int fd) int ret; ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0); - if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN) + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY) return; lassert(0); } diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index 2960e26c6ea4..2535c3677c7b 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -178,6 +178,8 @@ static const char *vbe_name(u32 index) return "(invalid)"; } +static struct page *__mbochs_get_page(struct mdev_state *mdev_state, + pgoff_t pgoff); static struct page *mbochs_get_page(struct mdev_state *mdev_state, pgoff_t pgoff); @@ -394,7 +396,7 @@ static ssize_t mdev_access(struct mdev_device *mdev, char *buf, size_t count, MBOCHS_MEMORY_BAR_OFFSET + mdev_state->memsize) { pos -= MBOCHS_MMIO_BAR_OFFSET; poff = pos & ~PAGE_MASK; - pg = mbochs_get_page(mdev_state, pos >> PAGE_SHIFT); + pg = __mbochs_get_page(mdev_state, pos >> PAGE_SHIFT); map = kmap(pg); if (is_write) memcpy(map + poff, buf, count); @@ -657,7 +659,7 @@ static void mbochs_put_pages(struct mdev_state *mdev_state) dev_dbg(dev, "%s: %d pages released\n", __func__, count); } -static int mbochs_region_vm_fault(struct vm_fault *vmf) +static vm_fault_t mbochs_region_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mdev_state *mdev_state = vma->vm_private_data; @@ -695,7 +697,7 @@ static int mbochs_mmap(struct mdev_device *mdev, struct vm_area_struct *vma) return 0; } -static int mbochs_dmabuf_vm_fault(struct vm_fault *vmf) +static vm_fault_t mbochs_dmabuf_vm_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mbochs_dmabuf *dmabuf = vma->vm_private_data; @@ -803,29 +805,26 @@ static void mbochs_release_dmabuf(struct dma_buf *buf) mutex_unlock(&mdev_state->ops_lock); } -static void *mbochs_kmap_atomic_dmabuf(struct dma_buf *buf, - unsigned long page_num) +static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num) { struct mbochs_dmabuf *dmabuf = buf->priv; struct page *page = dmabuf->pages[page_num]; - return kmap_atomic(page); + return kmap(page); } -static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num) +static void mbochs_kunmap_dmabuf(struct dma_buf *buf, unsigned long page_num, + void *vaddr) { - struct mbochs_dmabuf *dmabuf = buf->priv; - struct page *page = dmabuf->pages[page_num]; - - return kmap(page); + kunmap(vaddr); } static struct dma_buf_ops mbochs_dmabuf_ops = { .map_dma_buf = mbochs_map_dmabuf, .unmap_dma_buf = mbochs_unmap_dmabuf, .release = mbochs_release_dmabuf, - .map_atomic = mbochs_kmap_atomic_dmabuf, .map = mbochs_kmap_dmabuf, + .unmap = mbochs_kunmap_dmabuf, .mmap = mbochs_mmap_dmabuf, }; diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index c8156d61678c..86321f06461e 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -214,7 +214,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj # Prefix -I with $(srctree) if it is not an absolute path. # skip if -I has no parameter addtree = $(if $(patsubst -I%,%,$(1)), \ -$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1))) +$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)),$(1)) # Find all -I options and call addtree flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o))) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index e7889f486ca1..514ed63ff571 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -590,7 +590,4 @@ endif # We never want them to be removed automatically. .SECONDARY: $(targets) -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index 808d09f27ad4..17ef94c635cd 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -88,7 +88,4 @@ PHONY += $(subdir-ymn) $(subdir-ymn): $(Q)$(MAKE) $(clean)=$@ -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/Makefile.modbuiltin b/scripts/Makefile.modbuiltin index a763b4775d06..40867a41615b 100644 --- a/scripts/Makefile.modbuiltin +++ b/scripts/Makefile.modbuiltin @@ -54,8 +54,4 @@ PHONY += $(subdir-ym) $(subdir-ym): $(Q)$(MAKE) $(modbuiltin)=$@ - -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 51ca0244fc8a..ff5ca9817a85 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -35,8 +35,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D)) $(modules): $(call cmd,modules_install,$(MODLIB)/$(modinst_dir)) - -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable so we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index df4174405feb..dd92dbbbaa68 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -149,8 +149,4 @@ ifneq ($(cmd_files),) include $(cmd_files) endif - -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/Makefile.modsign b/scripts/Makefile.modsign index 171483bc0538..da56aa78d245 100644 --- a/scripts/Makefile.modsign +++ b/scripts/Makefile.modsign @@ -27,7 +27,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D)) $(modules): $(call cmd,sign_ko,$(MODLIB)/$(modinst_dir)) -# Declare the contents of the .PHONY variable as phony. We keep that -# information in a variable se we can use it in if_changed and friends. - .PHONY: $(PHONY) diff --git a/scripts/cc-can-link.sh b/scripts/cc-can-link.sh index 208eb2825dab..6efcead31989 100755 --- a/scripts/cc-can-link.sh +++ b/scripts/cc-can-link.sh @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y" +cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 #include <stdio.h> int main(void) { diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index a9c05506e325..447857ffaf6b 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5813,14 +5813,14 @@ sub process { defined $stat && $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s && $1 !~ /^_*volatile_*$/) { - my $specifier; - my $extension; - my $bad_specifier = ""; my $stat_real; my $lc = $stat =~ tr@\n@@; $lc = $lc + $linenr; for (my $count = $linenr; $count <= $lc; $count++) { + my $specifier; + my $extension; + my $bad_specifier = ""; my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0)); $fmt =~ s/%%//g; diff --git a/scripts/extract-vmlinux b/scripts/extract-vmlinux index 5061abcc2540..e6239f39abad 100755 --- a/scripts/extract-vmlinux +++ b/scripts/extract-vmlinux @@ -57,6 +57,8 @@ try_decompress '\3757zXZ\000' abcde unxz try_decompress 'BZh' xy bunzip2 try_decompress '\135\0\0\0' xxx unlzma try_decompress '\211\114\132' xy 'lzop -d' +try_decompress '\002!L\030' xxx 'lz4 -d' +try_decompress '(\265/\375' xxx unzstd # Bail out: echo "$me: Cannot find vmlinux." >&2 diff --git a/scripts/tags.sh b/scripts/tags.sh index 66f08bb1cce9..26de7d5aa5c8 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -152,6 +152,7 @@ regex_asm=( ) regex_c=( '/^SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/sys_\1/' + '/^BPF_CALL_[0-9](\([[:alnum:]_]*\).*/\1/' '/^COMPAT_SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/compat_sys_\1/' '/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1/' '/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1_rcuidle/' @@ -245,7 +246,7 @@ exuberant() { setup_regex exuberant asm c all_target_sources | xargs $1 -a \ - -I __initdata,__exitdata,__initconst, \ + -I __initdata,__exitdata,__initconst,__ro_after_init \ -I __initdata_memblock \ -I __refdata,__attribute,__maybe_unused,__always_unused \ -I __acquires,__releases,__deprecated \ diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 69616d00481c..b53026a72e73 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -635,7 +635,7 @@ static int snd_rawmidi_info_select_user(struct snd_card *card, int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream, struct snd_rawmidi_params * params) { - char *newbuf; + char *newbuf, *oldbuf; struct snd_rawmidi_runtime *runtime = substream->runtime; if (substream->append && substream->use_count > 1) @@ -648,13 +648,17 @@ int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream, return -EINVAL; } if (params->buffer_size != runtime->buffer_size) { - newbuf = krealloc(runtime->buffer, params->buffer_size, - GFP_KERNEL); + newbuf = kmalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; + spin_lock_irq(&runtime->lock); + oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; runtime->avail = runtime->buffer_size; + runtime->appl_ptr = runtime->hw_ptr = 0; + spin_unlock_irq(&runtime->lock); + kfree(oldbuf); } runtime->avail_min = params->avail_min; substream->active_sensing = !params->no_active_sensing; @@ -665,7 +669,7 @@ EXPORT_SYMBOL(snd_rawmidi_output_params); int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, struct snd_rawmidi_params * params) { - char *newbuf; + char *newbuf, *oldbuf; struct snd_rawmidi_runtime *runtime = substream->runtime; snd_rawmidi_drain_input(substream); @@ -676,12 +680,16 @@ int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream, return -EINVAL; } if (params->buffer_size != runtime->buffer_size) { - newbuf = krealloc(runtime->buffer, params->buffer_size, - GFP_KERNEL); + newbuf = kmalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; + spin_lock_irq(&runtime->lock); + oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; + runtime->appl_ptr = runtime->hw_ptr = 0; + spin_unlock_irq(&runtime->lock); + kfree(oldbuf); } runtime->avail_min = params->avail_min; return 0; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 4ff5320378e2..321e95c409c1 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1048,7 +1048,8 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ), SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ), SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI), - SND_PCI_QUIRK(0x1458, 0xA036, "Recon3Di", QUIRK_R3DI), + SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI), + SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), {} }; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e7fcfc3b8885..f641c20095f7 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -964,6 +964,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC), SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 98e1c411c56a..8a49415aebac 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -33,6 +33,7 @@ #include <linux/delay.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/pm_runtime.h> #include <sound/core.h> #include <sound/jack.h> #include <sound/asoundef.h> @@ -764,8 +765,10 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid, if (pin_idx < 0) return; + mutex_lock(&spec->pcm_lock); if (hdmi_present_sense(get_pin(spec, pin_idx), 1)) snd_hda_jack_report_sync(codec); + mutex_unlock(&spec->pcm_lock); } static void jack_callback(struct hda_codec *codec, @@ -1628,21 +1631,23 @@ static void sync_eld_via_acomp(struct hda_codec *codec, static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll) { struct hda_codec *codec = per_pin->codec; - struct hdmi_spec *spec = codec->spec; int ret; /* no temporary power up/down needed for component notifier */ - if (!codec_has_acomp(codec)) - snd_hda_power_up_pm(codec); + if (!codec_has_acomp(codec)) { + ret = snd_hda_power_up_pm(codec); + if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) { + snd_hda_power_down_pm(codec); + return false; + } + } - mutex_lock(&spec->pcm_lock); if (codec_has_acomp(codec)) { sync_eld_via_acomp(codec, per_pin); ret = false; /* don't call snd_hda_jack_report_sync() */ } else { ret = hdmi_present_sense_via_verbs(per_pin, repoll); } - mutex_unlock(&spec->pcm_lock); if (!codec_has_acomp(codec)) snd_hda_power_down_pm(codec); @@ -1654,12 +1659,16 @@ static void hdmi_repoll_eld(struct work_struct *work) { struct hdmi_spec_per_pin *per_pin = container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work); + struct hda_codec *codec = per_pin->codec; + struct hdmi_spec *spec = codec->spec; if (per_pin->repoll_count++ > 6) per_pin->repoll_count = 0; + mutex_lock(&spec->pcm_lock); if (hdmi_present_sense(per_pin, per_pin->repoll_count)) snd_hda_jack_report_sync(per_pin->codec); + mutex_unlock(&spec->pcm_lock); } static void intel_haswell_fixup_connect_list(struct hda_codec *codec, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5ad6c7e5f92e..f6af3e1c2b93 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2366,6 +2366,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), @@ -6569,6 +6570,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), @@ -6612,7 +6614,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), - SND_PCI_QUIRK(0x17aa, 0x3136, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), @@ -6796,6 +6797,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1a, 0x02a11040}, {0x1b, 0x01014020}, {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION, + {0x14, 0x90170110}, + {0x19, 0x02a11020}, + {0x1a, 0x02a11030}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60140}, {0x14, 0x90170110}, diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 32f9e397a6c0..3f140eff039f 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) int err; int fd; + if (argc < 3) { + p_err("too few arguments, id ID and FILE path is required"); + return -1; + } else if (argc > 3) { + p_err("too many arguments"); + return -1; + } + if (!is_prefix(*argv, "id")) { p_err("expected 'id' got %s", *argv); return -1; @@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) } NEXT_ARG(); - if (argc != 1) - usage(); - fd = get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 05f42a46d6ed..959aa53ab678 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -694,15 +694,19 @@ static int do_load(int argc, char **argv) return -1; } - if (do_pin_fd(prog_fd, argv[1])) { - p_err("failed to pin program"); - return -1; - } + if (do_pin_fd(prog_fd, argv[1])) + goto err_close_obj; if (json_output) jsonw_null(json_wtr); + bpf_object__close(obj); + return 0; + +err_close_obj: + bpf_object__close(obj); + return -1; } static int do_help(int argc, char **argv) diff --git a/tools/build/Build.include b/tools/build/Build.include index a4bbb984941d..950c1504ca37 100644 --- a/tools/build/Build.include +++ b/tools/build/Build.include @@ -63,8 +63,8 @@ dep-cmd = $(if $(wildcard $(fixdep)), $(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp; \ rm -f $(depfile); \ mv -f $(dot-target).tmp $(dot-target).cmd, \ - printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \ - printf '\# using basic dep data\n\n' >> $(dot-target).cmd; \ + printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \ + printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd; \ cat $(depfile) >> $(dot-target).cmd; \ printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd) @@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX ### ## HOSTCC C flags -host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj)) +host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj)) diff --git a/tools/build/Makefile b/tools/build/Makefile index 5eb4b5ad79cb..5edf65e684ab 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE $(Q)$(MAKE) $(build)=fixdep $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o - $(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $< + $(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $< FORCE: diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 4e60e105583e..7ec85d567598 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -302,19 +302,34 @@ static int read_symbols(struct elf *elf) continue; sym->pfunc = sym->cfunc = sym; coldstr = strstr(sym->name, ".cold."); - if (coldstr) { - coldstr[0] = '\0'; - pfunc = find_symbol_by_name(elf, sym->name); - coldstr[0] = '.'; - - if (!pfunc) { - WARN("%s(): can't find parent function", - sym->name); - goto err; - } - - sym->pfunc = pfunc; - pfunc->cfunc = sym; + if (!coldstr) + continue; + + coldstr[0] = '\0'; + pfunc = find_symbol_by_name(elf, sym->name); + coldstr[0] = '.'; + + if (!pfunc) { + WARN("%s(): can't find parent function", + sym->name); + goto err; + } + + sym->pfunc = pfunc; + pfunc->cfunc = sym; + + /* + * Unfortunately, -fnoreorder-functions puts the child + * inside the parent. Remove the overlap so we can + * have sane assumptions. + * + * Note that pfunc->len now no longer matches + * pfunc->sym.st_size. + */ + if (sym->sec == pfunc->sec && + sym->offset >= pfunc->offset && + sym->offset + sym->len == pfunc->offset + pfunc->len) { + pfunc->len -= sym->len; } } } @@ -504,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_flags = SHF_ALLOC; - /* Add section name to .shstrtab */ + /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); + if (!shstrtab) + shstrtab = find_section_by_name(elf, ".strtab"); if (!shstrtab) { - WARN("can't find .shstrtab section"); + WARN("can't find .shstrtab or .strtab section"); return NULL; } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index b5ac356ba323..f5a3b402589e 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -207,8 +207,7 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) endif diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 4b2caf6d48e7..fead6b3b4206 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) else if (rm[2].rm_so != rm[2].rm_eo) prefix[0] = '+'; else - strncpy(prefix, "+0", 2); + scnprintf(prefix, sizeof(prefix), "+0"); } /* Rename register */ diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 22547a490e1f..05be023c3f0e 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1742,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts) } } - if ((num_print_interval == 0 && metric_only) || interval_clear) + if ((num_print_interval == 0 || interval_clear) && metric_only) print_metric_headers(" ", true); if (++num_print_interval == 25) num_print_interval = 0; diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index 0c6d1002b524..ac1bcdc17dae 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -35,6 +35,7 @@ #include <sys/mman.h> #include <syscall.h> /* for gettid() */ #include <err.h> +#include <linux/kernel.h> #include "jvmti_agent.h" #include "../util/jitdump.h" @@ -249,7 +250,7 @@ void *jvmti_open(void) /* * jitdump file name */ - snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 17783913d330..215ba30b8534 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -1,7 +1,7 @@ hostprogs := jevents jevents-y += json.o jsmn.o jevents.o -CHOSTFLAGS_jevents.o = -I$(srctree)/tools/include +HOSTCFLAGS_jevents.o = -I$(srctree)/tools/include pmu-events-y += pmu-events.o JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index 38dfb720fb6f..54ace2f6bc36 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value): string = "" if flag_fields[event_name][field_name]: - print_delim = 0 - keys = flag_fields[event_name][field_name]['values'].keys() - keys.sort() - for idx in keys: + print_delim = 0 + for idx in sorted(flag_fields[event_name][field_name]['values']): if not value and not idx: string += flag_fields[event_name][field_name]['values'][idx] break @@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value): string = "" if symbolic_fields[event_name][field_name]: - keys = symbolic_fields[event_name][field_name]['values'].keys() - keys.sort() - for idx in keys: + for idx in sorted(symbolic_fields[event_name][field_name]['values']): if not value and not idx: - string = symbolic_fields[event_name][field_name]['values'][idx] + string = symbolic_fields[event_name][field_name]['values'][idx] break - if (value == idx): - string = symbolic_fields[event_name][field_name]['values'][idx] + if (value == idx): + string = symbolic_fields[event_name][field_name]['values'][idx] break return string @@ -74,19 +70,17 @@ def trace_flag_str(value): string = "" print_delim = 0 - keys = trace_flags.keys() - - for idx in keys: - if not value and not idx: - string += "NONE" - break - - if idx and (value & idx) == idx: - if print_delim: - string += " | "; - string += trace_flags[idx] - print_delim = 1 - value &= ~idx + for idx in trace_flags: + if not value and not idx: + string += "NONE" + break + + if idx and (value & idx) == idx: + if print_delim: + string += " | "; + string += trace_flags[idx] + print_delim = 1 + value &= ~idx return string diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py index 81a56cd2b3c1..21a7a1298094 100755 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py @@ -8,6 +8,7 @@ # PerfEvent is the base class for all perf event sample, PebsEvent # is a HW base Intel x86 PEBS event, and user could add more SW/HW # event classes based on requirements. +from __future__ import print_function import struct @@ -44,7 +45,8 @@ class PerfEvent(object): PerfEvent.event_num += 1 def show(self): - print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso) + print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % + (self.name, self.symbol, self.comm, self.dso)) # # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py index fdd92f699055..cac7b2542ee8 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py @@ -11,7 +11,7 @@ try: import wx except ImportError: - raise ImportError, "You need to install the wxpython lib for this script" + raise ImportError("You need to install the wxpython lib for this script") class RootFrame(wx.Frame): diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index f6c84966e4f8..7384dcb628c4 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -5,6 +5,7 @@ # This software may be distributed under the terms of the GNU General # Public License ("GPL") version 2 as published by the Free Software # Foundation. +from __future__ import print_function import errno, os @@ -33,7 +34,7 @@ def nsecs_str(nsecs): return str def add_stats(dict, key, value): - if not dict.has_key(key): + if key not in dict: dict[key] = (value, value, value, 1) else: min, max, avg, count = dict[key] @@ -72,10 +73,10 @@ try: except: if not audit_package_warned: audit_package_warned = True - print "Install the audit-libs-python package to get syscall names.\n" \ - "For example:\n # apt-get install python-audit (Ubuntu)" \ - "\n # yum install audit-libs-python (Fedora)" \ - "\n etc.\n" + print("Install the audit-libs-python package to get syscall names.\n" + "For example:\n # apt-get install python-audit (Ubuntu)" + "\n # yum install audit-libs-python (Fedora)" + "\n etc.\n") def syscall_name(id): try: diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index de66cb3b72c9..3473e7f66081 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -9,13 +9,17 @@ # This software is distributed under the terms of the GNU General # Public License ("GPL") version 2 as published by the Free Software # Foundation. - +from __future__ import print_function import os import sys from collections import defaultdict -from UserList import UserList +try: + from UserList import UserList +except ImportError: + # Python 3: UserList moved to the collections package + from collections import UserList sys.path.append(os.environ['PERF_EXEC_PATH'] + \ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') @@ -300,7 +304,7 @@ class TimeSliceList(UserList): if i == -1: return - for i in xrange(i, len(self.data)): + for i in range(i, len(self.data)): timeslice = self.data[i] if timeslice.start > end: return @@ -336,8 +340,8 @@ class SchedEventProxy: on_cpu_task = self.current_tsk[headers.cpu] if on_cpu_task != -1 and on_cpu_task != prev_pid: - print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ - (headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) + print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ + headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) threads[prev_pid] = prev_comm threads[next_pid] = next_comm diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 2bde505e2e7e..dd850a26d579 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size, #define for_each_shell_test(dir, base, ent) \ while ((ent = readdir(dir)) != NULL) \ - if (!is_directory(base, ent)) + if (!is_directory(base, ent) && ent->d_name[0] != '.') static const char *shell_tests__dir(char *path, size_t size) { diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 263057039693..94e513e62b34 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -14,35 +14,40 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { - idx=0 - expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" - expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" + + expected=`mktemp -u /tmp/expected.XXX` + + echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected + echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected case "$(uname -m)" in s390x) eventattr='call-graph=dwarf,max-stack=4' - expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" - expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" - expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected + echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected + echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; *) eventattr='max-stack=3' - expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" - expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; esac - file=`mktemp -u /tmp/perf.data.XXX` + perf_data=`mktemp -u /tmp/perf.data.XXX` + perf_script=`mktemp -u /tmp/perf.script.XXX` + perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + perf script -i $perf_data > $perf_script - perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1 - perf script -i $file | while read line ; do + exec 3<$perf_script + exec 4<$expected + while read line <&3 && read -r pattern <&4; do + [ -z "$pattern" ] && break echo $line - echo "$line" | egrep -q "${expected[$idx]}" + echo "$line" | egrep -q "$pattern" if [ $? -ne 0 ] ; then - printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line" + printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" exit 1 fi - let idx+=1 - [ -z "${expected[$idx]}" ] && break done # If any statements are executed from this point onwards, @@ -58,6 +63,6 @@ skip_if_no_perf_probe && \ perf probe -q $libc inet_pton && \ trace_libc_inet_pton_backtrace err=$? -rm -f ${file} +rm -f ${perf_data} ${perf_script} ${expected} perf probe -q -d probe_libc:inet_pton exit $err diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 55ad9793d544..4ce276efe6b4 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2 file=$(mktemp /tmp/temporary_file.XXXXX) trace_open_vfs_getname() { - evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') + evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') perf trace -e $evts touch $file 2>&1 | \ egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 976e658e38dc..5e94857dfca2 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -266,16 +266,16 @@ static const char *kinc_fetch_script = "#!/usr/bin/env sh\n" "if ! test -d \"$KBUILD_DIR\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "TMPDIR=`mktemp -d`\n" "if test -z \"$TMPDIR\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "cat << EOF > $TMPDIR/Makefile\n" "obj-y := dummy.o\n" diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 46e9e19ab1ac..bc32e57d17be 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample, if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - if (!dict) { + if (!dict) call_object(handler, t, handler_name); - } else { + else call_object(handler, t, default_handler_name); - Py_DECREF(dict); - } - Py_XDECREF(all_entries_dict); Py_DECREF(t); } @@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample, call_object(handler, t, handler_name); - Py_DECREF(dict); Py_DECREF(t); } @@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "# See the perf-script-python Documentation for the list " "of available functions.\n\n"); + fprintf(ofp, "from __future__ import print_function\n\n"); fprintf(ofp, "import os\n"); fprintf(ofp, "import sys\n\n"); @@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "from Core import *\n\n\n"); fprintf(ofp, "def trace_begin():\n"); - fprintf(ofp, "\tprint \"in trace_begin\"\n\n"); + fprintf(ofp, "\tprint(\"in trace_begin\")\n\n"); fprintf(ofp, "def trace_end():\n"); - fprintf(ofp, "\tprint \"in trace_end\"\n\n"); + fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "def %s__%s(", event->system, event->name); @@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) "common_secs, common_nsecs,\n\t\t\t" "common_pid, common_comm)\n\n"); - fprintf(ofp, "\t\tprint \""); + fprintf(ofp, "\t\tprint(\""); not_first = 0; count = 0; @@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, ")\n\n"); + fprintf(ofp, "))\n\n"); - fprintf(ofp, "\t\tprint 'Sample: {'+" - "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tprint('Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n"); fprintf(ofp, "\t\tfor node in common_callchain:"); fprintf(ofp, "\n\t\t\tif 'sym' in node:"); - fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))"); fprintf(ofp, "\n\t\t\telse:"); - fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); - fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n"); + fprintf(ofp, "\t\tprint()\n\n"); } fprintf(ofp, "def trace_unhandled(event_name, context, " "event_fields_dict, perf_sample_dict):\n"); - fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n"); - fprintf(ofp, "\t\tprint 'Sample: {'+" - "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n"); + fprintf(ofp, "\t\tprint('Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n"); fprintf(ofp, "def print_header(" "event_name, cpu, secs, nsecs, pid, comm):\n" - "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" - "(event_name, cpu, secs, nsecs, pid, comm),\n\n"); + "\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" + "(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n"); fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n" "\treturn delimiter.join" diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index a8fb63edcf89..e2926f72a821 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1991,8 +1991,7 @@ static void nfit_test0_setup(struct nfit_test *t) pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES; pcap->header.length = sizeof(*pcap); pcap->highest_capability = 1; - pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH | - ACPI_NFIT_CAPABILITY_MEM_FLUSH; + pcap->capabilities = ACPI_NFIT_CAPABILITY_MEM_FLUSH; offset += pcap->header.length; if (t->setup_hotplug) { diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7a6214e9ae58..a362e3d7abc6 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) -BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 7eb613ffef55..b4994a94968b 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -6,6 +6,7 @@ CONFIG_TEST_BPF=m CONFIG_CGROUP_BPF=y CONFIG_NETDEVSIM=m CONFIG_NET_CLS_ACT=y +CONFIG_NET_SCHED=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_IPIP=y CONFIG_IPV6=y diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index 35669ccd4d23..9df0d2ac45f8 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -1,6 +1,15 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ "$(id -u)" != "0" ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + SRC_TREE=../../../../ test_run() diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh index ce2e15e4f976..677686198df3 100755 --- a/tools/testing/selftests/bpf/test_lirc_mode2.sh +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -1,6 +1,15 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ $UID != 0 ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + GREEN='\033[0;92m' RED='\033[0;31m' NC='\033[0m' # No Color diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 1c77994b5e71..270fa8f49573 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -21,6 +21,15 @@ # An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this # datagram can be read on NS6 when binding to fb00::6. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +msg="skip all tests:" +if [ $UID != 0 ]; then + echo $msg please run this as root >&2 + exit $ksft_skip +fi + TMP_FILE="/tmp/selftest_lwt_seg6local.txt" cleanup() diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 05c8cb71724a..9e78df207919 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1413,18 +1413,12 @@ out: int main(int argc, char **argv) { - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; int iov_count = 1, length = 1024, rate = 1; struct sockmap_options options = {0}; int opt, longindex, err, cg_fd = 0; char *bpf_file = BPF_SOCKMAP_FILENAME; int test = PING_PONG; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (argc < 2) return test_suite(); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 2ecd27b670d7..41106d9d5cc7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -4975,6 +4975,24 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_LWT_XMIT, }, { + "make headroom for LWT_XMIT", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_skb_change_head), + /* split for s390 to succeed */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 42), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_skb_change_head), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { "invalid access of tc_classid for LWT_IN", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, @@ -11987,6 +12005,46 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "xadd/w check whether src/dst got mangled, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { + "xadd/w check whether src/dst got mangled, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { "bpf_get_stack return R0 within range", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -12554,8 +12612,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } if (fd_prog >= 0) { + __u8 tmp[TEST_DATA_LEN << 2]; + __u32 size_tmp = sizeof(tmp); + err = bpf_prog_test_run(fd_prog, 1, test->data, - sizeof(test->data), NULL, NULL, + sizeof(test->data), tmp, &size_tmp, &retval, NULL); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc new file mode 100644 index 000000000000..3b1f45e13a2e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Snapshot and tracing setting +# flags: instance + +[ ! -f snapshot ] && exit_unsupported + +echo "Set tracing off" +echo 0 > tracing_on + +echo "Allocate and take a snapshot" +echo 1 > snapshot + +# Since trace buffer is empty, snapshot is also empty, but allocated +grep -q "Snapshot is allocated" snapshot + +echo "Ensure keep tracing off" +test `cat tracing_on` -eq 0 + +echo "Set tracing on" +echo 1 > tracing_on + +echo "Take a snapshot again" +echo 1 > snapshot + +echo "Ensure keep tracing on" +test `cat tracing_on` -eq 1 + +exit 0 diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 78245d60d8bc..0f45633bd634 100644..100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -740,13 +740,6 @@ ipv6_rt_add() run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" log_test $? 2 "Attempt to add duplicate route - reject route" - # iproute2 prepend only sets NLM_F_CREATE - # - adds a new route; does NOT convert existing route to ECMP - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2" - check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024" - log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)" - # route append with same prefix adds a new route # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" @@ -754,27 +747,6 @@ ipv6_rt_add() check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" log_test $? 0 "Append nexthop to existing route - gw" - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" - check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1" - log_test $? 0 "Append nexthop to existing route - dev only" - - # multipath route can not have a nexthop that is a reject route - add_route6 "2001:db8:104::/64" "via 2001:db8:101::2" - run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64" - log_test $? 2 "Append nexthop to existing route - reject route" - - # reject route can not be converted to multipath route - run_cmd "$IP -6 ro flush 2001:db8:104::/64" - run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" - run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2" - log_test $? 2 "Append nexthop to existing reject route - gw" - - run_cmd "$IP -6 ro flush 2001:db8:104::/64" - run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64" - run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3" - log_test $? 2 "Append nexthop to existing reject route - dev only" - # insert mpath directly add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" @@ -819,13 +791,6 @@ ipv6_rt_replace_single() check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1" log_test $? 0 "Single path with multipath" - # single path with reject - # - add_initial_route6 "nexthop via 2001:db8:101::2" - run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" - check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" - log_test $? 0 "Single path with reject route" - # single path with single path using MULTIPATH attribute # add_initial_route6 "via 2001:db8:101::2" @@ -873,12 +838,6 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" - # multipath with reject - add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" - run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64" - check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024" - log_test $? 0 "Multipath with reject route" - # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 792fa4d0285e..850767befa47 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -35,9 +35,6 @@ run_udp() { echo "udp gso" run_in_netns ${args} -S - - echo "udp gso zerocopy" - run_in_netns ${args} -S -z } run_tcp() { diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index a4684112676c..86ce22417e0d 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -133,17 +133,27 @@ static inline uint32_t rseq_current_cpu(void) return cpu; } +static inline void rseq_clear_rseq_cs(void) +{ +#ifdef __LP64__ + __rseq_abi.rseq_cs.ptr = 0; +#else + __rseq_abi.rseq_cs.ptr.ptr32 = 0; +#endif +} + /* - * rseq_prepare_unload() should be invoked by each thread using rseq_finish*() - * at least once between their last rseq_finish*() and library unload of the - * library defining the rseq critical section (struct rseq_cs). This also - * applies to use of rseq in code generated by JIT: rseq_prepare_unload() - * should be invoked at least once by each thread using rseq_finish*() before - * reclaim of the memory holding the struct rseq_cs. + * rseq_prepare_unload() should be invoked by each thread executing a rseq + * critical section at least once between their last critical section and + * library unload of the library defining the rseq critical section + * (struct rseq_cs). This also applies to use of rseq in code generated by + * JIT: rseq_prepare_unload() should be invoked at least once by each + * thread executing a rseq critical section before reclaim of the memory + * holding the struct rseq_cs. */ static inline void rseq_prepare_unload(void) { - __rseq_abi.rseq_cs = 0; + rseq_clear_rseq_cs(); } #endif /* RSEQ_H_ */ diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index 95dd14648ba5..0f395dfb7774 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -44,12 +44,25 @@ /******************** Little Endian Handling ********************************/ -#define cpu_to_le16(x) htole16(x) -#define cpu_to_le32(x) htole32(x) +/* + * cpu_to_le16/32 are used when initializing structures, a context where a + * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way + * that allows them to be used when initializing structures. + */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define cpu_to_le16(x) (x) +#define cpu_to_le32(x) (x) +#else +#define cpu_to_le16(x) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)) +#define cpu_to_le32(x) \ + ((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >> 8) | \ + (((x) & 0x0000ff00u) << 8) | (((x) & 0x000000ffu) << 24)) +#endif + #define le32_to_cpu(x) le32toh(x) #define le16_to_cpu(x) le16toh(x) - /******************** Messages and Errors ***********************************/ static const char argv0[] = "ffs-test"; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 90d30fbe95ae..b20b751286fc 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -119,8 +119,12 @@ irqfd_shutdown(struct work_struct *work) { struct kvm_kernel_irqfd *irqfd = container_of(work, struct kvm_kernel_irqfd, shutdown); + struct kvm *kvm = irqfd->kvm; u64 cnt; + /* Make sure irqfd has been initalized in assign path. */ + synchronize_srcu(&kvm->irq_srcu); + /* * Synchronize with the wait-queue and unhook ourselves to prevent * further events. @@ -387,7 +391,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) idx = srcu_read_lock(&kvm->irq_srcu); irqfd_update(kvm, irqfd); - srcu_read_unlock(&kvm->irq_srcu, idx); list_add_tail(&irqfd->list, &kvm->irqfds.items); @@ -402,11 +405,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) if (events & EPOLLIN) schedule_work(&irqfd->inject); - /* - * do not drop the file until the irqfd is fully initialized, otherwise - * we might race against the EPOLLHUP - */ - fdput(f); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS if (kvm_arch_has_irq_bypass()) { irqfd->consumer.token = (void *)irqfd->eventfd; @@ -421,6 +419,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } #endif + srcu_read_unlock(&kvm->irq_srcu, idx); + + /* + * do not drop the file until the irqfd is fully initialized, otherwise + * we might race against the EPOLLHUP + */ + fdput(f); return 0; fail: |